Ugly Ducklings or Swans: A Tiered Quadruplet Network with Patient-Specific Mining for Improved Skin Lesion Classification

TL;DR

This paper introduces DMT-Quadruplet, a deep metric learning network with patient-specific mining, significantly improving skin lesion classification by capturing both global and local features across patients.

Contribution

The paper proposes a novel tiered quadruplet network with patient-specific mining and dynamic margin, enhancing lesion feature learning for better skin lesion classification.

Findings

Achieves 54% higher sensitivity than baseline ResNet18

Outperforms naive triplet network by 37% in sensitivity

Effectively classifies ugly duckling lesions in patient-specific and agnostic settings

Abstract

An ugly duckling is an obviously different skin lesion from surrounding lesions of an individual, and the ugly duckling sign is a criterion used to aid in the diagnosis of cutaneous melanoma by differentiating between highly suspicious and benign lesions. However, the appearance of pigmented lesions, can change drastically from one patient to another, resulting in difficulties in visual separation of ugly ducklings. Hence, we propose DMT-Quadruplet - a deep metric learning network to learn lesion features at two tiers - patient-level and lesion-level. We introduce a patient-specific quadruplet mining approach together with a tiered quadruplet network, to drive the network to learn more contextual information both globally and locally between the two tiers. We further incorporate a dynamic margin within the patient-specific mining to allow more useful quadruplets to be mined within individuals. Comprehensive experiments show that our proposed method outperforms traditional classifiers, achieving 54% higher sensitivity than a baseline ResNet18 CNN and 37% higher than a naive triplet network in classifying ugly duckling lesions. Visualisation of the data manifold in the metric space further illustrates that DMT-Quadruplet is capable of classifying ugly duckling lesions in both patient-specific and patient-agnostic manner successfully.