1
|
Wang GY, Zhu JF, Wang QC, Qin JX, Wang XL, Liu X, Liu XY, Chen JZ, Zhu JF, Zhuo SC, Wu D, Li N, Chao L, Meng FL, Lu H, Shi ZD, Jia ZG, Han CH. Prediction of non-muscle invasive bladder cancer recurrence using deep learning of pathology image. Sci Rep 2024; 14:18931. [PMID: 39147803 PMCID: PMC11327297 DOI: 10.1038/s41598-024-66870-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Accepted: 07/04/2024] [Indexed: 08/17/2024] Open
Abstract
We aimed to build a deep learning-based pathomics model to predict the early recurrence of non-muscle-infiltrating bladder cancer (NMIBC) in this work. A total of 147 patients from Xuzhou Central Hospital were enrolled as the training cohort, and 63 patients from Suqian Affiliated Hospital of Xuzhou Medical University were enrolled as the test cohort. Based on two consecutive phases of patch level prediction and WSI-level predictione, we built a pathomics model, with the initial model developed in the training cohort and subjected to transfer learning, and then the test cohort was validated for generalization. The features extracted from the visualization model were used for model interpretation. After migration learning, the area under the receiver operating characteristic curve for the deep learning-based pathomics model in the test cohort was 0.860 (95% CI 0.752-0.969), with good agreement between the migration training cohort and the test cohort in predicting recurrence, and the predicted values matched well with the observed values, with p values of 0.667766 and 0.140233 for the Hosmer-Lemeshow test, respectively. The good clinical application was observed using a decision curve analysis method. We developed a deep learning-based pathomics model showed promising performance in predicting recurrence within one year in NMIBC patients. Including 10 state prediction NMIBC recurrence group pathology features be visualized, which may be used to facilitate personalized management of NMIBC patients to avoid ineffective or unnecessary treatment for the benefit of patients.
Collapse
Affiliation(s)
- Guang-Yue Wang
- Department of Urology, Xuzhou Cancer Hospital, Affiliated Hospital of Jiangsu University, Xuzhou, China
- Department of Urology, Xuzhou Central Hospital, Jiefang South Road, No. 199, Xuzhou, Jiangsu, China
| | - Jing-Fei Zhu
- School of Mathematics and Statistics and Jiangsu Key Laboratory of Education Big Data Science and Engineering, Jiangsu Normal University, No.101, Shanghai Road, Tangshan New District, Xuzhou, Jiangsu, China
| | - Qi-Chao Wang
- Department of Urology, Xuzhou Cancer Hospital, Affiliated Hospital of Jiangsu University, Xuzhou, China
| | - Jia-Xin Qin
- Department of Urology, Xuzhou Central Hospital, Jiefang South Road, No. 199, Xuzhou, Jiangsu, China
- Department of Urology, Xuzhou Clinical School of Xuzhou Medical University, Xuzhou, China
| | - Xin-Lei Wang
- Department of Urology, Xuzhou Central Hospital, Jiefang South Road, No. 199, Xuzhou, Jiangsu, China
- Department of Urology, Xuzhou Clinical School of Xuzhou Medical University, Xuzhou, China
| | - Xing Liu
- Department of Urology, Xuzhou Central Hospital, Jiefang South Road, No. 199, Xuzhou, Jiangsu, China
- Department of Urology, Xuzhou Clinical School of Xuzhou Medical University, Xuzhou, China
| | - Xin-Yu Liu
- Department of Urology, Xuzhou Central Hospital, Jiefang South Road, No. 199, Xuzhou, Jiangsu, China
- Department of Urology, Xuzhou Clinical School of Xuzhou Medical University, Xuzhou, China
| | - Jun-Zhi Chen
- Department of Urology, Xuzhou Central Hospital, Jiefang South Road, No. 199, Xuzhou, Jiangsu, China
- Department of Urology, Xuzhou Clinical School of Xuzhou Medical University, Xuzhou, China
| | - Jie-Fei Zhu
- Department of Pathology, Xuzhou Central Hospital, Xuzhou, China
| | - Shi-Chao Zhuo
- Department of Pathology, Xuzhou Central Hospital, Xuzhou, China
| | - Di Wu
- Department of Pathology, Xuzhou Central Hospital, Xuzhou, China
| | - Na Li
- The First Affiliated Hospital of Kunming Medical University, Kunming, China
| | - Liu Chao
- School of Life Sciences, Jiangsu Normal University, Xuzhou, China
- Department of Urology, The Suqian Affiliated Hospital of Xuzhou Medical University, Suqian, China
| | - Fan-Lai Meng
- Department of Pathology, The Suqian Affiliated Hospital of Xuzhou Medical University, Suqian, China
| | - Hao Lu
- Department of Urology, Heilongjiang Provincial Hospital, Harbin, China
| | - Zhen-Duo Shi
- Department of Urology, Xuzhou Central Hospital, Jiefang South Road, No. 199, Xuzhou, Jiangsu, China
- Department of Urology, Xuzhou Clinical School of Xuzhou Medical University, Xuzhou, China
- School of Life Sciences, Jiangsu Normal University, Xuzhou, China
- Department of Urology, Heilongjiang Provincial Hospital, Harbin, China
| | - Zhi-Gang Jia
- School of Mathematics and Statistics and Jiangsu Key Laboratory of Education Big Data Science and Engineering, Jiangsu Normal University, No.101, Shanghai Road, Tangshan New District, Xuzhou, Jiangsu, China.
| | - Cong-Hui Han
- Department of Urology, Xuzhou Central Hospital, Jiefang South Road, No. 199, Xuzhou, Jiangsu, China.
- Department of Urology, Xuzhou Clinical School of Xuzhou Medical University, Xuzhou, China.
- School of Life Sciences, Jiangsu Normal University, Xuzhou, China.
- Department of Urology, Heilongjiang Provincial Hospital, Harbin, China.
| |
Collapse
|
2
|
Tao T, Chen Y, Shang Y, He J, Hao J. SMMF: a self-attention-based multi-parametric MRI feature fusion framework for the diagnosis of bladder cancer grading. Front Oncol 2024; 14:1337186. [PMID: 38515574 PMCID: PMC10955083 DOI: 10.3389/fonc.2024.1337186] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2023] [Accepted: 02/21/2024] [Indexed: 03/23/2024] Open
Abstract
Background Multi-parametric magnetic resonance imaging (MP-MRI) may provide comprehensive information for graded diagnosis of bladder cancer (BCa). Nevertheless, existing methods ignore the complex correlation between these MRI sequences, failing to provide adequate information. Therefore, the main objective of this study is to enhance feature fusion and extract comprehensive features from MP-MRI using deep learning methods to achieve an accurate diagnosis of BCa grading. Methods In this study, a self-attention-based MP-MRI feature fusion framework (SMMF) is proposed to enhance the performance of the model by extracting and fusing features of both T2-weighted imaging (T2WI) and dynamic contrast-enhanced imaging (DCE) sequences. A new multiscale attention (MA) model is designed to embed into the neural network (CNN) end to further extract rich features from T2WI and DCE. Finally, a self-attention feature fusion strategy (SAFF) was used to effectively capture and fuse the common and complementary features of patients' MP-MRIs. Results In a clinically collected sample of 138 BCa patients, the SMMF network demonstrated superior performance compared to the existing deep learning-based bladder cancer grading model, with accuracy, F1 value, and AUC values of 0.9488, 0.9426, and 0.9459, respectively. Conclusion Our proposed SMMF framework combined with MP-MRI information can accurately predict the pathological grading of BCa and can better assist physicians in diagnosing BCa.
Collapse
Affiliation(s)
- Tingting Tao
- Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China
| | - Ying Chen
- Department of Radiology, Second Affiliated Hospital of Kunming Medical University, Kunming, China
| | - Yunyun Shang
- Department of Radiology, Second Affiliated Hospital of Kunming Medical University, Kunming, China
| | - Jianfeng He
- Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China
- School of Physics and Electronic Engineering, Yuxi Normal University, Yuxi, China
| | - Jingang Hao
- Department of Radiology, Second Affiliated Hospital of Kunming Medical University, Kunming, China
| |
Collapse
|
3
|
Khoraminia F, Fuster S, Kanwal N, Olislagers M, Engan K, van Leenders GJLH, Stubbs AP, Akram F, Zuiverloon TCM. Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review. Cancers (Basel) 2023; 15:4518. [PMID: 37760487 PMCID: PMC10526515 DOI: 10.3390/cancers15184518] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 08/30/2023] [Accepted: 09/08/2023] [Indexed: 09/29/2023] Open
Abstract
Bladder cancer (BC) diagnosis and prediction of prognosis are hindered by subjective pathological evaluation, which may cause misdiagnosis and under-/over-treatment. Computational pathology (CPATH) can identify clinical outcome predictors, offering an objective approach to improve prognosis. However, a systematic review of CPATH in BC literature is lacking. Therefore, we present a comprehensive overview of studies that used CPATH in BC, analyzing 33 out of 2285 identified studies. Most studies analyzed regions of interest to distinguish normal versus tumor tissue and identify tumor grade/stage and tissue types (e.g., urothelium, stroma, and muscle). The cell's nuclear area, shape irregularity, and roundness were the most promising markers to predict recurrence and survival based on selected regions of interest, with >80% accuracy. CPATH identified molecular subtypes by detecting features, e.g., papillary structures, hyperchromatic, and pleomorphic nuclei. Combining clinicopathological and image-derived features improved recurrence and survival prediction. However, due to the lack of outcome interpretability and independent test datasets, robustness and clinical applicability could not be ensured. The current literature demonstrates that CPATH holds the potential to improve BC diagnosis and prediction of prognosis. However, more robust, interpretable, accurate models and larger datasets-representative of clinical scenarios-are needed to address artificial intelligence's reliability, robustness, and black box challenge.
Collapse
Affiliation(s)
- Farbod Khoraminia
- Department of Urology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands;
| | - Saul Fuster
- Department of Electrical Engineering and Computer Science, University of Stavanger, 4021 Stavanger, Norway; (S.F.); (N.K.); (K.E.)
| | - Neel Kanwal
- Department of Electrical Engineering and Computer Science, University of Stavanger, 4021 Stavanger, Norway; (S.F.); (N.K.); (K.E.)
| | - Mitchell Olislagers
- Department of Urology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands;
| | - Kjersti Engan
- Department of Electrical Engineering and Computer Science, University of Stavanger, 4021 Stavanger, Norway; (S.F.); (N.K.); (K.E.)
| | - Geert J. L. H. van Leenders
- Department of Pathology and Clinical Bioinformatics, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands; (G.J.L.H.v.L.); (A.P.S.); (F.A.)
| | - Andrew P. Stubbs
- Department of Pathology and Clinical Bioinformatics, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands; (G.J.L.H.v.L.); (A.P.S.); (F.A.)
| | - Farhan Akram
- Department of Pathology and Clinical Bioinformatics, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands; (G.J.L.H.v.L.); (A.P.S.); (F.A.)
| | - Tahlita C. M. Zuiverloon
- Department of Urology, Erasmus MC Cancer Institute, University Medical Center Rotterdam, 3015 GD Rotterdam, The Netherlands;
| |
Collapse
|
4
|
Cheng J, Zhang S, Fan A, Li Y, Xu P, Huang J, He M, Wang H. An immune-related gene signature for the prognosis of human bladder cancer based on WGCNA. Comput Biol Med 2022; 151:106186. [PMID: 36335813 DOI: 10.1016/j.compbiomed.2022.106186] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2022] [Revised: 08/30/2022] [Accepted: 10/08/2022] [Indexed: 12/27/2022]
Abstract
The innovation of immunotherapy was a milestone in the treatment of bladder cancer (BLCA). However, the treatment benefits varied by individual thus promoting the investigation of the biomarker of the patients. Unfortunately, there were not many effective predictive models, which were desired by clinicians, for BLCA that can predict the prognosis and benefit of immunotherapy. We constructed a three genes prognosis prediction model termed RiskScore based on the result of weighted correlation network analysis (WGCNA) from The Cancer Genome Atlas (TCGA) cohort (n = 406). We then validated the prediction accuracy with three validation cohort(GSE13507 (n = 165), GSE48075(n = 73), GSE32894(n = 224)). We compared the differences in gene expression, immune relate function, and immune infiltration between two groups divided by RiskScore. We further discovered the potential drug target and suitable compounds for high-risk groups. Our results suggested that the low-risk group may be more potential for immunotherapy for they have higher B cell infiltration, higher expression of immune checkpoints(PDCD1, CTLA4), and much more active immune-related pathways(B cell and T cell receptor signaling pathway). The RiskScore showed a well predictive accuracy for the prognosis of BLCA. After Spearman analysis, we found the suitable drug target and compounds for the patients in the high-risk group. The model we constructed is able to predict the prognosis of BLCA patients with ease and accuracy. PLK1 and gefitinib may be utilized for further treatment of BLCA patients.
Collapse
Affiliation(s)
- Jiangting Cheng
- Department of Urology, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Sihong Zhang
- Department of Urology, Xuhui Hospital, Fudan University, Shanghai, China
| | - Aoyu Fan
- Department of Urology, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Yaohui Li
- Department of Urology, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Peirong Xu
- Department of Urology, Xuhui Hospital, Fudan University, Shanghai, China
| | - Jiaqi Huang
- Department of Urology, Minhang Hospital, Fudan University, Shanghai, China
| | - Minke He
- Department of Urology, Minhang Hospital, Fudan University, Shanghai, China
| | - Hang Wang
- Department of Urology, Zhongshan Hospital, Fudan University, Shanghai, China.
| |
Collapse
|