1
|
Li H, Lee CH, Chia D, Lin Z, Huang W, Tan CH. Machine Learning in Prostate MRI for Prostate Cancer: Current Status and Future Opportunities. Diagnostics (Basel) 2022; 12:diagnostics12020289. [PMID: 35204380 PMCID: PMC8870978 DOI: 10.3390/diagnostics12020289] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2021] [Revised: 12/31/2021] [Accepted: 01/14/2022] [Indexed: 02/04/2023] Open
Abstract
Advances in our understanding of the role of magnetic resonance imaging (MRI) for the detection of prostate cancer have enabled its integration into clinical routines in the past two decades. The Prostate Imaging Reporting and Data System (PI-RADS) is an established imaging-based scoring system that scores the probability of clinically significant prostate cancer on MRI to guide management. Image fusion technology allows one to combine the superior soft tissue contrast resolution of MRI, with real-time anatomical depiction using ultrasound or computed tomography. This allows the accurate mapping of prostate cancer for targeted biopsy and treatment. Machine learning provides vast opportunities for automated organ and lesion depiction that could increase the reproducibility of PI-RADS categorisation, and improve co-registration across imaging modalities to enhance diagnostic and treatment methods that can then be individualised based on clinical risk of malignancy. In this article, we provide a comprehensive and contemporary review of advancements, and share insights into new opportunities in this field.
Collapse
Affiliation(s)
- Huanye Li
- School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore; (H.L.); (Z.L.)
| | - Chau Hung Lee
- Department of Diagnostic Radiology, Tan Tock Seng Hospital, Singapore 308433, Singapore;
| | - David Chia
- Department of Radiation Oncology, National University Cancer Institute (NUH), Singapore 119074, Singapore;
| | - Zhiping Lin
- School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore; (H.L.); (Z.L.)
| | - Weimin Huang
- Institute for Infocomm Research, A*Star, Singapore 138632, Singapore;
| | - Cher Heng Tan
- Department of Diagnostic Radiology, Tan Tock Seng Hospital, Singapore 308433, Singapore;
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore 639798, Singapore
- Correspondence:
| |
Collapse
|
2
|
Zavala-Romero O, Breto AL, Xu IR, Chang YCC, Gautney N, Dal Pra A, Abramowitz MC, Pollack A, Stoyanova R. Segmentation of prostate and prostate zones using deep learning : A multi-MRI vendor analysis. Strahlenther Onkol 2020; 196:932-942. [PMID: 32221622 PMCID: PMC8418872 DOI: 10.1007/s00066-020-01607-x] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2019] [Accepted: 03/10/2020] [Indexed: 11/25/2022]
Abstract
PURPOSE Develop a deep-learning-based segmentation algorithm for prostate and its peripheral zone (PZ) that is reliable across multiple MRI vendors. METHODS This is a retrospective study. The dataset consisted of 550 MRIs (Siemens-330, General Electric[GE]-220). A multistream 3D convolutional neural network is used for automatic segmentation of the prostate and its PZ using T2-weighted (T2-w) MRI. Prostate and PZ were manually contoured on axial T2‑w. The network uses axial, coronal, and sagittal T2‑w series as input. The preprocessing of the input data includes bias correction, resampling, and image normalization. A dataset from two MRI vendors (Siemens and GE) is used to test the proposed network. Six different models were trained, three for the prostate and three for the PZ. Of the three, two were trained on data from each vendor separately, and a third (Combined) on the aggregate of the datasets. The Dice coefficient (DSC) is used to compare the manual and predicted segmentation. RESULTS For prostate segmentation, the Combined model obtained DSCs of 0.893 ± 0.036 and 0.825 ± 0.112 (mean ± standard deviation) on Siemens and GE, respectively. For PZ, the best DSCs were from the Combined model: 0.811 ± 0.079 and 0.788 ± 0.093. While the Siemens model underperformed on the GE dataset and vice versa, the Combined model achieved robust performance on both datasets. CONCLUSION The proposed network has a performance comparable to the interexpert variability for segmenting the prostate and its PZ. Combining images from different MRI vendors on the training of the network is of paramount importance for building a universal model for prostate and PZ segmentation.
Collapse
Affiliation(s)
- Olmo Zavala-Romero
- Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Adrian L Breto
- Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Isaac R Xu
- Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| | | | - Nicole Gautney
- Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Alan Dal Pra
- Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Matthew C Abramowitz
- Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Alan Pollack
- Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Radka Stoyanova
- Department of Radiation Oncology, Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA.
| |
Collapse
|
3
|
Optimisation of 2D U-Net Model Components for Automatic Prostate Segmentation on MRI. APPLIED SCIENCES-BASEL 2020. [DOI: 10.3390/app10072601] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
In this paper, we develop an optimised state-of-the-art 2D U-Net model by studying the effects of the individual deep learning model components in performing prostate segmentation. We found that for upsampling, the combination of interpolation and convolution is better than the use of transposed convolution. For combining feature maps in each convolution block, it is only beneficial if a skip connection with concatenation is used. With respect to pooling, average pooling is better than strided-convolution, max, RMS or L2 pooling. Introducing a batch normalisation layer before the activation layer gives further performance improvement. The optimisation is based on a private dataset as it has a fixed 2D resolution and voxel size for every image which mitigates the need of a resizing operation in the data preparation process. Non-enhancing data preprocessing was applied and five-fold cross-validation was used to evaluate the fully automatic segmentation approach. We show it outperforms the traditional methods that were previously applied on the private dataset, as well as outperforming other comparable state-of-the-art 2D models on the public dataset PROMISE12.
Collapse
|
4
|
Towards a universal MRI atlas of the prostate and prostate zones : Comparison of MRI vendor and image acquisition parameters. Strahlenther Onkol 2018; 195:121-130. [PMID: 30140944 DOI: 10.1007/s00066-018-1348-5] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2018] [Accepted: 07/31/2018] [Indexed: 12/31/2022]
Abstract
BACKGROUND AND PURPOSE The aim of this study was to evaluate an automatic multi-atlas-based segmentation method for generating prostate, peripheral (PZ), and transition zone (TZ) contours on MRIs with and without fat saturation (±FS), and compare MRIs from different vendor MRI systems. METHODS T2-weighted (T2) and fat-saturated (T2FS) MRIs were acquired on 3T GE (GE, Waukesha, WI, USA) and Siemens (Erlangen, Germany) systems. Manual prostate and PZ contours were used to create atlas libraries. As a test MRI is entered, the procedure for atlas segmentation automatically identifies the atlas subjects that best match the test subject, followed by a normalized intensity-based free-form deformable registration. The contours are transformed to the test subject, and Dice similarity coefficients (DSC) and Hausdorff distances between atlas-generated and manual contours were used to assess performance. RESULTS Three atlases were generated based on GE_T2 (n = 30), GE_T2FS (n = 30), and Siem_T2FS (n = 31). When test images matched the contrast and vendor of the atlas, DSCs of 0.81 and 0.83 for T2 ± FS were obtained (baseline performance). Atlases performed with higher accuracy when segmenting (i) T2FS vs. T2 images, likely due to a superior contrast between prostate vs. surrounding tissue; (ii) prostate vs. zonal anatomy; (iii) in the mid-gland vs. base and apex. Atlases performance declined when tested with images with differing contrast and MRI vendor. Conversely, combined atlases showed similar performance to baseline. CONCLUSION The MRI atlas-based segmentation method achieved good results for prostate, PZ, and TZ compared to expert contoured volumes. Combined atlases performed similarly to matching atlas and scan type. The technique is fast, fully automatic, and implemented on commercially available clinical platform.
Collapse
|
5
|
Shahedi M, Cool DW, Bauman GS, Bastian-Jordan M, Fenster A, Ward AD. Accuracy Validation of an Automated Method for Prostate Segmentation in Magnetic Resonance Imaging. J Digit Imaging 2018; 30:782-795. [PMID: 28342043 DOI: 10.1007/s10278-017-9964-7] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022] Open
Abstract
Three dimensional (3D) manual segmentation of the prostate on magnetic resonance imaging (MRI) is a laborious and time-consuming task that is subject to inter-observer variability. In this study, we developed a fully automatic segmentation algorithm for T2-weighted endorectal prostate MRI and evaluated its accuracy within different regions of interest using a set of complementary error metrics. Our dataset contained 42 T2-weighted endorectal MRI from prostate cancer patients. The prostate was manually segmented by one observer on all of the images and by two other observers on a subset of 10 images. The algorithm first coarsely localizes the prostate in the image using a template matching technique. Then, it defines the prostate surface using learned shape and appearance information from a set of training images. To evaluate the algorithm, we assessed the error metric values in the context of measured inter-observer variability and compared performance to that of our previously published semi-automatic approach. The automatic algorithm needed an average execution time of ∼60 s to segment the prostate in 3D. When compared to a single-observer reference standard, the automatic algorithm has an average mean absolute distance of 2.8 mm, Dice similarity coefficient of 82%, recall of 82%, precision of 84%, and volume difference of 0.5 cm3 in the mid-gland. Concordant with other studies, accuracy was highest in the mid-gland and lower in the apex and base. Loss of accuracy with respect to the semi-automatic algorithm was less than the measured inter-observer variability in manual segmentation for the same task.
Collapse
Affiliation(s)
- Maysam Shahedi
- Baines Imaging Research Laboratory, London Regional Cancer Program, A3-123A, 790 Commissioners Rd E, London, ON, N6A 4L6, Canada. .,Robarts Research Institute, The University of Western Ontario, London, ON, Canada. .,Graduate Program in Biomedical Engineering, The University of Western Ontario, London, ON, Canada.
| | - Derek W Cool
- Robarts Research Institute, The University of Western Ontario, London, ON, Canada.,The Department of Medical Imaging, The University of Western Ontario, London, ON, Canada
| | - Glenn S Bauman
- Baines Imaging Research Laboratory, London Regional Cancer Program, A3-123A, 790 Commissioners Rd E, London, ON, N6A 4L6, Canada.,The Department of Medical Biophysics, The University of Western Ontario, London, ON, Canada.,The Department of Oncology, The University of Western Ontario, London, ON, Canada
| | - Matthew Bastian-Jordan
- The Department of Medical Imaging, The University of Western Ontario, London, ON, Canada
| | - Aaron Fenster
- Robarts Research Institute, The University of Western Ontario, London, ON, Canada.,Graduate Program in Biomedical Engineering, The University of Western Ontario, London, ON, Canada.,The Department of Medical Imaging, The University of Western Ontario, London, ON, Canada.,The Department of Medical Biophysics, The University of Western Ontario, London, ON, Canada
| | - Aaron D Ward
- Baines Imaging Research Laboratory, London Regional Cancer Program, A3-123A, 790 Commissioners Rd E, London, ON, N6A 4L6, Canada.,Graduate Program in Biomedical Engineering, The University of Western Ontario, London, ON, Canada.,The Department of Medical Biophysics, The University of Western Ontario, London, ON, Canada.,The Department of Oncology, The University of Western Ontario, London, ON, Canada
| |
Collapse
|
6
|
Shahedi M, Cool DW, Romagnoli C, Bauman GS, Bastian-Jordan M, Rodrigues G, Ahmad B, Lock M, Fenster A, Ward AD. Postediting prostate magnetic resonance imaging segmentation consistency and operator time using manual and computer-assisted segmentation: multiobserver study. J Med Imaging (Bellingham) 2016; 3:046002. [PMID: 27872873 DOI: 10.1117/1.jmi.3.4.046002] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2016] [Accepted: 09/19/2016] [Indexed: 11/14/2022] Open
Abstract
Prostate segmentation on T2w MRI is important for several diagnostic and therapeutic procedures for prostate cancer. Manual segmentation is time-consuming, labor-intensive, and subject to high interobserver variability. This study investigated the suitability of computer-assisted segmentation algorithms for clinical translation, based on measurements of interoperator variability and measurements of the editing time required to yield clinically acceptable segmentations. A multioperator pilot study was performed under three pre- and postediting conditions: manual, semiautomatic, and automatic segmentation. We recorded the required editing time for each segmentation and measured the editing magnitude based on five different spatial metrics. We recorded average editing times of 213, 328, and 393 s for manual, semiautomatic, and automatic segmentation respectively, while an average fully manual segmentation time of 564 s was recorded. The reduced measured postediting interoperator variability of semiautomatic and automatic segmentations compared to the manual approach indicates the potential of computer-assisted segmentation for generating a clinically acceptable segmentation faster with higher consistency. The lack of strong correlation between editing time and the values of typically used error metrics ([Formula: see text]) implies that the necessary postsegmentation editing time needs to be measured directly in order to evaluate an algorithm's suitability for clinical translation.
Collapse
Affiliation(s)
- Maysam Shahedi
- London Regional Cancer Program, 790 Commissioners Road, London, Ontario N6A 4L6, Canada; University of Western Ontario, Robarts Research Institute, 1151 Richmond Street, London, Ontario N6A 5B7, Canada; University of Western Ontario, Graduate Program in Biomedical Engineering, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - Derek W Cool
- University of Western Ontario, Robarts Research Institute, 1151 Richmond Street, London, Ontario N6A 5B7, Canada; University of Western Ontario, Department of Medical Imaging, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - Cesare Romagnoli
- University of Western Ontario , Department of Medical Imaging, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - Glenn S Bauman
- London Regional Cancer Program, 790 Commissioners Road, London, Ontario N6A 4L6, Canada; University of Western Ontario, Department of Medical Biophysics, 1151 Richmond Street, London, Ontario N6A 3K7, Canada; University of Western Ontario, Department of Oncology, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - Matthew Bastian-Jordan
- University of Western Ontario , Department of Medical Imaging, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - George Rodrigues
- London Regional Cancer Program, 790 Commissioners Road, London, Ontario N6A 4L6, Canada; University of Western Ontario, Department of Oncology, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - Belal Ahmad
- London Regional Cancer Program, 790 Commissioners Road, London, Ontario N6A 4L6, Canada; University of Western Ontario, Department of Oncology, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - Michael Lock
- London Regional Cancer Program, 790 Commissioners Road, London, Ontario N6A 4L6, Canada; University of Western Ontario, Department of Oncology, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - Aaron Fenster
- University of Western Ontario, Robarts Research Institute, 1151 Richmond Street, London, Ontario N6A 5B7, Canada; University of Western Ontario, Graduate Program in Biomedical Engineering, 1151 Richmond Street, London, Ontario N6A 3K7, Canada; University of Western Ontario, Department of Medical Imaging, 1151 Richmond Street, London, Ontario N6A 3K7, Canada; University of Western Ontario, Department of Medical Biophysics, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| | - Aaron D Ward
- London Regional Cancer Program, 790 Commissioners Road, London, Ontario N6A 4L6, Canada; University of Western Ontario, Graduate Program in Biomedical Engineering, 1151 Richmond Street, London, Ontario N6A 3K7, Canada; University of Western Ontario, Department of Medical Biophysics, 1151 Richmond Street, London, Ontario N6A 3K7, Canada; University of Western Ontario, Department of Oncology, 1151 Richmond Street, London, Ontario N6A 3K7, Canada
| |
Collapse
|