LensID: A CNN-RNN-Based Framework Towards Lens Irregularity Detection in Cataract Surgery Videos

TL;DR

This paper introduces LensID, a deep learning framework combining CNN and RNN models to automatically detect lens irregularities in cataract surgery videos, aiding in large-scale risk factor analysis.

Contribution

The paper presents a novel end-to-end RNN for surgical phase recognition and a new segmentation network for lens and pupil detection, advancing automated analysis in cataract surgery videos.

Findings

Effective surgical phase recognition demonstrated

Segmentation network outperforms state-of-the-art methods

Facilitates large-scale risk factor studies

Abstract

A critical complication after cataract surgery is the dislocation of the lens implant leading to vision deterioration and eye trauma. In order to reduce the risk of this complication, it is vital to discover the risk factors during the surgery. However, studying the relationship between lens dislocation and its suspicious risk factors using numerous videos is a time-extensive procedure. Hence, the surgeons demand an automatic approach to enable a larger-scale and, accordingly, more reliable study. In this paper, we propose a novel framework as the major step towards lens irregularity detection. In particular, we propose (I) an end-to-end recurrent neural network to recognize the lens-implantation phase and (II) a novel semantic segmentation network to segment the lens and pupil after the implantation phase. The phase recognition results reveal the effectiveness of the proposed surgical phase recognition approach. Moreover, the segmentation results confirm the proposed segmentation network's effectiveness compared to state-of-the-art rival approaches.