Asymmetric Lesion Detection with Geometric Patterns and CNN-SVM Classification

2025-07-23

AI Summary

This study addresses the clinical challenge that melanoma diagnosis from dermoscopic images relies heavily on lesion asymmetry assessment—a task difficult for non-experts to perform accurately. To this end, we propose an interpretable, hybrid辅助 method integrating geometric pattern analysis with deep learning. First, we establish a symmetry annotation scheme grounded in clinical guidelines. Next, we jointly encode lesion geometry—quantified via axial symmetry ratio and contour eccentricity—with shape-color-texture features extracted by a pretrained CNN, feeding the fused representation into a multi-class SVM for asymmetry grading. Our method achieves 99.00% detection accuracy on the geometric analysis subtask and, end-to-end, attains 94% Cohen’s Kappa, 95% macro-F1, and 97% weighted-F1. It significantly improves non-experts’ comprehension of asymmetry criteria and inter-rater consistency, while preserving clinical interpretability and high diagnostic accuracy.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

In dermoscopic images, which allow visualization of surface skin structures not visible to the naked eye, lesion shape offers vital insights into skin diseases. In clinically practiced methods, asymmetric lesion shape is one of the criteria for diagnosing melanoma. Initially, we labeled data for a non-annotated dataset with symmetrical information based on clinical assessments. Subsequently, we propose a supporting technique, a supervised learning image processing algorithm, to analyze the geometrical pattern of lesion shape, aiding non-experts in understanding the criteria of an asymmetric lesion. We then utilize a pre-trained convolutional neural network (CNN) to extract shape, color, and texture features from dermoscopic images for training a multiclass support vector machine (SVM) classifier, outperforming state-of-the-art methods from the literature. In the geometry-based experiment, we achieved a 99.00% detection rate for dermatological asymmetric lesions. In the CNN-based experiment, the best performance is found with 94% Kappa Score, 95% Macro F1-score, and 97% Weighted F1-score for classifying lesion shapes (Asymmetric, Half-Symmetric, and Symmetric).

Problem

• Detects asymmetric skin lesions using geometric patterns
• Classifies lesion shapes with CNN-SVM for melanoma diagnosis
• Improves accuracy in dermatological lesion shape analysis

Innovation

• Geometric pattern analysis for lesion asymmetry
• CNN-SVM hybrid for feature extraction and classification
• High accuracy in asymmetric lesion detection