1
|
Wu C, Montagne S, Hamzaoui D, Ayache N, Delingette H, Renard-Penna R. Automatic segmentation of prostate zonal anatomy on MRI: a systematic review of the literature. Insights Imaging 2022; 13:202. [PMID: 36543901 PMCID: PMC9772373 DOI: 10.1186/s13244-022-01340-2] [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: 08/11/2022] [Accepted: 11/27/2022] [Indexed: 12/24/2022] Open
Abstract
OBJECTIVES Accurate zonal segmentation of prostate boundaries on MRI is a critical prerequisite for automated prostate cancer detection based on PI-RADS. Many articles have been published describing deep learning methods offering great promise for fast and accurate segmentation of prostate zonal anatomy. The objective of this review was to provide a detailed analysis and comparison of applicability and efficiency of the published methods for automatic segmentation of prostate zonal anatomy by systematically reviewing the current literature. METHODS A Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) was conducted until June 30, 2021, using PubMed, ScienceDirect, Web of Science and EMBase databases. Risk of bias and applicability based on Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria adjusted with Checklist for Artificial Intelligence in Medical Imaging (CLAIM) were assessed. RESULTS A total of 458 articles were identified, and 33 were included and reviewed. Only 2 articles had a low risk of bias for all four QUADAS-2 domains. In the remaining, insufficient details about database constitution and segmentation protocol provided sources of bias (inclusion criteria, MRI acquisition, ground truth). Eighteen different types of terminology for prostate zone segmentation were found, while 4 anatomic zones are described on MRI. Only 2 authors used a blinded reading, and 4 assessed inter-observer variability. CONCLUSIONS Our review identified numerous methodological flaws and underlined biases precluding us from performing quantitative analysis for this review. This implies low robustness and low applicability in clinical practice of the evaluated methods. Actually, there is not yet consensus on quality criteria for database constitution and zonal segmentation methodology.
Collapse
Affiliation(s)
- Carine Wu
- grid.462844.80000 0001 2308 1657Sorbonne Université, Paris, France ,grid.50550.350000 0001 2175 4109Academic Department of Radiology, Hôpital Tenon, Assistance Publique des Hôpitaux de Paris, 4 Rue de La Chine, 75020 Paris, France
| | - Sarah Montagne
- grid.462844.80000 0001 2308 1657Sorbonne Université, Paris, France ,grid.50550.350000 0001 2175 4109Academic Department of Radiology, Hôpital Tenon, Assistance Publique des Hôpitaux de Paris, 4 Rue de La Chine, 75020 Paris, France ,grid.50550.350000 0001 2175 4109Academic Department of Radiology, Hôpital Pitié-Salpétrière, Assistance Publique des Hôpitaux de Paris, Paris, France ,grid.462844.80000 0001 2308 1657GRC N° 5, Oncotype-Uro, Sorbonne Université, Paris, France
| | - Dimitri Hamzaoui
- grid.460782.f0000 0004 4910 6551Inria, Epione Team, Sophia Antipolis, Université Côte d’Azur, Nice, France
| | - Nicholas Ayache
- grid.460782.f0000 0004 4910 6551Inria, Epione Team, Sophia Antipolis, Université Côte d’Azur, Nice, France
| | - Hervé Delingette
- grid.460782.f0000 0004 4910 6551Inria, Epione Team, Sophia Antipolis, Université Côte d’Azur, Nice, France
| | - Raphaële Renard-Penna
- grid.462844.80000 0001 2308 1657Sorbonne Université, Paris, France ,grid.50550.350000 0001 2175 4109Academic Department of Radiology, Hôpital Tenon, Assistance Publique des Hôpitaux de Paris, 4 Rue de La Chine, 75020 Paris, France ,grid.50550.350000 0001 2175 4109Academic Department of Radiology, Hôpital Pitié-Salpétrière, Assistance Publique des Hôpitaux de Paris, Paris, France ,grid.462844.80000 0001 2308 1657GRC N° 5, Oncotype-Uro, Sorbonne Université, Paris, France
| |
Collapse
|
2
|
Kalantar R, Lin G, Winfield JM, Messiou C, Lalondrelle S, Blackledge MD, Koh DM. Automatic Segmentation of Pelvic Cancers Using Deep Learning: State-of-the-Art Approaches and Challenges. Diagnostics (Basel) 2021; 11:1964. [PMID: 34829310 PMCID: PMC8625809 DOI: 10.3390/diagnostics11111964] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2021] [Revised: 10/14/2021] [Accepted: 10/19/2021] [Indexed: 12/18/2022] Open
Abstract
The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing. DL provides grounds for technological development of computer-aided diagnosis and segmentation in radiology and radiation oncology. Amongst the anatomical locations where recent auto-segmentation algorithms have been employed, the pelvis remains one of the most challenging due to large intra- and inter-patient soft-tissue variabilities. This review provides a comprehensive, non-systematic and clinically-oriented overview of 74 DL-based segmentation studies, published between January 2016 and December 2020, for bladder, prostate, cervical and rectal cancers on computed tomography (CT) and magnetic resonance imaging (MRI), highlighting the key findings, challenges and limitations.
Collapse
Affiliation(s)
- Reza Kalantar
- Division of Radiotherapy and Imaging, The Institute of Cancer Research, London SM2 5NG, UK; (R.K.); (J.M.W.); (C.M.); (S.L.); (D.-M.K.)
| | - Gigin Lin
- Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan 333, Taiwan;
| | - Jessica M. Winfield
- Division of Radiotherapy and Imaging, The Institute of Cancer Research, London SM2 5NG, UK; (R.K.); (J.M.W.); (C.M.); (S.L.); (D.-M.K.)
- Department of Radiology, The Royal Marsden Hospital, London SW3 6JJ, UK
| | - Christina Messiou
- Division of Radiotherapy and Imaging, The Institute of Cancer Research, London SM2 5NG, UK; (R.K.); (J.M.W.); (C.M.); (S.L.); (D.-M.K.)
- Department of Radiology, The Royal Marsden Hospital, London SW3 6JJ, UK
| | - Susan Lalondrelle
- Division of Radiotherapy and Imaging, The Institute of Cancer Research, London SM2 5NG, UK; (R.K.); (J.M.W.); (C.M.); (S.L.); (D.-M.K.)
- Department of Radiology, The Royal Marsden Hospital, London SW3 6JJ, UK
| | - Matthew D. Blackledge
- Division of Radiotherapy and Imaging, The Institute of Cancer Research, London SM2 5NG, UK; (R.K.); (J.M.W.); (C.M.); (S.L.); (D.-M.K.)
| | - Dow-Mu Koh
- Division of Radiotherapy and Imaging, The Institute of Cancer Research, London SM2 5NG, UK; (R.K.); (J.M.W.); (C.M.); (S.L.); (D.-M.K.)
- Department of Radiology, The Royal Marsden Hospital, London SW3 6JJ, UK
| |
Collapse
|
3
|
Meyer A, Ghosh S, Schindele D, Schostak M, Stober S, Hansen C, Rak M. Uncertainty-aware temporal self-learning (UATS): Semi-supervised learning for segmentation of prostate zones and beyond. Artif Intell Med 2021; 116:102073. [PMID: 34020751 DOI: 10.1016/j.artmed.2021.102073] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2020] [Revised: 02/09/2021] [Accepted: 04/07/2021] [Indexed: 10/21/2022]
Abstract
Various convolutional neural network (CNN) based concepts have been introduced for the prostate's automatic segmentation and its coarse subdivision into transition zone (TZ) and peripheral zone (PZ). However, when targeting a fine-grained segmentation of TZ, PZ, distal prostatic urethra (DPU) and the anterior fibromuscular stroma (AFS), the task becomes more challenging and has not yet been solved at the level of human performance. One reason might be the insufficient amount of labeled data for supervised training. Therefore, we propose to apply a semi-supervised learning (SSL) technique named uncertainty-aware temporal self-learning (UATS) to overcome the expensive and time-consuming manual ground truth labeling. We combine the SSL techniques temporal ensembling and uncertainty-guided self-learning to benefit from unlabeled images, which are often readily available. Our method significantly outperforms the supervised baseline and obtained a Dice coefficient (DC) of up to 78.9%, 87.3%, 75.3%, 50.6% for TZ, PZ, DPU and AFS, respectively. The obtained results are in the range of human inter-rater performance for all structures. Moreover, we investigate the method's robustness against noise and demonstrate the generalization capability for varying ratios of labeled data and on other challenging tasks, namely the hippocampus and skin lesion segmentation. UATS achieved superiority segmentation quality compared to the supervised baseline, particularly for minimal amounts of labeled data.
Collapse
Affiliation(s)
- Anneke Meyer
- Faculty of Computer Science and Research Campus STIMULATE, University of Magdeburg, Germany.
| | - Suhita Ghosh
- Faculty of Computer Science and Research Campus STIMULATE, University of Magdeburg, Germany
| | - Daniel Schindele
- Clinic of Urology and Pediatric Urology, University Hospital Magdeburg, Germany
| | - Martin Schostak
- Clinic of Urology and Pediatric Urology, University Hospital Magdeburg, Germany
| | - Sebastian Stober
- Faculty of Computer Science and Research Campus STIMULATE, University of Magdeburg, Germany
| | - Christian Hansen
- Faculty of Computer Science and Research Campus STIMULATE, University of Magdeburg, Germany
| | - Marko Rak
- Faculty of Computer Science and Research Campus STIMULATE, University of Magdeburg, Germany
| |
Collapse
|
4
|
3D multi-scale discriminative network with multi-directional edge loss for prostate zonal segmentation in bi-parametric MR images. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2020.07.116] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
|
5
|
Singh D, Kumar V, Das CJ, Singh A, Mehndiratta A. Segmentation of prostate zones using probabilistic atlas-based method with diffusion-weighted MR images. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 196:105572. [PMID: 32544780 DOI: 10.1016/j.cmpb.2020.105572] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/13/2019] [Revised: 05/10/2020] [Accepted: 05/24/2020] [Indexed: 06/11/2023]
Abstract
BACKGROUND AND OBJECTIVE Accurate segmentation of prostate and its zones constitute an essential preprocessing step for computer-aided diagnosis and detection system for prostate cancer (PCa) using diffusion-weighted imaging (DWI). However, low signal-to-noise ratio and high variability of prostate anatomic structures are challenging for its segmentation using DWI. We propose a semi-automated framework that segments the prostate gland and its zones simultaneously using DWI. METHODS In this paper, the Chan-Vese active contour model along with morphological opening operation was used for segmentation of prostate gland. Then segmentation of prostate zones into peripheral zone (PZ) and transition zone (TZ) was carried out using in-house developed probabilistic atlas with partial volume (PV) correction algorithm. The study cohort included MRI dataset of 18 patients (n = 18) as our dataset and methodology were also independently evaluated using 15 MRI scans (n = 15) of QIN-PROSTATE-Repeatability dataset. The atlas for zones of prostate gland was constructed using dataset of twelve patients of our patient cohort. Three-fold cross-validation was performed with 10 repetitions, thus total 30 instances of training and testing were performed on our dataset followed by independent testing on the QIN-PROSTATE-Repeatability dataset. Dice similarity coefficient (DSC), Jaccard coefficient (JC), and accuracy were used for quantitative assessment of the segmentation results with respect to boundaries delineated manually by an expert radiologist. A paired t-test was performed to evaluate the improvement in zonal segmentation performance with the proposed PV correction algorithm. RESULTS For our dataset, the proposed segmentation methodology produced improved segmentation with DSC of 90.76 ± 3.68%, JC of 83.00 ± 5.78%, and accuracy of 99.42 ± 0.36% for the prostate gland, DSC of 77.73 ± 2.76%, JC of 64.46 ± 3.43%, and accuracy of 82.47 ± 2.22% for the PZ, and DSC of 86.05 ± 1.50%, JC of 75.80 ± 2.10%, and accuracy of 91.67 ± 1.56% for the TZ. The segmentation performance for QIN-PROSTATE-Repeatability dataset was, DSC of 85.50 ± 4.43%, JC of 75.00 ± 6.34%, and accuracy of 81.52 ± 5.55% for prostate gland, DSC of 74.40 ± 1.79%, JC of 59.53 ± 8.70%, and accuracy of 80.91 ± 5.16% for PZ, and DSC of 85.80 ± 5.55%, JC of 74.87 ± 7.90%, and accuracy of 90.59 ± 3.74% for TZ. With the implementation of the PV correction algorithm, statistically significant (p<0.05) improvements were observed in all the metrics (DSC, JC, and accuracy) for both prostate zones, PZ and TZ segmentation. CONCLUSIONS The proposed segmentation methodology is stable, accurate, and easy to implement for segmentation of prostate gland and its zones (PZ and TZ). The atlas-based segmentation framework with PV correction algorithm can be incorporated into a computer-aided diagnostic system for PCa localization and treatment planning.
Collapse
Affiliation(s)
- Dharmesh Singh
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India
| | - Virendra Kumar
- Department of NMR, All India Institute of Medical Sciences, New Delhi, India
| | - Chandan J Das
- Department of Radiodiagnosis, All India Institute of Medical Sciences, New Delhi, India
| | - Anup Singh
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India; Department of Biomedical Engineering, All India Institute of Medical Sciences, New Delhi, India
| | - Amit Mehndiratta
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India; Department of Biomedical Engineering, All India Institute of Medical Sciences, New Delhi, India.
| |
Collapse
|
6
|
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
|
7
|
CNN-Based Prostate Zonal Segmentation on T2-Weighted MR Images: A Cross-Dataset Study. NEURAL APPROACHES TO DYNAMICS OF SIGNAL EXCHANGES 2020. [DOI: 10.1007/978-981-13-8950-4_25] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
|
8
|
USE-Net: Incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets. Neurocomputing 2019. [DOI: 10.1016/j.neucom.2019.07.006] [Citation(s) in RCA: 123] [Impact Index Per Article: 24.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
|
9
|
Jensen C, Sørensen KS, Jørgensen CK, Nielsen CW, Høy PC, Langkilde NC, Østergaard LR. Prostate zonal segmentation in 1.5T and 3T T2W MRI using a convolutional neural network. J Med Imaging (Bellingham) 2019; 6:014501. [PMID: 30820440 DOI: 10.1117/1.jmi.6.1.014501] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2018] [Accepted: 12/28/2018] [Indexed: 12/22/2022] Open
Abstract
Zonal segmentation of the prostate gland using magnetic resonance imaging (MRI) is clinically important for prostate cancer (PCa) diagnosis and image-guided treatments. A two-dimensional convolutional neural network (CNN) based on the U-net architecture was evaluated for segmentation of the central gland (CG) and peripheral zone (PZ) using a dataset of 40 patients (34 PCa positive and 6 PCa negative) scanned on two different MRI scanners (1.5T GE and 3T Siemens). Images were cropped around the prostate gland to exclude surrounding tissues, resampled to 0.5 × 0.5 × 0.5 mm voxels and z -score normalized before being propagated through the CNN. Performance was evaluated using the Dice similarity coefficient (DSC) and mean absolute distance (MAD) in a fivefold cross-validation setup. Overall performance showed DSC of 0.794 and 0.692, and MADs of 3.349 and 2.993 for CG and PZ, respectively. Dividing the gland into apex, mid, and base showed higher DSC for the midgland compared to apex and base for both CG and PZ. We found no significant difference in DSC between the two scanners. A larger dataset, preferably with multivendor scanners, is necessary for validation of the proposed algorithm; however, our results are promising and have clinical potential.
Collapse
Affiliation(s)
- Carina Jensen
- Aalborg University Hospital, Department of Medical Physics, Department of Oncology, Aalborg, Denmark
| | | | | | | | - Pia Christine Høy
- Aalborg University, Department of Health Science and Technology, Aalborg, Denmark
| | | | | |
Collapse
|
10
|
Antonelli M, Cardoso MJ, Johnston EW, Appayya MB, Presles B, Modat M, Punwani S, Ourselin S. GAS: A genetic atlas selection strategy in multi-atlas segmentation framework. Med Image Anal 2019; 52:97-108. [PMID: 30476698 DOI: 10.1016/j.media.2018.11.007] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2017] [Revised: 11/08/2018] [Accepted: 11/15/2018] [Indexed: 11/15/2022]
Abstract
Multi-Atlas based Segmentation (MAS) algorithms have been successfully applied to many medical image segmentation tasks, but their success relies on a large number of atlases and good image registration performance. Choosing well-registered atlases for label fusion is vital for an accurate segmentation. This choice becomes even more crucial when the segmentation involves organs characterized by a high anatomical and pathological variability. In this paper, we propose a new genetic atlas selection strategy (GAS) that automatically chooses the best subset of atlases to be used for segmenting the target image, on the basis of both image similarity and segmentation overlap. More precisely, the key idea of GAS is that if two images are similar, the performances of an atlas for segmenting each image are similar. Since the ground truth of each atlas is known, GAS first selects a predefined number of similar images to the target, then, for each one of them, finds a near-optimal subset of atlases by means of a genetic algorithm. All these near-optimal subsets are then combined and used to segment the target image. GAS was tested on single-label and multi-label segmentation problems. In the first case, we considered the segmentation of both the whole prostate and of the left ventricle of the heart from magnetic resonance images. Regarding multi-label problems, the zonal segmentation of the prostate into peripheral and transition zone was considered. The results showed that the performance of MAS algorithms statistically improved when GAS is used.
Collapse
Affiliation(s)
- Michela Antonelli
- Centre for Medical Image Computing, University College London, U.K..
| | - M Jorge Cardoso
- Dep. of Medical Physics and Biomedical Engineering, University College London, U.K.; School of Biomedical Engineering and Imaging Science, Kings College London, U.K
| | | | | | - Benoit Presles
- Centre for Medical Image Computing, University College London, U.K
| | - Marc Modat
- Dep. of Medical Physics and Biomedical Engineering, University College London, U.K.; School of Biomedical Engineering and Imaging Science, Kings College London, U.K
| | - Shonit Punwani
- Centre for Medical Imaging, University College London, U.K
| | - Sebastien Ourselin
- Dep. of Medical Physics and Biomedical Engineering, University College London, U.K.; School of Biomedical Engineering and Imaging Science, Kings College London, U.K
| |
Collapse
|
11
|
Jin J, Zhang L, Leng E, Metzger GJ, Koopmeiners JS. Detection of prostate cancer with multiparametric MRI utilizing the anatomic structure of the prostate. Stat Med 2018; 37:3214-3229. [PMID: 29923345 DOI: 10.1002/sim.7810] [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: 09/07/2017] [Revised: 03/05/2018] [Accepted: 04/05/2018] [Indexed: 01/02/2023]
Abstract
Multiparametric magnetic resonance imaging (mpMRI), which combines traditional anatomic and newer quantitative MRI methods, has been shown to result in improved voxel-wise classification of prostate cancer as compared with any single MRI parameter. While these results are promising, substantial heterogeneity in the mpMRI parameter values and voxel-wise prostate cancer risk has been observed both between and within regions of the prostate. This suggests that classification of prostate cancer can potentially be improved by incorporating structural information into the classifier. In this paper, we propose a novel voxel-wise classifier of prostate cancer that accounts for the anatomic structure of the prostate by Bayesian hierarchical modeling, which can be combined with post hoc spatial Gaussian kernel smoothing to account for residual spatial correlation. Our proposed classifier results in significantly improved area under the ROC curve (0.822 vs 0.729, P < .001) and sensitivity corresponding to 90% specificity (0.599 vs 0.429, P < .001), compared with a baseline model that does not account for the anatomic structure of the prostate. Furthermore, the classifier can also be applied on voxels with missing mpMRI parameters, resulting in similar performance, which is an important practical consideration that cannot be easily accommodated using regression-based classifiers. In addition, our classifier achieved high computational efficiency with a closed-form solution for the posterior predictive cancer probability.
Collapse
Affiliation(s)
- Jin Jin
- Division of Biostatistics, School of Public Health, University of Minnesota, Minneapolis, MN 55455, USA
| | - Lin Zhang
- Division of Biostatistics, School of Public Health, University of Minnesota, Minneapolis, MN 55455, USA
| | - Ethan Leng
- Center for Magnetic Resonance Research, Department of Radiology, University of Minnesota, Minneapolis, MN 55455, USA
| | - Gregory J Metzger
- Center for Magnetic Resonance Research, Department of Radiology, University of Minnesota, Minneapolis, MN 55455, USA
| | - Joseph S Koopmeiners
- Division of Biostatistics, School of Public Health, University of Minnesota, Minneapolis, MN 55455, USA
| |
Collapse
|
12
|
Algohary A, Viswanath S, Shiradkar R, Ghose S, Pahwa S, Moses D, Jambor I, Shnier R, Böhm M, Haynes AM, Brenner P, Delprado W, Thompson J, Pulbrock M, Purysko A, Verma S, Ponsky L, Stricker P, Madabhushi A. Radiomic features on MRI enable risk categorization of prostate cancer patients on active surveillance: Preliminary findings. J Magn Reson Imaging 2018; 48:10.1002/jmri.25983. [PMID: 29469937 PMCID: PMC6105554 DOI: 10.1002/jmri.25983] [Citation(s) in RCA: 68] [Impact Index Per Article: 11.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2017] [Accepted: 01/30/2018] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Radiomic analysis is defined as computationally extracting features from radiographic images for quantitatively characterizing disease patterns. There has been recent interest in examining the use of MRI for identifying prostate cancer (PCa) aggressiveness in patients on active surveillance (AS). PURPOSE To evaluate the performance of MRI-based radiomic features in identifying the presence or absence of clinically significant PCa in AS patients. STUDY TYPE Retrospective. SUBJECTS MODEL MRI/TRUS (transperineal grid ultrasound) fusion-guided biopsy was performed for 56 PCa patients on AS who had undergone prebiopsy. FIELD STRENGTH/SEQUENCE 3T, T2 -weighted (T2 w) and diffusion-weighted (DW) MRI. ASSESSMENT A pathologist histopathologically defined the presence of clinically significant disease. A radiologist manually delineated lesions on T2 w-MRs. Then three radiologists assessed MRIs using PIRADS v2.0 guidelines. Tumors were categorized into four groups: MRI-negative-biopsy-negative (Group 1, N = 15), MRI-positive-biopsy-positive (Group 2, N = 16), MRI-negative-biopsy-positive (Group 3, N = 10), and MRI-positive-biopsy-negative (Group 4, N = 15). In all, 308 radiomic features (First-order statistics, Gabor, Laws Energy, and Haralick) were extracted from within the annotated lesions on T2 w images and apparent diffusion coefficient (ADC) maps. The top 10 features associated with clinically significant tumors were identified using minimum-redundancy-maximum-relevance and used to construct three machine-learning models that were independently evaluated for their ability to identify the presence and absence of clinically significant disease. STATISTICAL TESTS Wilcoxon rank-sum tests with P < 0.05 considered statistically significant. RESULTS Seven T2 w-based (First-order Statistics, Haralick, Laws, and Gabor) and three ADC-based radiomic features (Laws, Gradient and Sobel) exhibited statistically significant differences (P < 0.001) between malignant and normal regions in the training groups. The three constructed models yielded overall accuracy improvement of 33, 60, 80% and 30, 40, 60% for patients in testing groups, when compared to PIRADS v2.0 alone. DATA CONCLUSION Radiomic features could help in identifying the presence and absence of clinically significant disease in AS patients when PIRADS v2.0 assessment on MRI contradicted pathology findings of MRI-TRUS prostate biopsies. LEVEL OF EVIDENCE 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.
Collapse
Affiliation(s)
- Ahmad Algohary
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA
| | - Satish Viswanath
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA
| | - Rakesh Shiradkar
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA
| | - Soumya Ghose
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA
| | - Shivani Pahwa
- Department of Radiology, Case Western Reserve University, Cleveland, Ohio, USA
| | - Daniel Moses
- Garvan Institute of Medical Research, Sydney, Australia
| | - Ivan Jambor
- Department of Diagnostic Radiology, University of Turku, Turku, Finland
| | - Ronald Shnier
- Garvan Institute of Medical Research, Sydney, Australia
| | - Maret Böhm
- Garvan Institute of Medical Research, Sydney, Australia
| | | | - Phillip Brenner
- Department of Urology, St. Vincent’s Hospital, Sydney, Australia
| | | | | | | | - Andrei Purysko
- Section of Abdominal Imaging, Imaging Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Sadhna Verma
- Department of Radiology, College of Medicine, University of Cincinnati, Cincinnati, OH, USA
| | - Lee Ponsky
- Department of Urology, Case Western Reserve University, Cleveland, Ohio, USA
| | - Phillip Stricker
- Department of Urology, St. Vincent’s Hospital, Sydney, Australia
| | - Anant Madabhushi
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA
| |
Collapse
|
13
|
Chilali O, Puech P, Lakroum S, Diaf M, Mordon S, Betrouni N. Gland and Zonal Segmentation of Prostate on T2W MR Images. J Digit Imaging 2018; 29:730-736. [PMID: 27363993 DOI: 10.1007/s10278-016-9890-0] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022] Open
Abstract
For many years, prostate segmentation on MR images concerned only the extraction of the entire gland. Currently, in the focal treatment era, there is a continuously increasing need for the separation of the different parts of the organ. In this paper, we propose an automatic segmentation method based on the use of T2W images and atlas images to segment the prostate and to isolate the peripheral and transition zones. The algorithm consists of two stages. First, the target image is registered with each zonal atlas image then the segmentation is obtained by the application of an evidential C-Means clustering. The method was evaluated on a representative and multi-centric image base and yielded mean Dice accuracy values of 0.81, 0.70, and 0.62 for the prostate, the transition zone, and peripheral zone, respectively.
Collapse
Affiliation(s)
- O Chilali
- INSERM, U1189 - ONCO-THAI - Image Assisted Laser Therapy for Oncology, University of Lille, 59000, Lille, France
- Automatic Department, Mouloud Mammeri University, Tizi-Ouzou, Algeria
| | - P Puech
- INSERM, U1189 - ONCO-THAI - Image Assisted Laser Therapy for Oncology, University of Lille, 59000, Lille, France
- CHRU Lille, Radiology Department, Claude Huriez Hospital, 59000, Lille, France
| | - S Lakroum
- INSERM, U1189 - ONCO-THAI - Image Assisted Laser Therapy for Oncology, University of Lille, 59000, Lille, France
| | - M Diaf
- Automatic Department, Mouloud Mammeri University, Tizi-Ouzou, Algeria
| | - S Mordon
- INSERM, U1189 - ONCO-THAI - Image Assisted Laser Therapy for Oncology, University of Lille, 59000, Lille, France
| | - N Betrouni
- INSERM, U1189 - ONCO-THAI - Image Assisted Laser Therapy for Oncology, University of Lille, 59000, Lille, France.
| |
Collapse
|
14
|
Clark T, Zhang J, Baig S, Wong A, Haider MA, Khalvati F. Fully automated segmentation of prostate whole gland and transition zone in diffusion-weighted MRI using convolutional neural networks. J Med Imaging (Bellingham) 2017; 4:041307. [PMID: 29057288 PMCID: PMC5644511 DOI: 10.1117/1.jmi.4.4.041307] [Citation(s) in RCA: 42] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2017] [Accepted: 09/27/2017] [Indexed: 12/24/2022] Open
Abstract
Prostate cancer is a leading cause of cancer-related death among men. Multiparametric magnetic resonance imaging has become an essential part of the diagnostic evaluation of prostate cancer. The internationally accepted interpretation scheme (Pi-Rads v2) has different algorithms for scoring of the transition zone (TZ) and peripheral zone (PZ) of the prostate as tumors can appear different in these zones. Computer-aided detection tools have shown different performances in TZ and PZ and separating these zones for training and detection is essential. The TZ-PZ segmentation which requires the segmentation of prostate whole gland and TZ is typically done manually. We present a fully automatic algorithm for delineation of the prostate gland and TZ in diffusion-weighted imaging (DWI) via a stack of fully convolutional neural networks. The proposed algorithm first detects the slices that contain a portion of prostate gland within the three-dimensional DWI volume and then it segments the prostate gland and TZ automatically. The segmentation stage of the algorithm was applied to DWI images of 104 patients and median Dice similarity coefficients of 0.93 and 0.88 were achieved for the prostate gland and TZ, respectively. The detection of image slices with and without prostate gland had an average accuracy of 0.97.
Collapse
Affiliation(s)
- Tyler Clark
- University of Toronto, Department of Medical Imaging, Sunnybrook Research Institute, Toronto, Canada
| | - Junjie Zhang
- University of Toronto, Department of Medical Imaging, Sunnybrook Research Institute, Toronto, Canada
| | - Sameer Baig
- University of Toronto, Department of Medical Imaging, Sunnybrook Research Institute, Toronto, Canada
| | - Alexander Wong
- University of Waterloo, Department of Systems Design Engineering, Waterloo, Canada
| | - Masoom A. Haider
- University of Toronto, Department of Medical Imaging, Sunnybrook Research Institute, Toronto, Canada
| | - Farzad Khalvati
- University of Toronto, Department of Medical Imaging, Sunnybrook Research Institute, Toronto, Canada
| |
Collapse
|
15
|
Zhen X, Zhang H, Islam A, Bhaduri M, Chan I, Li S. Direct and simultaneous estimation of cardiac four chamber volumes by multioutput sparse regression. Med Image Anal 2017; 36:184-196. [DOI: 10.1016/j.media.2016.11.008] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2016] [Revised: 09/22/2016] [Accepted: 11/22/2016] [Indexed: 12/19/2022]
|
16
|
Wang Q, Kang W, Hu H, Wang B. HOSVD-Based 3D Active Appearance Model: Segmentation of Lung Fields in CT Images. J Med Syst 2016; 40:176. [PMID: 27277277 DOI: 10.1007/s10916-016-0535-0] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2015] [Accepted: 06/01/2016] [Indexed: 11/24/2022]
Abstract
An Active Appearance Model (AAM) is a computer vision model which can be used to effectively segment lung fields in CT images. However, the fitting result is often inadequate when the lungs are affected by high-density pathologies. To overcome this problem, we propose a Higher-order Singular Value Decomposition (HOSVD)-based Three-dimensional (3D) AAM. An evaluation was performed on 310 diseased lungs form the Lung Image Database Consortium Image Collection. Other contemporary AAMs operate directly on patterns represented by vectors, i.e., before applying the AAM to a 3D lung volume,it has to be vectorized first into a vector pattern by some technique like concatenation. However, some implicit structural or local contextual information may be lost in this transformation. According to the nature of the 3D lung volume, HOSVD is introduced to represent and process the lung in tensor space. Our method can not only directly operate on the original 3D tensor patterns, but also efficiently reduce the computer memory usage. The evaluation resulted in an average Dice coefficient of 97.0 % ± 0.59 %, a mean absolute surface distance error of 1.0403 ± 0.5716 mm, a mean border positioning errors of 0.9187 ± 0.5381 pixel, and a Hausdorff Distance of 20.4064 ± 4.3855, respectively. Experimental results showed that our methods delivered significant and better segmentation results, compared with the three other model-based lung segmentation approaches, namely 3D Snake, 3D ASM and 3D AAM.
Collapse
Affiliation(s)
- Qingzhu Wang
- School of Information Engineering, Northeast Dianli University, Jilin, 132012, China.
| | - Wanjun Kang
- School of Information Engineering, Northeast Dianli University, Jilin, 132012, China
| | - Haihui Hu
- School of Information Engineering, Northeast Dianli University, Jilin, 132012, China
| | - Bin Wang
- Jilin Tumor Hospital, Changchun, China
| |
Collapse
|
17
|
Toth R, Sperling D, Madabhushi A. Quantifying Post- Laser Ablation Prostate Therapy Changes on MRI via a Domain-Specific Biomechanical Model: Preliminary Findings. PLoS One 2016; 11:e0150016. [PMID: 27088600 PMCID: PMC4835053 DOI: 10.1371/journal.pone.0150016] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2015] [Accepted: 02/08/2016] [Indexed: 11/18/2022] Open
Abstract
Focal laser ablation destroys cancerous cells via thermal destruction of tissue by a laser. Heat is absorbed, causing thermal necrosis of the target region. It combines the aggressive benefits of radiation treatment (destroying cancer cells) without the harmful side effects (due to its precise localization). MRI is typically used pre-treatment to determine the targeted area, and post-treatment to determine efficacy by detecting necrotic tissue, or tumor recurrence. However, no system exists to quantitatively evaluate the post-treatment effects on the morphology and structure via MRI. To quantify these changes, the pre- and post-treatment MR images must first be spatially aligned. The goal is to quantify (a) laser-induced shape-based changes, and (b) changes in MRI parameters post-treatment. The shape-based changes may be correlated with treatment efficacy, and the quantitative effects of laser treatment over time is currently poorly understood. This work attempts to model changes in gland morphology following laser treatment due to (1) patient alignment, (2) changes due to surrounding organs such as the bladder and rectum, and (3) changes due to the treatment itself. To isolate the treatment-induced shape-based changes, the changes from (1) and (2) are first modeled and removed using a finite element model (FEM). A FEM models the physical properties of tissue. The use of a physical biomechanical model is important since a stated goal of this work is to determine the physical shape-based changes to the prostate from the treatment, and therefore only physical real deformations are to be allowed. A second FEM is then used to isolate the physical, shape-based, treatment-induced changes. We applied and evaluated our model in capturing the laser induced changes to the prostate morphology on eight patients with 3.0 Tesla, T2-weighted MRI, acquired approximately six months following treatment. Our results suggest the laser treatment causes a decrease in prostate volume, which appears to manifest predominantly at the site of ablation. After spatially aligning the images, changes to MRI intensity values are clearly visible at the site of ablation. Our results suggest that our new methodology is able to capture and quantify the degree of laser-induced changes to the prostate. The quantitative measurements reflecting of the deformation changes can be used to track treatment response over time.
Collapse
Affiliation(s)
- Robert Toth
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States of America
- Toth Technology LLC, Long Valley, NJ, United States of America
- * E-mail:
| | - Dan Sperling
- Sperling Prostate Center, Manhattan, NY, United States of America
| | - Anant Madabhushi
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States of America
| |
Collapse
|
18
|
Nouranian S, Ramezani M, Spadinger I, Morris WJ, Salcudean SE, Abolmaesumi P. Learning-Based Multi-Label Segmentation of Transrectal Ultrasound Images for Prostate Brachytherapy. IEEE TRANSACTIONS ON MEDICAL IMAGING 2016; 35:921-932. [PMID: 26599701 DOI: 10.1109/tmi.2015.2502540] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
Low-dose-rate prostate brachytherapy treatment takes place by implantation of small radioactive seeds in and sometimes adjacent to the prostate gland. A patient specific target anatomy for seed placement is usually determined by contouring a set of collected transrectal ultrasound images prior to implantation. Standard-of-care in prostate brachytherapy is to delineate the clinical target anatomy, which closely follows the real prostate boundary. Subsequently, the boundary is dilated with respect to the clinical guidelines to determine a planning target volume. Manual contouring of these two anatomical targets is a tedious task with relatively high observer variability. In this work, we aim to reduce the segmentation variability and planning time by proposing an efficient learning-based multi-label segmentation algorithm. We incorporate a sparse representation approach in our methodology to learn a dictionary of sparse joint elements consisting of images, and clinical and planning target volume segmentation. The generated dictionary inherently captures the relationships among elements, which also incorporates the institutional clinical guidelines. The proposed multi-label segmentation method is evaluated on a dataset of 590 brachytherapy treatment records by 5-fold cross validation. We show clinically acceptable instantaneous segmentation results for both target volumes.
Collapse
|
19
|
Derraz F, Forzy G, Delebarre A, Taleb-Ahmed A, Oussalah M, Peyrodie L, Verclytte S. Prostate contours delineation using interactive directional active contours model and parametric shape prior model. INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING 2015; 31. [PMID: 26009857 DOI: 10.1002/cnm.2726] [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: 10/07/2013] [Revised: 05/17/2015] [Accepted: 05/17/2015] [Indexed: 06/04/2023]
Abstract
Prostate contours delineation on Magnetic Resonance (MR) images is a challenging and important task in medical imaging with applications of guiding biopsy, surgery and therapy. While a fully automated method is highly desired for this application, it can be a very difficult task due to the structure and surrounding tissues of the prostate gland. Traditional active contours-based delineation algorithms are typically quite successful for piecewise constant images. Nevertheless, when MR images have diffuse edges or multiple similar objects (e.g. bladder close to prostate) within close proximity, such approaches have proven to be unsuccessful. In order to mitigate these problems, we proposed a new framework for bi-stage contours delineation algorithm based on directional active contours (DAC) incorporating prior knowledge of the prostate shape. We first explicitly addressed the prostate contour delineation problem based on fast globally DAC that incorporates both statistical and parametric shape prior model. In doing so, we were able to exploit the global aspects of contour delineation problem by incorporating a user feedback in contours delineation process where it is shown that only a small amount of user input can sometimes resolve ambiguous scenarios raised by DAC. In addition, once the prostate contours have been delineated, a cost functional is designed to incorporate both user feedback interaction and the parametric shape prior model. Using data from publicly available prostate MR datasets, which includes several challenging clinical datasets, we highlighted the effectiveness and the capability of the proposed algorithm. Besides, the algorithm has been compared with several state-of-the-art methods.
Collapse
Affiliation(s)
- Foued Derraz
- Telecommunications Laboratory, Technology Faculty, Abou Bekr Belkaïd University, Tlemcen, 13000, Algeria
- Université Nord de France, F-59000, Lille, France
- Unité de Traitement de Signaux Biomédicaux, Faculté de médecine et maïeutique, Lille, France
- LAMIH UMR CNRS 8201, Le Mont Houy, Université de Valenciennes et Cambresis, 59313, Valenciennes, France
| | - Gérard Forzy
- Unité de Traitement de Signaux Biomédicaux, Faculté de médecine et maïeutique, Lille, France
- Groupement des Hopitaux de l'́Institut Catholique de Lille, France
| | - Arnaud Delebarre
- Groupement des Hopitaux de l'́Institut Catholique de Lille, France
| | - Abdelmalik Taleb-Ahmed
- Université Nord de France, F-59000, Lille, France
- LAMIH UMR CNRS 8201, Le Mont Houy, Université de Valenciennes et Cambresis, 59313, Valenciennes, France
| | - Mourad Oussalah
- School of Electronics, Electrical and Computer Engineering, University of Birmingham, Edgbaston, Birmingham, B15 2TT, UK
| | - Laurent Peyrodie
- Université Nord de France, F-59000, Lille, France
- Hautes Etudes dÍngénieur, 13 rue de Toul, 59000, Lille, France
| | | |
Collapse
|
20
|
Gao Y, Chen Y, Ma D, Jiang Y, Herrmann KA, Vincent JA, Dell KM, Drumm ML, Brady-Kalnay SM, Griswold MA, Flask CA, Lu L. Preclinical MR fingerprinting (MRF) at 7 T: effective quantitative imaging for rodent disease models. NMR IN BIOMEDICINE 2015; 28:384-394. [PMID: 25639694 PMCID: PMC4396690 DOI: 10.1002/nbm.3262] [Citation(s) in RCA: 43] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/10/2014] [Revised: 12/18/2014] [Accepted: 12/22/2014] [Indexed: 05/29/2023]
Abstract
High-field preclinical MRI scanners are now commonly used to quantitatively assess disease status and the efficacy of novel therapies in a wide variety of rodent models. Unfortunately, conventional MRI methods are highly susceptible to respiratory and cardiac motion artifacts resulting in potentially inaccurate and misleading data. We have developed an initial preclinical 7.0-T MRI implementation of the highly novel MR fingerprinting (MRF) methodology which has been described previously for clinical imaging applications. The MRF technology combines a priori variation in the MRI acquisition parameters with dictionary-based matching of acquired signal evolution profiles to simultaneously generate quantitative maps of T1 and T2 relaxation times and proton density. This preclinical MRF acquisition was constructed from a fast imaging with steady-state free precession (FISP) MRI pulse sequence to acquire 600 MRF images with both evolving T1 and T2 weighting in approximately 30 min. This initial high-field preclinical MRF investigation demonstrated reproducible and differentiated estimates of in vitro phantoms with different relaxation times. In vivo preclinical MRF results in mouse kidneys and brain tumor models demonstrated an inherent resistance to respiratory motion artifacts as well as sensitivity to known pathology. These results suggest that MRF methodology may offer the opportunity for the quantification of numerous MRI parameters for a wide variety of preclinical imaging applications.
Collapse
Affiliation(s)
- Ying Gao
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106
| | - Yong Chen
- Department of Radiology, Case Western Reserve University, Cleveland, OH 44106
| | - Dan Ma
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106
| | - Yun Jiang
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106
| | - Kelsey A. Herrmann
- Department of Molecular Biology and Microbiology, Case Western Reserve University, Cleveland, OH 44106
- Department of Neurosciences, Case Western Reserve University, Cleveland, OH 44106
| | - Jason A. Vincent
- Department of Molecular Biology and Microbiology, Case Western Reserve University, Cleveland, OH 44106
| | - Katherine M. Dell
- CWRU Center for the Study of Kidney Disease and Biology, MetroHealth Campus, Case Western Reserve University, Cleveland, OH 44109
- Pediatric Institute, Cleveland Clinic Foundation, Cleveland, OH 44106
- Department of Pediatrics, Case Western Reserve University, Cleveland, OH 44106
| | - Mitchell L. Drumm
- Department of Pediatrics, Case Western Reserve University, Cleveland, OH 44106
- Department of Genetics, Case Western Reserve University, Cleveland, OH 44106
| | - Susann M. Brady-Kalnay
- Department of Molecular Biology and Microbiology, Case Western Reserve University, Cleveland, OH 44106
- Department of Neurosciences, Case Western Reserve University, Cleveland, OH 44106
| | - Mark A. Griswold
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106
- Department of Radiology, Case Western Reserve University, Cleveland, OH 44106
| | - Chris A. Flask
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH 44106
- Department of Radiology, Case Western Reserve University, Cleveland, OH 44106
- Department of Pediatrics, Case Western Reserve University, Cleveland, OH 44106
| | - Lan Lu
- Department of Radiology, Case Western Reserve University, Cleveland, OH 44106
- Department of Urology, Case Western Reserve University, Cleveland, OH 44106
| |
Collapse
|
21
|
Rusu M, Bloch BN, Jaffe CC, Genega EM, Lenkinski RE, Rofsky NM, Feleppa E, Madabhushi A. Prostatome: a combined anatomical and disease based MRI atlas of the prostate. Med Phys 2015; 41:072301. [PMID: 24989400 DOI: 10.1118/1.4881515] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
PURPOSE In this work, the authors introduce a novel framework, the anatomically constrained registration (AnCoR) scheme and apply it to create a fused anatomic-disease atlas of the prostate which the authors refer to as the prostatome. The prostatome combines a MRI based anatomic and a histology based disease atlas. Statistical imaging atlases allow for the integration of information across multiple scales and imaging modalities into a single canonical representation, in turn enabling a fused anatomical-disease representation which may facilitate the characterization of disease appearance relative to anatomic structures. While statistical atlases have been extensively developed and studied for the brain, approaches that have attempted to combine pathology and imaging data for study of prostate pathology are not extant. This works seeks to address this gap. METHODS The AnCoR framework optimizes a scoring function composed of two surface (prostate and central gland) misalignment measures and one intensity-based similarity term. This ensures the correct mapping of anatomic regions into the atlas, even when regional MRI intensities are inconsistent or highly variable between subjects. The framework allows for creation of an anatomic imaging and a disease atlas, while enabling their fusion into the anatomic imaging-disease atlas. The atlas presented here was constructed using 83 subjects with biopsy confirmed cancer who had pre-operative MRI (collected at two institutions) followed by radical prostatectomy. The imaging atlas results from mapping thein vivo MRI into the canonical space, while the anatomic regions serve as domain constraints. Elastic co-registration MRI and corresponding ex vivo histology provides "ground truth" mapping of cancer extent on in vivo imaging for 23 subjects. RESULTS AnCoR was evaluated relative to alternative construction strategies that use either MRI intensities or the prostate surface alone for registration. The AnCoR framework yielded a central gland Dice similarity coefficient (DSC) of 90%, and prostate DSC of 88%, while the misalignment of the urethra and verumontanum was found to be 3.45 mm, and 4.73 mm, respectively, which were measured to be significantly smaller compared to the alternative strategies. As might have been anticipated from our limited cohort of biopsy confirmed cancers, the disease atlas showed that most of the tumor extent was limited to the peripheral zone. Moreover, central gland tumors were typically larger in size, possibly because they are only discernible at a much later stage. CONCLUSIONS The authors presented the AnCoR framework to explicitly model anatomic constraints for the construction of a fused anatomic imaging-disease atlas. The framework was applied to constructing a preliminary version of an anatomic-disease atlas of the prostate, the prostatome. The prostatome could facilitate the quantitative characterization of gland morphology and imaging features of prostate cancer. These techniques, may be applied on a large sample size data set to create a fully developed prostatome that could serve as a spatial prior for targeted biopsies by urologists. Additionally, the AnCoR framework could allow for incorporation of complementary imaging and molecular data, thereby enabling their careful correlation for population based radio-omics studies.
Collapse
Affiliation(s)
- Mirabela Rusu
- Case Western Reserve University, Cleveland, Ohio 44106
| | - B Nicolas Bloch
- Boston University School of Medicine, Boston, Massachusetts 02118
| | - Carl C Jaffe
- Boston University School of Medicine, Boston, Massachusetts 02118
| | | | | | | | | | | |
Collapse
|
22
|
Toth R, Traughber B, Ellis R, Kurhanewicz J, Madabhushi A. A Domain Constrained Deformable (DoCD) Model for Co-registration of Pre- and Post-Radiated Prostate MRI. Neurocomputing 2014; 114:3-12. [PMID: 25267873 DOI: 10.1016/j.neucom.2014.01.058] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
External beam radiation treatment (EBRT) is a popular method for treating prostate cancer (CaP) involving destroying tumor cells with ionizing radiation. Following EBRT, biochemical failure has been linked with disease recurrence. However, there is a need for methods for evaluating early treatment related changes to allow for an early intervention in case of incomplete disease response. One method for looking at treatment evaluation is to detect changes in MRI markers on a voxel-by-voxel basis following treatment. Changes in MRI markers may be correlated with disease recurrence and complete or partial response. In order to facilitate voxel-by-voxel imaging related treatment changes, and also to evaluate morphologic changes in the gland post treatment, the pre- and post-radiated MRI must first be brought into spatial alignment via image registration. However, EBRT induces changes in the prostate volume and distortion to the internal anatomy of the prostate following radiation treatment. The internal substructures of the prostate, the central gland (CG) and peripheral zone (PZ), may respond to radiation differently, and their resulting shapes may change drastically. Biomechanical models of the prostate that have been previously proposed tend to focus on how external forces affect the surface of the prostate (not the internals), and assume that the prostate is a volume-preserving entity. In this work we present DoCD, a biomechanical model for automatically registering pre-, post-EBRT MRI with the aim of expressly modeling the (1) changes in volume, and (2) changes to the CG and PZ. DoCD was applied to a cohort of 30 patients and achieved a root mean square error of 2.994 mm, which was statistically significantly better a traditional biomechanical model which did not consider changes to the internal anatomy of the prostate (mean of 5.071 mm).
Collapse
Affiliation(s)
- Robert Toth
- Rutgers, The State University of New Jersey. New Brunswick, NJ ; Case Western Reserve University, Cleveland, OH
| | | | | | - John Kurhanewicz
- Department of Radiology, University of California, San Francisco, CA
| | | |
Collapse
|
23
|
Chilali O, Ouzzane A, Diaf M, Betrouni N. A survey of prostate modeling for image analysis. Comput Biol Med 2014; 53:190-202. [PMID: 25156801 DOI: 10.1016/j.compbiomed.2014.07.019] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2013] [Revised: 06/22/2014] [Accepted: 07/23/2014] [Indexed: 11/18/2022]
Affiliation(s)
- O Chilali
- Inserm U703, 152, rue du Docteur Yersin, Lille University Hospital, 59120 Loos, France; Automatic Department, Mouloud Mammeri University, Tizi-Ouzou, Algeria
| | - A Ouzzane
- Inserm U703, 152, rue du Docteur Yersin, Lille University Hospital, 59120 Loos, France; Urology Department, Claude Huriez Hospital, Lille University Hospital, France
| | - M Diaf
- Automatic Department, Mouloud Mammeri University, Tizi-Ouzou, Algeria
| | - N Betrouni
- Inserm U703, 152, rue du Docteur Yersin, Lille University Hospital, 59120 Loos, France.
| |
Collapse
|
24
|
Qiu W, Yuan J, Ukwatta E, Sun Y, Rajchl M, Fenster A. Dual optimization based prostate zonal segmentation in 3D MR images. Med Image Anal 2014; 18:660-73. [PMID: 24721776 DOI: 10.1016/j.media.2014.02.009] [Citation(s) in RCA: 25] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2013] [Revised: 02/18/2014] [Accepted: 02/24/2014] [Indexed: 10/25/2022]
Abstract
Efficient and accurate segmentation of the prostate and two of its clinically meaningful sub-regions: the central gland (CG) and peripheral zone (PZ), from 3D MR images, is of great interest in image-guided prostate interventions and diagnosis of prostate cancer. In this work, a novel multi-region segmentation approach is proposed to simultaneously segment the prostate and its two major sub-regions from only a single 3D T2-weighted (T2w) MR image, which makes use of the prior spatial region consistency and incorporates a customized prostate appearance model into the segmentation task. The formulated challenging combinatorial optimization problem is solved by means of convex relaxation, for which a novel spatially continuous max-flow model is introduced as the dual optimization formulation to the studied convex relaxed optimization problem with region consistency constraints. The proposed continuous max-flow model derives an efficient duality-based algorithm that enjoys numerical advantages and can be easily implemented on GPUs. The proposed approach was validated using 18 3D prostate T2w MR images with a body-coil and 25 images with an endo-rectal coil. Experimental results demonstrate that the proposed method is capable of efficiently and accurately extracting both the prostate zones: CG and PZ, and the whole prostate gland from the input 3D prostate MR images, with a mean Dice similarity coefficient (DSC) of 89.3±3.2% for the whole gland (WG), 82.2±3.0% for the CG, and 69.1±6.9% for the PZ in 3D body-coil MR images; 89.2±3.3% for the WG, 83.0±2.4% for the CG, and 70.0±6.5% for the PZ in 3D endo-rectal coil MR images. In addition, the experiments of intra- and inter-observer variability introduced by user initialization indicate a good reproducibility of the proposed approach in terms of volume difference (VD) and coefficient-of-variation (CV) of DSC.
Collapse
Affiliation(s)
- Wu Qiu
- Robarts Research Institute, University of Western Ontario, London, ON, Canada.
| | - Jing Yuan
- Robarts Research Institute, University of Western Ontario, London, ON, Canada
| | - Eranga Ukwatta
- Robarts Research Institute, University of Western Ontario, London, ON, Canada; Biomedical Engineering Graduate Program, University of Western Ontario, London, ON, Canada
| | - Yue Sun
- Robarts Research Institute, University of Western Ontario, London, ON, Canada; Biomedical Engineering Graduate Program, University of Western Ontario, London, ON, Canada
| | - Martin Rajchl
- Robarts Research Institute, University of Western Ontario, London, ON, Canada; Biomedical Engineering Graduate Program, University of Western Ontario, London, ON, Canada
| | - Aaron Fenster
- Robarts Research Institute, University of Western Ontario, London, ON, Canada; Biomedical Engineering Graduate Program, University of Western Ontario, London, ON, Canada; Medical Biophysics, University of Western Ontario, London, ON, Canada
| |
Collapse
|
25
|
Matulewicz L, Jansen JFA, Bokacheva L, Vargas HA, Akin O, Fine SW, Shukla-Dave A, Eastham JA, Hricak H, Koutcher JA, Zakian KL. Anatomic segmentation improves prostate cancer detection with artificial neural networks analysis of 1H magnetic resonance spectroscopic imaging. J Magn Reson Imaging 2013; 40:1414-21. [PMID: 24243554 DOI: 10.1002/jmri.24487] [Citation(s) in RCA: 21] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2013] [Accepted: 10/07/2013] [Indexed: 11/06/2022] Open
Abstract
PURPOSE To assess whether an artificial neural network (ANN) model is a useful tool for automatic detection of cancerous voxels in the prostate from (1)H-MRSI datasets and whether the addition of information about anatomical segmentation improves the detection of cancer. MATERIALS AND METHODS The Institutional Review Board approved this HIPAA-compliant study and waived informed consent. Eighteen men with prostate cancer (median age, 55 years; range, 36-71 years) who underwent endorectal MRI/MRSI before radical prostatectomy were included in this study. These patients had at least one cancer area on whole-mount histopathological map and at least one matching MRSI voxel suspicious for cancer detected. Two ANN models for automatic classification of MRSI voxels in the prostate were implemented and compared: model 1, which used only spectra as input, and model 2, which used the spectra plus information from anatomical segmentation. The models were trained, tested and validated using spectra from voxels that the spectroscopist had designated as cancer and that were verified on histopathological maps. RESULTS At ROC analysis, model 2 (AUC = 0.968) provided significantly better (P = 0.03) classification of cancerous voxels than did model 1 (AUC = 0.949). CONCLUSION Automatic analysis of prostate MRSI to detect cancer using ANN model is feasible. Application of anatomical segmentation from MRI as an additional input to ANN improves the accuracy of detecting cancerous voxels from MRSI.
Collapse
Affiliation(s)
- Lukasz Matulewicz
- Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, New York, New York, USA; Department of Radiotherapy and Brachytherapy Planning, Maria Sklodowska-Curie Memorial Cancer Center and Institute of Oncology, Gliwice, Poland
| | | | | | | | | | | | | | | | | | | | | |
Collapse
|