CodaMal: Contrastive Domain Adaptation for Malaria Detection in Low-Cost Microscopes

TL;DR

CodaMal is an end-to-end contrastive domain adaptation framework that improves malaria detection in low-cost microscopes by reducing domain shift without extra annotation effort, achieving significant accuracy and speed gains.

Contribution

The paper introduces CodaMal, a novel end-to-end contrastive domain adaptation method that effectively bridges the gap between high-cost and low-cost microscope images for malaria detection.

Findings

Achieves 16% improvement in mean average precision (mAP) over state-of-the-art.

Provides 21x faster inference speed.

Uses half the number of learnable parameters compared to prior methods.

Abstract

Malaria is a major health issue worldwide, and its diagnosis requires scalable solutions that can work effectively with low-cost microscopes (LCM). Deep learning-based methods have shown success in computer-aided diagnosis from microscopic images. However, these methods need annotated images that show cells affected by malaria parasites and their life stages. Annotating images from LCM significantly increases the burden on medical experts compared to annotating images from high-cost microscopes (HCM). For this reason, a practical solution would be trained on HCM images which should generalize well on LCM images during testing. While earlier methods adopted a multi-stage learning process, they did not offer an end-to-end approach. In this work, we present an end-to-end learning framework, named CodaMal (COntrastive Domain Adpation for MALaria). In order to bridge the gap between HCM (training) and LCM (testing), we propose a domain adaptive contrastive loss. It reduces the domain shift by promoting similarity between the representations of HCM and its corresponding LCM image, without imposing an additional annotation burden. In addition, the training objective includes object detection objectives with carefully designed augmentations, ensuring the accurate detection of malaria parasites. On the publicly available large-scale M5-dataset, our proposed method shows a significant improvement of 16% over the state-of-the-art methods in terms of the mean average precision metric (mAP), provides 21x speed improvement during inference and requires only half of the learnable parameters used in prior methods. Our code is publicly available: https://daveishan.github.io/codamal-webpage/.