Mammary Tumor Screening using deep learning provides an innovative approach for early breast cancer detection. In this work, a model trained on Convolutional Neural Networks (CNNs) on the Kaggle Multi Cancer dataset, consisting of 10,000 high-resolution histopathological images of benign and malignant tumors. To improve model performance and lessen overfitting, preprocessing methods like resizing, normalisation, and data augmentation are used. The CNN model .The CNN model is designed for binary classification, and itsF1-score, recall, accuracy, and precision are used to assess performance. This inquiry seeks to fashion a faultless core, employing an exhaustive dataset used by a cancer detection system. The high-resolution dataset comes from Kaggle, consisting of histopathological images of both benign and malignant growths, specifically malignant breast tumors. It furnishes multiple images to procure thorough diagnostic evaluations quickly. Experimental results show high effectiveness, implying a high level of helpfulness. Every instance of breast cancer being detected early improves patient outcomes
Introduction
Breast cancer remains one of the leading causes of cancer-related deaths globally, emphasizing the urgent need for accurate and early detection methods. Traditional diagnostic tools like mammography and ultrasound, while essential, often face challenges such as delays, human error, and limitations in detecting tumors in dense breast tissue. Recent advances in artificial intelligence, particularly deep learning and Convolutional Neural Networks (CNNs), offer promising improvements in automating and enhancing the accuracy of breast cancer diagnosis through analysis of histopathological images.
This study develops a deep CNN model for mammary tumor screening using the Kaggle Multi Cancer dataset, which contains 10,000 high-resolution images of benign and malignant tumors. The approach includes image preprocessing, normalization, data augmentation, and rigorous model training for binary classification, achieving improved diagnostic accuracy and speed. The model is deployed via a cloud-based platform with a user-friendly graphical interface, enabling healthcare professionals to obtain rapid and reliable tumor classifications remotely.
The literature review highlights the limitations of existing screening methods like mammography, the potential of integrating thermal imaging with AI, and the growing role of explainable AI to improve transparency and trust in diagnostic models. Various machine learning techniques, including Support Vector Machines, Random Forest, and advanced CNN architectures (e.g., ResNet, EfficientNet), have shown high accuracy in tumor classification. Preprocessing methods and augmentation strategies play a critical role in enhancing model robustness.
The methodology involves careful data handling, resizing images to uniform dimensions, employing transfer learning, and using performance metrics such as accuracy, precision, recall, and F1 score for evaluation. The final system is designed for practical clinical use, offering a scalable and accessible tool to aid early detection and reduce breast cancer mortality.
Conclusion
In conclusion, this innovative approach holds great promise and analysis of image is very powerful procedure to recognize the existence of breast cancer. Continued research, for optimal results, the integration of new modern techniques on diverse datasets to enhance detection of accuracy, and for better outcomes.For advanced imaging technologies such as ultrasound, histopathology images, mammograms, and many more for high accuracy. The accurate categorizing of tumors as benign or malignant remarkably upgrade early diagnosis and treatment planning.
References
[1] Benefits and harms of breast cancer screening: cohort study of breast cancer mortality and overdiagnosis. Wang S, Sultana F, Kavanagh A, 2023.
[2] Multi-Input Deep Learning Approach for Breast Cancer Screening Using Thermal Infrared Imaging and Clinical Data , Dennies Tsietso, Abid Yahya , 2023.
[3] Breast Cancer Detection and Classification, 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE), Poonam Kathale, Snehal Thorat, 2020.
[4] A Systematic Review on Screening, Examining and Classification of Breast Cancer, 2021 Smart Technologies, Communication and Robotics (STCR), Sannasi Chakravarthy S R, Harikumar Rajaguru, 2021
[5] Deep Learning to Improve Breast Cancer Detection on Screening Mammography , Li Shen, Laurie R. Margolies, Joseph H. Rothstein, Eugene Fluder, Russell McBride & Weiva Sieh, 2019
[6] Mammography with deep learning for breast cancer detection, Lulu Wang, 2024.
[7] Breast Cancer Detection Using Machine Learning Algorithms , Kumar Shubham, Dr. R. Kamalraj,2022.
[8] Breast histopathological image analysis using image processing techniques for diagnostic purposes:A methodological review ,Rashmi R , Keerthana Prasad,Chethana Babu K Udupa, 2021.
[9] Computer-aided breast cancer detection and classification in mammography: A comprehensive review, Kosmia Loizidou , Rafaella Elia, Costas Pitris,2021.
[10] Breast Cancer Detection and Prevention Using Machine Learning , Arslan Khalid , Arif Mehmood , Amerah Alabrah , Bader Fahad Alkhamees , Farhan Amin , Hussain AlSalman and Gyu Sang Choi,2023.
[11] Deep Learning in Breast Cancer Detection and Classification, Ghada Hamed(B) , Mohammed Abd El-Rahman Marey, Safaa El-Sayed Amin, and Mohamed Fahmy Tolba,2020.
[12] Enhancing Breast Cancer Diagnosis in Mammography: Evaluation and Integration of Convolutional Neural Networks and Explainable AI,Maryam Ahmed, Tooba Bibi, Rizwan Ahmed Khan , and Sidra Nasir,2024.
[13] Using hybrid pre-trained models for breast cancer detection , Sameh ZarifID1, Hatem Abdulkader , Ibrahim Elaraby , Abdullah Alharbi, Wail S. Elkilani , Pawe? P?awiakI,2023.