From the Divisions of Research and Analytical Services.
Cardiothoracic Imaging, Department of Radiology.
Invest Radiol. 2022 Aug 1;57(8):552-559. doi: 10.1097/RLI.0000000000000869. Epub 2022 Apr 2.
This study trained and evaluated algorithms to detect, segment, and classify simple and complex pleural effusions on computed tomography (CT) scans.
For detection and segmentation, we randomly selected 160 chest CT scans out of all consecutive patients (January 2016-January 2021, n = 2659) with reported pleural effusion. Effusions were manually segmented and a negative cohort of chest CTs from 160 patients without effusions was added. A deep convolutional neural network (nnU-Net) was trained and cross-validated (n = 224; 70%) for segmentation and tested on a separate subset (n = 96; 30%) with the same distribution of reported pleural complexity features as in the training cohort (eg, hyperdense fluid, gas, pleural thickening and loculation). On a separate consecutive cohort with a high prevalence of pleural complexity features (n = 335), a random forest model was implemented for classification of segmented effusions with Hounsfield unit thresholds, density distribution, and radiomics-based features as input. As performance measures, sensitivity, specificity, and area under the curves (AUCs) for detection/classifier evaluation (per-case level) and Dice coefficient and volume analysis for the segmentation task were used.
Sensitivity and specificity for detection of effusion were excellent at 0.99 and 0.98, respectively (n = 96; AUC, 0.996, test data). Segmentation was robust (median Dice, 0.89; median absolute volume difference, 13 mL), irrespective of size, complexity, or contrast phase. The sensitivity, specificity, and AUC for classification in simple versus complex effusions were 0.67, 0.75, and 0.77, respectively.
Using a dataset with different degrees of complexity, a robust model was developed for the detection, segmentation, and classification of effusion subtypes. The algorithms are openly available at https://github.com/usb-radiology/pleuraleffusion.git.
本研究旨在训练和评估算法，以检测、分割和分类计算机断层扫描（CT）扫描上的单纯性和复杂性胸腔积液。
对于检测和分割，我们从所有连续患者（2016 年 1 月至 2021 年 1 月，n=2659）的胸部 CT 中随机选择了 160 例报告有胸腔积液的 CT 扫描。积液被手动分割，并添加了来自 160 例无积液患者的阴性胸部 CT 队列。一个深度卷积神经网络（nnU-Net）被训练和交叉验证（n=224；70%）用于分割，并在具有与训练队列相同报告胸腔复杂性特征分布的独立子集（n=96；30%）上进行测试（例如高密度积液、气体、胸膜增厚和分隔）。在一个具有高比例胸腔复杂性特征的连续队列（n=335）中，一个随机森林模型被用于分类分割积液的分类，其输入为体素单位阈值、密度分布和基于放射组学的特征。作为性能指标，使用了检测/分类器评估（每个病例水平）的灵敏度、特异性和曲线下面积（AUC），以及分割任务的 Dice 系数和体积分析。
积液检测的灵敏度和特异性均非常高，分别为 0.99 和 0.98（n=96；AUC，0.996，测试数据）。分割是稳健的（中位数 Dice，0.89；中位数绝对体积差异，13 毫升），无论大小、复杂性或对比阶段如何。简单性与复杂性胸腔积液分类的灵敏度、特异性和 AUC 分别为 0.67、0.75 和 0.77。
使用具有不同复杂程度的数据集，开发了一种用于胸腔积液亚型检测、分割和分类的稳健模型。该算法可在 https://github.com/usb-radiology/pleuraleffusion.git 上公开获取。
