Rusinovich Yury, Rusinovich Volha, Buhayenka Aliaksei, Liashko Vitalii, Sabanov Arsen, Holstein David J F, Aldmour Samer, Doss Markus, Branzan Daniela
Department of Vascular Surgery, University Hospital Leipzig, Leipzig, Germany.
Institute of Hygiene and Environmental Medicine, University Hospital Leipzig, Germany.
Vascular. 2025 Feb;33(1):26-33. doi: 10.1177/17085381241236571. Epub 2024 Feb 25.
The aim of this study was to investigate the potential of novel automated machine learning (AutoML) in vascular medicine by developing a discriminative artificial intelligence (AI) model for the classification of anatomical patterns of peripheral artery disease (PAD).
Random open-source angiograms of lower limbs were collected using a web-indexed search. An experienced researcher in vascular medicine labelled the angiograms according to the most applicable grade of femoropopliteal disease in the Global Limb Anatomic Staging System (GLASS). An AutoML model was trained using the Vertex AI (Google Cloud) platform to classify the angiograms according to the GLASS grade with a multi-label algorithm. Following deployment, we conducted a test using 25 random angiograms (five from each GLASS grade). Model tuning through incremental training by introducing new angiograms was executed to the limit of the allocated quota following the initial evaluation to determine its effect on the software's performance.
We collected 323 angiograms to create the AutoML model. Among these, 80 angiograms were labelled as grade 0 of femoropopliteal disease in GLASS, 114 as grade 1, 34 as grade 2, 25 as grade 3 and 70 as grade 4. After 4.5 h of training, the AI model was deployed. The AI self-assessed average precision was 0.77 (0 is minimal and 1 is maximal). During the testing phase, the AI model successfully determined the GLASS grade in 100% of the cases. The agreement with the researcher was almost perfect with the number of observed agreements being 22 (88%), Kappa = 0.85 (95% CI 0.69-1.0). The best results were achieved in predicting GLASS grade 0 and grade 4 (initial precision: 0.76 and 0.84). However, the AI model exhibited poorer results in classifying GLASS grade 3 (initial precision: 0.2) compared to other grades. Disagreements between the AI and the researcher were associated with the low resolution of the test images. Incremental training expanded the initial dataset by 23% to a total of 417 images, which improved the model's average precision by 11% to 0.86.
After a brief training period with a limited dataset, AutoML has demonstrated its potential in identifying and classifying the anatomical patterns of PAD, operating unhindered by the factors that can affect human analysts, such as fatigue or lack of experience. This technology bears the potential to revolutionize outcome prediction and standardize evidence-based revascularization strategies for patients with PAD, leveraging its adaptability and ability to continuously improve with additional data. The pursuit of further research in AutoML within the field of vascular medicine is both promising and warranted. However, it necessitates additional financial support to realize its full potential.
本研究旨在通过开发一种用于外周动脉疾病（PAD）解剖模式分类的判别式人工智能（AI）模型，探讨新型自动化机器学习（AutoML）在血管医学中的潜力。
通过网络索引搜索收集下肢随机开源血管造影图像。一位血管医学领域的经验丰富的研究人员根据全球肢体解剖分期系统（GLASS）中最适用的股腘动脉疾病分级对血管造影图像进行标注。使用Vertex AI（谷歌云）平台训练一个AutoML模型，通过多标签算法根据GLASS分级对血管造影图像进行分类。部署后，我们使用25张随机血管造影图像（每个GLASS分级各5张）进行测试。在初始评估后，通过引入新的血管造影图像进行增量训练来调整模型，直至达到分配配额的极限，以确定其对软件性能的影响。
我们收集了323张血管造影图像来创建AutoML模型。其中，80张血管造影图像在GLASS中被标注为股腘动脉疾病0级，114张为1级，34张为2级，25张为3级，70张为4级。经过4.5小时的训练，AI模型得以部署。AI自我评估的平均精度为0.77（0为最低，1为最高）。在测试阶段，AI模型在100%的病例中成功确定了GLASS分级。与研究人员的一致性几乎完美，观察到的一致数量为22例（88%），Kappa值 = 0.85（95%置信区间0.69 - 1.0）。在预测GLASS 0级和4级时取得了最佳结果（初始精度：0.76和0.84）。然而，与其他分级相比，AI模型在对GLASS 3级进行分类时表现较差（初始精度：0.2）。AI与研究人员之间的分歧与测试图像的低分辨率有关。增量训练将初始数据集扩大了23%，达到总共417张图像，这使模型的平均精度提高了11%，达到0.86。
在使用有限数据集进行简短训练后，AutoML已展示出其在识别和分类PAD解剖模式方面的潜力，不受可能影响人类分析人员的因素（如疲劳或经验不足）的阻碍。这项技术有潜力彻底改变结局预测，并为PAD患者规范基于证据的血管重建策略，利用其适应性和通过额外数据不断改进的能力。在血管医学领域对AutoML进行进一步研究既充满希望又很有必要。然而，要充分发挥其潜力还需要额外的资金支持。
