Hauback Mari Nyborg, Huynh Bao Ngoc, Steiro Sunniva Elisabeth Daae, Groendahl Aurora Rosvoll, Bredal William, Tomic Oliver, Futsaether Cecilia Marie, Skogmo Hege Kippenes
Department of Companion Animal Clinical Sciences, Faculty of Veterinary Medicine, Norwegian University of Life Sciences, Ås, Norway.
Faculty of Science and Technology, Norwegian University of Life Sciences, Ås, Norway.
Vet Radiol Ultrasound. 2025 Jan;66(1):e13465. doi: 10.1111/vru.13465.
Medical image analysis based on deep learning is a rapidly advancing field in veterinary diagnostics. The aim of this retrospective diagnostic accuracy study was to develop and assess a convolutional neural network (CNN, EfficientNet) to evaluate elbow radiographs from dogs screened for elbow dysplasia. An auto-cropping tool based on the deep learning model RetinaNet was developed for radiograph preprocessing to crop the radiographs to the region of interest around the elbow joint. A total of 7229 radiographs with corresponding International Elbow Working Group scoring were included for training (n = 4000), validation (n = 1000), and testing (n = 2229) of CNN models for elbow diagnostics. The radiographs were classified in a binary manner as normal (negative class) or abnormal (positive class), where abnormal radiographs had various severities of osteoarthrosis and/or visible primary elbow dysplasia lesions. Explainable artificial intelligence analysis were performed on both correctly and incorrectly classified radiographs using VarGrad heatmaps to visualize regions of importance for the CNN model's predictions. The highest-performing CNN model showed excellent test accuracy, sensitivity, and specificity, all achieving a value of 0.98. Explainability analysis showed frequent highlighting along the margins of the anconeal process of both correctly and incorrectly classified radiographs. Uncertainty estimation using entropy to characterize the uncertainty of the model predictions showed that radiographs with ambiguous predictions could be flagged for human evaluation. Our study demonstrates robust performance of CNNs for detecting abnormal elbow joints in dogs screened for elbow dysplasia.
基于深度学习的医学图像分析是兽医诊断领域中一个快速发展的领域。这项回顾性诊断准确性研究的目的是开发和评估一个卷积神经网络（CNN，EfficientNet），以评估从筛查肘部发育不良的犬只获得的肘部X光片。开发了一种基于深度学习模型RetinaNet的自动裁剪工具用于X光片预处理，将X光片裁剪到肘关节周围的感兴趣区域。总共纳入了7229张具有相应国际肘部工作组评分的X光片，用于肘部诊断的CNN模型的训练（n = 4000）、验证（n = 1000）和测试（n = 2229）。X光片以二元方式分类为正常（阴性类别）或异常（阳性类别），其中异常X光片具有不同严重程度的骨关节炎和/或可见的原发性肘部发育不良病变。使用VarGrad热图对正确和错误分类的X光片都进行了可解释人工智能分析，以可视化对于CNN模型预测重要的区域。性能最佳的CNN模型显示出优异的测试准确性、敏感性和特异性，所有指标均达到0.98的值。可解释性分析表明，在正确和错误分类的X光片的肘突边缘都经常出现高亮显示。使用熵来表征模型预测不确定性的不确定性估计表明，预测不明确的X光片可以标记出来以供人工评估。我们的研究证明了CNN在检测筛查肘部发育不良的犬只异常肘关节方面的强大性能。
