Tong Yubing, Udupa Jayaram K, Wang Chuang, Chen Jerry, Venigalla Sriram, Guzzo Thomas J, Mamtani Ronac, Baumann Brian C, Christodouleas John P, Torigian Drew A
Medical Image Processing Group, Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania.
The Perelman Center for Advanced Medicine, Department of Radiation Oncology, University of Pennsylvania, Philadelphia, Pennsylvania.
Adv Radiat Oncol. 2018 May 8;3(3):331-338. doi: 10.1016/j.adro.2018.04.011. eCollection 2018 Jul-Sep.
Current clinical staging methods are unable to accurately define the extent of invasion of localized bladder cancer, which affects the proper use of systemic therapy, surgery, and radiation. Our purpose was to test a novel radiomics approach to identify optimal imaging biomarkers from T2-weighted magnetic resonance imaging (MRI) scans that accurately classify localized bladder cancer into 2 tumor stage groups (≤T2 vs >T2) at both the patient level and within bladder subsectors.
Preoperative T2-weighted MRI scans of 65 consecutive patients followed by radical cystectomy were identified. A 3-layer, shell-like volume of interest (VOI) was defined on each MRI slice: Inner (lumen), middle (bladder wall), and outer (perivesical tissue). An optimal biomarker method was used to identify features from 15,834 intensity and texture properties that maximized the classification of patients into ≤T2 versus >T2 groups. A leave-one-out strategy was used to cross-validate the performance of the identified biomarker feature set at the patient level. The performance of the feature set was then evaluated at the subsector level of the bladder by dividing the VOIs into 8 radial sectors.
A total of 9 optimal biomarker features were derived and demonstrated a sensitivity, specificity, accuracy of prediction, and area under a receiver operating characteristic curve of 0.742, 0.824, 0.785, and 0.806, respectively, at the patient level and 0.681, 0.788, 0.763, and 0.813, respectively, at the radial sector level. All 9 selected features were extracted from the middle shell of the VOI and based on texture properties.
An approach to select a small, highly independent feature set that is derived from T2-weighted MRI scans that separate patients with bladder cancer into ≤T2 versus >T2 groups at both the patient level and within subsectors of the bladder has been developed and tested. With external validation, this radiomics approach could improve the clinical staging of bladder cancer and optimize therapeutic management.
目前的临床分期方法无法准确界定局限性膀胱癌的浸润范围，这影响了全身治疗、手术及放疗的合理应用。我们的目的是测试一种新型的放射组学方法，以从T2加权磁共振成像（MRI）扫描中识别出最佳影像生物标志物，从而在患者层面以及膀胱各亚区域内将局限性膀胱癌准确分类为两个肿瘤分期组（≤T2期与>T2期）。
确定了65例连续接受根治性膀胱切除术患者的术前T2加权MRI扫描资料。在每个MRI切片上定义一个三层的、壳状的感兴趣区（VOI）：内层（管腔）、中层（膀胱壁）和外层（膀胱周围组织）。采用一种最佳生物标志物方法从15834个强度和纹理特征中识别出能将患者最大限度地分类为≤T2期与>T2期组的特征。采用留一法策略在患者层面交叉验证所识别的生物标志物特征集的性能。然后通过将VOI划分为8个放射状区域，在膀胱的亚区域层面评估特征集的性能。
共得出9个最佳生物标志物特征，在患者层面其灵敏度、特异度、预测准确度及受试者工作特征曲线下面积分别为0.742、0.824、0.785和0.806，在放射状区域层面分别为0.681、0.788、0.763和0.813。所有9个选定特征均从VOI的中层壳中提取，且基于纹理特征。
已开发并测试了一种从T2加权MRI扫描中选择一个小型、高度独立特征集的方法，该方法可在患者层面以及膀胱亚区域内将膀胱癌患者分为≤T2期与>T2期组。经过外部验证，这种放射组学方法可改善膀胱癌的临床分期并优化治疗管理。
