1
|
He Q, Ge S, Zeng S, Wang Y, Ye J, He Y, Li J, Wang Z, Guan T. Global attention based GNN with Bayesian collaborative learning for glomerular lesion recognition. Comput Biol Med 2024; 173:108369. [PMID: 38552283 DOI: 10.1016/j.compbiomed.2024.108369] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2023] [Revised: 03/18/2024] [Accepted: 03/24/2024] [Indexed: 04/17/2024]
Abstract
BACKGROUND Glomerular lesions reflect the onset and progression of renal disease. Pathological diagnoses are widely regarded as the definitive method for recognizing these lesions, as the deviations in histopathological structures closely correlate with impairments in renal function. METHODS Deep learning plays a crucial role in streamlining the laborious, challenging, and subjective task of recognizing glomerular lesions by pathologists. However, the current methods treat pathology images as data in regular Euclidean space, limiting their ability to efficiently represent the complex local features and global connections. In response to this challenge, this paper proposes a graph neural network (GNN) that utilizes global attention pooling (GAP) to more effectively extract high-level semantic features from glomerular images. The model incorporates Bayesian collaborative learning (BCL), enhancing node feature fine-tuning and fusion during training. In addition, this paper adds a soft classification head to mitigate the semantic ambiguity associated with a purely hard classification. RESULTS This paper conducted extensive experiments on four glomerular datasets, comprising a total of 491 whole slide images (WSIs) and 9030 images. The results demonstrate that the proposed model achieves impressive F1 scores of 81.37%, 90.12%, 87.72%, and 98.68% on four private datasets for glomerular lesion recognition. These scores surpass the performance of the other models used for comparison. Furthermore, this paper employed a publicly available BReAst Carcinoma Subtyping (BRACS) dataset with an 85.61% F1 score to further prove the superiority of the proposed model. CONCLUSION The proposed model not only facilitates precise recognition of glomerular lesions but also serves as a potent tool for diagnosing kidney diseases effectively. Furthermore, the framework and training methodology of the GNN can be adeptly applied to address various pathology image classification challenges.
Collapse
Affiliation(s)
- Qiming He
- Department of Life and Health, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, Guangdong, China
| | - Shuang Ge
- Department of Life and Health, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, Guangdong, China; Peng Cheng Laboratory, Shenzhen, China
| | - Siqi Zeng
- Department of Life and Health, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, Guangdong, China; Greater Bay Area National Center of Technology Innovation, Guangzhou, China
| | - Yanxia Wang
- Department of Pathology, State Key Laboratory of Cancer Biology, Xijing Hospital, Fourth Military Medical University, Xi'an, China; School of Basic Medicine, Fourth Military Medical University, Xi'an, China
| | - Jing Ye
- Department of Pathology, State Key Laboratory of Cancer Biology, Xijing Hospital, Fourth Military Medical University, Xi'an, China; School of Basic Medicine, Fourth Military Medical University, Xi'an, China
| | - Yonghong He
- Department of Life and Health, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, Guangdong, China
| | - Jing Li
- Department of Pathology, State Key Laboratory of Cancer Biology, Xijing Hospital, Fourth Military Medical University, Xi'an, China; School of Basic Medicine, Fourth Military Medical University, Xi'an, China.
| | - Zhe Wang
- Department of Pathology, State Key Laboratory of Cancer Biology, Xijing Hospital, Fourth Military Medical University, Xi'an, China; School of Basic Medicine, Fourth Military Medical University, Xi'an, China
| | - Tian Guan
- Department of Life and Health, Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, Guangdong, China
| |
Collapse
|
2
|
Mukashyaka P, Sheridan TB, Foroughi Pour A, Chuang JH. SAMPLER: unsupervised representations for rapid analysis of whole slide tissue images. EBioMedicine 2024; 99:104908. [PMID: 38101298 PMCID: PMC10733087 DOI: 10.1016/j.ebiom.2023.104908] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Revised: 11/27/2023] [Accepted: 11/27/2023] [Indexed: 12/17/2023] Open
Abstract
BACKGROUND Deep learning has revolutionized digital pathology, allowing automatic analysis of hematoxylin and eosin (H&E) stained whole slide images (WSIs) for diverse tasks. WSIs are broken into smaller images called tiles, and a neural network encodes each tile. Many recent works use supervised attention-based models to aggregate tile-level features into a slide-level representation, which is then used for downstream analysis. Training supervised attention-based models is computationally intensive, architecture optimization of the attention module is non-trivial, and labeled data are not always available. Therefore, we developed an unsupervised and fast approach called SAMPLER to generate slide-level representations. METHODS Slide-level representations of SAMPLER are generated by encoding the cumulative distribution functions of multiscale tile-level features. To assess effectiveness of SAMPLER, slide-level representations of breast carcinoma (BRCA), non-small cell lung carcinoma (NSCLC), and renal cell carcinoma (RCC) WSIs of The Cancer Genome Atlas (TCGA) were used to train separate classifiers distinguishing tumor subtypes in FFPE and frozen WSIs. In addition, BRCA and NSCLC classifiers were externally validated on frozen WSIs. Moreover, SAMPLER's attention maps identify regions of interest, which were evaluated by a pathologist. To determine time efficiency of SAMPLER, we compared runtime of SAMPLER with two attention-based models. SAMPLER concepts were used to improve the design of a context-aware multi-head attention model (context-MHA). FINDINGS SAMPLER-based classifiers were comparable to state-of-the-art attention deep learning models to distinguish subtypes of BRCA (AUC = 0.911 ± 0.029), NSCLC (AUC = 0.940 ± 0.018), and RCC (AUC = 0.987 ± 0.006) on FFPE WSIs (internal test sets). However, training SAMLER-based classifiers was >100 times faster. SAMPLER models successfully distinguished tumor subtypes on both internal and external test sets of frozen WSIs. Histopathological review confirmed that SAMPLER-identified high attention tiles contained subtype-specific morphological features. The improved context-MHA distinguished subtypes of BRCA and RCC (BRCA-AUC = 0.921 ± 0.027, RCC-AUC = 0.988 ± 0.010) with increased accuracy on internal test FFPE WSIs. INTERPRETATION Our unsupervised statistical approach is fast and effective for analyzing WSIs, with greatly improved scalability over attention-based deep learning methods. The high accuracy of SAMPLER-based classifiers and interpretable attention maps suggest that SAMPLER successfully encodes the distinct morphologies within WSIs and will be applicable to general histology image analysis problems. FUNDING This study was supported by the National Cancer Institute (Grant No. R01CA230031 and P30CA034196).
Collapse
Affiliation(s)
- Patience Mukashyaka
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA; Department of Genetics and Genome Sciences, University of Connecticut Health Center, Farmington, CT, USA
| | - Todd B Sheridan
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA; Department of Pathology, Hartford Hospital, Hartford, CT, USA
| | | | - Jeffrey H Chuang
- The Jackson Laboratory for Genomic Medicine, Farmington, CT, USA; Department of Genetics and Genome Sciences, University of Connecticut Health Center, Farmington, CT, USA.
| |
Collapse
|
3
|
Jin L, Sun T, Liu X, Cao Z, Liu Y, Chen H, Ma Y, Zhang J, Zou Y, Liu Y, Shi F, Shen D, Wu J. A multi-center performance assessment for automated histopathological classification and grading of glioma using whole slide images. iScience 2023; 26:108041. [PMID: 37876818 PMCID: PMC10590813 DOI: 10.1016/j.isci.2023.108041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 08/10/2023] [Accepted: 09/21/2023] [Indexed: 10/26/2023] Open
Abstract
Accurate pathological classification and grading of gliomas is crucial in clinical diagnosis and treatment. The application of deep learning techniques holds promise for automated histological pathology diagnosis. In this study, we collected 733 whole slide images from four medical centers, of which 456 were used for model training, 150 for internal validation, and 127 for multi-center testing. The study includes 5 types of common gliomas. A subtask-guided multi-instance learning image-to-label training pipeline was employed. The pipeline leveraged "patch prompting" for the model to converge with reasonable computational cost. Experiments showed that an overall accuracy of 0.79 in the internal validation dataset. The performance on the multi-center testing dataset showed an overall accuracy to 0.73. The findings suggest a minor yet acceptable performance decrease in multi-center data, demonstrating the model's strong generalizability and establishing a robust foundation for future clinical applications.
Collapse
Affiliation(s)
- Lei Jin
- Glioma Surgery Division, Neurologic Surgery Department, Huashan Hospital Fudan University, Shanghai 200040, China
- National Center for Neurological Disorders, Huashan Hospital Fudan University, Shanghai 200040, China
| | - Tianyang Sun
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd, Shanghai 200030, China
| | - Xi Liu
- Glioma Surgery Division, Neurologic Surgery Department, Huashan Hospital Fudan University, Shanghai 200040, China
- National Center for Neurological Disorders, Huashan Hospital Fudan University, Shanghai 200040, China
| | - Zehong Cao
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd, Shanghai 200030, China
| | - Yan Liu
- Glioma Surgery Division, Neurologic Surgery Department, Huashan Hospital Fudan University, Shanghai 200040, China
- National Center for Neurological Disorders, Huashan Hospital Fudan University, Shanghai 200040, China
| | - Hong Chen
- National Center for Neurological Disorders, Huashan Hospital Fudan University, Shanghai 200040, China
- Department of Pathology, Huashan Hospital Fudan University, Shanghai 200040, China
| | - Yixin Ma
- Glioma Surgery Division, Neurologic Surgery Department, Huashan Hospital Fudan University, Shanghai 200040, China
- National Center for Neurological Disorders, Huashan Hospital Fudan University, Shanghai 200040, China
| | - Jun Zhang
- Wuhan Zhongji Biotechnology Co., Ltd, Wuhan 430206, China
| | - Yaping Zou
- Wuhan Zhongji Biotechnology Co., Ltd, Wuhan 430206, China
| | - Yingchao Liu
- Department of Neurosurgery, The Provincial Hospital Affiliated to Shandong First Medical University, Shandong 250021, China
| | - Feng Shi
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd, Shanghai 200030, China
| | - Dinggang Shen
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd, Shanghai 200030, China
- School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China
- Shanghai Clinical Research and Trial Center, Shanghai 201210, China
| | - Jinsong Wu
- Glioma Surgery Division, Neurologic Surgery Department, Huashan Hospital Fudan University, Shanghai 200040, China
- National Center for Neurological Disorders, Huashan Hospital Fudan University, Shanghai 200040, China
| |
Collapse
|
4
|
Mukashyaka P, Sheridan TB, Foroughi Pour A, Chuang JH. SAMPLER: Empirical distribution representations for rapid analysis of whole slide tissue images. bioRxiv 2023:2023.08.01.551468. [PMID: 37577691 PMCID: PMC10418159 DOI: 10.1101/2023.08.01.551468] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/15/2023]
Abstract
Deep learning has revolutionized digital pathology, allowing for automatic analysis of hematoxylin and eosin (H&E) stained whole slide images (WSIs) for diverse tasks. In such analyses, WSIs are typically broken into smaller images called tiles, and a neural network backbone encodes each tile in a feature space. Many recent works have applied attention based deep learning models to aggregate tile-level features into a slide-level representation, which is then used for slide-level prediction tasks. However, training attention models is computationally intensive, necessitating hyperparameter optimization and specialized training procedures. Here, we propose SAMPLER, a fully statistical approach to generate efficient and informative WSI representations by encoding the empirical cumulative distribution functions (CDFs) of multiscale tile features. We demonstrate that SAMPLER-based classifiers are as accurate or better than state-of-the-art fully deep learning attention models for classification tasks including distinction of: subtypes of breast carcinoma (BRCA: AUC=0.911 ± 0.029); subtypes of non-small cell lung carcinoma (NSCLC: AUC=0.940±0.018); and subtypes of renal cell carcinoma (RCC: AUC=0.987±0.006). A major advantage of the SAMPLER representation is that predictive models are >100X faster compared to attention models. Histopathological review confirms that SAMPLER-identified high attention tiles contain tumor morphological features specific to the tumor type, while low attention tiles contain fibrous stroma, blood, or tissue folding artifacts. We further apply SAMPLER concepts to improve the design of attention-based neural networks, yielding a context aware multi-head attention model with increased accuracy for subtype classification within BRCA and RCC (BRCA: AUC=0.921±0.027, and RCC: AUC=0.988±0.010). Finally, we provide theoretical results identifying sufficient conditions for which SAMPLER is optimal. SAMPLER is a fast and effective approach for analyzing WSIs, with greatly improved scalability over attention methods to benefit digital pathology analysis.
Collapse
Affiliation(s)
- Patience Mukashyaka
- The Jackson Laboratory for Genomic Medicine, Farmington, CT
- University of Connecticut Health Center, Department of Genetics and Genome Sciences, Farmington, CT
| | - Todd B Sheridan
- The Jackson Laboratory for Genomic Medicine, Farmington, CT
- Department of Pathology, Hartford hospital, Hartford, CT
| | | | - Jeffrey H Chuang
- The Jackson Laboratory for Genomic Medicine, Farmington, CT
- University of Connecticut Health Center, Department of Genetics and Genome Sciences, Farmington, CT
| |
Collapse
|