2
|
Zhu X, Li X, Ong K, Zhang W, Li W, Li L, Young D, Su Y, Shang B, Peng L, Xiong W, Liu Y, Liao W, Xu J, Wang F, Liao Q, Li S, Liao M, Li Y, Rao L, Lin J, Shi J, You Z, Zhong W, Liang X, Han H, Zhang Y, Tang N, Hu A, Gao H, Cheng Z, Liang L, Yu W, Ding Y. Hybrid AI-assistive diagnostic model permits rapid TBS classification of cervical liquid-based thin-layer cell smears. Nat Commun 2021; 12:3541. [PMID: 34112790 PMCID: PMC8192526 DOI: 10.1038/s41467-021-23913-3] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2021] [Accepted: 05/24/2021] [Indexed: 02/05/2023] Open
Abstract
Technical advancements significantly improve earlier diagnosis of cervical cancer, but accurate diagnosis is still difficult due to various factors. We develop an artificial intelligence assistive diagnostic solution, AIATBS, to improve cervical liquid-based thin-layer cell smear diagnosis according to clinical TBS criteria. We train AIATBS with >81,000 retrospective samples. It integrates YOLOv3 for target detection, Xception and Patch-based models to boost target classification, and U-net for nucleus segmentation. We integrate XGBoost and a logical decision tree with these models to optimize the parameters given by the learning process, and we develop a complete cervical liquid-based cytology smear TBS diagnostic system which also includes a quality control solution. We validate the optimized system with >34,000 multicenter prospective samples and achieve better sensitivity compared to senior cytologists, yet retain high specificity while achieving a speed of <180s/slide. Our system is adaptive to sample preparation using different standards, staining protocols and scanners.
Collapse
Affiliation(s)
- Xiaohui Zhu
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China
- Guangdong Province Key Laboratory of Molecular Tumor Pathology, Guangzhou, Guangdong Province, PR China
| | - Xiaoming Li
- Department of Pathology, Shenzhen Bao'an People's Hospital (group), Shenzhen, Guangdong Province, PR China
| | - Kokhaur Ong
- Institute of Molecular and Cell Biology, A*STAR, Singapore, Singapore
- Bioinformatics Institute, A*STAR, Singapore, Singapore
| | - Wenli Zhang
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China
- Guangdong Province Key Laboratory of Molecular Tumor Pathology, Guangzhou, Guangdong Province, PR China
| | - Wencai Li
- The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, PR China
| | - Longjie Li
- Institute of Molecular and Cell Biology, A*STAR, Singapore, Singapore
| | - David Young
- Institute of Molecular and Cell Biology, A*STAR, Singapore, Singapore
| | - Yongjian Su
- Guangzhou F.Q.PATHOTECH Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Bin Shang
- Guangzhou F.Q.PATHOTECH Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Linggan Peng
- Guangzhou F.Q.PATHOTECH Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Wei Xiong
- Guangzhou Kaipu Biotechnology Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Yunke Liu
- Laboratory Department, Guangzhou Tianhe District Maternal and Child Health Care Hospital, Guangzhou, Guangdong Province, PR China
| | - Wenting Liao
- State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-sen University Cancer Center, Guangzhou, Guangdong Province, PR China
| | - Jingjing Xu
- The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, PR China
| | - Feifei Wang
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China
- Guangdong Province Key Laboratory of Molecular Tumor Pathology, Guangzhou, Guangdong Province, PR China
| | - Qing Liao
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China
- Guangdong Province Key Laboratory of Molecular Tumor Pathology, Guangzhou, Guangdong Province, PR China
| | - Shengnan Li
- Guangzhou F.Q.PATHOTECH Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Minmin Liao
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China
- Guangdong Province Key Laboratory of Molecular Tumor Pathology, Guangzhou, Guangdong Province, PR China
| | - Yu Li
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China
- Guangdong Province Key Laboratory of Molecular Tumor Pathology, Guangzhou, Guangdong Province, PR China
| | - Linshang Rao
- Guangzhou F.Q.PATHOTECH Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Jinquan Lin
- Guangzhou F.Q.PATHOTECH Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Jianyuan Shi
- Guangzhou F.Q.PATHOTECH Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Zejun You
- Guangzhou F.Q.PATHOTECH Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Wenlong Zhong
- Guangzhou Huayin medical inspection center Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Xinrong Liang
- Guangzhou Huayin medical inspection center Co., Ltd, Guangzhou, Guangdong Province, PR China
| | - Hao Han
- Institute of Molecular and Cell Biology, A*STAR, Singapore, Singapore
| | - Yan Zhang
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China
- Department of Pathology, Shenzhen Longhua District Maternity & Child Healthcare Hospital, Shenzhen, PR China
| | - Na Tang
- Department of Pathology, Shenzhen First People's Hospital, Shenzhen, Guangdong Province, PR China
| | - Aixia Hu
- Department of Pathology, Henan Provincial People's Hospital, Zhengzhou, Henan Province, PR China
| | - Hongyi Gao
- Department of Pathology, Guangdong Provincial Women's and Children's Dispensary, Shenzhen, Guangdong Province, PR China
| | - Zhiqiang Cheng
- Department of Pathology, Shenzhen First People's Hospital, Shenzhen, Guangdong Province, PR China.
| | - Li Liang
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China.
- Guangdong Province Key Laboratory of Molecular Tumor Pathology, Guangzhou, Guangdong Province, PR China.
| | - Weimiao Yu
- Institute of Molecular and Cell Biology, A*STAR, Singapore, Singapore.
- Bioinformatics Institute, A*STAR, Singapore, Singapore.
| | - Yanqing Ding
- Department of Pathology, Nanfang Hospital and Basic Medical College, Southern Medical University, Guangzhou, Guangdong Province, PR China.
- Guangdong Province Key Laboratory of Molecular Tumor Pathology, Guangzhou, Guangdong Province, PR China.
| |
Collapse
|
4
|
Qin Z, Chen J, Jiang Z, Yu X, Hu C, Ma Y, Miao S, Zhou R. Learning fine-grained estimation of physiological states from coarse-grained labels by distribution restoration. Sci Rep 2020; 10:21947. [PMID: 33319835 PMCID: PMC7738684 DOI: 10.1038/s41598-020-79007-5] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2020] [Accepted: 11/30/2020] [Indexed: 11/09/2022] Open
Abstract
Due to its importance in clinical science, the estimation of physiological states (e.g., the severity of pathological tremor) has aroused growing interest in machine learning community. While the physiological state is a continuous variable, its continuity is lost when the physiological state is quantized into a few discrete classes during recording and labeling. The discreteness introduces misalignment between the true value and its label, meaning that these labels are unfortunately imprecise and coarse-grained. Most previous work did not consider the inaccuracy and directly utilized the coarse labels to train the machine learning algorithms, whose predictions are also coarse-grained. In this work, we propose to learn a precise, fine-grained estimation of physiological states using these coarse-grained ground truths. Established on mathematical rigorous proof, we utilize imprecise labels to restore the probabilistic distribution of precise labels in an approximate order-preserving fashion, then the deep neural network learns from this distribution and offers fine-grained estimation. We demonstrate the effectiveness of our approach in assessing the pathological tremor in Parkinson's Disease and estimating the systolic blood pressure from bioelectrical signals.
Collapse
Affiliation(s)
- Zengyi Qin
- Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China
| | - Jiansheng Chen
- Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China.
| | - Zhenyu Jiang
- Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China
| | - Xumin Yu
- Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China
| | - Chunhua Hu
- School of Aerospace Engineering, Tsinghua University, Beijing, 100084, China
| | - Yu Ma
- Tsinghua University Yuquan Hospital, Beijing, 100043, China
| | - Suhua Miao
- Tsinghua University Yuquan Hospital, Beijing, 100043, China
| | - Rongsong Zhou
- Tsinghua University Yuquan Hospital, Beijing, 100043, China
| |
Collapse
|