HHS Public Access

Author manuscript
Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
Author Manuscript

Published in final edited form as:

Clin Cancer Res. 2021 October 15; 27(20): 5557–5565. doi:10.1158/[Link]-21-0325.

An Open Source, Automated Tumor Infiltrating Lymphocyte

Algorithm for Prognosis in Triple-Negative Breast Cancer
Yalai Bai1, Kimberly Cole1, Sandra Martinez-Morilla1, Fahad Shabbir Ahmed1, Jon
Zugazagoitia1, Johan Staaf2, Ana Bosch2,3, Anna Ehinger4, Emma Nimeus2,5, Johan
Hartman6,7, Balazs Acs1,6,7, David L. Rimm1,8
1Department of Pathology, Yale School of Medicine, New Haven, CT
Author Manuscript

2Division
of Oncology, Department of Clinical Sciences Lund, Lund University, Medicon Village,
SE-22381 Lund, Sweden
3Department of Hematology, Oncology and Radiation Physics, Region Skåne, Lund, Sweden
4Department of Genetics and Pathology, Laboratory Medicine, Region Skåne, Lund, Sweden
5Division of Surgery, Department of Clinical Sciences, Lund University, Lund, Sweden
6Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden
7Department of Clinical Pathology and Cytology, Karolinska University Laboratory, Stockholm,
Sweden
8Department of Internal Medicine (Medical Oncology), Yale University School of Medicine, New
Author Manuscript

Haven, CT

Abstract
Purpose: Although tumor infiltrating lymphocytes (TIL) assessment has been acknowledged
to have both prognostic and predictive importance in triple negative breast cancer (TNBC), it
is subject to inter and intra-observer variability that has prevented widespread adoption. Here
we constructed a machine-learning based breast cancer TIL scoring approach and validated its
prognostic potential in multiple TNBC cohorts.

**
Corresponding Authors: David L. Rimm, M.D.- Ph.D., Professor of Pathology, Director, Yale Pathology Tissue Services,
Department of Pathology, BML 116, Yale University School of Medicine, 310 Cedar Street P.O. Box 208023, New Haven, CT
06520-8023. Phone: 203-737-4204; [Link]@[Link]; Balázs Ács, M.D.- PhD., Pathologist, Postdoctoral Research Fellow,
Author Manuscript

Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden; Department of Clinical Pathology and Cytology,
Karolinska University Laboratory; Address: CCK, Karolinska Institutet, R8:04, 17176 Stockholm, Sweden. Phone: +46 707 82 85 71;
[Link]@[Link].
Authors’ Contributions
Conception and design: Y. Bai, B. Acs, D.L. Rimm
Development of methodology: Y. Bai, B. Acs, D.L. Rimm
Acquisition of data (provided animals, acquired and managed patients, provided facilities, etc.): Y. Bai, B. Acs, K. Cole, S.
Martinez-Morilla, J. Staaf, A. Bosch, A. Ehinger, E. Nimeus, J. Hartman, F. S. Ahmed, J. Zugazagoitia
Analysis and interpretation of data (e.g., statistical analysis, biostatistics, computational analysis): Y. Bai, B. Acs, K. Martinez­
Morilla, F.S. Ahmed, J. Zugazagoitia, D.L. Rimm
Writing, review, and/or revision of the manuscript: Y. Bai, B. Acs, K. Cole, S. Martinez-Morilla, J. Staaf, A. Bosch, A. Ehinger, E.
Nimeus, J. Hartman, F. S. Ahmed, J. Zugazagoitia, D.L. Rimm
Administrative, technical, or material support (i.e., reporting or organizing data, constructing databases): Y. Bai, B. Acs, K.
Cole, S. Martinez-Morilla, J. Staaf, A. Bosch, A. Ehinger, E. Nimeus, J. Hartman, F. S. Ahmed, J. Zugazagoitia, D.L. Rimm
Study supervision: Y. Bai, B. Acs, D.L. Rimm
*B.A. and D.L.R. contributed equally as corresponding authors.
 Bai et al. Page 2

Experimental Design: Using the QuPath open source software, we built a neural-network
Author Manuscript

classifier for tumor cells, lymphocytes, fibroblasts and “other” cells on hematoxylin-eosin
(H&E) stained sections. We analyzed the classifier-derived TIL measurements with five unique
constructed TIL variables. A retrospective collection of 171 TNBC cases was used as the
discovery set to identify the optimal association of machine-read TIL variables with patient
outcome. For validation we evaluated a retrospective collection of 749 TNBC patients comprised
of four independent validation subsets.

Results: We found that all five machine TIL variables had significant prognostic association with
outcomes (p≤0.01 for all comparisons) but showed cell specific variation in validation sets. Cox
regression analysis demonstrated that all five TIL variables were independently associated with
improved overall survival after adjusting for clinicopathological factors including stage, age and
histological grade (p≤0.003 for all analyses).

Conclusions: Neural net driven cell classifier defined TIL variables were robust and
Author Manuscript

independent prognostic factors in several independent validation cohorts of TNBC patients. These
objective, open source TIL variables are freely available to download and can now be considered
for testing in a prospective setting to assess clinical utility.

Keywords
Tumor-infiltrating lymphocytes (TILs); survival; triple negative breast cancer

Introduction
Recent clinical trials have demonstrated that host anti-tumor immunity, as measured by
stromal tumor infiltrating lymphocytes (sTILs), has clinical importance in primary triple
Author Manuscript

negative breast cancer (TNBC) (1–4). Data from numerous studies have showed that
increased sTIL levels are associated with favorable recurrence free survival and better
response to neoadjuvant treatment in early stage and metastatic TNBC (1,4–8). However,
the clinical utility of sTILs is still limited in daily practice of breast cancer patient care due
to subjectivity and lack of standardization. Therefore, the International Immuno-Oncology
Biomarker Working Group on Breast Cancer has undertaken efforts to standardize TIL
assessments. They have introduced a TIL assessment guideline that has reached good but not
perfect reproducibility in a series of international ring studies (9–12).

However, inter and intra-observer variability could remain an issue in real world clinical
practice due to the difficulty and subjectivity in quantitatively evaluating histological
features (13–15). Automated digital analysis using machine learning derived algorithms
could provide a solution to the problems of standardization and operator variance due
Author Manuscript

to subjectivity (13). Recently developed machine-learning based TIL analysis algorithms

have demonstrated prognostic potential. In these studies, TILs were analyzed within either
the intra-tumoral stroma or whole tumor region (16–21) mimicking how pathologists
assess TILs where each marker reflected distinct TIL spatial information in their given
compartment. Moreover, only a few of the reported TIL scoring algorithms have been tested
in TNBC cohorts (16,18,20) and essentially all are “black box”. That is, the algorithm
cannot be translated back to numbers of specific cells or cell features and the algorithms

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 3

are neither open source nor easily achieved by current real-world regional pathology
Author Manuscript

departments.

Here, we have used an open source software platform (QuPath) to build a machine-learning
based breast cancer TIL scoring algorithm based on recognition of specific cells types.
Then math can be performed on the cell types to result in potentially meaningful TIL
measurement variables not easily calculated by pathologist. We do this by first defining
four cells types (tumor cells, TILs, fibroblast cells, and others and then mathematically
combining them to create variables that assess the proportion of TILs within different cell
populations or the density of TILs within variable tissue compartments. The aim of our
study was to identify and validate a transparent, accessible method for collection and use
of a cell type-based variable that is operator independent (reproducible) and prognostic in
TNBC cohorts.
Author Manuscript

Materials and Methods

Patient cohorts
Our retrospective collection of 920 TNBC patients included five independent cohorts, three
from the Pathology Department of Yale, School of Medicine, one from The Cancer Genome
Atlas (TCGA) and one from the Skåne healthcare region in southern Sweden, based on data
from the Swedish National Breast Cancer Quality Registry (NKBC) (Table 1). The WTS
(whole tissue slides) Yale cohort consists 171 breast cancer patients diagnosed between
1985 and 2012 with 66.1 months median follow-up. TMA (Tissue Microarray) Yale1
cohort comprises 139 patients diagnosed between 1962 and 2006 with 63.8 months median
follow-up. TMA Yale2 cohort consist 278 breast cancer patients diagnosed between 1981
and 2012 with 64.8 months median follow-up. The publicly available WTS-TCGA cohort
Author Manuscript

comprises 116 patients operated between 1996 and 2013 with 13 months median follow-up
([Link] last accessioned June, 2020). The WTS-Sweden
cohort consists 216 patients enrolled in the prospective, observational, population-based
SCAN-B study ([Link] ID NCT02306096, PMID:29341157) between 2010 and
2015 with 49.7 months median follow-up and has been described elsewhere (22). In the
Yale and TCGA cohorts, TNBC was defined as breast cancer with <1% of cells with
IHC-staining for ER, PR and an IHC HER2-staining score < 2, or for patients with IHC
2+ a non-amplified ISH-status. In Sweden, the definition of TNBC is a tumor with <10%
of cells with IHC-staining for ER and PR (thus including tumors with 1-9% stained cells)
and an IHC HER2-staining score < 2, or for patients with IHC 2+ a non-amplified ISH­
status. Representative tumor areas for TMA Yale1 and TMA Yale2 sets were selected by
pathologists based on H&E-stained slides. Tumor cores were punched and arrayed (each
Author Manuscript

0.6mm in diameter) into a recipient block by Yale Pathology Tissue Service (YPTS) facility.
In TMA Yale1 cohort, all cases have duplicate TMA cores, while in TMA Yale2 cohort,
the number and the percentage of tissue cores having one-fold, two-fold and three-fold
redundancy were 76 (27%), 124 (45%) and 78 (28%), respectively (Table. S1). The average
of multiple cores per tumor (0.57 mm2 per tumor) were analyzed for TMA cohorts. For
whole tissue section slide sets, one whole slide per patient selected by a pathologically
trained research scientist was used for this study. Average areas of assessment for WTS Yale,

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 4

WTS TCGA and WTS Sweden were 51.2 mm2, 59 mm2 and 96.1 mm2, respectively (Table.
Author Manuscript

S2). Our classifier training set contained 97 TMA spots originating from 95 patients with
breast cancer derived by random selection from multiple older Yale cohorts.

This study has complied with all relevant ethical regulations (Declaration of Helsinki,
CIOMS, Belmont Report, U.S. Common Rule), and it was approved by the Yale Human
Investigation Committee under protocol #9505008219, #0304025173 and #0003011706.
Patients in each cohort provided informed consent or (especially for older tissues) the
tissue was obtained through Yale Human Investigation Committee protocol #9505008219,
#0304025173 and #0003011706 which allows waiver of consent in some cases. The
data were analyzed anonymously. The SCAN-B study was approved by the Regional
Ethical Review Board in Lund, Sweden (applicable registration numbers 2009/658,
2015/277, 2016/742, 2018/267, and 2019/01252 for this study) as outlined in (22). All
patients provided written informed consent prior to enrolment. The clinicopathological
Author Manuscript

characteristics of all study cohorts are listed in Table 1.

Digital-image analysis
In the Yale cohorts, Aperio ScanScope CS2 platform (Leica Biosystems, Wetzlar, Germany)
was used to scan H&E-stained slides at 20x with a pixel size of 0.4986 μm x 0.4986
μm. WTS TCGA images were downloaded from NIH CDC porta specimen repository (23)
[Link] In the WTS Sweden cohort, H&E-stained slides
were digitized using the NanoZoomer 2.0-HT (Hamamatsu Photonics K.K., Hamamatsu,
Japan) platform at 20x, with a pixel size of 0.4537 × 0.4537 μm. QuPath open-source
software platform (version 0.1.2) was used to build an automated TIL scoring algorithm
(24,25). As the date of H&E staining varied both between and within cohorts, we refined
the H&E stain estimates for each digitized slide using the “estimate stain vectors” function
Author Manuscript

in QuPath. Watershed cell detection was used (25) to segment the cells in the image with
the following settings: Detection image: hematoxylin OD; requested pixel size: 0.5 μm;
background radius: 8 μm; median filter radius: 0 μm; sigma: 1.5 μm; minimum cell area:
10 μm2; maximum cell area: 400 μm2; threshold: 0.1; maximum background intensity: 2.
Cell expansion: 5μm. The quality control of the cell segmentation was performed by two
pathologists (DR and BA). In order to classify detected cells into tumor cells, immune
cells (TILs), fibroblast cells, and others (false detections, background) (Fig. S1), we used
neural network as a machine-learning method with eight hidden layers (maximum iterations:
100). The features used in the classification was previously described (21). In order to help
the algorithm perform an accurate classification, we also added smoothed object features
at 25 μm and 50 μm radius to supplement the existing measurements of individual cells.
Multiple rounds of cell classification review and correction were required to achieve the
Author Manuscript

most accurate algorithm on the classifier training set, resulting in an algorithm named
“CNN11”. Complete step by step instructions and the CNN11 TIL algorithm are available at
([Link]

Building breast cancer TIL quantification algorithm

A flowchart for the quantitative analysis of tissue images based on open-source software for
the TIL assessment was established (Fig.1). Estimated stain vector was first defined after

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 5

uploading H&E images. This step is required to normalize different staining properties and
Author Manuscript

batches and is image specific. This is followed by cell segmentation using standardized
watershed cell detection parameters. Next, a cell classifier was trained using neural network
with tumor cell, TILs, fibroblast, and other cell types (false detection, background) that
are color coded for each type. A temporary classifier was built and applied to the rest of
the images in a classifier training set. After several rounds of cell classification review
and correction, a trained classifier (CNN11) was locked down once it was considered to
have satisfactory performance, as defined by pathologist assessment where most cells are
correctly classified (Fig. 1A) (21). Note that no cell classifying algorithm achieves 100%
success, but rather the correct classification is made for >95% of cells. The result is that after
application of CNN11, the program delivers the number of cells in the image in one of four
categories, including: 1) tumor cells, 2) TILs, 3) fibroblasts and 4) others.

For WTS sets, the tumor region annotation was defined based on the guideline introduced by
Author Manuscript

the International Immuno-Oncology Biomarker Working Group (10) as follows: i) Include

TILs within the borders of the invasive tumor, including both “central tumor” and “invasive
margin. ii) All mononuclear cells (including lymphocytes and plasma cells) should be
scored, but polymorphonuclear leukocytes are excluded. iii) Exclude TILs at a distance
outside of the tumor borders. iv) Exclude TILS around DCIS and normal lobules. v) Exclude
areas with crush artifacts, necrosis, regressive hyalinization as well as in the previous core
biopsy site. Quality control of the algorithm to classify detected cells was performed by
two pathologists (DR and BA). Example workflow and images using the cell classification
mask are shown in Fig. 1C and Fig. 2. We have excluded areas with tissue artifacts, e.g.,
necrosis, before running the algorithm. The algorithm does not replace the pathologist since
the algorithm cannot select the correct area for analysis, nor can it eliminate common
artifacts. Finally, the algorithm output is quality controlled after the cell assignment. In the
Author Manuscript

validation sets, the tumor region annotations were defined by different pathologists (DR,
BA, JH). Furthermore, the algorithm was run by different observers (YB and BA) in order
to demonstrate user-independency. We observed catastrophic segmentation failure in 1-2%
of cases that must be flagged for repeated analysis or eliminated if some unusual artefact is
present that triggers failure. This is most common in invasive lobular carcinoma and in a rare
minority, cases with high proportion of intra-tumoral TILs (iTILs). Stromal TILs (sTILs) of
both WTS Yale and WTS Sweden cohorts were also traditionally visually assessed by expert
breast pathologists in the US (KC) and in Sweden (JH) according to the guidelines published
by the International Immuno-Oncology Biomarker Working Group.

Construction of TIL variables

Breast cancer classification algorithm CNN11-derived tissue annotation measurements
Author Manuscript

consist of: (1) assignment to one of the four cell types defined above, (2) annotation area
(mm2) (whole tumor region), and (3) accumulative area of each cell type (mm2).

TIL measurements were analyzed in the following constructed variables (Fig. S1):

1. eTILs%= 100 * [# of TILs / (# of Tumor Cells + # of TILs)]; representing

proportion of TILs over tumor cells.

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 6

2. etTILs%= 100 * (# of TILs / # of Total cells); representing proportion of TILs

Author Manuscript

over all detected cells.

3. esTILs= 100 * [# of TILs / (# Total cells - # Tumor cells)]; representing

proportion of TILs over stromal cells.

4. eaTILs (mm2) = # of TILs / Sum of tumor region areas analyzed (mm2);

representing density of TILs over tumor region.

5. easTILs= 100 * [sum of TIL Area (mm2)/Stroma Area (mm2)]-mimics the

international TIL working group variable as read by pathologists.
Note that Stroma Area (mm2) = Sum of tumor region areas analyzed (mm2) – Sum of
tumor cell area (mm2) in variable #5, easTILs represents the density of TILs over stroma
area which mimics the pathologist scoring of sTIL per instructions from the International
Immuno-Oncology Biomarker Working Group on Breast Cancer (10). However, all the
Author Manuscript

variables include iTILs in the measurements. Cases with high iTILs proportions were
excluded from the analysis.

Statistical analysis
Overall survival (OS) was defined as the elapsed time from the date of primary diagnosis
of the tumor to the date of death caused any events, or when patients were last censored
if still alive. We visualized continuous data and their association with patient outcome
using X-tile software (26). The statistically significant threshold (cut-point) of each TIL
variable determined by X-tile software was then tested in validation sets (Fig. 1B) (26).
The Kaplan–Meier analysis supported with Log-rank test was executed with GraphPad
Prism (GraphPad software Inc., San Diego, CA) to assess prognostic potential. Mann–
Whitney test was used to investigate the association between automated easTILs score
Author Manuscript

and visual sTILs by pathologists. Spearman’s rho coefficient (r) between pathologist-read
sTIL and automated easTIL scores was assessed. To test independent prognostic potential,
multivariate Cox-regression analysis was applied using JMP Pro 15 software (SAS institute,
Inc., Cary, NC). In all statistical analysis, the level of significance was set at p < 0.05.

Results
Development of the CNN11 TIL algorithm in the WTS Yale discovery cohort
Machine-learning is often used to define a black-box algorithm associated with human TILs
scores or outcome, without information related to the parameters of traditional pathology.
Here we take a different approach training the algorithm to define familiar cells types,
then performing mathematical operations on the cell type counts, as per description in the
Author Manuscript

methods Figure 1 and Fig. S1. Thus, from a single cell finding (segmentation) algorithm,
called CNN11, we generate five candidate variables that we can test and compare, to select
the optimal variable for future use. Note that this approach, even though automated, results
in variables familiar to traditional pathology. The five variables were chosen as described
above to test for prognostic value and potential future use as objective biomarkers.

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 7

Next, the numerical values for each variable were then tested for association with patient
Author Manuscript

outcome. This is no longer a training process, but a rather optimal cut-point discovery and
thus we obtained outcome information on a whole tissue section set of TNBC cases (WTS
Yale set) which is independent from the CNN11 cell segmentation algorithm training set.
This discovery set was used to find the optimal cut-point for each of the five TIL variables.

To test the variables for prognostic value in this discovery set we used the X-tile software
to visualize the association at every possible cut-point and each TIL variable with patient
outcome. Figure 3 shows the optimal cut-point of each variable and the unadjusted p-value
derived for assessment of the cohort for optimal cut-point. The cut-point, expressed as a
percentage or cells/mm2, is inset in each plot. Note that we chose to try five variables from
start, but the number of variables that could be generated is much larger. For example; high
eTILs% (≥ 18.2%) had statistically significant better overall survival (OS) rate compared
to patients with low eTILs% (Hazard ratio (HR): 0.35, Confidence Interval (CI)=0.20-0.61,
Author Manuscript

p=0.0002). Similar clinical associations were observed for the other four TIL variables
in the WTS Yale cohort, each with their own optimal cut-point: etTILs% (threshold:
≥16.9%. HR: 0.35, 95% CI=0.19-0.63, p=0.0005); esTILs (threshold: ≥57.4%, HR=0.35,
95% CI=0.18-0.65, p=0.001); eaTILs (mm2) (threshold: ≥ #1195.6/mm2, HR=0.35, 95%
CI=0.20-0.63, p=0.0005) and easTILs (threshold: ≥19.9%. HR=0.30, 95% CI=0.16-0.54,
p<0.0001). Pathologist-read sTIL scores were also significantly linked to OS (threshold
(≥19.9%, HR=0.44, 95% CI=0.23-0.83, p=0.01) (Fig. 3).

Performance of the CNN11 TIL algorithm constructed variables in validation sets

Next, to test each of the five variables for prognostic value we validated them on four
completely independent cohorts; TMA Yale 1, TMA Yale 2, WTS TCGA and WTS Sweden.
Using the TIL variable-specific cut-points defined above, patients of the TMA Yale1 set all
Author Manuscript

five variables were significantly separated into favorable and unfavorable prognostic subsets
[eTILs%: HR=0.64, 95% CI=0.43-0.94, p=0.025; etTILS%: HR=0.51, 95% CI=0.32-0.81,
p=0.004; esTILs: HR=0.48, 95% CI=0.25-0.89, p=0.02; eaTILs (mm2): HR=0.48, 95%
CI=0.31-0.74, p=0.0009 and easTILs: HR=0.65, 95% CI=0.43-0.98, p=0.04] (Fig. S2). In
the TMA Yale2 cohort, eTILs%, etTILs% and esTILs scores were significantly associated
with OS, while eaTILs and easTILs’s were not [eTILs%: HR=0.43, 95% CI=0.26-0.69,
p=0.0005; etTILS%: HR=0.47, 95% CI=0.28-0.77, p=0.003; esTILs: HR=0.42, 95%
CI=0.24-0.76, p=0.004; eaTILs (mm2): HR=0.62, 95% CI=0.37-1.01, p=0.06; easTILs:
HR=0.78, 95% CI=0.48-1.26, p=0.31] (Fig. S3), showing the inherently different properties
of the variables.

In the clinical setting, TIL assessment is performed exclusively on WTS slides, thus we
Author Manuscript

applied the CNN11 algorithm variables on two external and independent WTS cohorts.
Using the discovery set’s derived optimal cut-point on the WTS TCGA cohort, patients
with high eTILs% had a significantly favorable OS (eTILs%: HR=0.09, 95% CI=0.01-0.70,
p=0.02) when compared to the low eTILs% group. Similarly, patients with either high
etTILs% or high eaTILs (mm2) had significant favorable outcomes [etTILs%: HR=0.10,
95% CI=0.01-0.80, p=0.03; eaTILs (mm2): HR=0.10, 95% CI=0.01-0.76, p=0.03] (Fig.
4). In the WTS Sweden cohort, only easTILs was significantly linked to OS (easTILs:

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 8

HR=0.54, 95% CI=0.31-0.92, p=0.02) (Fig. S4). The Swedish cohort had more high stage
Author Manuscript

patients than the TCGA or Yale cohorts and this may explain the differential performance of
the five TIL variable algorithms. Future studies will assess the interaction of these variables
with tumor stage.

The eTILs% and etTILs% variables presented significant associations with clinical
outcomes, validated in three out of four validation sets. Meanwhile, the esTILs, eaTILs
(mm2) and easTILs variables were validated in two out of four validation sets (Table. S3).
When combining all the validation sets into a single cohort, all five TIL variables had
significant associations with OS with or without the adjustment of the staging status, age and
histological grade based on multivariate Cox regression analysis (Table 2).

Multivariate Cox regression model analyses were run in order to test independent prognostic
potential of machine-read algorithm variable adjusted for stage, age and histological grade.
Author Manuscript

All of the CNN11-derived TIL algorithm variables remained significant with similar HR
and overlapping CI values (HR<0.57, 95% CI=0.35-0.78, p<=0.0003, for all comparisons
(Table 2). Of note, both eTILs% and esTILs% appeared two more robust markers (eTILs%:
HR=0.53, 95% CI=0.39-0.70, p<0.0001; esTILs%: HR=0.49, 95% CI=0.35-0.70, p<0.0001)
(Table 2). While it is statistically unsound to compare p-values, hazard ratios may be
compared. As shown in Table 2, the hazard ratios are similar between all five TIL variables,
but two, eTIL% and esTIL% are consistently better performing algorithms.

Further analysis of the pathologist-read sTIL assessment in WTS Sweden cohorts revealed
that patients with high sTILs had better outcomes than the low sTILs patient group
(HR=0.52, 95% CI=0.30-0.90, p=0.02). This observation raises a general question about
comparison of TIL algorithm variables compared to pathologist reads. When we compared
Author Manuscript

the CNN11-derived easTLs variable score with the pathologist-read sTILs assessment,
a good correlation was observed in both WTS Yale (Spearman’s r coefficient =0.61,
p<0.0001) and WTS Sweden cohorts (Spearman’s r coefficient=0.63, p<0.0001). Further
analysis showed that cases with high sTILs had significantly higher easTILs in both cohorts
(Fig. S5). Finally, we also compared CNN11-derived variables performance on TMAs vs.
WTS. We found a moderate correlation between TMA and WTS specimens (Table. S4 and
Fig. S6).

Discussion
In recent years, TILs have been acknowledged to have both prognostic and predictive
importance in patients with early or metastatic TNBC (1,4–8). However, pathologist-read
TIL assessments can be a significant source of variability (14,15). Furthermore, adjacent
Author Manuscript

microenvironmental cellular populations are not accounted for due to the difficulty in
making such assessments. In an attempt to quantify TILs, computational studies have either
focused on mimicking the guidelines introduced by the International Immuno-Oncology
Biomarker Working Group(16–18,20) or generated black box algorithms (19,27). Our
algorithm to define cell types (CNN11) is similarly black box. However, the output variables
used for prognostic biomarkers are transparent cell type computations and thus more
familiar to pathologists.

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 9

Over the last couple years, different machine-learning approaches have been proposed to
Author Manuscript

score anti-tumor immunity, resulting in a variety of TIL biomarkers with potential clinical
applicability. Some of these machine-learning tools have been based on patch classification,
while others mainly relied on object (cell) detection/ and classification. Another widely­
adopted approach is the implementation of tissue pattern recognition distinguishing tissue
regions and evaluation of TILs in different tissue compartments (e.g.: in intra-tumoral
stroma) (16–20). However, many of these machine-learning derived TIL biomarkers lack
broad validation, which is essential for clinical adoption. Furthermore, there is a need
for studies comparing various TIL variables focusing on different spatial aspects. Here
we showed that machine-learning based TIL scoring is able to provide comprehensive
information of TILs in TNBC tumor microenvironment not easily determined by pathologist
assessment.

In our study, using the QuPath platform, we have developed a cell classifier to score TIL
Author Manuscript

measurements deriving five TIL variables (eTILs%, etTILs%, esTILs, eaTILs (mm2) and
easTILs) representing proportion of TILs in relation to cell counts in the whole tumor
region, and to the area of different tumor regions (e.g: intra-tumoral stroma) (21,24). The
digital analysis approach we used is an unsupervised nuclei segmentation followed by a
neural network-based machine-learning cell classification. The advantage of this concept is
that it requires relatively smaller sized training sets. However, it has the limitation that
segmentation sensitivity and classification performance is dependent on biological and
technical image variation which may lead to overfitting of the classifier in the training
set. To address this limitation, we have validated the classifier in four independent TNBC
cohorts that were retrieved from different institutions, varied in time of diagnosis and
format, using both TMA and WTS format. Furthermore, in our assessment protocol, we
keep pathologist review in the loop, both to select the tumor and related stroma and to
Author Manuscript

exclude catastrophic algorithm failures. Our results demonstrated the prognostic role of all
five TIL variables based on successful validation in independent TMA and WTS sets. We
have seen similar prognostic results with eTIL% in melanoma (21).

Although not proven in this pilot study, the potential clinical utility of objective TILs
assessment is to enable clinicians to identify a group of patients who might benefit from
immunotherapy (28) or de-escalation of therapy where chemotherapy could be omitted in
populations that are extremely unlikely to develop recurrent disease (29). Although our
machine-read TILs scores with pre-defined cut-points were validated in independent cohorts,
these cut-points are most likely not applicable generally as they were not adjusted for stage,
tumor types, type of therapy. For this reason, we propose this machine read scoring as a
continuous variable and clinical utility studies adjusted for the aforementioned factors are
Author Manuscript

needed to develop the specific cut-point for the specific indication. Also, the International
Immuno-Oncology Biomarker Working has not recommended a generally applicable TIL
threshold for clinical practice, however in recently published studies, the thresholds where
sTILs had an impact on prognosis were between 10% and 30% (5,12). In our validation
sets, after application of cut-points derived in the discovery set (WTS Yale set), we found
optimal prognostic cut-points in the same general range, but with tighter variance, and with
observer-independent reproducibility.

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 10

This pilot effort has a number of potential limitations. One limitation of our work is
Author Manuscript

algorithm assignment error as a potential pitfall in machine-read scoring. For example,

false-positive TILs have been detected in areas containing apoptotic figures, neutrophils, and
low-grade tumors with monotonously uniformed nuclei. Furthermore, our model was not
fine-tuned to distinguish iTILs from sTILs because iTILs accounts for only 1-3% minority
of TILs in the vast majority of cases. These errors tend to be catastrophic in rare cases,
requiring a pathologist to review the cases for exclusion or re-analysis. However, pathologist
cell assignment review validation is a reasonable step in the process, since we believe
computational algorithms, in the near term, will assist, not replace pathologists. Our goal
was not to build a fully automated TIL scoring application, but a computer-assisted, open
source tool that might help pathologist to improve reproducibility. Therefore, a pathologist is
still essential for quality control and systematic performance evaluation.

Perhaps the most significant limitation of this work is the fact that all of the cohorts
Author Manuscript

are retrospective collections. As such, they have heterogeneous treatment and variable
inclusion criteria. Furthermore, differences in tissue handling and HE staining might further
contribute to the variability between the cohorts. However, machine read TILs scores
showed prognostic performance in validation sets despite the variability among the cohorts
which further supports its robustness. In this study, prognostic association was assessed
without special consideration to administered therapy, as this varied between cohorts. To
truly evaluate prognostic value, the rigor of a clinical trial is best. However, tissue and data
from a clinical trial are a very precious and often limited resource. Thus pilot, discovery
studies such as this need to use retrospective cohort for proof of concept.

Finally, a variable to mention, although not necessarily a limitation, is that the WTS Sweden
cohort was scanned using a different brand of slide scanner (a NanoZoomer, rather than an
Author Manuscript

Aperio). It was not possible to rescan all of the Swedish Cohort with the Aperio Scanner and
it is beyond the scope of this work to compare the effect of different slide scanners on the
final results. However, this variable may generate variation that should be acknowledged as a
potential limitation of this work and should be considered in the results seen in the Swedish
Cohort. Future efforts will compare slide scanning hardware.

In conclusion, we demonstrated that machine-learning derived TIL algorithm variables were

significantly associated with outcomes in TNBC patients. They were also shown to be
objective and independent prognostic factors in several validation cohorts. With further
investigation in a clinical trial, we believe that this objective tool could be useful in the
clinical setting for objective quantification of TILs.
Author Manuscript

Supplementary Material
Refer to Web version on PubMed Central for supplementary material.

Acknowledgements:
This automated TIL algorithm research was supported by the Breast Cancer Research Foundation (David L. Rimm)

David L. Rimm was supported by the National Institute of Health (NIH) Yale SPORE in Lung Cancer Career
Development Program (NIH P50 CA196530)

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 11

We would like to thank Yale Pathology Tissue Service TMA facility (YPTS) for the valuable contributions.
Author Manuscript

Johan Staaf was supported by The Governmental Funding of Clinical Research within the National Health
Service (ALF) 2018/40612, The Swedish Cancer Society (CAN 2018/685) and a 2018 Senior Investigator Award
(SIA190013), as well as Mrs. Berta Kamprad Foundation FBKS-2020-5-282

Disclosure of Potential Conflict of Interest

David L. Rimm has served as an advisor for Astra Zeneca, Agendia, Amgen, BMS, Cell Signaling Technology,
Cepheid, Daiichi Sankyo, Genoptix/Novartis, GSK, Konica Minolta, Merck, NanoString, [Link], Perkin Elmer,
Roche, Sanofi, Ventana and Ultivue. Astra Zeneca, Cepheid, NavigateBP, NextCure, Nanostring, Lilly, and Ultivue
fund research in David L. Rimm’s lab. Ana Bosch has participated in Advisory Board meetings for Pfizer and
Novartis and received a travel grant from Roche. Other authors have no potential conflicts of interest.

References
1. Adams S, Gray RJ, Demaria S, Goldstein L, Perez EA, Shulman LN, et al. Prognostic value
of tumor-infiltrating lymphocytes in triple-negative breast cancers from two phase III randomized
Author Manuscript

adjuvant breast cancer trials: ECOG 2197 and ECOG 1199. J Clin Oncol 2014;32(27):2959–66 doi
10.1200/JCO.2013.55.0491. [PubMed: 25071121]
2. Dieci MV, Mathieu MC, Guarneri V, Conte P, Delaloge S, Andre F, et al. Prognostic and predictive
value of tumor-infiltrating lymphocytes in two phase III randomized adjuvant breast cancer trials.
Annals of Oncology 2015;26(8):1698–704 doi 10.1093/annonc/mdv239. [PubMed: 25995301]
3. Loi S, Michiels S, Salgado R, Sirtaine N, Jose V, Fumagalli D, et al. Tumor infiltrating lymphocytes
are prognostic in triple negative breast cancer and predictive for trastuzumab benefit in early
breast cancer: results from the FinHER trial. Annals of Oncology 2014;25(8):1544–50 doi 10.1093/
annonc/mdu112. [PubMed: 24608200]
4. Loi S, Sirtaine N, Piette F, Salgado R, Viale G, Van Eenoo F, et al. Prognostic and predictive
value of tumor-infiltrating lymphocytes in a phase III randomized adjuvant breast cancer trial in
node-positive breast cancer comparing the addition of docetaxel to doxorubicin with doxorubicin­
based chemotherapy: BIG 02-98. J Clin Oncol 2013;31(7):860–7 doi 10.1200/JCO.2011.41.0902.
[PubMed: 23341518]
5. Denkert C, von Minckwitz G, Darb-Esfahani S, Lederer B, Heppner BI, Weber KE, et al. Tumour­
Author Manuscript

infiltrating lymphocytes and prognosis in different subtypes of breast cancer: a pooled analysis
of 3771 patients treated with neoadjuvant therapy. Lancet Oncol 2018;19(1):40–50 doi 10.1016/
S1470-2045(17)30904-X. [PubMed: 29233559]
6. Savas P, Salgado R, Denkert C, Sotiriou C, Darcy PK, Smyth MJ, et al. Clinical relevance of host
immunity in breast cancer: from TILs to the clinic. Nat Rev Clin Oncol 2016;13(4):228–41 doi
10.1038/nrclinonc.2015.215. [PubMed: 26667975]
7. Pruneri G, Gray KP, Vingiani A, Viale G, Curigliano G, Criscitiello C, et al. Tumor-infiltrating
lymphocytes (TILs) are a powerful prognostic marker in patients with triple-negative breast
cancer enrolled in the IBCSG phase III randomized clinical trial 22-00. Breast Cancer Res Treat
2016;158(2):323–31 doi 10.1007/s10549-016-3863-3. [PubMed: 27372069]
8. Adams S, Schmid P, Rugo HS, Winer EP, Loirat D, Awada A, et al. Pembrolizumab
monotherapy for previously treated metastatic triple-negative breast cancer: cohort A of the phase
II KEYNOTE-086 study. Ann Oncol 2019;30(3):397–404 doi 10.1093/annonc/mdy517. [PubMed:
30475950]
9. Denkert C, Wienert S, Poterie A, Loibl S, Budczies J, Badve S, et al. Standardized evaluation
Author Manuscript

of tumor-infiltrating lymphocytes in breast cancer: results of the ring studies of the international
immuno-oncology biomarker working group. Mod Pathol 2016;29(10):1155–64 doi 10.1038/
modpathol.2016.109. [PubMed: 27363491]
10. Salgado R, Denkert C, Demaria S, Sirtaine N, Klauschen F, Pruneri G, et al. The evaluation of
tumor-infiltrating lymphocytes (TILs) in breast cancer: recommendations by an International TILs
Working Group 2014. Ann Oncol 2015;26(2):259–71 doi 10.1093/annonc/mdu450. [PubMed:
25214542]
11. Hendry S, Salgado R, Gevaert T, Russell PA, John T, Thapa B, et al. Assessing Tumor­
infiltrating Lymphocytes in Solid Tumors: A Practical Review for Pathologists and Proposal for

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 12

a Standardized Method From the International Immunooncology Biomarkers Working Group:

Part 1: Assessing the Host Immune Response, TILs in Invasive Breast Carcinoma and Ductal
Author Manuscript

Carcinoma In Situ, Metastatic Tumor Deposits and Areas for Further Research. Adv Anat Pathol
2017;24(5):235–51 doi 10.1097/PAP.0000000000000162. [PubMed: 28777142]
12. Loi S, Drubay D, Adams S, Pruneri G, Francis PA, Lacroix-Triki M, et al. Tumor-Infiltrating
Lymphocytes and Prognosis: A Pooled Individual Patient Analysis of Early-Stage Triple­
Negative Breast Cancers. J Clin Oncol 2019;37(7):559–69 doi 10.1200/JCO.18.01010. [PubMed:
30650045]
13. Klauschen F, Muller KR, Binder A, Bockmayr M, Hagele M, Seegerer P, et al. Scoring of
tumor-infiltrating lymphocytes: From visual estimation to machine learning. Semin Cancer Biol
2018;52(Pt 2):151–7 doi 10.1016/[Link].2018.07.001. [PubMed: 29990622]
14. Kos Z, Roblin E, Kim RS, Michiels S, Gallas BD, Chen W, et al. Pitfalls in assessing stromal
tumor infiltrating lymphocytes (sTILs) in breast cancer. NPJ Breast Cancer 2020;6:17 doi 10.1038/
s41523-020-0156-0. [PubMed: 32411819]
15. Wein L, Savas P, Luen SJ, Virassamy B, Salgado R, Loi S. Clinical Validity and Utility of Tumor­
Infiltrating Lymphocytes in Routine Clinical Practice for Breast Cancer Patients: Current and
Author Manuscript

Future Directions. Front Oncol 2017;7:156 doi 10.3389/fonc.2017.00156. [PubMed: 28824872]

16. Amgad M, Sarkar A, Srinivas C, Redman R, Ratra S, Bechert CJ, et al. Joint Region and Nucleus
Segmentation for Characterization of Tumor Infiltrating Lymphocytes in Breast Cancer. Proc SPIE
Int Soc Opt Eng 2019;10956 doi 10.1117/12.2512892.
17. Heindl A, Sestak I, Naidoo K, Cuzick J, Dowsett M, Yuan Y. Relevance of Spatial Heterogeneity
of Immune Infiltration for Predicting Risk of Recurrence After Endocrine Therapy of ER+ Breast
Cancer. J Natl Cancer Inst 2018;110(2) doi 10.1093/jnci/djx137.
18. Le H, Gupta R, Hou L, Abousamra S, Fassler D, Torre-Healy L, et al. Utilizing Automated Breast
Cancer Detection to Identify Spatial Distributions of Tumor-Infiltrating Lymphocytes in Invasive
Breast Cancer. Am J Pathol 2020;190(7):1491–504 doi 10.1016/[Link].2020.03.012. [PubMed:
32277893]
19. Saltz J, Gupta R, Hou L, Kurc T, Singh P, Nguyen V, et al. Spatial Organization and Molecular
Correlation of Tumor-Infiltrating Lymphocytes Using Deep Learning on Pathology Images. Cell
Rep 2018;23(1):181–93 e7 doi 10.1016/[Link].2018.03.086. [PubMed: 29617659]
20. Yuan Y, Failmezger H, Rueda OM, Ali HR, Graf S, Chin SF, et al. Quantitative image analysis
Author Manuscript

of cellular heterogeneity in breast tumors complements genomic profiling. Sci Transl Med
2012;4(157):157ra43 doi 10.1126/scitranslmed.3004330.
21. Acs B, Ahmed FS, Gupta S, Wong PF, Gartrell RD, Sarin Pradhan J, et al. An open source
automated tumor infiltrating lymphocyte algorithm for prognosis in melanoma. Nat Commun
2019;10(1):5440 doi 10.1038/s41467-019-13043-2. [PubMed: 31784511]
22. Staaf J, Glodzik D, Bosch A, Vallon-Christersson J, Reutersward C, Hakkinen J, et al. Whole­
genome sequencing of triple-negative breast cancers in a population-based clinical study. Nat Med
2019;25(10):1526–33 doi 10.1038/s41591-019-0582-4. [PubMed: 31570822]
23. Cancer Genome Atlas Research N, Weinstein JN, Collisson EA, Mills GB, Shaw KR, Ozenberger
BA, et al. The Cancer Genome Atlas Pan-Cancer analysis project. Nat Genet 2013;45(10):1113–20
doi 10.1038/ng.2764. [PubMed: 24071849]
24. Bankhead P, Loughrey MB, Fernandez JA, Dombrowski Y, McArt DG, Dunne PD, et al. QuPath:
Open source software for digital pathology image analysis. Sci Rep 2017;7(1):16878 doi 10.1038/
s41598-017-17204-5. [PubMed: 29203879]
Author Manuscript

25. Malpica N, de Solorzano CO, Vaquero JJ, Santos A, Vallcorba I, Garcia-Sagredo JM,
et al. Applying watershed algorithms to the segmentation of clustered nuclei. Cytometry
1997;28(4):289–97 doi 10.1002/(sici)1097-0320(19970801)28:4<289::aid-cyto3>[Link];2-7.
[PubMed: 9266748]
26. Camp RL, Dolled-Filhart M, Rimm DL. X-tile: a new bio-informatics tool for biomarker
assessment and outcome-based cut-point optimization. Clin Cancer Res 2004;10(21):7252–9 doi
10.1158/[Link]-04-0713. [PubMed: 15534099]
27. Corredor G, Wang X, Zhou Y, Lu C, Fu P, Syrigos K, et al. Spatial Architecture and
Arrangement of Tumor-Infiltrating Lymphocytes for Predicting Likelihood of Recurrence

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 13

in Early-Stage Non-Small Cell Lung Cancer. Clin Cancer Res 2019;25(5):1526–34 doi
10.1158/[Link]-18-2013. [PubMed: 30201760]
Author Manuscript

28. Luen SJ, Salgado R, Dieci MV, Vingiani A, Curigliano G, Gould RE, et al. Prognostic
implications of residual disease tumor-infiltrating lymphocytes and residual cancer burden in
triple-negative breast cancer patients after neoadjuvant chemotherapy. Ann Oncol 2019;30(2):236–
42 doi 10.1093/annonc/mdy547. [PubMed: 30590484]
29. Park JH, Jonas SF, Bataillon G, Criscitiello C, Salgado R, Loi S, et al. Prognostic value of
tumor-infiltrating lymphocytes in patients with early-stage triple-negative breast cancers (TNBC)
who did not receive adjuvant chemotherapy. Ann Oncol 2019;30(12):1941–9 doi 10.1093/annonc/
mdz395. [PubMed: 31566659]
Author Manuscript
Author Manuscript
Author Manuscript

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 14

Translational Relevance:
Author Manuscript

The presence of high TILs (tumor infiltrating lymphocytes) have been shown to be
predictive of the response to chemotherapy and is also a prognostic factor associated with
a better outcome in breast cancer, especially in early stage triple-negative (TNBC) and
HER2-positive breast cancers. Despite the standardization efforts of the TIL assessment,
the subjective nature and degree of variability in evaluation has prevented its broad
adoption. Using QuPath open source software, we built an algorithm for H&E image­
based automated assessment of TILs and invented a method for TIL assessment that is
beyond human capability. Using one discovery set and four validation sets from three
institutions, we have found that machine-read measured TIL variables have stratified
patients with TNBC into favorable and poor prognosis cohorts, where higher TILs
scores were significantly associated with better overall survival. This open source method
of assessment is broadly accessible and machine-read TILs scoring is now ready for
Author Manuscript

consideration for prospective testing to prove clinical utility.

Author Manuscript
Author Manuscript

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 15
Author Manuscript
Author Manuscript

Figure 1.
Flowchart of algorithm training, developing to algorithm validation. A. Estimate stain vector
was first defined after uploading H&E images. This is followed by cell segmentation
Author Manuscript

using standardized watershed cell detection parameters. Next, a CNN was trained using
neural network with tumor cell, TILs, fibroblast and other type or background cells
with color coding of each type. A temporary classifier was built and applied to rest
of images in classifier training set. After many rounds of cell classification review and
correction, a trained classifier (CNN11) was locked once it was morphologically judged to
be at least 95% accurate on most images. B: Application of trained classifier resulted in
TIL measurements which were calculated as following TIL variables: eTILs%, etTILs%,
esTILs%, eaTILs (mm2) and easTILs (see methods section for definition of variables).
Associations between TIL variables and patient outcome were identified in WTS Yale
(discovery set) using the optimal cut-points determined by X-tile software. All TIL variables
were subsequently tested in validation sets including TMA Yale1, TMA Yale2, WTS
TCGA and WTS Sweden. C: Workflow explaining how TIL quantification is performed
Author Manuscript

in H&E image-based whole tissue image. Step of tumor region definition is followed by
estimate stain vector to normalize hematoxylin and eosin colors. Then, cell segmentation
is performed using standardized watershed cell detection parameters and cell classification
using the trained classifier. At last, TIL measurements were analyzed into constructed
variables. * Pathologist’s supervision is required.

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 16
Author Manuscript
Author Manuscript

Figure. 2.
Representative images of four sample cases showing the H&E images (A, C, E and G) and
the cell classification masks (B, D, F and H). E and F: representative image of sample cases
with inaccurate cell classification, these rare fields are ultimately censored. G and H: only
invasive breast cancer regions were selected and analyzed. Color code of cell classification
mask: tumor cells (red), TILs (purple), fibroblasts (green) and others (yellow). Scale bar
from A to F: 20um; scale bar from G to H: 200um.
Author Manuscript
Author Manuscript

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 17
Author Manuscript
Author Manuscript

Figure 3.
Identification of QuPath TIL prognostic role in discovery set (WTS Yale). Kaplan-Meier
curves of overall survival (OS) in WTS Yale Discovery set by eTILs% dichotomized
at the value of 18.2% (A), etTILs% dichotomized at the value at 16.9%. (B) esTILs%
dichotomized at the value 57.4%. (C) eaTILs (mm2) dichotomized at the value #1195.6/
Author Manuscript

mm2. (D) easTILs dichotomized at the value 19.9% (E) and pathologist sTILs% at 19.9%
(F). Corresponding Hazard Ratio with 95% Cl and P values are illustrated. Note, P values in
this figure are not corrected for multiple testing as occurs in optimal cut-point discovery
Author Manuscript

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 18
Author Manuscript
Author Manuscript

Figure 4.
Validation of QuPath TIL algorithms in WTS TCGA. Kaplan-Meier curves of overall
survival (OS) in WTS TCGA set by eTILs% dichotomized at the value of 18.2% (A),
etTILs% dichotomized at the value at 16.9% (B), esTILs% dichotomized at the value 57.4%
(C), eaTILs (mm2) dichotomized at the value #1195.6/mm2(D) and easTILs dichotomized at
Author Manuscript

the value 19.9% (E). Corresponding Hazard Ratio with 95% Cl and P values are illustrated.
Author Manuscript

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 19

Table 1.

Clinicopathological information of discovery and validation sets

Author Manuscript

WTS Yale TMA Yale1 TMA Yale2* WTS TCGA WTS Sweden

n (%) n (%) n (%) n (%) n (%)

Cases 171 (100%) 139 (100%) 278 (100%) 116 (100%) 216 (100%)

Age < 50 49 (28,7%) 54 (38.8%) 109 (39.2%) 40 (34.5%) 49 (22.7%)

≥ 50 92 (53.8%) 85 (61.2%) 151 (54.3%) 76 (65.5%) 167 (77.3%)
NA 30 (17.5%) 0 (0.0%) 18 (6.5%) 0 (0.0%) 0 (0.0%)

Race White 122 (71.3%) 124 (89.2%) 148 (53.2%) 75 (65.0%)

African American 38 (22.2%) 9 (6.5%) 60 (21.6%) 33 (28.0%)
other 9 (5.3%) 1 (0.7%) 13 (4.7%) 3 (3.0%)
NA 2 (1.2%) 5 (3.6%) 57 (20.5%) 5 (4.0%) 216 (100%)
Author Manuscript

Tumor size (cm) Median, range 2, 0.45-6.5 2.5, 0.5-12 2, 0.45-10 2.1, 0.5-10
≤2 74 (43.3%) 53 (38.1%) 130 (46.8%) 85 (39.4%)
>2 64 (37.4%) 71 (51.1%) 120 (43.2%) 123 (56.9%)
NA 33 (19.3%) 23 (16.5%) 28 (10.1%) 116 (100%) 8 (3.7%)

Histological grade Well-DI** 2 (1.2%) 2 (1.4%) 3 (1.1%) 0 (0.0%)

Moderate-DI 39 (22.8%) 42 (30.2%) 61 (21.9%) 22 (10.2%)

Poor-DI 122 (71.3%) 49 (35.3%) 190 (68.3%) 191 (88.4%)
NA 8 (4.7%) 55 (39.6%) 24 (8.6%) 116 (100%) 3 (1.4%)

Stage I 60 (35.1%) 19 (13.7%) 102 (36.7%) 21 (18.0%) 60 (27.8%)

II 78 (45.6%) 51 (36.7%) 128 (46.0%) 72 (62.0%) 49 (22.7%)
III 13 (7.6%) 53 (38.1%) 34 (12.2%) 19 (16.0%) 52 (24.1%)
Author Manuscript

IV 7 (4.1%) 7 (5.0%) 6 (2.2%) 1 (1.0%) 49 (22.7%)

NA 13 (7.6%) 9 (6.5%) 8 (2.9%) 3 (3.0%) 6 (2.8%)

Chemotherapy Chemo 56 (32.7%) 138 (49.6%) 58 (50%) 158 (73.1%)

No chemo 6 (3.5%) 31 (11.2%) 58 (50%) 55 (25.5%)
NA 109 (63.7%) 139 (100%) 109 (39.2%) 3 (1.4%)

Follow up (months) OS median, range 66.1, 0.5-233.1 63.8, 2.4-455.6 64.8, 3.3-338 13, 0.07-109 49.7, 1.9-84.8

*
TMA Yale2 and WTS Yale sets have 65 overlapped cases which were collected from different tissue blocks and in either TMA or WTS format
**
DI: differentiation
Author Manuscript

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.
 Bai et al. Page 20

Table 2.

Cox regression analysis of TIL variables for OS in combined validation sets

Author Manuscript

Univariate (N=749) Multivariate* (N=529)

Parameter HR 95% CI p HR 95% CI p
All validation cases

eTILs% low (<18.2%) 1 1

eTILs% high (≥18.2%) 0.53 0.41-0.68 <0.0001 0.53 0.39-0.70 <0.0001

etTILs% low (<16.9%) 1 1

etTILs% high (≥16.9%) 0.51 0.39-0.67 <0.0001 0.56 0.41-0.76 0.0002

esTILs% low (<57.4%) 1 1

esTILs% high (≥57.4%) 0.51 0.38-0.68 <0.0001 0.49 0.35-0.70 <0.0001
Author Manuscript

eaTILs (mm[ISP]^2) Low (<1195.6) 1 1

eaTILs (mm^2) high (≥1195.6) 0.55 0.42-0.72 <0.0001 0.56 0.42-0.77 0.0003

easTILs low (<19.9) 1 1

easTILs high (≥19.9) 0.61 0.47-0.79 0.0002 0.57 0.42-0.78 0.0003

*
multivariate analysis was adjusted by staging status (stage I&II: low; III&IV: high), age (<50 or ≥50) and histological grade
Author Manuscript
Author Manuscript

Clin Cancer Res. Author manuscript; available in PMC 2022 April 15.