Li Huiqi, Lim Joo Hwee, Liu Jiang, Wong Damon Wing Kee, Tan Ngan Meng, Lu Shijian, Zhang Zhuo, Wong Tien Yin
Institute for Infocomm Research, A*STAR, Connexis, Singapore.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:3693-6. doi: 10.1109/IEMBS.2009.5334735.
An automatic diagnosis system of nuclear cataract is presented in this paper. Nuclear cataract is graded according to the severity of opacity using slit-lamp lens images. Anatomical structure in the lens image is detected using a modified active shape model (ASM). Based on the anatomical landmark, local features are extracted according to clinical grading protocol. Support vector machine (SVM) regression is employed to train a grading model for grade prediction. The system is tested using clinical images and clinical ground truth. More than five thousands slit-lamp images were tested. The success rate of feature extraction is 95% and the mean grading difference is 0.36. The automatic diagnosis system can help to improve the grading objectivity and save the workload of ophthalmologists.
本文提出了一种核性白内障自动诊断系统。利用裂隙灯晶状体图像，根据混浊程度对核性白内障进行分级。使用改进的主动形状模型（ASM）检测晶状体图像中的解剖结构。基于解剖标志点，根据临床分级方案提取局部特征。采用支持向量机（SVM）回归训练分级模型进行分级预测。使用临床图像和临床真值对该系统进行测试。测试了五千多张裂隙灯图像。特征提取成功率为95%，平均分级差异为0.36。该自动诊断系统有助于提高分级的客观性，减轻眼科医生的工作量。
