CAJ | 학술논문

在基于图像信息的疾病临床诊断中，医生通常将患者的采集图像与标准照片对比，通过比较图像中的视觉特征信息来判断患者疾病的严重程度。然而，这种诊断方法比较主观且可重复性不高，因此提出一种新颖的基于图像信息和排序学习技术的计算机辅助诊断疾病方法，并通过白内障疾病诊断的临床实验来验证方法的有效性。该方法利用排序函数对记录了患者白内障疾病的裂隙灯图像进行排序，而该排序函数则是基于一类新提出的近似排序标准并通过梯度法优化而求解的。在实验中，以1000名具备白内障疾病患者的裂隙灯图像来组建实验用数据库，用提出的新方法和现有的其他基于模式识别技术的诊断方法分别对这1000个案例进行了疾病诊断预测，预测结果采用统计学方法进行了比较和分析，新提出的方法可行性和优越性均得到了验证。
재기우도상신식적질병림상진단중，의생통상장환자적채집도상여표준조편대비，통과비교도상중적시각특정신식래판단환자질병적엄중정도。연이，저충진단방법비교주관차가중복성불고，인차제출일충신영적기우도상신식화배서학습기술적계산궤보조진단질병방법，병통과백내장질병진단적림상실험래험증방법적유효성。해방법이용배서함수대기록료환자백내장질병적렬극등도상진행배서，이해배서함수칙시기우일류신제출적근사배서표준병통과제도법우화이구해적。재실험중，이1000명구비백내장질병환자적렬극등도상래조건실험용수거고，용제출적신방법화현유적기타기우모식식별기술적진단방법분별대저1000개안례진행료질병진단예측，예측결과채용통계학방법진행료비교화분석，신제출적방법가행성화우월성균득도료험증。
In clinical diagnosis,a grade indicating the severity of nuclear cataract is often manually as-signed by a trained ophthalmologist to a patient after comparing the lens’opacity severity in his/her slit-lamp images with a set of standard photos. This grading scheme is often subjective and time-consuming. In this paper,a novel computer-aided diagnosis method via ranking is proposed to facilitate nuclear cataract grading following conventional clinical decision-making process. The grade of nuclear cataract in a slit-lamp image is predicted using its neighboring labeled images in a ranked image list,which is achieved u-sing a learned ranking function. This ranking function is learned via direct optimization on a newly pro-posed approximation to a ranking evaluation measure. Our proposed method has been evaluated by a large dataset composed of 1000 cases,which are collected from an ongoing clinical population-based study. Both experimental results and comparison with several existing methods demonstrate the benefit of grading via ranking by our proposed method.