1
|
Xu J, Wang H, Lu M, Bi H, Li D, Xue Z, Zhang Q. An accurate and trustworthy deep learning approach for bladder tumor segmentation with uncertainty estimation. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2025; 263:108645. [PMID: 39954510 DOI: 10.1016/j.cmpb.2025.108645] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/05/2024] [Revised: 01/19/2025] [Accepted: 02/02/2025] [Indexed: 02/17/2025]
Abstract
BACKGROUND AND OBJECTIVE Although deep learning-based intelligent diagnosis of bladder cancer has achieved excellent performance, the reliability of neural network predicted results may not be evaluated. This study aims to explore a trustworthy AI-based tumor segmentation model, which not only outputs predicted results but also provides confidence information about the predictions. METHODS This paper proposes a novel model for bladder tumor segmentation with uncertainty estimation (BSU), which is not merely able to effectively segment the lesion area but also yields an uncertainty map showing the confidence information of the segmentation results. In contrast to previous uncertainty estimation, we utilize test time augmentation (TTA) and test time dropout (TTD) to estimate aleatoric uncertainty and epistemic uncertainty in both internal and external datasets to explore the effects of both uncertainties on different datasets. RESULTS Our BSU model achieved the Dice coefficients of 0.766 and 0.848 on internal and external cystoscopy datasets, respectively, along with accuracy of 0.950 and 0.954. Compared to the state-of-the-art methods, our BSU model demonstrated superior performance, which was further validated by the statistically significance of the t-tests at the conventional level. Clinical experiments verified the practical value of uncertainty estimation in real-world bladder cancer diagnostics. CONCLUSIONS The proposed BSU model is able to visualize the confidence of the segmentation results, serving as a valuable addition for assisting urologists in enhancing both the precision and efficiency of bladder cancer diagnoses in clinical practice.
Collapse
Affiliation(s)
- Jie Xu
- School of Information Technology and Management, University of International Business and Economics, Beijing 100029, China
| | - Haixin Wang
- Cadre Medical Department, The 1st medical Center, Chinese PLA General Hospital, Beijing 100853, China
| | - Min Lu
- Department of Pathology, School of Basic Medical Sciences, Peking University Third Hospital, Peking University Health Science Center, Beijing 100191, China
| | - Hai Bi
- Department of Urology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 201620, China
| | - Deng Li
- Department of Urology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 201620, China
| | - Zixuan Xue
- Department of Urology, Peking University Third Hospital, Beijing 100191, China
| | - Qi Zhang
- School of Information Technology and Management, University of International Business and Economics, Beijing 100029, China.
| |
Collapse
|
2
|
Dai L, Md Johar MG, Alkawaz MH. The diagnostic value of MRI segmentation technique for shoulder joint injuries based on deep learning. Sci Rep 2024; 14:28885. [PMID: 39572780 PMCID: PMC11582322 DOI: 10.1038/s41598-024-80441-y] [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: 08/07/2024] [Accepted: 11/19/2024] [Indexed: 11/24/2024] Open
Abstract
This work is to investigate the diagnostic value of a deep learning-based magnetic resonance imaging (MRI) image segmentation (IS) technique for shoulder joint injuries (SJIs) in swimmers. A novel multi-scale feature fusion network (MSFFN) is developed by optimizing and integrating the AlexNet and U-Net algorithms for the segmentation of MRI images of the shoulder joint. The model is evaluated using metrics such as the Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity (SE). A cohort of 52 swimmers with SJIs from Guangzhou Hospital serve as the subjects for this study, wherein the accuracy of the developed shoulder joint MRI IS model in diagnosing swimmers' SJIs is analyzed. The results reveal that the DSC for segmenting joint bones in MRI images based on the MSFFN algorithm is 92.65%, with PPV of 95.83% and SE of 96.30%. Similarly, the DSC for segmenting humerus bones in MRI images is 92.93%, with PPV of 95.56% and SE of 92.78%. The MRI IS algorithm exhibits an accuracy of 86.54% in diagnosing types of SJIs in swimmers, surpassing the conventional diagnostic accuracy of 71.15%. The consistency between the diagnostic results of complete tear, superior surface tear, inferior surface tear, and intratendinous tear of SJIs in swimmers and arthroscopic diagnostic results yield a Kappa value of 0.785 and an accuracy of 87.89%. These findings underscore the significant diagnostic value and potential of the MRI IS technique based on the MSFFN algorithm in diagnosing SJIs in swimmers.
Collapse
Affiliation(s)
- Lina Dai
- School of Information Technology and Engineering, Guangzhou College of Commerce, Guangzhou, China.
- School of Graduate Studies, Management and Science University, Shah Alam, 40100, Selangor, Malaysia.
| | - Md Gapar Md Johar
- Software Engineering and Digital Innovation Center, Management and Science University, Shah Alam, 40100, Selangor, Malaysia
| | - Mohammed Hazim Alkawaz
- Department of Computer Science, College of Education for Pure Science, University of Mosul, Mosul, Nineveh, Iraq
| |
Collapse
|
3
|
Wen F, Zhou J, Chen Z, Dou M, Yao Y, Wang X, Xu F, Shen Y. Efficient application of deep learning-based elective lymph node regions delineation for pelvic malignancies. Med Phys 2024; 51:7057-7066. [PMID: 39072765 DOI: 10.1002/mp.17330] [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: 10/04/2023] [Revised: 07/02/2024] [Accepted: 07/13/2024] [Indexed: 07/30/2024] Open
Abstract
BACKGROUND While there are established international consensuses on the delineation of pelvic lymph node regions (LNRs), significant inter- and intra-observer variabilities persist. Contouring these clinical target volumes for irradiation in pelvic malignancies is both time-consuming and labor-intensive. PURPOSE The purpose of this study was to develop a deep learning model of pelvic LNRs delineation for patients with pelvic cancers. METHODS Planning computed tomography (CT) studies of 160 patients with pelvic primary malignancies (including rectal, prostate, and cervical cancer) were retrospectively collected and divided into training set (n = 120) and testing set (n = 40). Six pelvic LNRs, including abdominal presacral, pelvic presacral, internal iliac nodes, external iliac nodes, obturator nodes, and inguinal nodes were delineated by two radiation oncologists as ground truth (Gt) contours. The cascaded multi-heads U-net (CMU-net) was constructed based on the Gt contours from training cohort, which was subsequently verified in the testing cohort. The automatic delineation of six LNRs (Auto) was evaluated using dice similarity coefficient (DSC), average surface distance (ASD), 95th percentile Hausdorff distance (HD95), and a 7-point scale score. RESULTS In the testing set, the DSC of six pelvic LNRs by CMU-net model varied from 0.851 to 0.942, ASD from 0.381 to 1.037 mm, and HD95 from 2.025 to 3.697 mm. No significant differences were founded in these three parameters between postoperative and preoperative cases. 95.9% and 96.2% of auto delineations by CMU-net model got a score of 1-3 by two expert radiation oncologists, respectively, meaning only minor edits needed. CONCLUSIONS The CMU-net was successfully developed for automated delineation of pelvic LNRs for pelvic malignancies radiotherapy with improved contouring efficiency and highly consistent, which might justify its implementation in radiotherapy work flow.
Collapse
Affiliation(s)
- Feng Wen
- Division of Abdominal Tumor Multimodality Treatment, Department of Radiation Oncology, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
- Med-X Center for Informatics, Sichuan University, Chengdu, China
| | - Jie Zhou
- Lung Cancer Center, West China Hospital, Sichuan University, Chengdu, China
| | - Zhebin Chen
- Chengdu Institute of Compute Application, Chinese Academy of Sciences, Chengdu, China
| | - Meng Dou
- Chengdu Institute of Compute Application, Chinese Academy of Sciences, Chengdu, China
| | - Yu Yao
- Chengdu Institute of Compute Application, Chinese Academy of Sciences, Chengdu, China
| | - Xin Wang
- Division of Abdominal Tumor Multimodality Treatment, Department of Radiation Oncology, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
| | - Feng Xu
- Lung Cancer Center, West China Hospital, Sichuan University, Chengdu, China
| | - Yali Shen
- Division of Abdominal Tumor Multimodality Treatment, Department of Radiation Oncology, Cancer Center, West China Hospital, Sichuan University, Chengdu, China
| |
Collapse
|
4
|
Ye Y, Luo Z, Qiu Z, Cao K, Huang B, Deng L, Zhang W, Liu G, Zou Y, Zhang J, Li J. Radiomics Prediction of Muscle Invasion in Bladder Cancer Using Semi-Automatic Lesion Segmentation of MRI Compared with Manual Segmentation. Bioengineering (Basel) 2023; 10:1355. [PMID: 38135946 PMCID: PMC10740947 DOI: 10.3390/bioengineering10121355] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Revised: 11/10/2023] [Accepted: 11/23/2023] [Indexed: 12/24/2023] Open
Abstract
Conventional radiomics analysis requires the manual segmentation of lesions, which is time-consuming and subjective. This study aimed to assess the feasibility of predicting muscle invasion in bladder cancer (BCa) with radiomics using a semi-automatic lesion segmentation method on T2-weighted images. Cases of non-muscle-invasive BCa (NMIBC) and muscle-invasive BCa (MIBC) were pathologically identified in a training cohort and in internal and external validation cohorts. For bladder tumor segmentation, a deep learning-based semi-automatic model was constructed, while manual segmentation was performed by a radiologist. Semi-automatic and manual segmentation results were respectively used in radiomics analyses to distinguish NMIBC from MIBC. An equivalence test was used to compare the models' performance. The mean Dice similarity coefficients of the semi-automatic segmentation method were 0.836 and 0.801 in the internal and external validation cohorts, respectively. The area under the receiver operating characteristic curve (AUC) were 1.00 (0.991) and 0.892 (0.894) for the semi-automated model (manual) on the internal and external validation cohort, respectively (both p < 0.05). The average total processing time for semi-automatic segmentation was significantly shorter than that for manual segmentation (35 s vs. 92 s, p < 0.001). The BCa radiomics model based on semi-automatic segmentation method had a similar diagnostic performance as that of manual segmentation, while being less time-consuming and requiring fewer manual interventions.
Collapse
Affiliation(s)
- Yaojiang Ye
- Department of Radiology, The Tenth Affiliated Hospital of Southern Medical University (Dongguan People’s Hospital), Dongguan 523059, China; (Y.Y.); (L.D.); (Y.Z.)
| | - Zixin Luo
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; (Z.L.); (Z.Q.); (K.C.); (B.H.)
| | - Zhengxuan Qiu
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; (Z.L.); (Z.Q.); (K.C.); (B.H.)
| | - Kangyang Cao
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; (Z.L.); (Z.Q.); (K.C.); (B.H.)
| | - Bingsheng Huang
- Medical AI Lab, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China; (Z.L.); (Z.Q.); (K.C.); (B.H.)
| | - Lei Deng
- Department of Radiology, The Tenth Affiliated Hospital of Southern Medical University (Dongguan People’s Hospital), Dongguan 523059, China; (Y.Y.); (L.D.); (Y.Z.)
| | - Weijing Zhang
- Imaging Department, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China;
| | - Guoqing Liu
- College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen 518060, China;
| | - Yujian Zou
- Department of Radiology, The Tenth Affiliated Hospital of Southern Medical University (Dongguan People’s Hospital), Dongguan 523059, China; (Y.Y.); (L.D.); (Y.Z.)
| | - Jian Zhang
- Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China
- Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Shenzhen 518060, China
| | - Jianpeng Li
- Department of Radiology, The Tenth Affiliated Hospital of Southern Medical University (Dongguan People’s Hospital), Dongguan 523059, China; (Y.Y.); (L.D.); (Y.Z.)
| |
Collapse
|
5
|
Akin O, Lema-Dopico A, Paudyal R, Konar AS, Chenevert TL, Malyarenko D, Hadjiiski L, Al-Ahmadie H, Goh AC, Bochner B, Rosenberg J, Schwartz LH, Shukla-Dave A. Multiparametric MRI in Era of Artificial Intelligence for Bladder Cancer Therapies. Cancers (Basel) 2023; 15:5468. [PMID: 38001728 PMCID: PMC10670574 DOI: 10.3390/cancers15225468] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Revised: 10/27/2023] [Accepted: 10/30/2023] [Indexed: 11/26/2023] Open
Abstract
This review focuses on the principles, applications, and performance of mpMRI for bladder imaging. Quantitative imaging biomarkers (QIBs) derived from mpMRI are increasingly used in oncological applications, including tumor staging, prognosis, and assessment of treatment response. To standardize mpMRI acquisition and interpretation, an expert panel developed the Vesical Imaging-Reporting and Data System (VI-RADS). Many studies confirm the standardization and high degree of inter-reader agreement to discriminate muscle invasiveness in bladder cancer, supporting VI-RADS implementation in routine clinical practice. The standard MRI sequences for VI-RADS scoring are anatomical imaging, including T2w images, and physiological imaging with diffusion-weighted MRI (DW-MRI) and dynamic contrast-enhanced MRI (DCE-MRI). Physiological QIBs derived from analysis of DW- and DCE-MRI data and radiomic image features extracted from mpMRI images play an important role in bladder cancer. The current development of AI tools for analyzing mpMRI data and their potential impact on bladder imaging are surveyed. AI architectures are often implemented based on convolutional neural networks (CNNs), focusing on narrow/specific tasks. The application of AI can substantially impact bladder imaging clinical workflows; for example, manual tumor segmentation, which demands high time commitment and has inter-reader variability, can be replaced by an autosegmentation tool. The use of mpMRI and AI is projected to drive the field toward the personalized management of bladder cancer patients.
Collapse
Affiliation(s)
- Oguz Akin
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Alfonso Lema-Dopico
- Department of Medical Physics, Memorial Sloan Kettering Cancer, New York, NY 10065, USA
| | - Ramesh Paudyal
- Department of Medical Physics, Memorial Sloan Kettering Cancer, New York, NY 10065, USA
| | | | | | - Dariya Malyarenko
- Department of Radiology, University of Michigan, Ann Arbor, MI 48109, USA
| | - Lubomir Hadjiiski
- Department of Radiology, University of Michigan, Ann Arbor, MI 48109, USA
| | - Hikmat Al-Ahmadie
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Alvin C. Goh
- Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Bernard Bochner
- Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Jonathan Rosenberg
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
| | - Lawrence H. Schwartz
- Department of Medical Physics, Memorial Sloan Kettering Cancer, New York, NY 10065, USA
| | - Amita Shukla-Dave
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
- Department of Medical Physics, Memorial Sloan Kettering Cancer, New York, NY 10065, USA
| |
Collapse
|