日本磁気共鳴医学会雑誌
Online ISSN : 2434-0499
Print ISSN : 0914-9457
大会長賞記録
“正常”を学習させた機械学習モデルによる脳梗塞病変の検出[大会長賞記録]
和田 昭彦斎藤 勇哉加藤 伸平萩原 彰文藤田 翔平藤本 幸多朗池之内 穣佐藤 香菜子明石 敏昭天野 真紀鎌形 康司隈丸 加奈子中西 淳鈴木 通真堀 正明青木 茂樹
著者情報
ジャーナル フリー

2020 年 40 巻 1 号 p. 26-29

詳細
抄録

 We attempted to detect and diagnose cerebral infarction on diffusion weighted image (DWI) using a machine learning model trained using normal brain data. Our machine learning model consisted of two parts. One consisted of an autoencoder (AE), which learned only normal DWI information. This AE model did not reproduce the lesion ; the input image was subtracted and the generated image contributed to abnormal signal detection. The other part was a classifier constructed with SqueezeNet, which distinguished between infarct and normal areas using the original DWI image, AE generated images, and subtraction images. The accuracy of the combination of AE and SqueezeNet in 2-class classification for abnormal detection on DWI was 0.97.

著者関連情報
© 2020 一般社団法人日本磁気共鳴医学会
前の記事 次の記事
feedback
Top