1
|
Wang J, Yang X, Jia X, Xue W, Chen R, Chen Y, Zhu X, Liu L, Cao Y, Zhou J, Ni D, Gu N. Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training. Comput Biol Med 2024; 171:108087. [PMID: 38364658 DOI: 10.1016/j.compbiomed.2024.108087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2023] [Revised: 01/04/2024] [Accepted: 01/27/2024] [Indexed: 02/18/2024]
Abstract
Thyroid nodule classification and segmentation in ultrasound images are crucial for computer-aided diagnosis; however, they face limitations owing to insufficient labeled data. In this study, we proposed a multi-view contrastive self-supervised method to improve thyroid nodule classification and segmentation performance with limited manual labels. Our method aligns the transverse and longitudinal views of the same nodule, thereby enabling the model to focus more on the nodule area. We designed an adaptive loss function that eliminates the limitations of the paired data. Additionally, we adopted a two-stage pre-training to exploit the pre-training on ImageNet and thyroid ultrasound images. Extensive experiments were conducted on a large-scale dataset collected from multiple centers. The results showed that the proposed method significantly improves nodule classification and segmentation performance with limited manual labels and outperforms state-of-the-art self-supervised methods. The two-stage pre-training also significantly exceeded ImageNet pre-training.
Collapse
Affiliation(s)
- Jian Wang
- Key Laboratory for Bio-Electromagnetic Environment and Advanced Medical Theranostics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, 211166, China
| | - Xin Yang
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518073, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, 518073, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, 518073, China
| | - Xiaohong Jia
- Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025, China
| | - Wufeng Xue
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518073, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, 518073, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, 518073, China
| | - Rusi Chen
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518073, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, 518073, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, 518073, China
| | - Yanlin Chen
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518073, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, 518073, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, 518073, China
| | - Xiliang Zhu
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518073, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, 518073, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, 518073, China
| | - Lian Liu
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518073, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, 518073, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, 518073, China
| | - Yan Cao
- Shenzhen RayShape Medical Technology Co., Ltd, Shenzhen, 518051, China
| | - Jianqiao Zhou
- Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, 200025, China.
| | - Dong Ni
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518073, China; Marshall Laboratory of Biomedical Engineering, Shenzhen University, Shenzhen, 518073, China; Medical UltraSound Image Computing (MUSIC) Lab, Shenzhen University, Shenzhen, 518073, China.
| | - Ning Gu
- Key Laboratory for Bio-Electromagnetic Environment and Advanced Medical Theranostics, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, 211166, China; Cardiovascular Disease Research Center, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Medical School, Nanjing University, Nanjing, 210093, China.
| |
Collapse
|
2
|
Tian D, Chen W, Xu D, Xu L, Xu G, Guo Y, Yao Y. A review of traditional Chinese medicine diagnosis using machine learning: Inspection, auscultation-olfaction, inquiry, and palpation. Comput Biol Med 2024; 170:108074. [PMID: 38330826 DOI: 10.1016/j.compbiomed.2024.108074] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2023] [Revised: 12/15/2023] [Accepted: 01/27/2024] [Indexed: 02/10/2024]
Abstract
Traditional Chinese medicine (TCM) is an essential part of the Chinese medical system and is recognized by the World Health Organization as an important alternative medicine. As an important part of TCM, TCM diagnosis is a method to understand a patient's illness, analyze its state, and identify syndromes. In the long-term clinical diagnosis practice of TCM, four fundamental and effective diagnostic methods of inspection, auscultation-olfaction, inquiry, and palpation (IAOIP) have been formed. However, the diagnostic information in TCM is diverse, and the diagnostic process depends on doctors' experience, which is subject to a high-level subjectivity. At present, the research on the automated diagnosis of TCM based on machine learning is booming. Machine learning, which includes deep learning, is an essential part of artificial intelligence (AI), which provides new ideas for the objective and AI-related research of TCM. This paper aims to review and summarize the current research status of machine learning in TCM diagnosis. First, we review some key factors for the application of machine learning in TCM diagnosis, including data, data preprocessing, machine learning models, and evaluation metrics. Second, we review and summarize the research and applications of machine learning methods in TCM IAOIP and the synthesis of the four diagnostic methods. Finally, we discuss the challenges and research directions of using machine learning methods for TCM diagnosis.
Collapse
Affiliation(s)
- Dingcheng Tian
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110819, China
| | - Weihao Chen
- Research Institute for Medical and Biological Engineering, Ningbo University, Ningbo, 315211, China
| | - Dechao Xu
- Research Institute for Medical and Biological Engineering, Ningbo University, Ningbo, 315211, China
| | - Lisheng Xu
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110819, China
| | - Gang Xu
- The First Affiliated Hospital of Liaoning University of TraditionalChinese Medicine, Shenyang, 110000, China
| | - Yaochen Guo
- The Affiliated Hospital of the Medical School of Ningbo University, Ningbo, 315020, China
| | - Yudong Yao
- Research Institute for Medical and Biological Engineering, Ningbo University, Ningbo, 315211, China.
| |
Collapse
|
3
|
Li X, Chen K, Yang J, Wang C, Yang T, Luo C, Li N, Liu Z. TLDA: A transfer learning based dual-augmentation strategy for traditional Chinese Medicine syndrome differentiation in rare disease. Comput Biol Med 2024; 169:107808. [PMID: 38101119 DOI: 10.1016/j.compbiomed.2023.107808] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2023] [Revised: 11/30/2023] [Accepted: 12/01/2023] [Indexed: 12/17/2023]
Abstract
The Traditional Chinese Medicine (TCM) has demonstrated its significant medical value over the decades, particularly during the COVID-19 pandemic. TCM-AI interdisciplinary models have been proposed to model TCM knowledge, diagnosis, and treatment experiments in clinical practice. Among them, numerous models have been developed to simulate the syndrome differentiation process of human TCM doctors for automatic syndrome diagnosis. However, these models are designed for normal scenarios and trained using a supervised learning paradigm which needs tens of thousands of training samples. They fail to effectively differentiate syndromes in rare disease scenarios where the available TCM electronic medical records (EMRs) are very limited for each unique syndrome. To address the challenge of rare diseases, this study proposes a simple yet effective method called Transfer Learning based Dual-Augmentation (TLDA). TLDA aims to augment the limited EMRs at both the sample-level and feature-level, enriching the pathological and medical information during training. Extended experiments involving 11 comparison models, including the state-of-the-art model, demonstrate the effectiveness of TLDA. TLDA outperforms all comparison models by a significant margin. Furthermore, TLDA can also be extended to other medical tasks when the EMRs for diagnosis are limited in samples.
Collapse
Affiliation(s)
- Xiaochen Li
- Interdisciplinary Research Centers, Zhejiang Lab, Hangzhou, 311100, China
| | - Kui Chen
- Interdisciplinary Research Centers, Zhejiang Lab, Hangzhou, 311100, China
| | - Jiaxi Yang
- Interdisciplinary Research Centers, Zhejiang Lab, Hangzhou, 311100, China
| | - Cheng Wang
- Interdisciplinary Research Centers, Zhejiang Lab, Hangzhou, 311100, China
| | - Tao Yang
- TCM Department, Beijing Shijitan Hospital, Capital Medical University, Beijing, 100038, China
| | - Changyong Luo
- Infectious Fever Center, Dongfang Hospital of Beijing University of Chinese Medicine, Beijing, 100078, China
| | - Nan Li
- Interdisciplinary Research Centers, Zhejiang Lab, Hangzhou, 311100, China
| | - Zhi Liu
- Interdisciplinary Research Centers, Zhejiang Lab, Hangzhou, 311100, China.
| |
Collapse
|
4
|
Li M, Wang L, Wu Q, Zhu J, Zhang M. Diagnosis knowledge constrained network based on first-order logic for syndrome differentiation. Artif Intell Med 2024; 147:102739. [PMID: 38044249 DOI: 10.1016/j.artmed.2023.102739] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Revised: 10/16/2023] [Accepted: 11/28/2023] [Indexed: 12/05/2023]
Abstract
Traditional Chinese medicine (TCM) has been recognized worldwide as a valuable asset of human medicine. The procedure of TCM is to treatment based on syndrome differentiation. However, the effect of TCM syndrome differentiation relies heavily on the experience of doctors. The gratifying progress of machine learning research in recent years has brought new ideas for TCM syndrome differentiation. In this paper, we propose a deep network model for TCM syndrome differentiation, which improves network performance by injecting TCM syndrome differentiation knowledge in the form of first-order logic into the deep network. Experimental results show that the accuracy of our proposed model reaches 89%, which is significantly better than the deep learning model MLP and other traditional machine learning models. In addition, we present the collected and formatted TCM syndrome differentiation (TSD) dataset, which contains more than 40,000 TCM clinical records. Moreover, 45 symptoms (""), 322 patterns(""), and more than 500 symptoms are labeled in TSD respectively. To the best of our knowledge, this is the first TCM syndrome differentiation dataset labeling diseases, syndromes and pattern. Such detailed labeling is helpful to explore the relationship between various elements of syndrome differentiation.
Collapse
Affiliation(s)
- Meiwen Li
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China.
| | - Lin Wang
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China.
| | - Qingtao Wu
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China.
| | - Junlong Zhu
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China.
| | - Mingchuan Zhang
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, China.
| |
Collapse
|
5
|
Deep Learning Multi-label Tongue Image Analysis and Its Application in a Population Undergoing Routine Medical Checkup. EVIDENCE-BASED COMPLEMENTARY AND ALTERNATIVE MEDICINE 2022; 2022:3384209. [PMID: 36212950 PMCID: PMC9536899 DOI: 10.1155/2022/3384209] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/12/2022] [Revised: 06/09/2022] [Accepted: 09/07/2022] [Indexed: 11/23/2022]
Abstract
Background Research on intelligent tongue diagnosis is a main direction in the modernization of tongue diagnosis technology. Identification of tongue shape and texture features is a difficult task for tongue diagnosis in traditional Chinese medicine (TCM). This study aimed to explore the application of deep learning techniques in tongue image analyses. Methods A total of 8676 tongue images were annotated by clinical experts, into seven categories, including the fissured tongue, tooth-marked tongue, stasis tongue, spotted tongue, greasy coating, peeled coating, and rotten coating. Based on the labeled tongue images, the deep learning model faster region-based convolutional neural networks (Faster R-CNN) was utilized to classify tongue images. Four performance indices, i.e., accuracy, recall, precision, and F1-score, were selected to evaluate the model. Also, we applied it to analyze tongue image features of 3601 medical checkup participants in order to explore gender and age factors and the correlations among tongue features in diseases through complex networks. Results The average accuracy, recall, precision, and F1-score of our model achieved 90.67%, 91.25%, 99.28%, and 95.00%, respectively. Over the tongue images from the medical checkup population, the model Faster R-CNN detected 41.49% fissured tongue images, 37.16% tooth-marked tongue images, 29.66% greasy coating images, 18.66% spotted tongue images, 9.97% stasis tongue images, 3.97% peeled coating images, and 1.22% rotten coating images. There were significant differences in the incidence of the fissured tongue, tooth-marked tongue, spotted tongue, and greasy coating among age and gender. Complex networks revealed that fissured tongue and tooth-marked were closely related to hypertension, dyslipidemia, overweight and nonalcoholic fatty liver disease (NAFLD), and a greasy coating tongue was associated with hypertension and overweight. Conclusion The model Faster R-CNN shows good performance in the tongue image classification. And we have preliminarily revealed the relationship between tongue features and gender, age, and metabolic diseases in a medical checkup population.
Collapse
|
6
|
Yang T, Yu X, Ma N, Zhang Y, Li H. Deep representation-based transfer learning for deep neural networks. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2022.109526] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|