CVJun 17, 2022

CDNet: Contrastive Disentangled Network for Fine-Grained Image Categorization of Ocular B-Scan Ultrasound

arXiv:2206.08524v111 citationsh-index: 42Has Code
Originality Incremental advance
AI Analysis

This addresses the challenge of distinguishing ocular diseases in ultrasound for ophthalmologists, though it appears incremental as it builds on existing contrastive and disentanglement methods.

The paper tackles fine-grained image categorization of ocular B-scan ultrasound images for diseases like intraocular tumor and retinal detachment, achieving state-of-the-art performance on a dataset of 5213 samples and validating on chest X-ray benchmarks.

Precise and rapid categorization of images in the B-scan ultrasound modality is vital for diagnosing ocular diseases. Nevertheless, distinguishing various diseases in ultrasound still challenges experienced ophthalmologists. Thus a novel contrastive disentangled network (CDNet) is developed in this work, aiming to tackle the fine-grained image categorization (FGIC) challenges of ocular abnormalities in ultrasound images, including intraocular tumor (IOT), retinal detachment (RD), posterior scleral staphyloma (PSS), and vitreous hemorrhage (VH). Three essential components of CDNet are the weakly-supervised lesion localization module (WSLL), contrastive multi-zoom (CMZ) strategy, and hyperspherical contrastive disentangled loss (HCD-Loss), respectively. These components facilitate feature disentanglement for fine-grained recognition in both the input and output aspects. The proposed CDNet is validated on our ZJU Ocular Ultrasound Dataset (ZJUOUSD), consisting of 5213 samples. Furthermore, the generalization ability of CDNet is validated on two public and widely-used chest X-ray FGIC benchmarks. Quantitative and qualitative results demonstrate the efficacy of our proposed CDNet, which achieves state-of-the-art performance in the FGIC task. Code is available at: https://github.com/ZeroOneGame/CDNet-for-OUS-FGIC .

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes