1
|
Fassia MK, Balasubramanian A, Woo S, Vargas HA, Hricak H, Konukoglu E, Becker AS. Deep Learning Prostate MRI Segmentation Accuracy and Robustness: A Systematic Review. Radiol Artif Intell 2024; 6:e230138. [PMID: 38568094 PMCID: PMC11294957 DOI: 10.1148/ryai.230138] [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: 04/26/2023] [Revised: 02/24/2024] [Accepted: 03/19/2024] [Indexed: 04/28/2024]
Abstract
Purpose To investigate the accuracy and robustness of prostate segmentation using deep learning across various training data sizes, MRI vendors, prostate zones, and testing methods relative to fellowship-trained diagnostic radiologists. Materials and Methods In this systematic review, Embase, PubMed, Scopus, and Web of Science databases were queried for English-language articles using keywords and related terms for prostate MRI segmentation and deep learning algorithms dated to July 31, 2022. A total of 691 articles from the search query were collected and subsequently filtered to 48 on the basis of predefined inclusion and exclusion criteria. Multiple characteristics were extracted from selected studies, such as deep learning algorithm performance, MRI vendor, and training dataset features. The primary outcome was comparison of mean Dice similarity coefficient (DSC) for prostate segmentation for deep learning algorithms versus diagnostic radiologists. Results Forty-eight studies were included. Most published deep learning algorithms for whole prostate gland segmentation (39 of 42 [93%]) had a DSC at or above expert level (DSC ≥ 0.86). The mean DSC was 0.79 ± 0.06 (SD) for peripheral zone, 0.87 ± 0.05 for transition zone, and 0.90 ± 0.04 for whole prostate gland segmentation. For selected studies that used one major MRI vendor, the mean DSCs of each were as follows: General Electric (three of 48 studies), 0.92 ± 0.03; Philips (four of 48 studies), 0.92 ± 0.02; and Siemens (six of 48 studies), 0.91 ± 0.03. Conclusion Deep learning algorithms for prostate MRI segmentation demonstrated accuracy similar to that of expert radiologists despite varying parameters; therefore, future research should shift toward evaluating segmentation robustness and patient outcomes across diverse clinical settings. Keywords: MRI, Genital/Reproductive, Prostate Segmentation, Deep Learning Systematic review registration link: osf.io/nxaev © RSNA, 2024.
Collapse
Affiliation(s)
- Mohammad-Kasim Fassia
- From the Departments of Radiology (M.K.F.) and Urology (A.B.), New York-Presbyterian Weill Cornell Medical Center, 525 E 68th St, New York, NY 10065-4870; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY (S.W., H.A.V., H.H., A.S.B.); and Department of Biomedical Imaging, ETH-Zurich, Zurich Switzerland (E.K.)
| | - Adithya Balasubramanian
- From the Departments of Radiology (M.K.F.) and Urology (A.B.), New York-Presbyterian Weill Cornell Medical Center, 525 E 68th St, New York, NY 10065-4870; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY (S.W., H.A.V., H.H., A.S.B.); and Department of Biomedical Imaging, ETH-Zurich, Zurich Switzerland (E.K.)
| | - Sungmin Woo
- From the Departments of Radiology (M.K.F.) and Urology (A.B.), New York-Presbyterian Weill Cornell Medical Center, 525 E 68th St, New York, NY 10065-4870; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY (S.W., H.A.V., H.H., A.S.B.); and Department of Biomedical Imaging, ETH-Zurich, Zurich Switzerland (E.K.)
| | - Hebert Alberto Vargas
- From the Departments of Radiology (M.K.F.) and Urology (A.B.), New York-Presbyterian Weill Cornell Medical Center, 525 E 68th St, New York, NY 10065-4870; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY (S.W., H.A.V., H.H., A.S.B.); and Department of Biomedical Imaging, ETH-Zurich, Zurich Switzerland (E.K.)
| | - Hedvig Hricak
- From the Departments of Radiology (M.K.F.) and Urology (A.B.), New York-Presbyterian Weill Cornell Medical Center, 525 E 68th St, New York, NY 10065-4870; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY (S.W., H.A.V., H.H., A.S.B.); and Department of Biomedical Imaging, ETH-Zurich, Zurich Switzerland (E.K.)
| | - Ender Konukoglu
- From the Departments of Radiology (M.K.F.) and Urology (A.B.), New York-Presbyterian Weill Cornell Medical Center, 525 E 68th St, New York, NY 10065-4870; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY (S.W., H.A.V., H.H., A.S.B.); and Department of Biomedical Imaging, ETH-Zurich, Zurich Switzerland (E.K.)
| | - Anton S. Becker
- From the Departments of Radiology (M.K.F.) and Urology (A.B.), New York-Presbyterian Weill Cornell Medical Center, 525 E 68th St, New York, NY 10065-4870; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY (S.W., H.A.V., H.H., A.S.B.); and Department of Biomedical Imaging, ETH-Zurich, Zurich Switzerland (E.K.)
| |
Collapse
|
2
|
Inomata T, Nakaya K, Matsuhiro M, Takei J, Shiozaki H, Noda Y. Clinical Use of Hematoma Volume Based On Automated Segmentation of Chronic Subdural Hematoma Using 3D U-Net. Clin Neuroradiol 2024:10.1007/s00062-024-01428-w. [PMID: 38814451 DOI: 10.1007/s00062-024-01428-w] [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: 01/22/2024] [Accepted: 05/12/2024] [Indexed: 05/31/2024]
Abstract
PURPOSE To propose a method for calculating hematoma volume based on automatic segmentation of chronic subdural hematoma (CSDH) using 3D U‑net and investigate whether it can be used clinically to predict recurrence. METHODS Hematoma volumes manually measured from pre- and postoperative computed tomography (CT) images were used as ground truth data to train 3D U‑net in 200 patients (400 CT scans). A total of 215 patients (430 CT scans) were used as test data to output segmentation results from the trained 3D U‑net model. The similarity with the ground truth data was evaluated using Dice scores for pre and postoperative separately. The recurrence prediction accuracy was evaluated by obtaining receiver operating characteristic (ROC) curves for the segmentation results. Using a typical mobile PC, the computation time per case was measured and the average time was calculated. RESULTS The median Dice score of the test data were preoperative hematoma volume (Pre-HV): 0.764 and postoperative subdural cavity volume (Post-SCV): 0.741. In ROC analyses assessing recurrence prediction, the area under the curve (AUC) of the manual was 0.755 in Pre-HV, whereas the 3D U‑net was 0.735. In Post-SCV, the manual AUC was 0.779; the 3D U‑net was 0.736. No significant differences were found between manual and 3D U‑net for all results. Using a mobile PC, the average time taken to output the test data results was 30 s per case. CONCLUSION The proposed method is a simple, accurate, and clinically applicable; it can contribute to the widespread use of recurrence prediction scoring systems for CSDH.
Collapse
Affiliation(s)
- Takayuki Inomata
- Department of Radiological Technology, Faculty of Health Science, Suzuka University of Medical Science, 1001-1 Kishioka, 510-0293, Suzuka City, Mie, Japan.
- Department of Radiological Technology, Fuji City General Hospital, 50 Takashima-cho, 417-8567, Fuji City, Shizuoka, Japan.
| | - Koji Nakaya
- Department of Radiological Technology, Faculty of Health Science, Suzuka University of Medical Science, 1001-1 Kishioka, 510-0293, Suzuka City, Mie, Japan
| | - Mikio Matsuhiro
- Department of Radiological Technology, Faculty of Health Science, Suzuka University of Medical Science, 1001-1 Kishioka, 510-0293, Suzuka City, Mie, Japan
| | - Jun Takei
- Department of Neurosurgery, The Jikei University School of Medicine, 3-25-8 Nishishinbashi, Minato-ku, 105-8461, Tokyo, Japan
| | - Hiroto Shiozaki
- Department of Radiological Technology, Fuji City General Hospital, 50 Takashima-cho, 417-8567, Fuji City, Shizuoka, Japan
| | - Yasuto Noda
- Department of Neurosurgery, Fuji City General Hospital, 50 Takashima-cho, 417-8567, Fuji City, Shizuoka, Japan
| |
Collapse
|
3
|
Rodrigues NM, Almeida JGD, Verde ASC, Gaivão AM, Bilreiro C, Santiago I, Ip J, Belião S, Moreno R, Matos C, Vanneschi L, Tsiknakis M, Marias K, Regge D, Silva S, Papanikolaou N. Analysis of domain shift in whole prostate gland, zonal and lesions segmentation and detection, using multicentric retrospective data. Comput Biol Med 2024; 171:108216. [PMID: 38442555 DOI: 10.1016/j.compbiomed.2024.108216] [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: 12/12/2023] [Revised: 02/09/2024] [Accepted: 02/25/2024] [Indexed: 03/07/2024]
Abstract
Despite being one of the most prevalent forms of cancer, prostate cancer (PCa) shows a significantly high survival rate, provided there is timely detection and treatment. Computational methods can help make this detection process considerably faster and more robust. However, some modern machine-learning approaches require accurate segmentation of the prostate gland and the index lesion. Since performing manual segmentations is a very time-consuming task, and highly prone to inter-observer variability, there is a need to develop robust semi-automatic segmentation models. In this work, we leverage the large and highly diverse ProstateNet dataset, which includes 638 whole gland and 461 lesion segmentation masks, from 3 different scanner manufacturers provided by 14 institutions, in addition to other 3 independent public datasets, to train accurate and robust segmentation models for the whole prostate gland, zones and lesions. We show that models trained on large amounts of diverse data are better at generalizing to data from other institutions and obtained with other manufacturers, outperforming models trained on single-institution single-manufacturer datasets in all segmentation tasks. Furthermore, we show that lesion segmentation models trained on ProstateNet can be reliably used as lesion detection models.
Collapse
Affiliation(s)
- Nuno Miguel Rodrigues
- Computational Clinical Imaging Group, Champalimaud Foundation, Portugal; LASIGE, Faculty of Sciences, University of Lisbon, Portugal.
| | | | | | - Ana Mascarenhas Gaivão
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Carlos Bilreiro
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Inês Santiago
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Joana Ip
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Sara Belião
- Radiology Department, Champalimaud Clinical Center, Champalimaud Foundation, Lisbon, Portugal
| | - Raquel Moreno
- Computational Clinical Imaging Group, Champalimaud Foundation, Portugal
| | - Celso Matos
- Computational Clinical Imaging Group, Champalimaud Foundation, Portugal
| | - Leonardo Vanneschi
- NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa, Portugal
| | - Manolis Tsiknakis
- Institute of Computer Science, Foundation for Research and Technology Hellas (FORTH), GR 700 13, Heraklion, Greece; Department of Electrical and Computer Engineering, Hellenic Mediterranean University, GR 710 04, Heraklion, Greece
| | - Kostas Marias
- Department of Electrical and Computer Engineering, Hellenic Mediterranean University, GR 710 04, Heraklion, Greece; Computational BioMedicine Laboratory (CBML), Institute of Computer Science, Foundation for Research and Technology - Hellas (FORTH), Heraklion, Greece
| | - Daniele Regge
- Department of Radiology, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale 142 Km 3.95, Candiolo, Turin 10060, Italy; Department of Surgical Sciences, University of Turin, Turin 10124, Italy
| | - Sara Silva
- LASIGE, Faculty of Sciences, University of Lisbon, Portugal
| | - Nickolas Papanikolaou
- Computational Clinical Imaging Group, Champalimaud Foundation, Portugal; Department of Radiology, Royal Marsden Hospital, Sutton, UK
| |
Collapse
|
4
|
Index lesion contouring on prostate MRI for targeted MRI/US fusion biopsy - Evaluation of mismatch between radiologists and urologists. Eur J Radiol 2023; 162:110763. [PMID: 36898172 DOI: 10.1016/j.ejrad.2023.110763] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2023] [Revised: 02/04/2023] [Accepted: 02/28/2023] [Indexed: 03/06/2023]
Abstract
PURPOSE Mistargeting of focal lesions due to inaccurate segmentations can lead to false-negative findings on MRI-guided targeted biopsies. The purpose of this retrospective study was to examine inter-reader agreement of prostate index lesion segmentations from actual biopsy data between urologists and radiologists. METHOD Consecutive patients undergoing transperineal MRI-targeted prostate biopsy for PI-RADS 3-5 lesions between January 2020 and December 2021 were included. Agreement between segmentations on T2w-images between urologists and radiologists was assessed with Dice similarity coefficient (DSC) and 95 % Hausdorff distance (95 % HD). Differences in similarity scores were compared using Wilcoxon test. Differences depending on lesion features (size, zonal location, PI-RADS scores, lesion distinctness) were tested with Mann-Whitney U test. Correlation with prostate signal-intensity homogeneity score (PSHS) and lesion size was tested with Spearman's rank correlation. RESULTS Ninety-three patients (mean age 64.9 ± 7.1y, median serum PSA 6.5 [4.33-10.00]) were included. Mean similarity scores were statistically significantly lower between urologists and radiologists compared to radiologists only (DSC 0.41 ± 0.24 vs. 0.59 ± 0.23, p < 0.01; 95 %HD 6.38 ± 5.45 mm vs. 4.47 ± 4.12 mm, p < 0.01). There was a moderate and strong positive correlation between DSC scores and lesion size for segmentations from urologists and radiologists (ρ = 0.331, p = 0.002) and radiologists only (ρ = 0.501, p < 0.001). Similarity scores were worse in lesions ≤ 10 mm while other lesion features did not significantly influence similarity scores. CONCLUSION There is significant mismatch of prostate index lesion segmentations between urologists and radiologists. Segmentation agreement positively correlates with lesion size. PI-RADS scores, zonal location, lesion distinctness, and PSHS show no significant impact on segmentation agreement. These findings could underpin benefits of perilesional biopsies.
Collapse
|
5
|
A Comparative Study of Multiparametric MRI Sequences in Measuring Prostate Cancer Index Lesion Volume. J Belg Soc Radiol 2022; 106:105. [DOI: 10.5334/jbsr.2832] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2022] [Accepted: 10/19/2022] [Indexed: 11/11/2022] Open
|
6
|
Zheng H, Miao Q, Liu Y, Mirak SA, Hosseiny M, Scalzo F, Raman SS, Sung K. Multiparametric MRI-based radiomics model to predict pelvic lymph node invasion for patients with prostate cancer. Eur Radiol 2022; 32:5688-5699. [PMID: 35238971 PMCID: PMC9283224 DOI: 10.1007/s00330-022-08625-6] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2021] [Revised: 02/01/2022] [Accepted: 02/02/2022] [Indexed: 02/07/2023]
Abstract
OBJECTIVE To identify which patient with prostate cancer (PCa) could safely avoid extended pelvic lymph node dissection (ePLND) by predicting lymph node invasion (LNI), via a radiomics-based machine learning approach. METHODS An integrative radiomics model (IRM) was proposed to predict LNI, confirmed by the histopathologic examination, integrating radiomics features, extracted from prostatic index lesion regions on MRI images, and clinical features via SVM. The study cohort comprised 244 PCa patients with MRI and followed by radical prostatectomy (RP) and ePLND within 6 months between 2010 and 2019. The proposed IRM was trained in training/validation set and evaluated in an internal independent testing set. The model's performance was measured by area under the curve (AUC), sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). AUCs were compared via Delong test with 95% confidence interval (CI), and the rest measurements were compared via chi-squared test or Fisher's exact test. RESULTS Overall, 17 (10.6%) and 14 (16.7%) patients with LNI were included in training/validation set and testing set, respectively. Shape and first-order radiomics features showed usefulness in building the IRM. The proposed IRM achieved an AUC of 0.915 (95% CI: 0.846-0.984) in the testing set, superior to pre-existing nomograms whose AUCs were from 0.698 to 0.724 (p < 0.05). CONCLUSION The proposed IRM could be potentially feasible to predict the risk of having LNI for patients with PCa. With the improved predictability, it could be utilized to assess which patients with PCa could safely avoid ePLND, thus reduce the number of unnecessary ePLND. KEY POINTS • The combination of MRI-based radiomics features with clinical information improved the prediction of lymph node invasion, compared with the model using only radiomics features or clinical features. • With improved prediction performance on predicting lymph node invasion, the number of extended pelvic lymph node dissection (ePLND) could be reduced by the proposed integrative radiomics model (IRM), compared with the existing nomograms.
Collapse
Affiliation(s)
- Haoxin Zheng
- Radiological Sciences, University of California - Los Angeles, 757 Westwood Plaza, Los Angeles, CA, 90095, USA
- Computer Science, University of California - Los Angeles, Los Angeles, CA, 90095, USA
| | - Qi Miao
- Radiological Sciences, University of California - Los Angeles, 757 Westwood Plaza, Los Angeles, CA, 90095, USA.
- Department of Radiology, The First Affiliated Hospital of China Medical University, Shenyang City, 110001, Liaoning Province, China.
| | - Yongkai Liu
- Radiological Sciences, University of California - Los Angeles, 757 Westwood Plaza, Los Angeles, CA, 90095, USA
| | - Sohrab Afshari Mirak
- Radiological Sciences, University of California - Los Angeles, 757 Westwood Plaza, Los Angeles, CA, 90095, USA
| | - Melina Hosseiny
- Radiological Sciences, University of California - Los Angeles, 757 Westwood Plaza, Los Angeles, CA, 90095, USA
| | - Fabien Scalzo
- Computer Science, University of California - Los Angeles, Los Angeles, CA, 90095, USA
- Seaver College, Pepperdine University, Malibu, CA, 90263, USA
| | - Steven S Raman
- Radiological Sciences, University of California - Los Angeles, 757 Westwood Plaza, Los Angeles, CA, 90095, USA
| | - Kyunghyun Sung
- Radiological Sciences, University of California - Los Angeles, 757 Westwood Plaza, Los Angeles, CA, 90095, USA
| |
Collapse
|
7
|
Evaluation of Traumatic Subdural Hematoma Volume by Using Image Segmentation Assessment Based on Deep Learning. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:3830245. [PMID: 35799650 PMCID: PMC9256325 DOI: 10.1155/2022/3830245] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/19/2022] [Revised: 05/31/2022] [Accepted: 06/09/2022] [Indexed: 11/23/2022]
Abstract
Rapid and accurate evaluations of hematoma volume can guide the treatment of traumatic subdural hematoma. We aim to explore the consistency between the measurement results of traumatic subdural hematoma (TSDH) using a deep learn-based image segmentation algorithm. A retrospective study was conducted on 90 CT images of patients diagnosed with TSDH in our hospital from January 2019 to January 2022. All image data were measured by manual segmentation, convolutional neural networks (CNN) algorithm segmentation, and ABC/2 volume formula. With manual segmentation as the “golden standard,” a consistency test was carried out with CNN algorithm segmentation and ABC/2 volume formula, respectively. The percentage error of CNN algorithm segmentation is less than ABC/2 volume formula. There is no significant difference between CNN algorithm segmentation and manual segmentation (P > 0.05). The area under curve of the ABC/2 volume formula, manual segmentation, and CNN algorithm segmentation is 0.811 (95% CI: 0.717~0.905), 0.840 (95% CI: 0.753~0.928), and 0.832 (95% CI: 0.742~0.922), respectively. From our results, the algorithm based on CNN has a good efficiency in segmentation and accurate calculation of TSDH hematoma volume.
Collapse
|
8
|
Fully Automatic Whole-Volume Tumor Segmentation in Cervical Cancer. Cancers (Basel) 2022; 14:cancers14102372. [PMID: 35625977 PMCID: PMC9139985 DOI: 10.3390/cancers14102372] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2022] [Revised: 05/02/2022] [Accepted: 05/05/2022] [Indexed: 02/04/2023] Open
Abstract
Simple Summary Uterine cervical cancer (CC) is a leading cause of cancer-related deaths in women worldwide. Pelvic magnetic resonance imaging (MRI) allows the assessment of local tumor extent and guides the choice of primary treatment. MRI tumor segmentation enables whole-volume radiomic tumor profiling, which is potentially useful for prognostication and individualization of therapy in CC. Manual tumor segmentation is, however, labor intensive and thus not part of routine clinical workflow. In the current work, we trained a deep learning (DL) algorithm to automatically segment the primary tumor in CC patients. Although the achieved segmentation performance of the trained DL algorithm is slightly lower than that for human experts, it is still relatively good. This study suggests that automated MRI primary tumor segmentations by DL algorithms without any human interaction is possible in patients with CC. Abstract Uterine cervical cancer (CC) is the most common gynecologic malignancy worldwide. Whole-volume radiomic profiling from pelvic MRI may yield prognostic markers for tailoring treatment in CC. However, radiomic profiling relies on manual tumor segmentation which is unfeasible in the clinic. We present a fully automatic method for the 3D segmentation of primary CC lesions using state-of-the-art deep learning (DL) techniques. In 131 CC patients, the primary tumor was manually segmented on T2-weighted MRI by two radiologists (R1, R2). Patients were separated into a train/validation (n = 105) and a test- (n = 26) cohort. The segmentation performance of the DL algorithm compared with R1/R2 was assessed with Dice coefficients (DSCs) and Hausdorff distances (HDs) in the test cohort. The trained DL network retrieved whole-volume tumor segmentations yielding median DSCs of 0.60 and 0.58 for DL compared with R1 (DL-R1) and R2 (DL-R2), respectively, whereas DSC for R1-R2 was 0.78. Agreement for primary tumor volumes was excellent between raters (R1-R2: intraclass correlation coefficient (ICC) = 0.93), but lower for the DL algorithm and the raters (DL-R1: ICC = 0.43; DL-R2: ICC = 0.44). The developed DL algorithm enables the automated estimation of tumor size and primary CC tumor segmentation. However, segmentation agreement between raters is better than that between DL algorithm and raters.
Collapse
|
9
|
Gunashekar DD, Bielak L, Hägele L, Oerther B, Benndorf M, Grosu AL, Brox T, Zamboglou C, Bock M. Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology. Radiat Oncol 2022; 17:65. [PMID: 35366918 PMCID: PMC8976981 DOI: 10.1186/s13014-022-02035-0] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2022] [Accepted: 03/15/2022] [Indexed: 12/15/2022] Open
Abstract
Automatic prostate tumor segmentation is often unable to identify the lesion even if multi-parametric MRI data is used as input, and the segmentation output is difficult to verify due to the lack of clinically established ground truth images. In this work we use an explainable deep learning model to interpret the predictions of a convolutional neural network (CNN) for prostate tumor segmentation. The CNN uses a U-Net architecture which was trained on multi-parametric MRI data from 122 patients to automatically segment the prostate gland and prostate tumor lesions. In addition, co-registered ground truth data from whole mount histopathology images were available in 15 patients that were used as a test set during CNN testing. To be able to interpret the segmentation results of the CNN, heat maps were generated using the Gradient Weighted Class Activation Map (Grad-CAM) method. The CNN achieved a mean Dice Sorensen Coefficient 0.62 and 0.31 for the prostate gland and the tumor lesions -with the radiologist drawn ground truth and 0.32 with whole-mount histology ground truth for tumor lesions. Dice Sorensen Coefficient between CNN predictions and manual segmentations from MRI and histology data were not significantly different. In the prostate the Grad-CAM heat maps could differentiate between tumor and healthy prostate tissue, which indicates that the image information in the tumor was essential for the CNN segmentation.
Collapse
Affiliation(s)
- Deepa Darshini Gunashekar
- Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
| | - Lars Bielak
- Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
- German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
| | - Leonard Hägele
- Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Benedict Oerther
- Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Matthias Benndorf
- Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Anca-L Grosu
- German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
- Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Thomas Brox
- Department of Computer Science, University of Freiburg, Freiburg, Germany
| | - Constantinos Zamboglou
- German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
- Department of Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Michael Bock
- Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
- German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany
| |
Collapse
|
10
|
Wu X, Pastel DA, Khan R, Eskey CJ, Shi Y, Sramek M, Paydarfar JA, Halter RJ. Quantifying Tumor and Vasculature Deformations during Laryngoscopy. Ann Biomed Eng 2022; 50:94-107. [PMID: 34993696 PMCID: PMC9035291 DOI: 10.1007/s10439-021-02896-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2021] [Accepted: 11/17/2021] [Indexed: 01/09/2023]
Abstract
Retractors and scopes used in head and neck surgery to provide adequate surgical exposure also deform critical structures in the region. Surgeons typically use preoperative imaging to plan and guide their tumor resections, however the large tissue deformation resulting from placement of retractors and scopes reduces the utility of preoperative imaging as a reliable roadmap. We quantify the extent of tumor and vasculature deformation in patients with tumors of the larynx and pharynx undergoing diagnostic laryngoscopy. A mean tumor displacement of 1.02 cm was observed between the patients' pre- and intra-operative states. Mean vasculature displacement at key bifurcation points was 0.99 cm. Registration to the hyoid bone can reduce tumor displacement to 0.67 cm and improve carotid stem angle deviations but increase overall vasculature displacement. The large deformation results suggest limitations in reliance on preoperative imaging and that using specific landmarks intraoperatively or having more intraoperative information could help to compensate for these deviations and ultimately improve surgical success.
Collapse
Affiliation(s)
- Xiaotian Wu
- Gordon Center for Medical Imaging at Massachusetts General Hospital and Harvard Medical School, 13th St, CNY149-5212, Charlestown, MA, 02129, USA.
| | - David A Pastel
- Department of Radiology, Dartmouth-Hitchcock Medical Center, 1 Medical Center Dr., Lebanon, NH, 03756, USA
- Geisel School of Medicine at Dartmouth College, 1 Rope Ferry Rd., Hanover, NH, 03755, USA
| | - Rihan Khan
- Department of Radiology, Dartmouth-Hitchcock Medical Center, 1 Medical Center Dr., Lebanon, NH, 03756, USA
- Geisel School of Medicine at Dartmouth College, 1 Rope Ferry Rd., Hanover, NH, 03755, USA
| | - Clifford J Eskey
- Department of Radiology, Dartmouth-Hitchcock Medical Center, 1 Medical Center Dr., Lebanon, NH, 03756, USA
- Geisel School of Medicine at Dartmouth College, 1 Rope Ferry Rd., Hanover, NH, 03755, USA
| | - Yuan Shi
- Thayer School of Engineering at Dartmouth College, 14 Engineering Dr., Hanover, NH, 03755, USA
| | - Michael Sramek
- Geisel School of Medicine at Dartmouth College, 1 Rope Ferry Rd., Hanover, NH, 03755, USA
| | - Joseph A Paydarfar
- Geisel School of Medicine at Dartmouth College, 1 Rope Ferry Rd., Hanover, NH, 03755, USA
- Thayer School of Engineering at Dartmouth College, 14 Engineering Dr., Hanover, NH, 03755, USA
- Section of Otolaryngology, Dartmouth-Hitchcock Medical Center, 1 Medical Center Dr., Lebanon, NH, 03756, USA
| | - Ryan J Halter
- Geisel School of Medicine at Dartmouth College, 1 Rope Ferry Rd., Hanover, NH, 03755, USA
- Thayer School of Engineering at Dartmouth College, 14 Engineering Dr., Hanover, NH, 03755, USA
| |
Collapse
|
11
|
Aydin OU, Taha AA, Hilbert A, Khalil AA, Galinovic I, Fiebach JB, Frey D, Madai VI. On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking. Eur Radiol Exp 2021; 5:4. [PMID: 33474675 PMCID: PMC7817746 DOI: 10.1186/s41747-020-00200-2] [Citation(s) in RCA: 36] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2020] [Accepted: 12/03/2020] [Indexed: 02/07/2023] Open
Abstract
Average Hausdorff distance is a widely used performance measure to calculate the distance between two point sets. In medical image segmentation, it is used to compare ground truth images with segmentations allowing their ranking. We identified, however, ranking errors of average Hausdorff distance making it less suitable for applications in segmentation performance assessment. To mitigate this error, we present a modified calculation of this performance measure that we have coined “balanced average Hausdorff distance”. To simulate segmentations for ranking, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation as our use-case. Adding the created errors consecutively and randomly to the ground truth, we created sets of simulated segmentations with increasing number of errors. Each set of simulated segmentations was ranked using both performance measures. We calculated the Kendall rank correlation coefficient between the segmentation ranking and the number of errors in each simulated segmentation. The rankings produced by balanced average Hausdorff distance had a significantly higher median correlation (1.00) than those by average Hausdorff distance (0.89). In 200 total rankings, the former misranked 52 whilst the latter misranked 179 segmentations. Balanced average Hausdorff distance is more suitable for rankings and quality assessment of segmentations than average Hausdorff distance.
Collapse
Affiliation(s)
- Orhun Utku Aydin
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany.
| | - Abdel Aziz Taha
- Research Studio Data Science, Research Studios Austria, Salzburg, Austria
| | - Adam Hilbert
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Ahmed A Khalil
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany.,Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany.,Mind, Brain, Body Institute, Berlin School of Mind and Brain, Humboldt-Universität Berlin, Berlin, Germany
| | - Ivana Galinovic
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Jochen B Fiebach
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Dietmar Frey
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Vince Istvan Madai
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany.,School of Computing and Digital Technology, Faculty of Computing, Engineering and the Built Environment, Birmingham City University, Birmingham, UK
| |
Collapse
|
12
|
Giganti F, Stavrinides V, Stabile A, Osinibi E, Orczyk C, Radtke JP, Freeman A, Haider A, Punwani S, Allen C, Emberton M, Kirkham A, Moore CM. Prostate cancer measurements on serial MRI during active surveillance: it's time to be PRECISE. Br J Radiol 2020; 93:20200819. [PMID: 32955923 DOI: 10.1259/bjr.20200819] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022] Open
Abstract
OBJECTIVE The PRECISE criteria for reporting multiparametric MRI in patients on active surveillance (AS) for prostate cancer (PCa) score the likelihood of clinically significant change over time using a 1-5 scale, where 4 or 5 indicates radiological progression. According to the PRECISE recommendations, the index lesion size can be reported using different definitions of volume (planimetry or ellipsoid formula) or by measuring one or two diameters. We compared different measurements using planimetry as the reference standard and stratified changes according to the PRECISE scores. METHODS We retrospectively analysed 196 patients on AS with PCa confirmed by targeted biopsy who had two MR scans (baseline and follow-up). Lesions were measured on T2 weighted imaging (T2WI) according to all definitions. A PRECISE score was assessed for each patient. RESULTS The ellipsoid formula exhibited the highest correlation with planimetry at baseline (ρ = 0.97) and follow-up (ρ = 0.98) imaging, compared to the biaxial measurement and single maximum diameter. There was a significant difference (p < 0.001) in the yearly percentage volume change between radiological regression/stability (PRECISE 2-3) and progression (PRECISE 4-5) for planimetry (39.64%) and for the ellipsoid formula (46.78%). CONCLUSION The ellipsoid formula could be used to monitor tumour growth during AS. Evidence of a significant yearly percentage volume change between radiological regression/stability (PRECISE 2-3) and progression (PRECISE 4-5) has been also observed. ADVANCES IN KNOWLEDGE The ellipsoid formula is a reasonable surrogate for planimetry in capturing tumour volume changes on T2WI in patients on imaging-led AS. This is also associated with radiological changes using the PRECISE recommendations.
Collapse
Affiliation(s)
- Francesco Giganti
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK.,Division of Surgery & Interventional Science, University College London, London, UK
| | - Vasilis Stavrinides
- Division of Surgery & Interventional Science, University College London, London, UK.,Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | - Armando Stabile
- Department of Urology and Division of Experimental Oncology, Vita-Salute San Raffaele University, Milan, Italy
| | - Elizabeth Osinibi
- Division of Surgery & Interventional Science, University College London, London, UK
| | - Clement Orczyk
- Division of Surgery & Interventional Science, University College London, London, UK.,Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | | | - Alex Freeman
- Department of Pathology, University College London Hospital NHS Foundation Trust, London, UK
| | - Aiman Haider
- Department of Pathology, University College London Hospital NHS Foundation Trust, London, UK
| | - Shonit Punwani
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK.,Centre for Medical Imaging, University College London, London, UK
| | - Clare Allen
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
| | - Mark Emberton
- Division of Surgery & Interventional Science, University College London, London, UK.,Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| | - Alex Kirkham
- Department of Radiology, University College London Hospital NHS Foundation Trust, London, UK
| | - Caroline M Moore
- Division of Surgery & Interventional Science, University College London, London, UK.,Department of Urology, University College London Hospital NHS Foundation Trust, London, UK
| |
Collapse
|
13
|
Hiremath A, Shiradkar R, Merisaari H, Prasanna P, Ettala O, Taimen P, Aronen HJ, Boström PJ, Jambor I, Madabhushi A. Test-retest repeatability of a deep learning architecture in detecting and segmenting clinically significant prostate cancer on apparent diffusion coefficient (ADC) maps. Eur Radiol 2020; 31:379-391. [PMID: 32700021 DOI: 10.1007/s00330-020-07065-4] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2020] [Revised: 05/22/2020] [Accepted: 07/02/2020] [Indexed: 12/16/2022]
Abstract
OBJECTIVES To evaluate short-term test-retest repeatability of a deep learning architecture (U-Net) in slice- and lesion-level detection and segmentation of clinically significant prostate cancer (csPCa: Gleason grade group > 1) using diffusion-weighted imaging fitted with monoexponential function, ADCm. METHODS One hundred twelve patients with prostate cancer (PCa) underwent 2 prostate MRI examinations on the same day. PCa areas were annotated using whole mount prostatectomy sections. Two U-Net-based convolutional neural networks were trained on three different ADCm b value settings for (a) slice- and (b) lesion-level detection and (c) segmentation of csPCa. Short-term test-retest repeatability was estimated using intra-class correlation coefficient (ICC(3,1)), proportionate agreement, and dice similarity coefficient (DSC). A 3-fold cross-validation was performed on training set (N = 78 patients) and evaluated for performance and repeatability on testing data (N = 34 patients). RESULTS For the three ADCm b value settings, repeatability of mean ADCm of csPCa lesions was ICC(3,1) = 0.86-0.98. Two CNNs with U-Net-based architecture demonstrated ICC(3,1) in the range of 0.80-0.83, agreement of 66-72%, and DSC of 0.68-0.72 for slice- and lesion-level detection and segmentation of csPCa. Bland-Altman plots suggest that there is no systematic bias in agreement between inter-scan ground truth segmentation repeatability and segmentation repeatability of the networks. CONCLUSIONS For the three ADCm b value settings, two CNNs with U-Net-based architecture were repeatable for the problem of detection of csPCa at the slice-level. The network repeatability in segmenting csPCa lesions is affected by inter-scan variability and ground truth segmentation repeatability and may thus improve with better inter-scan reproducibility. KEY POINTS • For the three ADCm b value settings, two CNNs with U-Net-based architecture were repeatable for the problem of detection of csPCa at the slice-level. • The network repeatability in segmenting csPCa lesions is affected by inter-scan variability and ground truth segmentation repeatability and may thus improve with better inter-scan reproducibility.
Collapse
Affiliation(s)
- Amogh Hiremath
- Department of Biomedical Engineering, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH, 44106, USA.
| | - Rakesh Shiradkar
- Department of Biomedical Engineering, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH, 44106, USA
| | - Harri Merisaari
- Department of Biomedical Engineering, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH, 44106, USA.,Department of Diagnostic Radiology, University of Turku, Turku, Finland
| | - Prateek Prasanna
- Department of Biomedical Engineering, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH, 44106, USA.,Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA
| | - Otto Ettala
- Department of Urology, University of Turku and Turku University Hospital, Turku, Finland
| | - Pekka Taimen
- Institute of Biomedicine, Department of Pathology, University of Turku and Turku University Hospital, Turku, Finland
| | - Hannu J Aronen
- Medical Imaging Centre of Southwest Finland, Turku University Hospital, Turku, Finland
| | - Peter J Boström
- Department of Urology, University of Turku and Turku University Hospital, Turku, Finland
| | - Ivan Jambor
- Department of Diagnostic Radiology, University of Turku, Turku, Finland.,Department of Radiology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Anant Madabhushi
- Department of Biomedical Engineering, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH, 44106, USA.,Louis Stokes Cleveland Veterans Administration Medical Center, Cleveland, Ohio, USA
| |
Collapse
|