Prediction Modeling for Breast Cancer Treatment Planning Using Contrast-Enhanced Mammography

Deep Learning-Based Segmentation, Classification, and Explainable Diagnosis of Breast Cancer Lesions

Breast cancer remains one of the most prevalent malignancies affecting women worldwide, and early, accurate detection through medical imaging is central to improving survival outcomes. This paper presents an end-to-end computer-aided diagnosis (CAD) framework that performs lesion segmentation, region-of-interest (ROI) extraction, tumor stage estimation, benign/malignant classification, and visual explainability across two complementary imaging modalities: digital mammography, represented by the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM), and breast ultrasound, represented by the Breast Ultrasound Images (BUSI) dataset. For each modality, a modality-specific U-Net architecture was trained to generate binary lesion masks, from which tumor coverage percentage and a rule-based disease stage were derived. Three classifier backbones were benchmarked per modality — ResNet50, VGG16, and a custom convolutional neural network (CNN) for CBIS-DDSM (benign vs. malignant), and ResNet50, EfficientNet-B0, and a custom CNN for BUSI (benign vs. malignant vs. normal) — with Gradient-weighted Class Activation Mapping (Grad-CAM) applied to the strongest classifiers for interpretability. The trained pipelines were deployed in a Django-based web application allowing end users to upload an image and receive segmentation, ROI, stage, classification, confidence, and Grad-CAM outputs in real time. Results show a pronounced modality gap: the U-Net segmentation network achieved a validation Dice coefficient of 0.462 on BUSI versus 0.247 on CBIS-DDSM, and the best classifier reached 84.07% test accuracy on BUSI (ResNet50) compared with 61.86% on CBIS-DDSM (ResNet50), with markedly lower malignant-class recall on mammography (37%) than on ultrasound (76%). These findings quantify how imaging modality, lesion conspicuity, and dataset scale materially affect both segmentation and diagnostic performance, and they underscore the necessity of transparent, modality-aware reporting — including recall/sensitivity for the malignant class, not just aggregate accuracy — when evaluating deep learning systems intended to support breast cancer screening.

A novel hierarchical transfer learning to enhance breast cancer detection on screening mammography using deep learning.

Transfer Learning Model for Breast Cancer Detection Using Mammograms from Low-Resource Settings

Breast cancer remains a leading cause of cancer death that affects women worldwide, and the burden is felt most acutely in low resource settings where mammography access is scarce, and radiologist coverage is thin. Transfer learning-based deep learning models were evaluated for practical utility in breast cancer screening where imaging resources are restricted. The CBIS-DDSM dataset (Kaggle JPG version) was used for this study, with pathology labels mapped into a binary benign-versus-malignant classification scheme. The dataset consisted of 3,568 full mammograms and 3,461 ROI images from over 1,500 patients after quality control. 5-fold StratifiedGroupKFold cross-validation was used to prevent patient-level data leakage, which causes performance inflation in published studies, and ensured that no patient data combined training and validation datasets. The research evaluated two types of input data which included cropped region-of-interest lesion patches and complete mammogram images. InceptionV3 achieved the highest performance among ROI models by reaching ROC-AUC 0.821 and PR-AUC 0.775 and sensitivity 0.785. The study used full mammograms to evaluate ResNet50 performance which achieved ROC-AUC 0.838 and sensitivity 0.790 results. The study shows that transfer learning acts as a strong base for AI-assisted mammography triage systems in low-resource environments when patient level assessment continues throughout system development.

Breast cancer detection and classification via a robust deep learning approach

This work presents a leakage-controlled deep-learning framework for breast cancer classification using the CBIS-DDSM mammography archive. The proposed pipeline combines patient-level data partitioning before augmentation, a two-stage transfer-learning strategy based on ResNet50, and an Inter-View Attention Fusion (IVAF) module for adaptive fusion of paired craniocaudal (CC) and mediolateral oblique (MLO) feature maps. IVAF was modeled as a light-weighted convolutional gating strategy added after the last ResNet50 convolutional layer in order to create a weighted spatial-channel representation from the paired mammography images. In terms of the performance of the model under CBIS-DDSM held-out testing protocol, the entire model scored an accuracy of 97.12%, sensitivity of 96.44%, specificity of 97.68%, and AUC-ROC of 0.9876 based on the test results obtained on 6,117 images of 222 different patients. The average accuracy obtained using 100 random seeds was found to be 97.11% ± 0.18%.

Deep Learning for Early Breast Cancer Detection and Personalized Treatment Strategies

An extended deep learning framework for early breast cancer detection using histopathological images is presented and it is suggested that AI-assisted pathology can reduce diagnostic workload, improve detection efficiency, and support personalized clinical decision-making.

Breast Cancer Detection Using Transfer Learning Contribution

: Breast cancer remains one of the most critical health concerns for women, and early detection plays a major role in improving survival rates. With the rapid growth of deep learning techniques, computer-based systems have become increasingly effective at analyzing and classifying medical images. In this work, deep learning particularly transfer learning is used to identify breast cancer from histopathological images. Transfer learning allows us to take advantage of powerful models that have already been trained on vast image datasets and adapt them to our specific task. For this study, three well-known pre-trained convolutional neural network (CNN) architectures InceptionV3, EfficientNet, and ResNet50 were evaluated to determine which performs best for breast cancer classification. Each model was fine-tuned using our collection of breast tissue images. During experimentation, we noticed that some models had difficulty learning the necessary patterns for correct classification. Among them, ResNet50 stood out by producing more reliable and accurate predictions. The workflow followed several essential stages: images were preprocessed and resized according to each model’s input requirements, and data augmentation was applied to increase variety and prevent overfitt ing. After preparing the dataset, the models were trained and assessed using standard evaluation metrics, helping us compare their strengths and weaknesses. The results clearly indicate that the choice of architecture has a major impact on performance, esp ecially in medical image analysis. ResNet50’s deeper network and skip connections enabled it to capture fine-grained features within the images, leading to improved accuracy. This demonstrates the strong potential of deep learning techniques in healthcare. Beyond building an effective classifier, this project also emphasizes how artificial intelligence can support medical professionals in diagnosis. A dependable system can minimize human error, assist doctors in decision-making, and accelerate the detection process particularly in regions where experienced pathologists may be scarce. Overall, this work shows that transfer learning is a practical and efficient method for breast cancer detection and could contribute to better patient outcomes in the future.