基于深度学习的肝脏磁共振图像自动处方：开发、评估与前瞻性实施。
Automated MR Image Prescription of the Liver Using Deep Learning: Development, Evaluation, and Prospective Implementation.
机构信息
Department of Radiology, University of Wisconsin, Madison, Wisconsin, USA.
Department of Medical Physics, University of Wisconsin, Madison, Wisconsin, USA.
出版信息
J Magn Reson Imaging. 2023 Aug;58(2):429-441. doi: 10.1002/jmri.28564. Epub 2022 Dec 30.
BACKGROUND
There is an unmet need for fully automated image prescription of the liver to enable efficient, reproducible MRI.
PURPOSE
To develop and evaluate artificial intelligence (AI)-based liver image prescription.
STUDY TYPE
Prospective.
POPULATION
A total of 570 female/469 male patients (age: 56 ± 17 years) with 72%/8%/20% assigned randomly for training/validation/testing; two female/four male healthy volunteers (age: 31 ± 6 years).
FIELD STRENGTH/SEQUENCE: 1.5 T, 3.0 T; spin echo, gradient echo, bSSFP.
ASSESSMENT
A total of 1039 three-plane localizer acquisitions (26,929 slices) from consecutive clinical liver MRI examinations were retrieved retrospectively and annotated by six radiologists. The localizer images and manual annotations were used to train an object-detection convolutional neural network (YOLOv3) to detect multiple object classes (liver, torso, and arms) across localizer image orientations and to output corresponding 2D bounding boxes. Whole-liver image prescription in standard orientations was obtained based on these bounding boxes. 2D detection performance was evaluated on test datasets by calculating intersection over union (IoU) between manual and automated labeling. 3D prescription accuracy was calculated by measuring the boundary mismatch in each dimension and percentage of manual volume covered by AI prescription. The automated prescription was implemented on a 3 T MR system and evaluated prospectively on healthy volunteers.
STATISTICAL TESTS
Paired t-tests (threshold = 0.05) were conducted to evaluate significance of performance difference between trained networks.
RESULTS
In 208 testing datasets, the proposed method with full network had excellent agreement with manual annotations, with median IoU > 0.91 (interquartile range < 0.09) across all seven classes. The automated 3D prescription was accurate, with shifts <2.3 cm in superior/inferior dimension for 3D axial prescription for 99.5% of test datasets, comparable to radiologists' interreader reproducibility. The full network had significantly superior performance than the tiny network for 3D axial prescription in patients. Automated prescription performed well across single-shot fast spin-echo, gradient-echo, and balanced steady-state free-precession sequences in the prospective study.
DATA CONCLUSION
AI-based automated liver image prescription demonstrated promising performance across the patients, pathologies, and field strengths studied.
EVIDENCE LEVEL
TECHNICAL EFFICACY
Stage 1.
背景
人们需要一种全自动的肝脏图像定位方法，以实现高效、可重复的 MRI 检查。
目的
开发并评估基于人工智能（AI）的肝脏图像定位方法。
研究类型
前瞻性研究。
人群
共纳入 570 名女性/469 名男性患者（年龄：56±17 岁），72%/8%/20%的患者随机分为训练/验证/测试组；纳入 2 名女性/4 名男性健康志愿者（年龄：31±6 岁）。
磁场强度/序列：1.5T、3.0T；自旋回波、梯度回波、bSSFP。
评估
回顾性检索了连续进行的临床肝脏 MRI 检查中总共 1039 次三平面定位采集（26929 个层面），由 6 名放射科医生进行标注。定位图像和手动标注用于训练目标检测卷积神经网络（YOLOv3），以检测定位图像方向上的多个目标类别（肝脏、躯干和手臂），并输出相应的 2D 边界框。基于这些边界框，获得标准方位的全肝图像定位。通过计算手动和自动标注之间的交并比（IoU）来评估测试数据集上的 2D 检测性能。通过测量每个维度的边界不匹配和 AI 处方覆盖的手动体积百分比来计算 3D 处方的准确性。在 3T MR 系统上实现了自动化处方，并前瞻性地对健康志愿者进行了评估。
统计学检验
采用配对 t 检验（阈值=0.05）评估网络训练前后性能差异的显著性。
结果
在 208 个测试数据集上，具有全网络的方法与手动标注具有极好的一致性，所有 7 个类别中中位数 IoU＞0.91（四分位距＜0.09）。自动化 3D 处方准确，99.5%的测试数据集 3D 轴向定位的上下方向移位＜2.3cm，与放射科医生的读者间可重复性相当。全网络在患者中进行 3D 轴向定位的性能明显优于微小网络。在前瞻性研究中，自动化处方在单次快速自旋回波、梯度回波和平衡稳态自由进动序列中表现良好。
数据结论
基于人工智能的自动肝脏图像定位在研究的患者、病变和场强中表现出良好的性能。
证据水平
4。
技术功效
阶段 1。
Zotero 插件