LAM-CATNet: lambda-aware multi-scale cross-attention swin transformer network for mammogram classification

The fundamental requirement for the initial recognition of a mammogram is the accurate segmentation and classification of breast lesions in mammograms, especially when small or hard-to-identify lesions are involved. We present here a methodology that uses statistical analysis of variability to upgrade the execution of automated detection of breast lesions through a new model, called LAM-CATNet (Lambda-Aware Multi-scale Cross-Attention Swin Transformer Network). LAM-CATNet is designed with the intent of creating a transformer fusion model that applies statistical intensity modelling with a distribution function for deriving the data from the mammogram as well as deriving features with deep learning to produce segmented mammograms and classify lesions based on that segmentation. It is crucial to identify accurately and consistently segment breast cancer lesions that are detected in mammograms so that they can be detected early, particularly in small or difficult-to-identify cancers. This work examines statistical variability and improves diagnostic performance in automated breast lesion analysis with LAM-CATNet, a Lambda Distribution-Guided Transformer-Fused Hybrid Segmentation Network. As shown, the proposed LAM-CATNet outperformed both the baseline hybrid model and the conventional models by achieving Dice coefficients for the segmentation of 0.786 (CBIS-DDSM) and 0.869 (MIAS). For classification, the network achieved an accuracy of 94.7% and an area under the ROC curve of 98.2%. The attention map visualizations provided increased interpretability of the model regarding clinical decision confidence, as attention was focused on relevant areas of the lesion. In overall, LAM-CATNet improves automated breast lesion segmentation and classification by integrating transformer-based global context modelling along with conventional U-Net local feature extraction and lambda statistical principle. Its high interpretability for clinical use, consistent statistical reasoning, and high performance demonstrates potential as a supportive tool for computer-aided diagnosis, subject to further clinical validation in breast cancer screening using mammography.