Edge- and Color–Texture-Aware Bag-of-Local-Features Model for Accurate and Interpretable Skin Lesion Diagnosis

<b>Background/Objectives</b>: Deep models have achieved remarkable progress in the diagnosis of skin lesions but face two significant drawbacks. First, they cannot effectively explain the basis of their predictions. Although attention visualization tools like Grad-CAM can create heatmaps...

Full description

Saved in:
Bibliographic Details
Main Authors: Dichao Liu, Kenji Suzuki
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/15/1883
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:<b>Background/Objectives</b>: Deep models have achieved remarkable progress in the diagnosis of skin lesions but face two significant drawbacks. First, they cannot effectively explain the basis of their predictions. Although attention visualization tools like Grad-CAM can create heatmaps using deep features, these features often have large receptive fields, resulting in poor spatial alignment with the input image. Second, the design of most deep models neglects interpretable traditional visual features inspired by clinical experience, such as color–texture and edge features. This study aims to propose a novel approach integrating deep learning with traditional visual features to handle these limitations. <b>Methods</b>: We introduce the edge- and color–texture-aware bag-of-local-features model (ECT-BoFM), which limits the receptive field of deep features to a small size and incorporates edge and color–texture information from traditional features. A non-rigid reconstruction strategy ensures that traditional features enhance rather than constrain the model’s performance. <b>Results</b>: Experiments on the ISIC 2018 and 2019 datasets demonstrated that ECT-BoFM yields precise heatmaps and achieves high diagnostic performance, outperforming state-of-the-art methods. Furthermore, training models using only a small number of the most predictive patches identified by ECT-BoFM achieved diagnostic performance comparable to that obtained using full images, demonstrating its efficiency in exploring key clues. <b>Conclusions</b>: ECT-BoFM successfully combines deep learning and traditional visual features, addressing the interpretability and diagnostic accuracy challenges of existing methods. ECT-BoFM provides an interpretable and accurate framework for skin lesion diagnosis, advancing the integration of AI in dermatological research and clinical applications.
ISSN:2075-4418