Zou Kelly H, Warfield Simon K, Fielding Julia R, Tempany Clare M C, William M Wells, Kaus Michael R, Jolesz Ferenc A, Kikinis Ron
Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 180 Longwood Ave, Boston, MA 02115 USA.
Acad Radiol. 2003 Dec;10(12):1359-68. doi: 10.1016/s1076-6332(03)00538-5.
The accuracy of diagnostic test and imaging segmentation is important in clinical practice because it has a direct impact on therapeutic planning. Statistical validations of classification accuracy was conducted based on parametric receiver operating characteristic analysis, illustrated on three radiologic examples,
Two parametric models were developed for diagnostic or imaging data. Example 1: A semi-automated fractional segmentation algorithm was applied to magnetic resonance imaging of nine cases of brain tumors. The tumor and background pixel data were assumed to have bi-beta distributions. Fractional segmentation was validated against an estimated composite pixel-wise gold standard based on multi-reader manual segmentations. Example 2: The predictive value of 100 cases of spiral computed tomography of ureteral stone sizes, distributed as bi-normal after a non-linear transformation, under two treatment options received. Example 3: One hundred eighty cases had prostate-specific antigen levels measured in a prospective clinical trial. Radical prostatectomy was performed in all to provide a binary gold standard of local and advanced cancer stages. Prostate-specific antigen level was transformed and modeled by bi-normal distributions. In all examples, areas under the receiver operating characteristic curves were computed. RESULTS. The areas under the receiver operating characteristic curves were: Example 1: Fractional segmentation of magnetic resonance imaging of brain tumors: meningiomas (0.924-0.984); astrocytomas (0.786-0.986); and other low-grade gliomas (0.896-0.983). Example 3: Ureteral stone size for treatment planning (0.813). Example 2: Prostate-specific antigen for staging prostate cancer (0.768).
All clinical examples yielded fair to excellent accuracy. The validation metric area under the receiver operating characteristic curves may be generalized to evaluating the performances of several continuous classifiers related to imaging.
诊断测试和影像分割的准确性在临床实践中至关重要，因为它直接影响治疗方案的制定。基于参数化接收器操作特性分析对分类准确性进行了统计验证，并通过三个放射学实例进行说明。
针对诊断或影像数据开发了两种参数模型。实例1：将一种半自动分数分割算法应用于9例脑肿瘤的磁共振成像。假设肿瘤和背景像素数据具有双β分布。基于多读者手动分割，针对估计的复合像素级金标准对分数分割进行验证。实例2：在两种治疗方案下，对100例输尿管结石大小的螺旋计算机断层扫描进行预测价值分析，经非线性变换后呈双正态分布。实例3：在一项前瞻性临床试验中测量了180例患者的前列腺特异性抗原水平。所有患者均接受了根治性前列腺切除术，以提供局部和晚期癌症分期的二元金标准。前列腺特异性抗原水平经变换后用双正态分布建模。在所有实例中，计算了接收器操作特性曲线下的面积。结果：接收器操作特性曲线下的面积为：实例1：脑肿瘤磁共振成像的分数分割：脑膜瘤（0.924 - 0.984）；星形细胞瘤（0.786 - 0.986）；以及其他低级别胶质瘤（0.896 - 0.983）。实例3：用于治疗规划的输尿管结石大小（0.813）。实例2：用于前列腺癌分期的前列腺特异性抗原（0.768）。
所有临床实例均取得了中等至优异的准确性。接收器操作特性曲线下的验证指标面积可推广用于评估与影像相关的几种连续分类器的性能。
