Wei-Hsiang Yu
Research Subjects
Research Interests
Wei-Hsiang Yu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Chao-Yuan Yeh
AetherAI
3 shared publications - Chi-Chung Chen
AetherAI Co., Ltd., Taipei, Taiwan
2 shared publications Chi-Ju Yeh
Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, Taoyuan, Taiwan; School of Medicine, Chang Gung University, Taoyuan, Taiwan
2 shared publicationsChuen Hsueh
Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, Taoyuan, Taiwan; School of Medicine, Chang Gung University, Taoyuan, Taiwan; Chang Gung Molecular Medicine Research Center, Chang Gung University, Taoyuan, Taiwan
2 shared publications- Tong-Hong Wang
Biobank, Chang Gung Memorial Hospital Taoyuan Taiwan
2 shared publications - Wen-Yu Chuang
Department of Pathology, Chang Gung Memorial Hospital
2 shared publications
Latest Publications
- Open Access
- 21 September 2022
- Published by Elsevier in The American Journal of Pathology
- Vol. 192 (12) , 1763-1778
Deep Learning–Based Nuclear Morphometry Reveals an Independent Prognostic Factor in Mantle Cell Lymphoma
- 21 September 2022
- Published by Elsevier in The American Journal of Pathology
- Vol. 192 (12) , 1763-1778
Open AccessDeep Learning–Based Nuclear Morphometry Reveals an Independent Prognostic Factor in Mantle Cell Lymphoma
- Open Access
- 8 June 2021
- Published by Elsevier in Laboratory Investigation
- Vol. 34 (10) , 1901-1911
Identification of nodal micrometastasis in colorectal cancer using deep learning on annotation-free whole-slide images
- 8 June 2021
- Published by Elsevier in Laboratory Investigation
- Vol. 34 (10) , 1901-1911
Open AccessIdentification of nodal micrometastasis in colorectal cancer using deep learning on annotation-free whole-slide images
- Top Cited PapersOpen Access
- 19 February 2021
- Published by Springer Nature in Nature Communications
- Vol. 12 (1) , 1-13
An annotation-free whole-slide training approach to pathological classification of lung cancer types using deep learning
Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole-slide images (WSIs). Most studies have employed patch-based methods, which often require detailed annotation of image patches. This typically involves laborious free-hand contouring on WSIs. To alleviate the burden of such contouring and obtain benefits from scaling up training with numerous WSIs, we develop a method for training neural networks on entire WSIs using only slide-level diagnoses. Our method leverages the unified memory mechanism to overcome the memory constraint of compute accelerators. Experiments conducted on a data set of 9662 lung cancer WSIs reveal that the proposed method achieves areas under the receiver operating characteristic curve of 0.9594 and 0.9414 for adenocarcinoma and squamous cell carcinoma classification on the testing set, respectively. Furthermore, the method demonstrates higher classification performance than multiple-instance learning as well as strong localization results for small lesions through class activation mapping.
- 19 February 2021
- Published by Springer Nature in Nature Communications
- Vol. 12 (1) , 1-13
Top Cited PapersOpen AccessAn annotation-free whole-slide training approach to pathological classification of lung cancer types using deep learning
Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole-slide images (WSIs). Most studies have employed patch-based methods, which often require detailed annotation of image patches. This typically involves laborious free-hand contouring on WSIs. To alleviate the burden of such contouring and obtain benefits from scaling up training with numerous WSIs, we develop a method for training neural networks on entire WSIs using only slide-level diagnoses. Our method leverages the unified memory mechanism to overcome the memory constraint of compute accelerators. Experiments conducted on a data set of 9662 lung cancer WSIs reveal that the proposed method achieves areas under the receiver operating characteristic curve of 0.9594 and 0.9414 for adenocarcinoma and squamous cell carcinoma classification on the testing set, respectively. Furthermore, the method demonstrates higher classification performance than multiple-instance learning as well as strong localization results for small lesions through class activation mapping.