Details

Autor(en) / Beteiligte

• Xu, Chaoxi
• Zhu, Xiangjia
• He, Wenwen
• Lu, Yi
• He, Xixi
• Shang, Zongjiang
• Wu, Jun
• Zhang, Keke
• Zhang, Yinglei
• Rong, Xianfang
• Zhao, Zhennan
• Cai, Lei
• Ding, Dayong
• Li, Xirong

Titel

Fully Deep Learning for Slit-Lamp Photo Based Nuclear Cataract Grading

Ist Teil von

• Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, p.513-521

Ort / Verlag

Cham: Springer International Publishing

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Age-related cataract is a priority eye disease, with nuclear cataract as its most common type. This paper aims for automated nuclear cataract grading based on slit-lamp photos. Different from previous efforts which rely on traditional feature extraction and grade modeling techniques, we propose in this paper a fully deep learning based solution. Given a slit-lamp photo, we localize its nuclear region by Faster R-CNN, followed by a ResNet-101 based grading model. In order to alleviate the issue of imbalanced data, a simple batch balancing strategy is introduced for improving the training of the grading network. Tested on a clinical dataset of 157 slit-lamp photos from 39 female and 31 male patients, the proposed solution outperforms the state-of-the-art, reducing the mean absolute error from 0.357 to 0.313. In addition, our solution processes a slit-lamp photo in approximately 0.1 s, which is two order faster than the state-of-the-art. With its effectiveness and efficiency, the new solution is promising for automated nuclear cataract grading.