Jeonbuk Pathology Research Group, Korea Institute of Toxicology, Jeonbuk, Republic of Korea.
Center for Companion Animal New Drug Development, Korea Institute of Toxicology, Jeonbuk, Republic of Korea.
PLoS One. 2023 Feb 2;18(2):e0280438. doi: 10.1371/journal.pone.0280438. eCollection 2023.
Feline hypertrophic cardiomyopathy (HCM) is a common heart disease affecting 10-15% of all cats. Cats with HCM exhibit breathing difficulties, lethargy, and heart murmur; furthermore, feline HCM can also result in sudden death. Among various methods and indices, radiography and ultrasound are the gold standards in the diagnosis of feline HCM. However, only 75% accuracy has been achieved using radiography alone. Therefore, we trained five residual architectures (ResNet50V2, ResNet152, InceptionResNetV2, MobileNetV2, and Xception) using 231 ventrodorsal radiographic images of cats (143 HCM and 88 normal) and investigated the optimal architecture for diagnosing feline HCM through radiography. To ensure the generalizability of the data, the x-ray images were obtained from 5 independent institutions. In addition, 42 images were used in the test. The test data were divided into two; 22 radiographic images were used in prediction analysis and 20 radiographic images of cats were used in the evaluation of the peeking phenomenon and the voting strategy. As a result, all models showed > 90% accuracy; Resnet50V2: 95.45%; Resnet152: 95.45; InceptionResNetV2: 95.45%; MobileNetV2: 95.45% and Xception: 95.45. In addition, two voting strategies were applied to the five CNN models; softmax and majority voting. As a result, the softmax voting strategy achieved 95% accuracy in combined test data. Our findings demonstrate that an automated deep-learning system using a residual architecture can assist veterinary radiologists in screening HCM.
猫肥厚型心肌病（HCM）是一种常见的心脏病，影响所有猫的 10-15%。患有 HCM 的猫表现出呼吸困难、嗜睡和心杂音；此外，猫 HCM 还可能导致猝死。在各种方法和指标中，放射摄影和超声是诊断猫 HCM 的金标准。然而，仅使用放射摄影 alone 就达到了 75%的准确性。因此，我们使用 231 张猫的腹背放射图像（143 张 HCM 和 88 张正常）训练了五个残差架构（ResNet50V2、ResNet152、InceptionResNetV2、MobileNetV2 和 Xception），并通过放射摄影研究了诊断猫 HCM 的最佳架构。为了确保数据的可推广性，X 射线图像来自 5 个独立的机构。此外，还使用了 42 张图像进行测试。将测试数据分为两部分；22 张放射图像用于预测分析，20 张猫的放射图像用于评估偷看现象和投票策略。结果，所有模型的准确率均>90%；Resnet50V2：95.45%；Resnet152：95.45%；InceptionResNetV2：95.45%；MobileNetV2：95.45%和 Xception：95.45%。此外，还将两种投票策略应用于五个 CNN 模型；softmax 和多数投票。结果，softmax 投票策略在组合测试数据中达到了 95%的准确率。我们的研究结果表明，使用残差架构的自动化深度学习系统可以帮助兽医放射科医生筛查 HCM。
