非酒精性脂肪肝（NAFLD）可發展為非酒精性脂肪性肝炎（NASH），這已成為肝硬化的主要原因。NASH的主要特徵和關鍵發現之一是肝細胞的氣球樣變性。一般來說，肝細胞的氣球樣變性是由專業的病理學家使用整個幻燈片圖像（WSIs）手動檢測的。然而，這一程序效率低下，耗時長，而且容易出錯。因此，本研究提出了一個新的基於YOLOv5的架構來解決這個問題，並採用了三種注意力方法來提高該架構在檢測肝細胞氣球樣變性方面的性能：（1）給卷積層配備一個注意力塊；（2）加強網路的快捷連接；（3）使用更先進的方法計算損失函數。來自臺灣一家公立醫院的34名NASH患者的注釋WSIs被用來評估所提出的架構的可行性。實驗結果顯示，使用該架構檢測肝細胞的氣球狀變性，可以達到83.5%的mAP@0.5。總的來說，結果表明，所提出的架構為肝細胞氣球變性提供了一個很有前途的解決方案。

Nonalcoholic fatty liver disease (NAFLD) can progress to nonalcoholic steatohepatitis (NASH), which has become the leading cause of cirrhosis. One of the key features and crucial findings in NASH is the ballooning degeneration of hepatocytes. Generally, ballooning degeneration of hepatocytes is manually detected by professional pathologists using whole slide images (WSIs). Nevertheless, this procedure is inefficient, time-consuming, and error prone. Based on YOLOv5, this study presents a novel architecture to improve the performance in detecting ballooning degeneration of hepatocytes by employing three attention methods: (1) equipping convolution layers with an attention block; (2) enhancing the network's shortcut connections; (3) calculating the loss function using a more advanced approach. Annotated WSIs from 34 NASH patients in a public hospital in Taiwan were used to assess the feasibility of the proposed architecture. The experimental outcomes reveal that the proposed method achieves mAP@0.5 of 83.5% for the detection of ballooning degeneration of hepatocytes. Overall, the results demonstrate that the proposed architecture provides a promising solution for ballooning degeneration of hepatocytes.

[1] N. Chalasani et al., “The diagnosis and management of nonalcoholic fatty liver disease: Practice guidance from the American Association for the study of liver diseases,” Hepatology, vol. 67, no. 1, pp. 328–357, 2017. doi:10.1002/hep.29367
[2] A. M. Dinani, K. V. Kowdley, and M. Noureddin, “Application of artificial intelligence for diagnosis and risk stratification in NAFLD and Nash: The state of the art,” Hepatology, vol. 74, no. 4, pp. 2233–2240, 2021. doi:10.1002/hep.31869.
[3] A. C. Sheka et al., “Nonalcoholic steatohepatitis,” JAMA, vol. 323, no. 12, p. 1175, 2020. doi:10.1001/jama.2020.2298
[4] Z. M. Younossi et al., “Global epidemiology of nonalcoholic Fatty Liver Disease—meta‐analytic assessment of prevalence, incidence, and outcomes,” Hepatology, vol. 64, no. 1, pp. 73–84, 2016. doi:10.1002/hep.28431
[5] J. Ludwig, T. R. Viggiano, D. B. McGill, and B. J. Oh, “Nonalcoholic steatohepatitis: Mayo Clinic experiences with a hitherto unnamed disease,” Mayo Clin Proceedings, vol. 55, no. 7, pp. 434-438, 1980.
[6] F. Schaffner and H. Thaler, “Nonalcoholic fatty liver disease,” Progress in liver diseases, vol. 8, pp. 283-298, 1986.
[7] S. Caldwell et al., “Hepatocellular ballooning in Nash,” Journal of Hepatology, vol. 53, no. 4, pp. 719–723, 2010. doi:10.1016/j.jhep.2010.04.031
[8] S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional Block Attention Module,” Computer Vision – ECCV 2018, pp. 3–19, 2018. doi:10.1007/978-3-030-01234-2_1
[9] J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/cvpr.2018.00745
[10] Q. Wang et al., “ECA-net: Efficient channel attention for deep convolutional neural networks,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. doi:10.1109/cvpr42600.2020.01155
[11] J. Hu, L. Shen, S. Albanie, G. Sun, and A. Vedaldi, “Gather-excite: Exploiting feature context in Convolutional Neural Networks,” Advances in Neural Information Processing Systems, vol. 31, 2018.
[12] Q. Hou, D. Zhou, and J. Feng, “Coordinate attention for efficient mobile network design,” 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. doi:10.1109/cvpr46437.2021.01350
[13] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Lecture Notes in Computer Science, pp. 234–241, 2015. doi:10.1007/978-3-319-24574-4_28.
[14] W. Liu et al., “SSD: Single shot multibox detector,” Computer Vision – ECCV 2016, pp. 21–37, 2016. doi:10.1007/978-3-319-46448-0_2.
[15] M. Tan and Q. Le, “EfficientNet: Rethinking model scaling for Convolutional Neural Networks,” International conference on machine learning，vol. 97, pp. 6105-6114, PMLR, 2019.
[16] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. doi:10.1109/cvpr.2016.91
[17] J. Redmon and A. Farhadi, “Yolo9000: Better, faster, stronger,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. doi:10.1109/cvpr.2017.690
[18] J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv.org, https://arxiv.org/abs/1804.02767, 2018.
[19] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal Speed and accuracy of object detection,” arXiv.org, https://arxiv.org/abs/2004.10934, 2020.
[20] G. Jocher, ‘YOLOv5 Github’, 2020. https://github.com/ultralytics/yolov5.
[21] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464-7475, 2023.
[22] C.-Y. Wang et al., “CSPNet: A new backbone that can enhance learning capability of CNN,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020. doi:10.1109/cvprw50498.2020.00203
[23] K. He, X. Zhang, S. Ren, and J. Sun, “Spatial pyramid pooling in deep convolutional networks for visual recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 9, pp. 1904–1916, 2015. doi:10.1109/tpami.2015.2389824
[24] S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path Aggregation Network for instance segmentation,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/cvpr.2018.00913
[25] H. Rezatofighi et al., “Generalized intersection over union: A metric and a loss for bounding box regression,” 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. doi:10.1109/cvpr.2019.00075
[26] Z. Zheng et al., “Distance-IOU loss: Faster and better learning for bounding box regression,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12993–13000, 2020. doi:10.1609/aaai.v34i07.6999
[27] M. Tan, R. Pang, and Q. V. Le, “EfficientDet: Scalable and efficient object detection,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. doi:10.1109/cvpr42600.2020.01079
[28] K. Wang, ‘YOLOv7 Github’, 2022. https://github.com/WongKinYiu/yolov7.