Scribd Logo
Upload

Welcome to Scribd!

  • 33 views

    Zeroth Review Minor P

    Uploaded by

    vedant bhatnagar
    The document discusses a proposed breast cancer detection system (BCDS) that uses machine learning techniques. It outlines challenges in existing methods and how the BCDS aims to improve accuracy through preprocessing, feature extraction, and rigorous performance evaluation. Comparative analysis is used to show the proposed approach is superior to traditional methods.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Zeroth Review Minor P

    Uploaded by

    vedant bhatnagar
    33 views11 pages
    The document discusses a proposed breast cancer detection system (BCDS) that uses machine learning techniques. It outlines challenges in existing methods and how the BCDS aims to improve accuracy through preprocessing, feature extraction, and rigorous performance evaluation. Comparative analysis is used to show the proposed approach is superior to traditional methods.

    Original Description:

    base paper

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses a proposed breast cancer detection system (BCDS) that uses machine learning techniques. It outlines challenges in existing methods and how the BCDS aims to improve accuracy through preprocessing, feature extraction, and rigorous performance evaluation. Comparative analysis is used to show the proposed approach is superior to traditional methods.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    33 views11 pages

    Zeroth Review Minor P

    Uploaded by

    vedant bhatnagar
    The document discusses a proposed breast cancer detection system (BCDS) that uses machine learning techniques. It outlines challenges in existing methods and how the BCDS aims to improve accuracy through preprocessing, feature extraction, and rigorous performance evaluation. Comparative analysis is used to show the proposed approach is superior to traditional methods.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 11

    SRM INSTITUTE OF SCIENCE AND TECHNOLOGY

    COLLEGE OF ENGINEERING AND TECHNOLOGY


    DEPARTMENT OF NETWORKING AND COMMUNICATIONS
    18CSP107L - MINOR PROJECT

    Breast Cancer Detection

    Student 1 Reg No: RA2011028010017


    Student 2 Reg No:RA2011028010055
    Batch ID:
    Guide name and Designation:Dr.Meenakshi K ,Assistant Professor
    Table of content

    ● Abstract
    ● Introduction
    ● Motivation and Statistics
    ● Challenges
    ● Proposed Idea
    ● Novelty
    ● Conclusion
    ● References
    Abstract
    Breast cancer is a prevalent and significant health issue affecting women worldwide. Early
    identification is crucial for effective management and reducing mortality rates.
    Computer-aided detection/diagnosis (CAD) systems play a vital role in early identification.
    This paper aims to leverage recent advances in CAD systems and related techniques to
    predict breast cancer presence. Machine learning, where machines learn and perform tasks
    independently, is employed using trained data to predict whether a person has breast
    cancer or not.
    Introduction
    The proposed BCDS ( Breast Cancer Detection System) encompasses a multi-step
    approach, starting with the pre-processing of mammography images to enhance their
    quality and remove noise. Subsequently, a feature extraction module is employed to extract
    relevant features from the pre-processed images, focusing on areas of interest,
    microcalcifications, and masses. These features act as vital discriminative characteristics
    for distinguishing between benign and malignant tissues. To assess the system's
    performance, the BCDS is rigorously evaluated using a variety of metrics, including
    accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve
    (AUC-ROC). Comparative analysis is conducted to demonstrate the superiority of the
    proposed approach over traditional methods.
    Motivation & Statistics
    ● Breast Cancer Impact: Breast cancer is a significant health concern
    worldwide, affecting millions of women each year. Early detection is
    crucial for effective treatment and improved survival rates. Machine
    learning algorithms have shown great promise in aiding early breast
    cancer detection.

    ● Improving Accuracy: Traditional breast cancer screening methods may


    have limitations in terms of accuracy and false-positive/negative rates.
    Machine learning techniques can help enhance the accuracy of breast
    cancer detection, leading to better outcomes for patients.

    ● Survival Rates: Early detection significantly improves breast cancer


    survival rates. The American Cancer Society reports that the 5-year
    relative survival rate for localized breast cancer (confined to the breast)
    is 99%, while it drops to 27% for distant-stage breast cancer (spread to
    distant organs).
    Challenges and Proposed Ideas

    Challenges are mostly modeling based on records of only one database, and the
    lack of access to genetic data that could influence the findings of the study.

    Usage of different machine learning approaches are used considering


    demographic, laboratory, and mammography features, resulting in comparing the
    performance of different approaches in predicting breast cancer.
    Novelty
    ● Enhanced Accuracy: Machine learning algorithms, especially deep learning techniques like CNNs,
    can process vast amounts of data and extract intricate patterns. This enables higher accuracy in
    distinguishing between malignant and benign tumors compared to traditional diagnostic methods.

    ● Early Detection: Machine learning models can analyze subtle changes in breast tissue patterns,
    allowing for early detection of potential tumors before they become clinically evident. This early
    detection significantly improves the chances of successful treatment and better patient outcomes.

    ● Personalized Treatment Plans: ML-based systems can analyze patient data, including genetic
    information, medical history, and imaging results, to create personalized treatment plans. This
    approach ensures that patients receive tailored therapies that are more effective and have fewer
    side effects.
    .● Handling Big Data: Machine learning can efficiently handle and process massive
    datasets, including medical images, patient records, and genomic data. It enables
    researchers to extract valuable insights and trends from big data, leading to better
    understanding of breast cancer and potential breakthroughs.
    ● Integration with Imaging Technology: Machine learning algorithms can be
    integrated with various medical imaging technologies, such as mammograms,
    ultrasounds, and MRIs. This integration enhances the accuracy and reliability of
    breast cancer detection and reduces the chances of false negatives or false
    positives.
    ● Real-time Decision Support: ML models can provide real-time decision support to
    healthcare professionals, assisting them in making accurate diagnoses and
    treatment recommendations promptly.
    ● Continuous Learning: ML models can continuously learn and improve over time as
    they receive more data, leading to adaptive and updated diagnostic approaches.
    ● Cost-effectiveness: ML-based systems have the potential to streamline healthcare
    processes, reduce manual workload, and optimize resource utilization, making
    breast cancer detection and treatment more cost-effective.
    Conclusion
    The results demonstrate that the BCDS achieves high accuracy and sensitivity in detecting
    breast cancer, outperforming existing systems and demonstrating its potential to
    significantly impact breast cancer diagnostics. Furthermore, the system's efficiency allows
    for quick processing and real-time diagnosis, leading to reduced waiting times for patients
    and better allocation of medical resources.
    Reference
    1. Sweta Bhise, Simran Bepari, Shrutika Gadeka, Dr. Shailendra Aswale “Breast
    Cancer Detection using Machine Learning Techniques”(July-2021)
    2. Ali Bou Nasser, Manar Abu Talib, Qassim MH Nasir, Yaman Mohamad Afadar
    “Breast cancer detection using artificial intelligence techniques: A systematic
    literature review”(March 2022)
    3. Thippaluru Umamaheswari; Y. Murali Mohan Babu “Literature Review on
    Breast Cancer Diagnosis using 3D Images: Methods and Performance
    Analysis”(2021)
    4. Wenbin Yue,Zidong Wang ,Hongwei Chen ,Annette Payne and Xiaohu
    “Machine Learning with Applications in Breast Cancer Diagnosis and
    Prognosis”(May 2018)
    Thank You

    You might also like