Nguyen Tri-Thien, Folle Lukas, Bayer Thomas
Institute of Neuroradiology and Radiology, Klinikum Fürth, Fürth, Germany.
Faculty of Pattern Recognition, Friedrich-Alexander-University Erlangen-Nuremberg, Erlangen, Germany.
Eur Radiol Exp. 2024 Mar 13;8(1):30. doi: 10.1186/s41747-024-00433-5.
This study evaluated a deep learning (DL) algorithm for detecting vessel steno-occlusions in patients with peripheral arterial disease (PAD). It utilised a private dataset, which was acquired and annotated by the authors through their institution and subsequently validated by two blinded readers.
A single-centre retrospective study analysed 105 magnetic resonance angiography (MRA) images using an EfficientNet B0 DL model. Initially, inter-reader variability was assessed using the complete dataset. For a subset of these images (29 from the left side and 35 from the right side) where digital subtraction angiography (DSA) data was available as the ground truth, the model's accuracy and the area under the curve at receiver operating characteristics analysis (ROC-AUC) were evaluated.
A total of 105 patient examinations (mean age, 75 years ±12 [mean ± standard deviation], 61 men) were evaluated. Radiologist-DL model agreement had a quadratic weighted Cohen κ ≥ 0.72 (left side) and ≥ 0.66 (right side). Radiologist inter-reader agreement was ≥ 0.90 (left side) and ≥ 0.87 (right side). The DL model achieved a 0.897 accuracy and a 0.913 ROC-AUC (left side) and 0.743 and 0.830 (right side). Radiologists achieved 0.931 and 0.862 accuracies, with 0.930 and 0.861 ROC-AUCs (left side), and 0.800 and 0.799 accuracies, with 0.771 ROC-AUCs (right side).
The DL model provided valid results in identifying arterial steno-occlusion in the superficial femoral and popliteal arteries on MRA among PAD patients. However, it did not reach the inter-reader agreement of two radiologists.
The tested DL model is a promising tool for assisting in the detection of arterial steno-occlusion in patients with PAD, but further optimisation is necessary to provide radiologists with useful support in their daily routine diagnostics.
• This study focused on the application of DL for arterial steno-occlusion detection in lower extremities on MRA. • A previously developed DL model was tested for accuracy and inter-reader agreement. • While the model showed promising results, it does not yet replace human expertise in detecting arterial steno-occlusion on MRA.
本研究评估了一种深度学习（DL）算法，用于检测外周动脉疾病（PAD）患者的血管狭窄闭塞情况。该研究使用了一个私有数据集，该数据集由作者通过其所在机构获取并标注，随后由两名不知情的读者进行验证。
一项单中心回顾性研究使用EfficientNet B0 DL模型分析了105例磁共振血管造影（MRA）图像。最初，使用完整数据集评估读者间的变异性。对于其中一部分可获得数字减影血管造影（DSA）数据作为金标准的图像（左侧29例，右侧35例），评估了模型的准确性以及在接受者操作特征分析（ROC-AUC）中的曲线下面积。
共评估了105例患者的检查（平均年龄75岁±12[平均值±标准差]，男性61例）。放射科医生与DL模型的一致性在左侧二次加权Cohen κ≥0.72，右侧≥0.66。放射科医生之间的一致性在左侧≥0.90，右侧≥0.87。DL模型在左侧的准确率为0.897，ROC-AUC为0.913；在右侧的准确率为0.743，ROC-AUC为0.830。放射科医生在左侧的准确率分别为0.931和0.862，ROC-AUC分别为0.930和0.861；在右侧的准确率分别为0.800和0.799，ROC-AUC为0.771。
DL模型在识别PAD患者MRA上股浅动脉和腘动脉的动脉狭窄闭塞方面提供了有效的结果。然而，它未达到两名放射科医生之间的一致性。
所测试的DL模型是辅助检测PAD患者动脉狭窄闭塞的一种有前景的工具，但需要进一步优化，以便在日常诊断中为放射科医生提供有用的支持。
• 本研究聚焦于DL在MRA上检测下肢动脉狭窄闭塞的应用。• 对先前开发的DL模型进行了准确性和读者间一致性测试。• 虽然该模型显示出有前景的结果，但在MRA上检测动脉狭窄闭塞时，它尚未取代人类专业知识。
