Deep learning-based automatic pipeline for 3D needle localization on intra-procedural 3D MRI.

PURPOSE: Accurate and rapid needle localization on 3D magnetic resonance imaging (MRI) is critical for MRI-guided percutaneous interventions. The current workflow requires manual needle localization on 3D MRI, which is time-consuming and cumbersome. Automatic methods using 2D deep learning networks for needle segmentation require manual image plane localization, while 3D networks are challenged by the need for sufficient training datasets. This work aimed to develop an automatic deep learning-based pipeline for accurate and rapid 3D needle localization on in vivo intra-procedural 3D MRI using a limited training dataset. METHODS: The proposed automatic pipeline adopted Shifted Window (Swin) Transformers and employed a coarse-to-fine segmentation strategy: (1) initial 3D needle feature segmentation with 3D Swin UNEt TRansfomer (UNETR); (2) generation of a 2D reformatted image containing the needle feature; (3) fine 2D needle feature segmentation with 2D Swin Transformer and calculation of 3D needle tip position and axis orientation. Pre-training and data augmentation were performed to improve network training. The pipeline was evaluated via cross-validation with 49 in vivo intra-procedural 3D MR images from preclinical pig experiments. The needle tip and axis localization errors were compared with human intra-reader variation using the Wilcoxon signed rank test, with p < 0.05 considered significant. RESULTS: The average end-to-end computational time for the pipeline was 6 s per 3D volume. The median Dice scores of the 3D Swin UNETR and 2D Swin Transformer in the pipeline were 0.80 and 0.93, respectively. The median 3D needle tip and axis localization errors were 1.48 mm (1.09 pixels) and 0.98°, respectively. Needle tip localization errors were significantly smaller than human intra-reader variation (median 1.70 mm; p < 0.01). CONCLUSION: The proposed automatic pipeline achieved rapid pixel-level 3D needle localization on intra-procedural 3D MRI without requiring a large 3D training dataset and has the potential to assist MRI-guided percutaneous interventions.

Understanding Spatial Correlation Between Multiparametric MRI Performance and Prostate Cancer.

BACKGROUND: Multiparametric MRI (mpMRI) has shown a substantial impact on prostate cancer (PCa) diagnosis. However, the understanding of the spatial correlation between mpMRI performance and PCa location is still limited. PURPOSE: To investigate the association between mpMRI performance and tumor spatial location within the prostate using a prostate sector map, described by Prostate Imaging Reporting and Data System (PI-RADS) v2.1. STUDY TYPE: Retrospective. SUBJECTS: One thousand one hundred forty-three men who underwent mpMRI before radical prostatectomy between 2010 and 2022. FIELD STRENGTH/SEQUENCE: 3.0 T. T2-weighted turbo spin-echo, a single-shot spin-echo EPI sequence for diffusion-weighted imaging, and a gradient echo sequence for dynamic contrast-enhanced MRI sequences. ASSESSMENT: Integrated relative cancer prevalence (rCP), detection rate (DR), and positive predictive value (PPV) maps corresponding to the prostate sector map for PCa lesions were created. The relationship between tumor location and its detection/missing by radiologists on mpMRI compared to WMHP as a reference standard was investigated. STATISTICAL TESTS: A weighted chi-square test was performed to examine the statistical differences for rCP, DR, and PPV of the aggregated sectors within the zone, anterior/posterior, left/right prostate, and different levels of the prostate with a statistically significant level of 0.05. RESULTS: A total of 1665 PCa lesions were identified in 1143 patients, and from those 1060 lesions were clinically significant (cs)PCa tumors (any Gleason score [GS] ≥7). Our sector-based analysis utilizing weighted chi-square tests suggested that the left posterior part of PZ had a high likelihood of missing csPCa lesions at a DR of 67.0%. Aggregated sector analysis indicated that the anterior or apex locations in PZ had the significantly lowest csPCa detection at 67.3% and 71.5%, respectively. DATA CONCLUSION: Spatial characteristics of the per-lesion-based mpMRI performance for diagnosis of PCa were studied. Our results demonstrated that there is a spatial correlation between mpMRI performance and locations of PCa on the prostate. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 2.

Evaluation of Spatial Attentive Deep Learning for Automatic Placental Segmentation on Longitudinal MRI.

BACKGROUND: Automated segmentation of the placenta by MRI in early pregnancy may help predict normal and aberrant placenta function, which could improve the efficiency of placental assessment and the prediction of pregnancy outcomes. An automated segmentation method that works at one gestational age may not transfer effectively to other gestational ages. PURPOSE: To evaluate a spatial attentive deep learning method (SADL) for automated placental segmentation on longitudinal placental MRI scans. STUDY TYPE: Prospective, single-center. SUBJECTS: A total of 154 pregnant women who underwent MRI scans at both 14-18 weeks of gestation and at 19-24 weeks of gestation, divided into training (N = 108), validation (N = 15), and independent testing datasets (N = 31). FIELD STRENGTH/SEQUENCE: A 3 T, T2-weighted half Fourier single-shot turbo spin-echo (T2-HASTE) sequence. ASSESSMENT: The reference standard of placental segmentation was manual delineation on T2-HASTE by a third-year neonatology clinical fellow (B.L.) under the supervision of an experienced maternal-fetal medicine specialist (C.J. with 20 years of experience) and an MRI scientist (K.S. with 19 years of experience). STATISTICAL TESTS: The three-dimensional Dice similarity coefficient (DSC) was used to measure the automated segmentation performance compared to the manual placental segmentation. A paired t-test was used to compare the DSCs between SADL and U-Net methods. A Bland-Altman plot was used to analyze the agreement between manual and automated placental volume measurements. A P value < 0.05 was considered statistically significant. RESULTS: In the testing dataset, SADL achieved average DSCs of 0.83 ± 0.06 and 0.84 ± 0.05 in the first and second MRI, which were significantly higher than those achieved by U-Net (0.77 ± 0.08 and 0.76 ± 0.10, respectively). A total of 6 out of 62 MRI scans (9.6%) had volume measurement differences between the SADL-based automated and manual volume measurements that were out of 95% limits of agreement. DATA CONCLUSIONS: SADL can automatically detect and segment the placenta with high performance in MRI at two different gestational ages. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 2.

Racial Disparities in Quantitative MRI for African American and White Men with Prostate Cancer.

The risk of prostate cancer (PCa) is strongly influenced by race and ethnicity. The purpose of this study is to investigate differences in the diagnostic performance of multiparametric MRI (mpMRI) in African American (AA) and white (W) men. 111 patients (37 AA and 74 W men) were selected from the study's initial cohort of 885 patients after matching age, prostate-specific antigen, and prostate volume. The diagnostic performance of mpMRI was assessed using detection rates (DRs) and positive predictive values (PPVs) with/without combining Ktrans (volume transfer constant) stratified by prostate zones for AA and W sub-cohorts. The DRs of mpMRI for clinically significant PCa (csPCa) lesions in AA and W sub-cohort with PI-RADS scores ≥ 3 were 67.3% vs. 80.3% in the transition zone (TZ; p=0.026) and 81.2% vs. 76.1% in the peripheral zone (PZ; p>0.9). The Ktrans of csPCa in AA men was significantly higher than in W men (0.23±0.08 min-1 vs. 0.19±0.07 min-1; p=0.022). This emphasizes that there are race-related differences in the performance of mpMRI and quantitative MRI measures that are not reflected in age, PSA, and prostate volume.

Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network.

PURPOSE: Contouring clinical target volume (CTV) from medical images is an essential step for radiotherapy (RT) planning. Magnetic resonance imaging (MRI) is used as a standard imaging modality for CTV segmentation in cervical cancer due to its superior soft-tissue contrast. However, the delineation of CTV is challenging as CTV contains microscopic extensions that are not clearly visible even in MR images, resulting in significant contour variability among radiation oncologists depending on their knowledge and experience. In this study, we propose a fully automated deep learning-based method to segment CTV from MR images. METHODS: Our method begins with the bladder segmentation, from which the CTV position is estimated in the axial view. The superior-inferior CTV span is then detected using an Attention U-Net. A CTV-specific region of interest (ROI) is determined, and three-dimensional (3-D) blocks are extracted from the ROI volume. Finally, a CTV segmentation map is computed using a 3-D U-Net from the extracted 3-D blocks. RESULTS: We developed and evaluated our method using 213 MRI scans obtained from 125 patients (183 for training, 30 for test). Our method achieved (mean ± SD) Dice similarity coefficient of 0.85 ± 0.03 and the 95th percentile Hausdorff distance of 3.70 ± 0.35 mm on test cases, outperforming other state-of-the-art methods significantly (p-value < 0.05). Our method also produces an uncertainty map along with the CTV segmentation by employing the Monte Carlo dropout technique to draw physician's attention to the regions with high uncertainty, where careful review and manual correction may be needed. CONCLUSIONS: Experimental results show that the developed method is accurate, fast, and reproducible for contouring CTV from MRI, demonstrating its potential to assist radiation oncologists in alleviating the burden of tedious contouring for RT planning in cervical cancer.

Transfer learning-based approach for automated kidney segmentation on multiparametric MRI sequences.

Purpose: Multiparametric magnetic resonance imaging (mp-MRI) is being investigated for kidney cancer because of better soft tissue contrast ability. The necessity of manual labels makes the development of supervised kidney segmentation algorithms challenging for each mp-MRI protocol. Here, we developed a transfer learning-based approach to improve kidney segmentation on a small dataset of five other mp-MRI sequences. Approach: We proposed a fully automated two-dimensional (2D) attention U-Net model for kidney segmentation on T1 weighted-nephrographic phase contrast enhanced (CE)-MRI (T1W-NG) dataset ( N = 108 ). The pretrained weights of T1W-NG kidney segmentation model transferred to five other distinct mp-MRI sequences model (T2W, T1W-in-phase (T1W-IP), T1W-out-of-phase (T1W-OP), T1W precontrast (T1W-PRE), and T1W-corticomedullary-CE (T1W-CM), N = 50 ) and fine-tuned by unfreezing the layers. The individual model performances were evaluated with and without transfer-learning fivefold cross-validation on average Dice similarity coefficient (DSC), absolute volume difference, Hausdorff distance (HD), and center-of-mass distance (CD) between algorithm generated and manually segmented kidneys. Results: The developed 2D attention U-Net model for T1W-NG produced kidney segmentation DSC of 89.34 ± 5.31 % . Compared with randomly initialized weight models, the transfer learning-based models of five mp-MRI sequences showed average increase of 2.96% in DSC of kidney segmentation ( p = 0.001 to 0.006). Specifically, the transfer-learning approach increased average DSC on T2W from 87.19% to 89.90%, T1W-IP from 83.64% to 85.42%, T1W-OP from 79.35% to 83.66%, T1W-PRE from 82.05% to 85.94%, and T1W-CM from 85.65% to 87.64%. Conclusions: We demonstrate that a pretrained model for automated kidney segmentation of one mp-MRI sequence improved automated kidney segmentation on five other additional sequences.

Fully automated multiorgan segmentation of female pelvic magnetic resonance images with coarse-to-fine convolutional neural network.

PURPOSE: Brachytherapy combined with external beam radiotherapy (EBRT) is the standard treatment for cervical cancer and has been shown to improve overall survival rates compared to EBRT only. Magnetic resonance (MR) imaging is used for radiotherapy (RT) planning and image guidance due to its excellent soft tissue image contrast. Rapid and accurate segmentation of organs at risk (OAR) is a crucial step in MR image-guided RT. In this paper, we propose a fully automated two-step convolutional neural network (CNN) approach to delineate multiple OARs from T2-weighted (T2W) MR images. METHODS: We employ a coarse-to-fine segmentation strategy. The coarse segmentation step first identifies the approximate boundary of each organ of interest and crops the MR volume around the centroid of organ-specific region of interest (ROI). The cropped ROI volumes are then fed to organ-specific fine segmentation networks to produce detailed segmentation of each organ. A three-dimensional (3-D) U-Net is trained to perform the coarse segmentation. For the fine segmentation, a 3-D Dense U-Net is employed in which a modified 3-D dense block is incorporated into the 3-D U-Net-like network to acquire inter and intra-slice features and improve information flow while reducing computational complexity. Two sets of T2W MR images (221 cases for MR1 and 62 for MR2) were taken with slightly different imaging parameters and used for our network training and test. The network was first trained on MR1 which was a larger sample set. The trained model was then transferred to the MR2 domain via a fine-tuning approach. Active learning strategy was utilized for selecting the most valuable data from MR2 to be included in the adaptation via transfer learning. RESULTS: The proposed method was tested on 20 MR1 and 32 MR2 test sets. Mean ± SD dice similarity coefficients are 0.93 ± 0.04, 0.87 ± 0.03, and 0.80 ± 0.10 on MR1 and 0.94 ± 0.05, 0.88 ± 0.04, and 0.80 ± 0.05 on MR2 for bladder, rectum, and sigmoid, respectively. Hausdorff distances (95th percentile) are 4.18 ± 0.52, 2.54 ± 0.41, and 5.03 ± 1.31 mm on MR1 and 2.89 ± 0.33, 2.24 ± 0.40, and 3.28 ± 1.08 mm on MR2, respectively. The performance of our method is superior to other state-of-the-art segmentation methods. CONCLUSIONS: We proposed a two-step CNN approach for fully automated segmentation of female pelvic MR bladder, rectum, and sigmoid from T2W MR volume. Our experimental results demonstrate that the developed method is accurate, fast, and reproducible, and outperforms alternative state-of-the-art methods for OAR segmentation significantly (p < 0.05).

Detection of COVID-19 from chest x-ray images using transfer learning.

Purpose: The objective of this study is to develop and evaluate a fully automated, deep learning-based method for detection of COVID-19 infection from chest x-ray images. Approach: The proposed model was developed by replacing the final classifier layer in DenseNet201 with a new network consisting of global averaging layer, batch normalization layer, a dense layer with ReLU activation, and a final classification layer. Then, we performed an end-to-end training using the initial pretrained weights on all the layers. Our model was trained using a total of 8644 images with 4000 images each in normal and pneumonia cases and 644 in COVID-19 cases representing a large real dataset. The proposed method was evaluated based on accuracy, sensitivity, specificity, ROC curve, and F 1 -score using a test dataset comprising 1729 images (129 COVID-19, 800 normal, and 800 pneumonia). As a benchmark, we also compared the results of our method with those of seven state-of-the-art pretrained models and with a lightweight CNN architecture designed from scratch. Results: The proposed model based on DenseNet201 was able to achieve an accuracy of 94% in detecting COVID-19 and an overall accuracy of 92.19%. The model was able to achieve an AUC of 0.99 for COVID-19, 0.97 for normal, and 0.97 for pneumonia. The model was able to outperform alternative models in terms of overall accuracy, sensitivity, and specificity. Conclusions: Our proposed automated diagnostic model yielded an accuracy of 94% in the initial screening of COVID-19 patients and an overall accuracy of 92.19% using chest x-ray images.

Quantitative Prostate MRI.

Prostate MRI is reported in clinical practice using the Prostate Imaging and Data Reporting System (PI-RADS). PI-RADS aims to standardize, as much as possible, the acquisition, interpretation, reporting, and ultimately the performance of prostate MRI. PI-RADS relies upon mainly subjective analysis of MR imaging findings, with very few incorporated quantitative features. The shortcomings of PI-RADS are mainly: low-to-moderate interobserver agreement and modest accuracy for detection of clinically significant tumors in the transition zone. The use of a more quantitative analysis of prostate MR imaging findings is therefore of interest. Quantitative MR imaging features including: tumor size and volume, tumor length of capsular contact, tumor apparent diffusion coefficient (ADC) metrics, tumor T1 and T2 relaxation times, tumor shape, and texture analyses have all shown value for improving characterization of observations detected on prostate MRI and for differentiating between tumors by their pathological grade and stage. Quantitative analysis may therefore improve diagnostic accuracy for detection of cancer and could be a noninvasive means to predict patient prognosis and guide management. Since quantitative analysis of prostate MRI is less dependent on an individual users' assessment, it could also improve interobserver agreement. Semi- and fully automated analysis of quantitative (radiomic) MRI features using artificial neural networks represent the next step in quantitative prostate MRI and are now being actively studied. Validation, through high-quality multicenter studies assessing diagnostic accuracy for clinically significant prostate cancer detection, in the domain of quantitative prostate MRI is needed. This article reviews advances in quantitative prostate MRI, highlighting the strengths and limitations of existing and emerging techniques, as well as discussing opportunities and challenges for evaluation of prostate MRI in clinical practice when using quantitative assessment. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

Machine Learning-Based Segmentation of Left Ventricular Myocardial Fibrosis from Magnetic Resonance Imaging.

PURPOSE OF REVIEW: Myocardial fibrosis (MF) arises due to myocardial infarction and numerous cardiac diseases. MF may lead to several heart disorders, such as heart failure, arrhythmias, and ischemia. Cardiac magnetic resonance (CMR) imaging techniques, such as late gadolinium enhancement (LGE) CMR, enable non-invasive assessment of MF in the left ventricle (LV). Manual assessment of MF on CMR is a tedious and time-consuming task that is subject to high observer variability. Automated segmentation and quantification of MF is important for risk stratification and treatment planning in patients with heart disorders. This article aims to review the machine learning (ML)-based methodologies developed for MF quantification in the LV using CMR images. RECENT FINDINGS: With the availability of relatively large labeled datasets supervised learning methods based on both conventional ML and state-of-the-art deep learning (DL) methods have been successfully applied for automated segmentation of MF. The incorporation of ML algorithms into imaging techniques such as 3D LGE CMR permits fast characterization of MF on CMR imaging and may enhance the diagnosis and prognosis of patients with heart disorders. Concurrently, the studies using cine CMR images have revealed that accurate segmentation of MF on non-contrast CMR imaging might be possible. The application of ML/DL tools in CMR image interpretation is likely to result in accurate and efficient quantification of MF.

Automated classification of solid renal masses on contrast-enhanced computed tomography images using convolutional neural network with decision fusion.

OBJECTIVES: To develop a deep learning-based method for automated classification of renal cell carcinoma (RCC) from benign solid renal masses using contrast-enhanced computed tomography (CECT) images. METHODS: This institutional review board-approved retrospective study evaluated CECT in 315 patients with 77 benign (57 oncocytomas, and 20 fat-poor angiomyolipoma) and 238 malignant (RCC: 123 clear cell, 69 papillary, and 46 chromophobe subtypes) tumors identified consecutively between 2015 and 2017. We employed a decision fusion-based model to aggregate slice level predictions determined by convolutional neural network (CNN) via a majority voting system to evaluate renal masses on CECT. The CNN-based model was trained using 7023 slices with renal masses manually extracted from CECT images of 155 patients, cropped automatically around kidneys, and augmented artificially. We also examined the fully automated approach for renal mass evaluation on CECT. Moreover, a 3D CNN was trained and tested using the same datasets and the obtained results were compared with those acquired from slice-wise algorithms. RESULTS: For differentiation of RCC versus benign solid masses, the semi-automated majority voting-based CNN algorithm achieved accuracy, precision, and recall of 83.75%, 89.05%, and 91.73% using 160 test cases, respectively. Fully automated pipeline yielded accuracy, precision, and recall of 77.36%, 85.92%, and 87.22% on the same test cases, respectively. 3D CNN reported accuracy, precision, and recall of 79.24%, 90.32%, and 84.21% using 160 test cases, respectively. CONCLUSIONS: A semi-automated majority voting CNN-based methodology enabled accurate classification of RCC from benign neoplasms among solid renal masses on CECT. KEY POINTS: • Our proposed semi-automated majority voting CNN-based algorithm achieved accuracy of 83.75% for the diagnosis of RCC from benign solid renal masses on CECT images. • A fully automated CNN-based methodology classified solid renal masses with moderate accuracy of 77.36% using the same test images. • Employing 3D CNN-based methodology yielded slightly lower accuracy for renal mass classification compared with the semi- automated 2D CNN-based algorithm (79.24%).

Fully automated segmentation of left ventricular scar from 3D late gadolinium enhancement magnetic resonance imaging using a cascaded multi-planar U-Net (CMPU-Net).

PURPOSE: Three-dimensional (3D) late gadolinium enhancement magnetic resonance (LGE-MR) imaging enables the quantification of myocardial scar at high resolution with unprecedented volumetric visualization. Automated segmentation of myocardial scar is critical for the potential clinical translation of this technique given the number of tomographic images acquired. METHODS: In this paper, we describe the development of cascaded multi-planar U-Net (CMPU-Net) to efficiently segment the boundary of the left ventricle (LV) myocardium and scar from 3D LGE-MR images. In this approach, two subnets, each containing three U-Nets, were cascaded to first segment the LV myocardium and then segment the scar within the presegmented LV myocardium. The U-Nets were trained separately using two-dimensional (2D) slices extracted from axial, sagittal, and coronal slices of 3D LGE-MR images. We used 3D LGE-MR images from 34 subjects with chronic ischemic cardiomyopathy. The U-Nets were trained using 8430 slices, extracted in three orthogonal directions from 18 images. In the testing phase, the outputs of U-Nets of each subnet were combined using the majority voting system for final label prediction of each voxel in the image. The developed method was tested for accuracy by comparing its results to manual segmentations of LV myocardium and LV scar from 7250 slices extracted from 16 3D LGE-MR images. Our method was also compared to numerous alternative methods based on machine learning, energy minimization, and intensity-thresholds. RESULTS: Our algorithm reported a mean dice similarity coefficient (DSC), absolute volume difference (AVD), and Hausdorff distance (HD) of 85.14% ± 3.36%, 43.72 ± 27.18 cm3 , and 19.21 ± 4.74 mm for determining the boundaries of LV myocardium from LGE-MR images. Our method also yielded a mean DSC, AVD, and HD of 88.61% ± 2.54%, 9.33 ± 7.24 cm3 , and 17.04 ± 9.93 mm for LV scar segmentation on the unobserved test dataset. Our method significantly outperformed the alternative techniques in segmentation accuracy (P < 0.05). CONCLUSIONS: The CMPU-Net method provided fully automated segmentation of LV scar from 3D LGE-MR images and outperformed the alternative techniques.

Fully automated localization of prostate peripheral zone tumors on apparent diffusion coefficient map MR images using an ensemble learning method.

BACKGROUND: Accurate detection and localization of prostate cancer (PCa) in men undergoing prostate MRI is a fundamental step for future targeted prostate biopsies and treatment planning. Fully automated localization of peripheral zone (PZ) PCa using the apparent diffusion coefficient (ADC) map might be clinically useful. PURPOSE/HYPOTHESIS: To describe automated localization of PCa in the PZ on ADC map MR images using an ensemble U-Net-based model. STUDY TYPE: Retrospective, case-control. POPULATION: In all, 226 patients (154 and 72 patients with and without clinically significant PZ PCa, respectively), training, and testing was performed using dataset images of 146 and 80 patients, respectively. FIELD STRENGTH: 3T, ADC maps. SEQUENCE: ADC map. ASSESSMENT: The ground truth was established by manual delineation of the prostate and prostate PZ tumors on ADC maps by dedicated radiologists using MRI-radical prostatectomy maps as a reference standard. Statistical Tests: Performance of the ensemble model was evaluated using Dice similarity coefficient (DSC), sensitivity, and specificity metrics on a per-slice basis. Receiver operating characteristic (ROC) curve and area under the curve (AUC) were employed as well. The paired t-test was used to test the differences between the performances of constituent networks of the ensemble model. RESULTS: Our developed algorithm yielded DSC, sensitivity, and specificity of 86.72% ± 9.93%, 85.76% ± 23.33%, and 76.44% ± 23.70%, respectively (mean ± standard deviation) on 80 test cases consisting of 41 and 39 instances from patients with and without clinically significant tumors including 660 extracted 2D slices. AUC was reported as 0.779. DATA CONCLUSION: An ensemble U-Net-based approach can accurately detect and segment PCa in the PZ from ADC map MR prostate images. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2020;51:1223-1234.

Automated segmentation of prostate zonal anatomy on T2-weighted (T2W) and apparent diffusion coefficient (ADC) map MR images using U-Nets.

PURPOSE: Accurate regional segmentation of the prostate boundaries on magnetic resonance (MR) images is a fundamental requirement before automated prostate cancer diagnosis can be achieved. In this paper, we describe a novel methodology to segment prostate whole gland (WG), central gland (CG), and peripheral zone (PZ), where PZ + CG = WG, from T2W and apparent diffusion coefficient (ADC) map prostate MR images. METHODS: We designed two similar models each made up of two U-Nets to delineate the WG, CG, and PZ from T2W and ADC map MR images, separately. The U-Net, which is a modified version of a fully convolutional neural network, includes contracting and expanding paths with convolutional, pooling, and upsampling layers. Pooling and upsampling layers help to capture and localize image features with a high spatial consistency. We used a dataset consisting of 225 patients (combining 153 and 72 patients with and without clinically significant prostate cancer) imaged with multiparametric MRI at 3 Tesla. RESULTS AND CONCLUSION: Our proposed model for prostate zonal segmentation from T2W was trained and tested using 1154 and 1587 slices of 100 and 125 patients, respectively. Median of Dice similarity coefficient (DSC) on test dataset for prostate WG, CG, and PZ were 95.33 ± 7.77%, 93.75 ± 8.91%, and 86.78 ± 3.72%, respectively. Designed model for regional prostate delineation from ADC map images was trained and validated using 812 and 917 slices from 100 and 125 patients. This model yielded a median DSC of 92.09 ± 8.89%, 89.89 ± 10.69%, and 86.1 ± 9.56% for prostate WG, CG, and PZ on test samples, respectively. Further investigation indicated that the proposed algorithm reported high DSC for prostate WG segmentation from both T2W and ADC map MR images irrespective of WG size. In addition, segmentation accuracy in terms of DSC does not significantly vary among patients with or without significant tumors. SIGNIFICANCE: We describe a method for automated prostate zonal segmentation using T2W and ADC map MR images independent of prostate size and the presence or absence of tumor. Our results are important in terms of clinical perspective as fully automated methods for ADC map images, which are considered as one of the most important sequences for prostate cancer detection in the PZ and CG, have not been reported previously.

Convolutional neural network-based approach for segmentation of left ventricle myocardial scar from 3D late gadolinium enhancement MR images.

PURPOSE: Accurate three-dimensional (3D) segmentation of myocardial replacement fibrosis (i.e., scar) is emerging as a potentially valuable tool for risk stratification and procedural planning in patients with ischemic cardiomyopathy. The main purpose of this study was to develop a semiautomated method using a 3D convolutional neural network (CNN)-based for the segmentation of left ventricle (LV) myocardial scar from 3D late gadolinium enhancement magnetic resonance (LGE-MR) images. METHODS: Our proposed CNN is built upon several convolutional and pooling layers aimed at choosing appropriate features from LGE-MR images to distinguish between myocardial scar and healthy tissues of the left ventricle. In contrast to previous methods that consider image intensity as the sole feature, CNN-based algorithms have the potential to improve the accuracy of scar segmentation through the creation of unconventional features that separate scar from normal myocardium in the feature space. The first step of our pipeline was to manually delineate the left ventricular myocardium, which was used as the region of interest for scar segmentation. Our developed algorithm was trained using 265,220 volume patches extracted from ten 3D LGE-MR images, then was validated on 450,454 patches from a testing dataset of 24 3D LGE-MR images, all obtained from patients with chronic myocardial infarction. We evaluated our method in the context of several alternative methods by comparing algorithm-generated segmentations to manual delineations performed by experts. RESULTS: Our CNN-based method reported an average Dice similarity coefficient (DSC) and Jaccard Index (JI) of 93.63% ± 2.6% and 88.13% ± 4.70%. In comparison to several previous methods, including K-nearest neighbor (KNN), hierarchical max flow (HMF), full width at half maximum (FWHM), and signal threshold to reference mean (STRM), the developed algorithm reported significantly higher accuracy for DSC with a P-value less than 0.0001. CONCLUSIONS: Our experimental results demonstrated that our CNN-based proposed method yielded the highest accuracy of all contemporary LV myocardial scar segmentation methodologies, inclusive of the most widely used signal intensity-based methods, such as FWHM and STRM. To our knowledge, this is the first description of LV myocardial scar tissue segmentation from 3D LGE-MR images using a CNN-based method.

Virtual electrophysiological study as a tool for evaluating efficacy of MRI techniques in predicting adverse arrhythmic events in ischemic patients.

Myocardial infarct (MI) related indices determined by late gadolinium enhancement (LGE) MRI have been widely investigated in determining patients suitable for implantable cardiovascular-defibrillator (ICD) therapy to complement left ventricular ejection fraction (LV EF). In comparison to LGE-MRI using inversion-recovery fast-gradient-echo (IR-FGRE), T1 mapping techniques, such as multi contrast late enhancement (MCLE), have been shown to provide more quantitative and reproducible estimates of infarct regions. The objective of this study is to use individualized heart computer models in determining the efficacy of IR-FGRE and MCLE techniques in predicting the occurrence of post-MI ventricular tachycardia (VT). Twenty-seven patients with MI underwent LGE-MRI using IR-FGRE and MCLE prior to ICD implantation and were followed up for 6-46 months. Individualized image-based computational models were built separately for each imaging technique; simulations of propensity to VT were conducted with each model. The imaging methods were evaluated by comparing simulated inducibility of VT to clinical outcome (appropriate ICD therapy) in patients. Twelve patients had at least one appropriate ICD therapy for VT at follow-up. For both MCLE and IR-FGRE, the outcomes of the simulations of VT were significantly associated with the events of appropriate ICD therapy. This indicates that, as compared to conventional measurements such as LV EF, the simulations of VT corresponding to both MCLE and IR-FGRE were more sensitive in predicting appropriate ICD therapy in post-MI patients.