Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration

TL;DR

The paper presents the elsarticle LaTeX class, a redesigned document class for formatting manuscripts destined for Elsevier journals. Built on the standard article class, it emphasizes compatibility to minimize package conflicts and centralizes common features and dependencies such as natbib, geometry, and hyperref. It provides flexible front matter support (author blocks, abstract, keyword lists) and supports multiple journal formats (preprint, final, one- or two-column layouts) as well as theorem environments. The installation workflow is documented, with sources available from Elsevier author resources and CTAN, plus guidance for generating elsarticle.cls and integrating it into the local TeX tree. Collectively, the class simplifies submission preparation and improves interoperability across LaTeX packages for authors.

Abstract

Recently computer-aided diagnosis has demonstrated promising performance, effectively alleviating the workload of clinicians. However, the inherent sample imbalance among different diseases leads algorithms biased to the majority categories, leading to poor performance for rare categories. Existing works formulated this challenge as a long-tailed problem and attempted to tackle it by decoupling the feature representation and classification. Yet, due to the imbalanced distribution and limited samples from tail classes, these works are prone to biased representation learning and insufficient classifier calibration. To tackle these problems, we propose a new Long-tailed Medical Diagnosis (LMD) framework for balanced medical image classification on long-tailed datasets. In the initial stage, we develop a Relation-aware Representation Learning (RRL) scheme to boost the representation ability by encouraging the encoder to capture intrinsic semantic features through different data augmentations. In the subsequent stage, we propose an Iterative Classifier Calibration (ICC) scheme to calibrate the classifier iteratively. This is achieved by generating a large number of balanced virtual features and fine-tuning the encoder using an Expectation-Maximization manner. The proposed ICC compensates for minority categories to facilitate unbiased classifier optimization while maintaining the diagnostic knowledge in majority classes. Comprehensive experiments on three public long-tailed medical datasets demonstrate that our LMD framework significantly surpasses state-of-the-art approaches. The source code can be accessed at https://github.com/peterlipan/LMD.