# MSA-DCNN: A Data-Efficient Multi-Scale Attention Deformable CNN for Medical Image Classification Source: [MSA-DCNN: A Data-Efficient Multi-Scale Attention Deformable CNN for Medical Image Classification]() Collection index: [llms.txt]() Data updated: 2026-08-08T05:00:13.568Z Authors: Hamza Hussaini, Shahana Bano, Eyad Elyan, Carlos Francisco Moreno-Garc\\'ia Published: 2026-07-07T09:52:46.000Z ## Abstract Existing deep learning methods perform well in medical image classification but struggle with multi-scale morphology and limited annotations due to fixed sampling and data-hungry training. Existing approaches address these challenges in isolation: DCN-based models provide adaptive sampling but lack explicit multi-scale attention fusion and label-efficient regularisation; multi-scale architectures typically rely on static fusion; and semi-supervised methods target label scarcity without jointly modelling adaptive cross-scale representations. We propose MSA-DCNN, a scale-consistent deformable attention learning framework that introduces adaptive multi-scale sampling, within-scale saliency refinement, learned cross-scale fusion, and auxiliary self-distillation within a unified optimisation scheme, with potential to generalise to structurally heterogeneous anatomy. We evaluate on three public benchmarks and an external hold-out set for leukaemia. MSA-DCNN demonstrates competitive and often better performance against ViT baselines, CNN baselines, and a MICCAI semi-supervised baseline under distribution shift and label scarcity in accuracy, F1, and AUC (binary), while using fewer parameters. Ablations confirm complementary component contributions, supporting MSA-DCNN as a practical foundation for data-efficient medical image classification. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ISIC 2020](): Image Classification; ISIC 2020; Accuracy: 95. - [Image Classification on PBC](): Image Classification; PBC; Accuracy: 94. - [Image Classification on C-NMC](): Image Classification; C-NMC; AUC: 96. - [Image Classification on ALL (Hold-Out)](): Image Classification; ALL (Hold-Out); AUC: 93. ## Original sources and implementation [Original paper]() [PDF]()