DAYANANDA SAGAR ACADEMY OF TECHNOLOGY & MANAGEMENT

Department of Information Science & Engineering

Computational Technique Based on Machine Learning

and Image Processing for Medical Image Analysis of
Breast Cancer Diagnosis
Technical Seminar Presentation

1DT20IS091 : SINDHU A

GUIDE NAME :Dr. POOJA NAYAK S

(ASSOCIATE PROFESSOR)

1
 TECHNICAL SEMINAR PRESENTATION
Contents

 Introduction
 Abstract
 Literature Survey
 Methodology
 Results
 Conclusion and Future Enhancement
 References (As per IEEE format)

2
 1. INTRODUCTION

Cancer, a multifaceted disease affecting various body regions, poses significant challenges to healthcare
systems worldwide. By leveraging data mining processes, the study aims to refine the statistical analysis of
cancer data, particularly focusing on the Greece Cancer Log dataset spanning from 1998 to 2004. Through
the utilization of computational models and advanced algorithms, the research endeavors to improve the
predictive capabilities for breast cancer risk assessment based on mammographic image analysis.

The proposed computational technique offers a novel approach to categorizing and identifying breast
cancer, marking a significant advancement in the field of medical image analysis. By integrating image
preprocessing, feature extraction, and machine learning methodologies, the model aims to provide accurate
classification and identification of breast cancer, distinguishing between benign, malignant, and
noncancerous cases. The inclusion of the geometric mean filter for image enhancement and the utilization
of AlexNet for feature extraction underscore the sophistication and innovation of the approach.

3
 2. ABSTRACT

Breast cancer is the most lethal type of cancer for all women worldwide. At the moment, there are no
effective techniques for preventing or curing breast cancer, as the source of the disease is unclear. Early
diagnosis is a highly successful means of detecting and managing breast cancer, and early identification
may result in a greater likelihood of complete recovery. Mammography is the most effective method of
detecting breast cancer early. Additionally, this instrument enables the detection of additional illnesses
and may provide information about the nature of cancer, such as benign, malignant, or normal. This
model combines image preprocessing, feature extraction, feature selection, and machine learning
techniques to aid in the classification and identification of skin diseases. To enhance the image’s quality,
a geometric mean filter is used. AlexNet is used for extracting features. Feature selection is performed
using the relief algorithm. For disease categorization and detection, the model makes use of the
machine learning techniques such as least square support vector machine. This proposed technology is
advantageous for accurately identifying breast cancer disease using image analysis.
4
3. LITERATURE SURVEY

5
4. METHODOLOGY

6
 5. RESULTS

1. Noise Reduction: The research emphasized the importance of noise reduction in mammographic images for
accurate analysis and interpretation. Background information, the pectoral muscle, and various types of noise
present in the images were identified as factors requiring mitigation to enhance the quality of image analysis.

2. Algorithm Performance Evaluation: The study evaluated the performance of different algorithms using
parameters such as accuracy, sensitivity, and specificity. This analysis provided insights into the effectiveness of
the computational techniques employed in the classification and identification of breast cancer cases.

3. Feature Extraction and Selection: The research utilized advanced techniques such as image preprocessing,
feature extraction using AlexNet, and feature selection with the relief algorithm. These methodologies played a
crucial role in identifying relevant characteristics for accurate disease diagnosis.

4. Machine Learning Algorithms: The study employed machine learning algorithms including the least square
support vector machine, KNN, random forest, and Naïve Bayes for disease identification and classification. By
leveraging these algorithms, the model demonstrated its capability to effectively diagnose various illnesses
beyond breast cancer, showcasing its versatility and potential for broader medical applications .

7
 6. CONCLUSION AND FUTURE ENHANCEMENT

It integrates machine learning and image processing techniques for the accurate
diagnosis and classification of breast cancer using the MIAS database. By
leveraging advanced algorithms and data mining processes, the study demonstrates
the potential to enhance the efficiency and precision of medical image analysis,
particularly in the context of breast cancer detection. The results highlight the
importance of noise reduction, feature extraction, and algorithm performance
evaluation in improving the diagnostic capabilities of the proposed computational
technique. Future enhancement are Collaboration with Healthcare Professionals,
Enhanced Feature Selection Expansion to Other Medical Conditions and Clinical
Validation .

8
 7. REFERENCES
1. R. Thippa, S. Bhattacharya, P. K. R. Maddikunta, and S. Hakak, “Antlion re-sampling based deep neural network
model for classification of imbalanced multimodal stroke dataset,” Multimed Tools Appl, Springer, Berlin,
Germany, 2020.

2. S. Suman, C. K. Loo, K. S. Yap, K. W. Wong, T. Beng, and . Huang, “Image enhancement using geometric mean filter
and gamma correction for WCE images,” Neural Information Processing. ICONIP 2014, Springer, Cham,
Switzerland, vol. 8836, 2014.

3. M. Canayaz and M. H. COVIDNet, “MH-COVIDNet: diagnosis of COVID-19 using deep neural networks and meta-
heuristic-based feature selection on X-ray images,” Biomedical Signal Processing and Control, vol. 64, Article ID
102257, 2021.

4. Y. Ma, X. Liang, G. Sheng, J. T. Kwok, M. Wang, and G. Li, “Noniterative sparse LS-SVM based on globally
representative point selection,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 2, pp.
788–798, 2021.

5. B. Sun and H. Chen, “A survey of k nearest neighbor algorithms for solving the class imbalanced
problem,” Wireless Communications and Mobile Computing, vol. 2021, Article ID 5520990, 12 pages, 2021.
6. [Link], “The mini-MIAS database of mammograms,” 2012, [Link]
9
 THANK YOU

1DT20IS091 : SINDHU A

10