Convolutional Neural Net Learning Can Achieve Production-Level Brain Segmentation in Structural Magnetic Resonance Imaging.
Ontology highlight
ABSTRACT:
SUBMITTER: Fletcher E
PROVIDER: S-EPMC8255694 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Objectives: We developed a 3D U-Net-based deep convolutional neural network for the automatic segmentation of the vertebral cortex. The purpose of this study was to evaluate the accuracy of the 3D U-Net deep learning model. Methods: In this study, a fully automated vertebral cortical segmentation method with 3D U-Net was developed, and ten-fold cross-validation was employed. Through data augmentation, we obtained 1,672 3D images of chest CT scans. Segmentation was performed using a conventional image processing method and manually corrected by a senior radiologist to create the gold standard. To compare the segmentation performance, 3D U-Net, Res U-Net, Ki U-Net, and Seg Net were used to segment the vertebral cortex in CT images. The segmentation performance of 3D U-Net and the other three deep learning algorithms was evaluated using DSC, mIoU, MPA, and FPS. Results: The DSC, mIoU, and MPA of 3D U-Net are better than the other three strategies, reaching 0.71 ± 0.03, 0.74 ± 0.08, and 0.83 ± 0.02, respectively, indicating promising automated segmentation results. The FPS is slightly lower than that of Seg Net (23.09 ± 1.26 vs. 30.42 ± 3.57). Conclusion: Cortical bone can be effectively segmented based on 3D U-net.
| S-EPMC9626964 | biostudies-literature
Project description:PurposeAccurate delineation of the prostate gland and intraprostatic lesions (ILs) is essential for prostate cancer dose-escalated radiation therapy. The aim of this study was to develop a sophisticated deep neural network approach to magnetic resonance image analysis that will help IL detection and delineation for clinicians.Methods and materialsWe trained and evaluated mask region-based convolutional neural networks to perform the prostate gland and IL segmentation. There were 2 cohorts in this study: 78 public patients (cohort 1) and 42 private patients from our institution (cohort 2). Prostate gland segmentation was performed using T2-weighted images (T2WIs), although IL segmentation was performed using T2WIs and coregistered apparent diffusion coefficient maps with prostate patches cropped out. The IL segmentation model was extended to select 5 highly suspicious volumetric lesions within the entire prostate.ResultsThe mask region-based convolutional neural networks model was able to segment the prostate with dice similarity coefficient (DSC) of 0.88 ± 0.04, 0.86 ± 0.04, and 0.82 ± 0.05; sensitivity (Sens.) of 0.93, 0.95, and 0.95; and specificity (Spec.) of 0.98, 0.85, and 0.90. However, ILs were segmented with DSC of 0.62 ± 0.17, 0.59 ± 0.14, and 0.38 ± 0.19; Sens. of 0.55 ± 0.30, 0.63 ± 0.28, and 0.22 ± 0.24; and Spec. of 0.974 ± 0.010, 0.964 ± 0.015, and 0.972 ± 0.015 in public validation/public testing/private testing patients when trained with patients from cohort 1 only. When trained with patients from both cohorts, the values were as follows: DSC of 0.64 ± 0.11, 0.56 ± 0.15, and 0.46 ± 0.15; Sens. of 0.57 ± 0.23, 0.50 ± 0.28, and 0.33 ± 0.17; and Spec. of 0.980 ± 0.009, 0.969 ± 0.016, and 0.977 ± 0.013.ConclusionsOur research framework is able to perform as an end-to-end system that automatically segmented the prostate gland and identified and delineated highly suspicious ILs within the entire prostate. Therefore, this system demonstrated the potential for assisting the clinicians in tumor delineation.
| S-EPMC7280293 | biostudies-literature
Project description:BackgroundCine Displacement Encoding with Stimulated Echoes (DENSE) facilitates the quantification of myocardial deformation, by encoding tissue displacements in the cardiovascular magnetic resonance (CMR) image phase, from which myocardial strain can be estimated with high accuracy and reproducibility. Current methods for analyzing DENSE images still heavily rely on user input, making this process time-consuming and subject to inter-observer variability. The present study sought to develop a spatio-temporal deep learning model for segmentation of the left-ventricular (LV) myocardium, as spatial networks often fail due to contrast-related properties of DENSE images.Methods2D + time nnU-Net-based models have been trained to segment the LV myocardium from DENSE magnitude data in short- and long-axis images. A dataset of 360 short-axis and 124 long-axis slices was used to train the networks, from a combination of healthy subjects and patients with various conditions (hypertrophic and dilated cardiomyopathy, myocardial infarction, myocarditis). Segmentation performance was evaluated using ground-truth manual labels, and a strain analysis using conventional methods was performed to assess strain agreement with manual segmentation. Additional validation was performed using an externally acquired dataset to compare the inter- and intra-scanner reproducibility with respect to conventional methods.ResultsSpatio-temporal models gave consistent segmentation performance throughout the cine sequence, while 2D architectures often failed to segment end-diastolic frames due to the limited blood-to-myocardium contrast. Our models achieved a DICE score of 0.83 ± 0.05 and a Hausdorff distance of 4.0 ± 1.1 mm for short-axis segmentation, and 0.82 ± 0.03 and 7.9 ± 3.9 mm respectively for long-axis segmentations. Strain measurements obtained from automatically estimated myocardial contours showed good to excellent agreement with manual pipelines, and remained within the limits of inter-user variability estimated in previous studies.ConclusionSpatio-temporal deep learning shows increased robustness for the segmentation of cine DENSE images. It provides excellent agreement with manual segmentation for strain extraction. Deep learning will facilitate the analysis of DENSE data, bringing it one step closer to clinical routine.
| S-EPMC10061808 | biostudies-literature
Project description:Convolutional neural networks (CNNs) have recently been popular for classification and segmentation through numerous network architectures offering a substantial performance improvement. Their value has been particularly appreciated in the domain of biomedical applications, where even a small improvement in the predicted segmented region (e.g., a malignancy) compared to the ground truth can potentially lead to better diagnosis or treatment planning. Here, we introduce a novel architecture, namely the Overall Convolutional Network (O-Net), which takes advantage of different pooling levels and convolutional layers to extract more deeper local and containing global context. Our quantitative results on 2D images from two distinct datasets show that O-Net can achieve a higher dice coefficient when compared to either a U-Net or a Pyramid Scene Parsing Net. We also look into the stability of results for training and validation sets which can show the robustness of model compared with new datasets. In addition to comparison to the decoder, we use different encoders including simple, VGG Net, and ResNet. The ResNet encoder could help to improve the results in most of the cases.
| S-EPMC8286447 | biostudies-literature
Project description:BackgroundMagnetic resonance imaging (MRI) noninvasively quantifies disc structure but requires segmentation that is both time intensive and susceptible to human error. Recent advances in neural networks can improve on manual segmentation. The aim of this study was to establish a method for automatic slice-wise segmentation of 3D disc volumes from subjects with a wide range of age and degrees of disc degeneration. A U-Net convolutional neural network was trained to segment 3D T1-weighted spine MRI.MethodsLumbar spine MRIs were acquired from 43 subjects (23-83 years old) and manually segmented. A U-Net architecture was trained using the TensorFlow framework. Two rounds of model tuning were performed. The performance of the model was measured using a validation set that did not cross over from the training set. The model version with the best Dice similarity coefficient (DSC) was selected in each tuning round. After model development was complete and a final U-Net model was selected, performance of this model was compared between disc levels and degeneration grades.ResultsPerformance of the final model was equivalent to manual segmentation, with a mean DSC = 0.935 ± 0.014 for degeneration grades I-IV. Neither the manual segmentation nor the U-Net model performed as well for grade V disc segmentation. Compared with the baseline model at the beginning of round 1, the best model had fewer filters/parameters (75%), was trained using only slices with at least one disc-labeled pixel, applied contrast stretching to its input images, and used a greater dropout rate.ConclusionThis study successfully trained a U-Net model for automatic slice-wise segmentation of 3D disc volumes from populations with a wide range of ages and disc degeneration. The final trained model is available to support scientific use.
| S-EPMC11372286 | biostudies-literature
Project description:Due to the high heterogeneity of brain tumors, automatic segmentation of brain tumors remains a challenging task. In this paper, we propose RDAU-Net by adding dilated feature pyramid blocks with 3D CBAM blocks and inserting 3D CBAM blocks after skip-connection layers. Moreover, a CBAM with channel attention and spatial attention facilitates the combination of more expressive feature information, thereby leading to more efficient extraction of contextual information from images of various scales. The performance was evaluated on the Multimodal Brain Tumor Segmentation (BraTS) challenge data. Experimental results show that RDAU-Net achieves state-of-the-art performance. The Dice coefficient for WT on the BraTS 2019 dataset exceeded the baseline value by 9.2%.
| S-EPMC8924611 | biostudies-literature
Project description:Early detection is critical for effective management of Alzheimer's disease (AD) and screening for mild cognitive impairment (MCI) is common practice. Among several deep-learning techniques that have been applied to assessing structural brain changes on magnetic resonance imaging (MRI), convolutional neural network (CNN) has gained popularity due to its superb efficiency in automated feature learning with the use of a variety of multilayer perceptrons. Meanwhile, ensemble learning (EL) has shown to be beneficial in the robustness of learning-system performance via integrating multiple models. Here, we proposed a classifier ensemble developed by combining CNN and EL, i.e., the CNN-EL approach, to identify subjects with MCI or AD using MRI: i.e., classification between (1) AD and healthy cognition (HC), (2) MCIc (MCI patients who will convert to AD) and HC, and (3) MCIc and MCInc (MCI patients who will not convert to AD). For each binary classification task, a large number of CNN models were trained applying a set of sagittal, coronal, or transverse MRI slices; these CNN models were then integrated into a single ensemble. Performance of the ensemble was evaluated using stratified fivefold cross-validation method for 10 times. The number of the intersection points determined by the most discriminable slices separating two classes in a binary classification task among the sagittal, coronal, and transverse slice sets, transformed into the standard Montreal Neurological Institute (MNI) space, acted as an indicator to assess the ability of a brain region in which the points were located to classify AD. Thus, the brain regions with most intersection points were considered as those mostly contributing to the early diagnosis of AD. The result revealed an accuracy rate of 0.84 ± 0.05, 0.79 ± 0.04, and 0.62 ± 0.06, respectively, for classifying AD vs. HC, MCIc vs. HC, and MCIc vs. MCInc, comparable to previous reports and a 3D deep learning approach (3D-SENet) based on a more state-of-the-art and popular Squeeze-and-Excitation Networks model using channel attention mechanism. Notably, the intersection points accurately located the medial temporal lobe and several other structures of the limbic system, i.e., brain regions known to be struck early in AD. More interestingly, the classifiers disclosed multiple patterned MRI changes in the brain in AD and MCIc, involving these key regions. These results suggest that as a data-driven method, the combined CNN and EL approach can locate the most discriminable brain regions indicated by the trained ensemble model while the generalization ability of the ensemble model was maximized to successfully capture AD-related brain variations early in the disease process; it can also provide new insights into understanding the complex heterogeneity of whole-brain MRI changes in AD. Further research is needed to examine the clinical implication of the finding, capability of the advocated CNN-EL approach to help understand and evaluate an individual subject's disease status, symptom burden and progress, and the generalizability of the advocated CNN-EL approach to locate the most discriminable brain regions in the detection of other brain disorders such as schizophrenia, autism, and severe depression, in a data-driven way.
| S-EPMC7238823 | biostudies-literature
Project description:Magnetic resonance imaging (MRI) provides detailed anatomical images of the prostate and its zones. It has a crucial role for many diagnostic applications. Automatic segmentation such as that of the prostate and prostate zones from MR images facilitates many diagnostic and therapeutic applications. However, the lack of a clear prostate boundary, prostate tissue heterogeneity, and the wide interindividual variety of prostate shapes make this a very challenging task. To address this problem, we propose a new neural network to automatically segment the prostate and its zones. We term this algorithm Dense U-net as it is inspired by the two existing state-of-the-art tools-DenseNet and U-net. We trained the algorithm on 141 patient datasets and tested it on 47 patient datasets using axial T2-weighted images in a four-fold cross-validation fashion. The networks were trained and tested on weakly and accurately annotated masks separately to test the hypothesis that the network can learn even when the labels are not accurate. The network successfully detects the prostate region and segments the gland and its zones. Compared with U-net, the second version of our algorithm, Dense-2 U-net, achieved an average Dice score for the whole prostate of 92.1± 0.8% vs. 90.7 ± 2%, for the central zone of [Formula: see text]% vs. [Formula: see text] %, and for the peripheral zone of 78.1± 2.5% vs. [Formula: see text]%. Our initial results show Dense-2 U-net to be more accurate than state-of-the-art U-net for automatic segmentation of the prostate and prostate zones.
| S-EPMC7459118 | biostudies-literature
Project description:PurposeTo develop and validate a fully automated deep-learning-based tool for segmentation of the human eyeball using a three-dimensional (3D) U-Net, compare its performance to semiautomatic segmentation ground truth and a two-dimensional (2D) U-Net, and analyze age and sex differences in eyeball volume, as well as gaze-dependent volume consistency in normal subjects.MethodsWe retrospectively collected 474 magnetic resonance imaging (MRI) scans, including different gazing scans, from 119 patients. A 10-fold cross-validation was applied to separate the dataset into training, test, and validation sets for both the 3D U-Net and 2D U-Net. Performance accuracy was measured using four quantitative metrics compared to the ground truth, and Bland-Altman plot analysis was conducted. Age and sex differences in eyeball volume and variability in eyeball volume differences across gazing directions were analyzed.ResultsThe 3D U-Net outperformed the 2D U-Net with mean accuracy scores >0.95, showing acceptable agreement in the Bland-Altman plot analysis despite a tendency for slight overestimation (mean difference = -0.172 cm³). Significant sex differences and age effects on eyeball volume were observed for both methods (P < 0.05). No significant volume differences were found between the segmentation methods or within each method for the different gazing directions. Significant differences in performance accuracy were identified among the five gazing directions, with the upward direction showing a notably lower performance.ConclusionsOur study demonstrated the effectiveness of 3D U-Net human eyeball volume segmentation using T2-weighted MRI. The robustness and reliability of 3D U-Net across diverse populations and gaze directions support enhanced ophthalmic diagnosis and treatment strategies.Translational relevanceOur findings demonstrate the feasibility of using the proposed 3D U-Net model for the automatic segmentation of the human eyeball, with potential applications in various ophthalmic research fields that require the analysis of 3D geometric eye globe shapes or eye movement detection.
| S-EPMC10664726 | biostudies-literature
Project description:Magnetic resonance imaging (MRI) is widely used for ischemic stroke lesion detection in mice. A challenge is that lesion segmentation often relies on manual tracing by trained experts, which is labor-intensive, time-consuming, and prone to inter- and intra-rater variability. Here, we present a fully automated ischemic stroke lesion segmentation method for mouse T2-weighted MRI data. As an end-to-end deep learning approach, the automated lesion segmentation requires very little preprocessing and works directly on the raw MRI scans. We randomly split a large dataset of 382 MRI scans into a subset (n = 293) to train the automated lesion segmentation and a subset (n = 89) to evaluate its performance. We compared Dice coefficients and accuracy of lesion volume against manual segmentation, as well as its performance on an independent dataset from an open repository with different imaging characteristics. The automated lesion segmentation produced segmentation masks with a smooth, compact, and realistic appearance that are in high agreement with manual segmentation. We report dice scores higher than the agreement between two human raters reported in previous studies, highlighting the ability to remove individual human bias and standardize the process across research studies and centers.
| S-EPMC10432383 | biostudies-literature