Yu Heejung, Lee In-Gyu, Oh Jun-Young, Kim Jaehwan, Jeong Ji-Hoon, Eom Kidong
Department of Veterinary Medical Imaging, College of Veterinary Medicine, Konkuk University, Seoul, Republic of Korea.
Department of Computer Science, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju-si, Republic of Korea.
Front Vet Sci. 2024 Sep 4;11:1443234. doi: 10.3389/fvets.2024.1443234. eCollection 2024.
In veterinary medicine, attempts to apply artificial intelligence (AI) to ultrasonography have rarely been reported, and few studies have investigated the value of AI in ultrasonographic diagnosis. This study aimed to develop a deep learning-based model for classifying the status of canine chronic kidney disease (CKD) using renal ultrasonographic images and assess its diagnostic performance in comparison with that of veterinary imaging specialists, thereby verifying its clinical utility.
In this study, 883 ultrasonograms were obtained from 198 dogs, including those diagnosed with CKD according to the International Renal Interest Society (IRIS) guidelines and healthy dogs. After preprocessing and labeling each image with its corresponding IRIS stage, the renal regions were extracted and classified based on the IRIS stage using the convolutional neural network-based object detection algorithm You Only Look Once. The training scenarios consisted of multi-class classification, categorization of images into IRIS stages, and four binary classifications based on specific IRIS stages. To prevent model overfitting, we balanced the dataset, implemented early stopping, used lightweight models, and applied dropout techniques. Model performance was assessed using accuracy, recall, precision, F1 score, and receiver operating characteristic curve and compared with the diagnostic accuracy of four specialists. Inter- and intra-observer variabilities among specialists were also evaluated.
The developed model exhibited a low accuracy of 0.46 in multi-class classification. However, a significant performance improvement was observed in binary classifications, with the model designed to distinguish stage 3 or higher showing the highest accuracy of 0.85. In this classification, recall, precision, and F1 score values were all 0.85, and the area under the curve was 0.89. Compared with radiologists, whose accuracy ranged from 0.48 to 0.62 in this experimental scenario, the AI model exhibited superiority. Intra-observer reliability among radiologists was substantial, whereas inter-observer variability showed a moderate level of agreement.
This study developed a deep-learning framework capable of reliably classifying CKD IRIS stages 3 and 4 in dogs using ultrasonograms. The developed framework demonstrated higher accuracy than veterinary imaging specialists and provided more objective and consistent interpretations. Therefore, deep-learning-based ultrasound diagnostics are potentially valuable tools for diagnosing CKD in dogs.
在兽医学中，将人工智能（AI）应用于超声检查的尝试鲜有报道，且很少有研究探讨AI在超声诊断中的价值。本研究旨在开发一种基于深度学习的模型，用于利用肾脏超声图像对犬慢性肾病（CKD）的状态进行分类，并与兽医影像专家的诊断性能进行比较，从而验证其临床实用性。
在本研究中，从198只犬获取了883张超声图像，包括根据国际肾脏兴趣协会（IRIS）指南诊断为CKD的犬以及健康犬。在对每张图像进行预处理并标注其相应的IRIS分期后，使用基于卷积神经网络的目标检测算法You Only Look Once提取肾脏区域并根据IRIS分期进行分类。训练场景包括多类分类、将图像分类为IRIS分期以及基于特定IRIS分期的四个二分类。为防止模型过拟合，我们平衡了数据集、实施了早停法、使用了轻量级模型并应用了随机失活技术。使用准确率、召回率、精确率、F1分数和受试者工作特征曲线评估模型性能，并与四位专家的诊断准确率进行比较。还评估了专家之间的观察者间和观察者内变异性。
所开发的模型在多类分类中的准确率较低，为0.46。然而，在二分类中观察到性能有显著提升，旨在区分3期或更高分期的模型显示出最高准确率，为0.85。在此分类中，召回率、精确率和F1分数值均为0.85，曲线下面积为0.89。与在该实验场景中准确率在0.48至0.62之间的放射科医生相比，AI模型表现出优越性。放射科医生的观察者内可靠性较高，而观察者间变异性显示出中等程度的一致性。
本研究开发了一个深度学习框架，能够使用超声图像可靠地对犬CKD的IRIS 3期和4期进行分类。所开发的框架显示出比兽医影像专家更高的准确率，并提供了更客观和一致的解读。因此，基于深度学习的超声诊断是诊断犬CKD的潜在有价值工具。
