Accurate skin-lesion segmentation remains a key technical challenge for computer-aided diagnosis of skin cancer. Convolutional neural networks, while effective, are constrained by limited receptive fields and thus struggle to model long-range dependencies. Vision Transformers capture global context, yet their quadratic complexity and large parameter budgets hinder use on the small-sample medical datasets common in dermatology. We introduce the MedLiteNet, a lightweight CNN Transformer hybrid tailored for dermoscopic segmentation that achieves high precision through hierarchical feature extraction and multi-scale context aggregation. The encoder stacks depth-wise Mobile Inverted Bottleneck blocks to curb computation, inserts a bottleneck-level cross-scale token-mixing unit to exchange information between resolutions, and embeds a boundary-aware self-attention module to sharpen lesion contours.
@article{arxiv.2509.03041,
title = {MedLiteNet: Lightweight Hybrid Medical Image Segmentation Model},
author = {Pengyang Yu and Haoquan Wang and Gerard Marks and Tahar Kechadi and Laurence T. Yang and Sahraoui Dhelim and Nyothiri Aung},
journal= {arXiv preprint arXiv:2509.03041},
year = {2025}
}