CTT-Net: A Multi-view Cross-token Transformer for Cataract Postoperative Visual Acuity Prediction

TL;DR

This paper introduces CTT-Net, a novel multi-view transformer model that integrates clinical prior knowledge to improve postoperative visual acuity prediction from OCT images, outperforming existing methods.

Contribution

The paper proposes a cross-token attention mechanism and auxiliary classification loss within a transformer framework for enhanced multi-view OCT analysis and VA prediction.

Findings

CTT-Net achieves superior accuracy over existing methods.

The model effectively fuses multi-view OCT features.

Incorporating preoperative VA improves prediction performance.

Abstract

Surgery is the only viable treatment for cataract patients with visual acuity (VA) impairment. Clinically, to assess the necessity of cataract surgery, accurately predicting postoperative VA before surgery by analyzing multi-view optical coherence tomography (OCT) images is crucially needed. Unfortunately, due to complicated fundus conditions, determining postoperative VA remains difficult for medical experts. Deep learning methods for this problem were developed in recent years. Although effective, these methods still face several issues, such as not efficiently exploring potential relations between multi-view OCT images, neglecting the key role of clinical prior knowledge (e.g., preoperative VA value), and using only regression-based metrics which are lacking reference. In this paper, we propose a novel Cross-token Transformer Network (CTT-Net) for postoperative VA prediction by analyzing both the multi-view OCT images and preoperative VA. To effectively fuse multi-view features of OCT images, we develop cross-token attention that could restrict redundant/unnecessary attention flow. Further, we utilize the preoperative VA value to provide more information for postoperative VA prediction and facilitate fusion between views. Moreover, we design an auxiliary classification loss to improve model performance and assess VA recovery more sufficiently, avoiding the limitation by only using the regression metrics. To evaluate CTT-Net, we build a multi-view OCT image dataset collected from our collaborative hospital. A set of extensive experiments validate the effectiveness of our model compared to existing methods in various metrics. Code is available at: https://github.com/wjh892521292/Cataract OCT.