Toward automated interpretable AAST grading for blunt splenic injury.
Toward automated interpretable AAST grading for blunt splenic injury.
复制标题
DOI：
10.1007/s10140-022-02099-1
复制
发表时间：
2023-02
影响因子：
2.2
通讯作者：
Dreizin, David
中科院分区：
文献类型：
--
作者：
Chen, Haomin;Unberath, Mathias;Dreizin, David
美国创伤外科协会（AAST）脾器官损伤评分（OIS）是钝性脾损伤最常用的CT分级系统。然而，报告的评分员之间的一致性是适度的，并且基于透明和可验证的标准客观地自动评分的算法可以作为高信任的诊断辅助工具。试验开发一种自动化可解释的基于多阶段深度学习的系统，以预测入院创伤CT的AAST等级。我们的管道包括4个部分：（1）自动脾脏定位，（2）基于R-CNN的假性动脉瘤（PSA）和活动性出血（AB）的快速检测，（3）nnU-Net分割和量化脾实质破裂（SPD），以及（4）从检测和分割结果推断AAST等级的有向图。在具有逐体素标记、共识AAST分级和随访相关结局数据的成人患者（年龄≥ 18岁）数据集上进行训练和验证（n = 174）。自动和共识AAST分级之间的AAST分类一致性（加权κ）显著（0.79）。预测高级别（IV和V）损伤的准确性、阳性预测值和阴性预测值分别为92%、95%和89%。预测出血控制干预的曲线下面积在专家共识和自动AAST分级之间相当（0.83 vs 0.88）。流水线的平均组合推理时间为96.9 s。我们的方法的结果是快速和可验证的，自动化和专家共识等级之间的高度一致性。在成人患者中，高级别病变的诊断和出血控制干预的预测产生了准确的结果。
The American Association for the Surgery of Trauma (AAST) splenic organ injury scale (OIS) is the most frequently used CT-based grading system for blunt splenic trauma. However, reported inter-rater agreement is modest, and an algorithm that objectively automates grading based on transparent and verifiable criteria could serve as a high-trust diagnostic aid. To pilot the development of an automated interpretable multi-stage deep learning-based system to predict AAST grade from admission trauma CT. Our pipeline includes 4 parts: (1) automated splenic localization, (2) Faster R-CNN-based detection of pseudoaneurysms (PSA) and active bleeds (AB), (3) nnU-Net segmentation and quantification of splenic parenchymal disruption (SPD), and (4) a directed graph that infers AAST grades from detection and segmentation results. Training and validation is performed on a dataset of adult patients (age ≥ 18) with voxelwise labeling, consensus AAST grading, and hemorrhage-related outcome data (n = 174). AAST classification agreement (weighted κ) between automated and consensus AAST grades was substantial (0.79). High-grade (IV and V) injuries were predicted with accuracy, positive predictive value, and negative predictive value of 92%, 95%, and 89%. The area under the curve for predicting hemorrhage control intervention was comparable between expert consensus and automated AAST grading (0.83 vs 0.88). The mean combined inference time for the pipeline was 96.9 s. The results of our method were rapid and verifiable, with high agreement between automated and expert consensus grades. Diagnosis of high-grade lesions and prediction of hemorrhage control intervention produced accurate results in adult patients.