Only Positive Cases: 5-fold High-order Attention Interaction Model for Skin Segmentation Derived Classification

TL;DR

This paper introduces MHA-UNet, a highly explainable skin lesion segmentation model that predicts lesion presence without negative samples, utilizing high-order attention interactions for improved interpretability and performance.

Contribution

The paper proposes a novel high-order attention interaction mechanism and MHA-UNet model that enable lesion classification and segmentation without negative training samples, enhancing interpretability.

Findings

Achieved up to 81.0% positive detection rate.

Achieved up to 83.5% negative detection rate.

Demonstrated state-of-the-art segmentation performance across multiple datasets.

Abstract

Computer-aided diagnosis of skin diseases is an important tool. However, the interpretability of computer-aided diagnosis is currently poor. Dermatologists and patients cannot intuitively understand the learning and prediction process of neural networks, which will lead to a decrease in the credibility of computer-aided diagnosis. In addition, traditional methods need to be trained using negative samples in order to predict the presence or absence of a lesion, but medical data is often in short supply. In this paper, we propose a multiple high-order attention interaction model (MHA-UNet) for use in a highly explainable skin lesion segmentation task. MHA-UNet is able to obtain the presence or absence of a lesion by explainable reasoning without the need for training on negative samples. Specifically, we propose a high-order attention interaction mechanism that introduces squeeze attention to a higher level for feature attention. In addition, a multiple high-order attention interaction (MHAblock) module is proposed by combining the different features of different orders. For classifying the presence or absence of lesions, we conducted classification experiments on several publicly available datasets in the absence of negative samples, based on explainable reasoning about the interaction of 5 attention orders of MHAblock. The highest positive detection rate obtained from the experiments was 81.0% and the highest negative detection rate was 83.5%. For segmentation experiments, comparison experiments of the proposed method with 13 medical segmentation models and external validation experiments with 8 state-of-the-art models in three public datasets and our clinical dataset demonstrate the state-of-the-art performance of our model. The code is available from https://github.com/wurenkai/MHA-UNet.