Breast Cancer Treatment Progress Prediction Using Deep Learning And Ssim
Keywords:
Breast cancer, Mammogram analysis, Convo- lutional Neural Networks (CNN), Structural Similarity Index (SSIM), Treatment recommendation.Abstract
Breast cancer requires timely and effective treat- ment strategies to ensure the best possible outcomes. Evaluating the progress of chemotherapy is critical for determining whether treatment should continue or be adjusted. This research proposes a deep learning-based application using Convolutional Neural Networks (CNNs) to analyze mammogram scans taken before and after chemotherapy. To objectively assess treatment effectiveness, the system employs the Structural Similarity Index (SSIM) to compare old and recent mammograms. Based on the SSIM score and CNN analysis, the system predicts whether the disease has regressed. If a reduction is detected, it suggests shifting to normal medications; otherwise, it recommends continuing chemotherapy. This solution provides an automated, non-invasive, and cost- effective tool to support oncologists in making evidence-based decisions, reducing reliance on subjective interpretation and min- imizing diagnostic delays. Ultimately, it enhances the precision and personalization of breast cancer treatment plans.
Downloads
References
Jehad Feras AlSamhori, Abdel Rahman Feras AlSamhori “Artificial Intelligence for Breast Cancer: Implications for Diagnosis and Man- agement.” Elsevier on 14 Jun 2024.
[2] Lulu Wang ”Mammography with deep learning for breast cancer detec- tion.” Frontiers in Oncology on feb 12 2024.
Leslie R. Lamb, Constance D. Lehman, Aimilia Gastounioti, Emily
F. Conant, Manisha Bahl “Artificial Intelligence (AI) for Screening Mammography, From the AJR Special Series on AI Applications.” American Journal of Roentgenology on 12 Jan 2022.
[4] Alejandro Rodr´ıguez-Ruiz ”Detection of Breast Cancer with Mammog- raphy: Effect of an Artificial Intelligence Support System” Radiological Society of North America (RSNA) on nov 20 2018.
[5] Jong Seok Ahn, Sangwon Shin “Artificial Intelligence in Breast cancer diagnosis and personalized medicine.” Journal of breast cancer on oct 17 2023.
[6] Carlo Boeri, Corrado Chiappa, Federica Galli, Valentina De Berardinis, Laura Bardelli, Giulio Carcano, Francesca Rovera “Machine Learning techniques in breast cancer prognosis prediction.” wiley on 13 Dec 2019.
[7] Clayton R. Taylor, Natasha Monga, Candise Johnson, Jeffrey R. Hawley and Mitva Patel “Artificial Intelligence Applications in Breast Imaging.” MDPI (Journal: Diagnostics) 13 Jun 2023.
[8] Serena C. Houghton and Susan E. Hankinson “Cancer Progress and Priorities: Breast Cancer.” American Association for Cancer Research (AACR) on 30 May 2021.
[9] Yogendra Singh Solanki, Prasun Chakrabarti ”A hybrid supervised machine learning classifier system for breast cancer using feature selec- tion and data imbalance handling approaches.”MDPI (Multidisciplinary Digital Publishing Institute) on 16 mar 2021.
[10] Kai Bian, Mengran Zhou, Feng Hu and Wenhao Lai ”A new solution for rapid identification of breast cancer categorical data based on attribute selection and feature extraction.” Frontiers in genetics on 09 sep 2020.
[11] Hua Chai, Siyin Lin, Junqi Lin ”An uncertainty-based interpretable deep learning framework for predicting breast cancer outcome.” BMC Informatics on 21 feb 2024.
[12] Pei Liu , Bo Fu , Simon X. Yang ”Optimizing Survival Analysis of XGBoost for Ties to Predict Disease Progression of Breast Cancer.” Institute of Electricals and Electronics Engineering(IEEE.org) on may 11 2020.
[13] Nehmat Houssamia and M Luke Marinovich ”AI for mammography screening: enter evidence from prospective trials.” The Lancent on sep 8 2023.
[14] Ahmed S. Elkorany and Zeinab F. Elsharkawy ”Efficient breast cancer mammograms diagnosis using three deep neural networks and term variance.” Nature scientific reports on feb 15 2023.
[15] Maurizio Ce` and Elena Caloro ”Artificial intelligence in breast cancer imaging: risk stratification, lesion detection and classification,
treatment planning and prognosis—a narrative review” Open Exploration publish- ing on dec 27 2022.
