[cov3-cov5] :正常 :異常陰影 COVID-19画像所見 推定結果 [cov1] M Oda, et al., Lung infection and normal region segmentation from CT volumes of COVID-19 cases, SPIE Medical Imaging, 2021 [cov2] M Oda, et al., COVID-19 Infection Segmentation from Chest CT Images Based on Scale Uncertainty, CLIP2021, LNCS 12969, pp.88-97, 2021 [cov3] M Oda, et al., Automated classification method of COVID-19 cases from chest CT volumes using 2D and 3D hybrid CNN for anisotropic volumes, SPIE Medical Imaging, 2022 [cov4] M Oda, et al., Classification of COVID-19 cases from chest CT volumes using hybrid model of 3D CNN and 3D MLP-mixer, SPIE Medical Imaging, 2023 [cov5] R Toda, et al., Improved method for COVID-19 classification of complex-architecture CNN from chest CT volumes using orthogonal ensemble networks, SPIE Medical Imaging, 2023 約85%の分類精度達成 17
不確実性マップ 正解領域 セグメンテーション結果 不確実性高 → 十分学習していない 形状パターンが出現 セグメンテーション結果 ? [8] Z Zheng, et al., Taking full advantage of uncertainty estimation: an uncertainty-assisted two-stage pipeline for multi-organ segmentation, SPIE Medical Imaging, 2022 22
モデルから仮想的な医用画像を生成可能 XCATファントム(仮想人体モデル)[9] 実CT像とモデルから生成した仮想CT像 [9] [9] WP Segars, et al. Application of the 4D XCAT Phantoms in Biomedical Imaging and Beyond. IEEE Trans Med Imag, 37(3), 680-692, 2017 26