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

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.

[1]  M. C. Leske,et al.  The Lens Opacities Classification System III , 1993 .

[2]  Huiqi Li,et al.  Boundary detection of optic disk by a modified ASM method , 2003, Pattern Recognit..

[3]  Charles R. Dyer,et al.  An Automatic System for Classification of Nuclear Sclerosis from Slit-Lamp Photographs , 2003, MICCAI.

[4]  H. Taylor,et al.  External factors in the development of cataract , 2005, Eye.

[5]  P. Asbell,et al.  Age-related cataract , 2005, The Lancet.

[6]  Joo-Hwee Lim,et al.  A Computer-Aided Diagnosis System of Nuclear Cataract , 2010, IEEE Transactions on Biomedical Engineering.

[7]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[8]  Joo-Hwee Lim,et al.  A Computer Assisted Method for Nuclear Cataract Grading From Slit-Lamp Images Using Ranking , 2011, IEEE Transactions on Medical Imaging.

[9]  Andrew Y. Ng,et al.  Convolutional-Recursive Deep Learning for 3D Object Classification , 2012, NIPS.

[10]  Stephen Lin,et al.  Automatic Grading of Nuclear Cataracts from Slit-Lamp Lens Images Using Group Sparsity Regression , 2013, MICCAI.

[11]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Stephen Lin,et al.  Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning , 2014, IEEE Transactions on Biomedical Engineering.

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Jiangtao Cui,et al.  Localization and diagnosis framework for pediatric cataracts based on slit-lamp images using deep features of a convolutional neural network , 2017, PloS one.