Papers › Evaluating Deep Learning Models for Breast Cancer Classification: A Comparative Study

Evaluating Deep Learning Models for Breast Cancer Classification: A Comparative Study

29 Aug 2024arXiv:2408.16859archive 2025-07-28

Sania Eskandari, Ali Eslamian, Nusrat Munia, Amjad Alqarni, Qiang Cheng

This study evaluates the effectiveness of deep learning models in classifying histopathological images for early and accurate detection of breast cancer. Eight advanced models, including ResNet-50, DenseNet-121, ResNeXt-50, Vision Transformer (ViT), GoogLeNet (Inception v3), EfficientNet, MobileNet, and SqueezeNet, were compared using a dataset of 277,524 image patches. The Vision Transformer (ViT) model, with its attention-based mechanisms, achieved the highest validation accuracy of 94%, outperforming conventional CNNs. The study demonstrates the potential of advanced machine learning methods to enhance precision and efficiency in breast cancer diagnosis in clinical settings.

PaperPDFCode

Code

saniaesk/Breast-Cancer-Classification officialmentioned on GitHubpytorch report
aseslamian/BreastCancerTransferModels mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Breast Cancer DetectionCancer ClassificationTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAbsolute Position EncodingsAdamAttentionAuxiliary ClassifierAverage PoolingBPEBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetFire ModuleGlobal Average PoolingGoogLeNetInception ModuleInverted Residual BlockLabel SmoothingLayer NormalizationLinear LayerLocal Response NormalizationMax PoolingMulti-Head AttentionPointwise ConvolutionPosition-Wise Feed-Forward LayerRMSPropReLUResidual ConnectionSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockSqueezeNetTransformerVision TransformerXavier Initialization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections