BRAIN and NERVE－神経研究の進歩74巻8号

2022年08月発行

総説

「人工知能（AI）による筋病理判読アルゴリズム」の開発

著者： 大久保真理子¹ 壁谷佳典² 西野一三¹

所属機関： ¹国立精神・神経医療研究センター神経研究所疾病研究第一部 ²日本IBM

ページ範囲：P.1019 - P.1024

文献概要

筋疾患の診断には生検筋に対する筋病理診断が重要であり，特に筋炎は治療法が確立されていることから，正確な診断が求められている。今回われわれは深層学習を用い，筋病理画像から筋炎であるか否かを判別するモデルの構築を試みた。1,400検体のヘマトキシリン・エオジン染色標本の顕微鏡画像を用い，AIを用いたモデルの訓練と評価を行った。その結果，われわれの筋炎判別モデルは専門医に匹敵する判別精度を有することが明らかとなった。

参考文献

1）Selva-O'Callaghan A, Pinal-Fernandez I, Trallero-Araguás E, Milisenda JC, Grau-Junyent JM, et al: Classification and management of adult inflammatory myopathies. Lancet Neurol 17: 816-828, 2018

2）Liang WC, Uruha A, Suzuki S, Murakami N, Takeshita E, et al: Pediatric necrotizing myopathy associated with anti-3-hydroxy-3-methylglutaryl-coenzyme A reductase antibodies. Rheumatology (Oxford) 56: 287-293, 2017

3）Tanboon J, Nishino I: Classification of idiopathic inflammatory myopathies: pathology perspectives. Curr Opin Neurol 32: 704-714, 2019

4）Kabeya Y, Okubo M, Yonezawa S, Nakano H, Inoue M, et al: Deep convolutional neural network-based algorithm for muscle biopsy diagnosis. Lab Invest 102: 220-226, 2022

5）Ehteshami Bejnordi B, Veta M, Johannes van Diest P, van Ginneken B, Karssemeijer N, et al: Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318: 2199-2210, 2017

6）Coudray N, Ocampo PS, Sakellaropoulos T, Narula N, Snuderl M, et al: Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med 24: 1559-1567, 2018

7）Iizuka O, Kanavati F, Kato K, Rambeau M, Arihiro K, et al: Deep learning models for histopathological classification of gastric and colonic epithelial tumours. Sci Rep 10: 1504, 2020［doi: 10.1038/s41598-020-58467-9］

8）Wang S, Yang DM, Rong R, Zhan X, Xiao G: Pathology image analysis using segmentation deep learning algorithms. Am J Pathol 189: 1686-1698, 2019

9）Echle A, Rindtorff NT, Brinker TJ, Luedde T, Pearson AT, et al: Deep learning in cancer pathology: a new generation of clinical biomarkers. Br J Cancer 124: 686-696, 2021

10）Kabeya Y, Iwamori T, Yonezawa S, Takeuchi Y, Nakano H, et al: Physician-level aggregated classifier for genetic muscle disorders. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) 1850-1854, 2019

11）Deng J, Dong W, Socher R, Li LJ, Li K, et al: Image net: a large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition 248-255, 2009

12）Huang G, Liu Z, van Der Maaten L, Weinberger KQ: Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2261-2269, 2017

13）Liu L, Jiang H, He P, Chen W, Liu X, et al: On the variance of the adaptive learning rate and beyond. 2019［doi: 10.48550/arXiv.1908.03265］

14）Cho H, Hwang YH, Chung JK, Lee KB, Park JS, et al: Deep learning ensemble method for classifying glaucoma stages using fundus photographs and convolutional neural networks. Curr Eye Res 46: 1516-1524, 2021

15）Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, et al: Grad-cam: visual explanations from deep networks via gradient-based localization. 2017 IEEE International Conference on Computer Vision (ICCV) 618-626, 2017