Deep Learning Predicts Total Knee Replacement from Magnetic Resonance Images.
Ontology highlight
ABSTRACT:
SUBMITTER: Tolpadi AA
PROVIDER: S-EPMC7156761 | biostudies-literature | 2020 Apr
REPOSITORIES: biostudies-literature
Publications
Deep Learning Predicts Total Knee Replacement from Magnetic Resonance Images.
Tolpadi Aniket A AA Lee Jinhee J JJ Pedoia Valentina V Majumdar Sharmila S
Scientific reports 20200414 1
Knee Osteoarthritis (OA) is a common musculoskeletal disorder in the United States. When diagnosed at early stages, lifestyle interventions such as exercise and weight loss can slow OA progression, but at later stages, only an invasive option is available: total knee replacement (TKR). Though a generally successful procedure, only 2/3 of patients who undergo the procedure report their knees feeling "normal" post-operation, and complications can arise that require revision. This necessitates a mo ...[more]
Similar Datasets
Project description:Obesity is increasingly prevalent and associated with increased risk of developing type 2 diabetes, cardiovascular diseases, and cancer. Magnetic resonance imaging (MRI) is an accurate method for determination of body fat volume and distribution. However, quantifying body fat from numerous MRI slices is tedious and time-consuming. Here we developed a deep learning-based method for measuring visceral and subcutaneous fat in the abdominal region of mice. Congenic mice only differ from C57BL/6 (B6) Apoe knockout (Apoe-/-) mice in chromosome 9 that is replaced by C3H/HeJ genome. Male congenic mice had lighter body weight than B6-Apoe-/- mice after being fed 14 weeks of Western diet. Axial and coronal T1-weighted sequencing at 1-mm-thickness and 1-mm-gap was acquired with a 7T Bruker ClinScan scanner. A deep learning approach was developed for segmenting visceral and subcutaneous fat based on the U-net architecture made publicly available through the open-source ANTsRNet library-a growing repository of well-known neural networks. The volumes of subcutaneous and visceral fat measured through our approach were highly comparable with those from manual measurements. The Dice score, root-mean-square error (RMSE), and correlation analysis demonstrated the similarity between two methods in quantifying visceral and subcutaneous fat. Analysis with the automated method showed significant reductions in volumes of visceral and subcutaneous fat but not non-fat tissues in congenic mice compared to B6 mice. These results demonstrate the accuracy of deep learning in quantification of abdominal fat and its significance in determining body weight.
| S-EPMC6147491 | biostudies-literature
Project description:Deep Learning based Convolutional Neural Networks (CNNs) are the state-of-the-art machine learning technique with medical image data. They have the ability to process large amounts of data and learn image features directly from the raw data. Based on their training, these networks are ultimately able to classify unknown data and make predictions. Magnetic resonance imaging (MRI) is the imaging modality of choice for many spinal cord disorders. Proper interpretation requires time and expertise from radiologists, so there is great interest in using artificial intelligence to more quickly interpret and diagnose medical imaging data. In this study, a CNN was trained and tested using thoracolumbar MR images from 500 dogs. T1- and T2-weighted MR images in sagittal and transverse planes were used. The network was trained with unremarkable images as well as with images showing the following spinal cord pathologies: intervertebral disc extrusion (IVDE), intervertebral disc protrusion (IVDP), fibrocartilaginous embolism (FCE)/acute non-compressive nucleus pulposus extrusion (ANNPE), syringomyelia and neoplasia. 2,693 MR images from 375 dogs were used for network training. The network was tested using 7,695 MR images from 125 dogs. The network performed best in detecting IVDPs on sagittal T1-weighted images, with a sensitivity of 100% and specificity of 95.1%. The network also performed very well in detecting IVDEs, especially on sagittal T2-weighted images, with a sensitivity of 90.8% and specificity of 98.98%. The network detected FCEs and ANNPEs with a sensitivity of 62.22% and a specificity of 97.90% on sagittal T2-weighted images and with a sensitivity of 91% and a specificity of 90% on transverse T2-weighted images. In detecting neoplasms and syringomyelia, the CNN did not perform well because of insufficient training data or because the network had problems differentiating different hyperintensities on T2-weighted images and thus made incorrect predictions. This study has shown that it is possible to train a CNN in terms of recognizing and differentiating various spinal cord pathologies on canine MR images. CNNs therefore have great potential to act as a "second eye" for imagers in the future, providing a faster focus on the altered image area and thus increasing workflow in radiology.
| S-EPMC8593183 | biostudies-literature
Project description:BackgroundHigh-resolution medical images that include facial regions can be used to recognize the subject's face when reconstructing 3-dimensional (3D)-rendered images from 2-dimensional (2D) sequential images, which might constitute a risk of infringement of personal information when sharing data. According to the Health Insurance Portability and Accountability Act (HIPAA) privacy rules, full-face photographic images and any comparable image are direct identifiers and considered as protected health information. Moreover, the General Data Protection Regulation (GDPR) categorizes facial images as biometric data and stipulates that special restrictions should be placed on the processing of biometric data.ObjectiveThis study aimed to develop software that can remove the header information from Digital Imaging and Communications in Medicine (DICOM) format files and facial features (eyes, nose, and ears) at the 2D sliced-image level to anonymize personal information in medical images.MethodsA total of 240 cranial magnetic resonance (MR) images were used to train the deep learning model (144, 48, and 48 for the training, validation, and test sets, respectively, from the Alzheimer's Disease Neuroimaging Initiative [ADNI] database). To overcome the small sample size problem, we used a data augmentation technique to create 576 images per epoch. We used attention-gated U-net for the basic structure of our deep learning model. To validate the performance of the software, we adapted an external test set comprising 100 cranial MR images from the Open Access Series of Imaging Studies (OASIS) database.ResultsThe facial features (eyes, nose, and ears) were successfully detected and anonymized in both test sets (48 from ADNI and 100 from OASIS). Each result was manually validated in both the 2D image plane and the 3D-rendered images. Furthermore, the ADNI test set was verified using Microsoft Azure's face recognition artificial intelligence service. By adding a user interface, we developed and distributed (via GitHub) software named "Deface program" for medical images as an open-source project.ConclusionsWe developed deep learning-based software for the anonymization of MR images that distorts the eyes, nose, and ears to prevent facial identification of the subject in reconstructed 3D images. It could be used to share medical big data for secondary research while making both data providers and recipients compliant with the relevant privacy regulations.
| S-EPMC7759440 | biostudies-literature
Project description:BACKGROUND:Magnetic resonance imaging (MRI) of the knee is the preferred method for diagnosing knee injuries. However, interpretation of knee MRI is time-intensive and subject to diagnostic error and variability. An automated system for interpreting knee MRI could prioritize high-risk patients and assist clinicians in making diagnoses. Deep learning methods, in being able to automatically learn layers of features, are well suited for modeling the complex relationships between medical images and their interpretations. In this study we developed a deep learning model for detecting general abnormalities and specific diagnoses (anterior cruciate ligament [ACL] tears and meniscal tears) on knee MRI exams. We then measured the effect of providing the model's predictions to clinical experts during interpretation. METHODS AND FINDINGS:Our dataset consisted of 1,370 knee MRI exams performed at Stanford University Medical Center between January 1, 2001, and December 31, 2012 (mean age 38.0 years; 569 [41.5%] female patients). The majority vote of 3 musculoskeletal radiologists established reference standard labels on an internal validation set of 120 exams. We developed MRNet, a convolutional neural network for classifying MRI series and combined predictions from 3 series per exam using logistic regression. In detecting abnormalities, ACL tears, and meniscal tears, this model achieved area under the receiver operating characteristic curve (AUC) values of 0.937 (95% CI 0.895, 0.980), 0.965 (95% CI 0.938, 0.993), and 0.847 (95% CI 0.780, 0.914), respectively, on the internal validation set. We also obtained a public dataset of 917 exams with sagittal T1-weighted series and labels for ACL injury from Clinical Hospital Centre Rijeka, Croatia. On the external validation set of 183 exams, the MRNet trained on Stanford sagittal T2-weighted series achieved an AUC of 0.824 (95% CI 0.757, 0.892) in the detection of ACL injuries with no additional training, while an MRNet trained on the rest of the external data achieved an AUC of 0.911 (95% CI 0.864, 0.958). We additionally measured the specificity, sensitivity, and accuracy of 9 clinical experts (7 board-certified general radiologists and 2 orthopedic surgeons) on the internal validation set both with and without model assistance. Using a 2-sided Pearson's chi-squared test with adjustment for multiple comparisons, we found no significant differences between the performance of the model and that of unassisted general radiologists in detecting abnormalities. General radiologists achieved significantly higher sensitivity in detecting ACL tears (p-value = 0.002; q-value = 0.019) and significantly higher specificity in detecting meniscal tears (p-value = 0.003; q-value = 0.019). Using a 1-tailed t test on the change in performance metrics, we found that providing model predictions significantly increased clinical experts' specificity in identifying ACL tears (p-value < 0.001; q-value = 0.006). The primary limitations of our study include lack of surgical ground truth and the small size of the panel of clinical experts. CONCLUSIONS:Our deep learning model can rapidly generate accurate clinical pathology classifications of knee MRI exams from both internal and external datasets. Moreover, our results support the assertion that deep learning models can improve the performance of clinical experts during medical imaging interpretation. Further research is needed to validate the model prospectively and to determine its utility in the clinical setting.
| S-EPMC6258509 | biostudies-other
Project description:Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with cancer in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through a deep learning-based model. When applied to a cohort of 1,010 patients with breast cancer (Training set: n = 858, Test set: n = 152) from The Cancer Genome Atlas where 485 patients have high CIN status, our model accurately classified CIN status, achieving an area under the curve of 0.822 with 81.2% sensitivity and 68.7% specificity in the test set. Patch-level predictions of CIN status suggested intra-tumor heterogeneity within slides. Moreover, presence of patches with high predicted CIN score within an entire slide was more predictive of clinical outcome than the average CIN score of the slide, thus underscoring the clinical importance of intra-tumor heterogeneity.
| S-EPMC8099498 | biostudies-literature
Project description:Stereotactic radiosurgery planning for cerebral arteriovenous malformations (AVM) is complicated by the variability in appearance of an AVM nidus across different imaging modalities. We developed a deep learning approach to automatically segment cerebrovascular-anatomical maps from multiple high-resolution magnetic resonance imaging/angiography (MRI/MRA) sequences in AVM patients, with the goal of facilitating target delineation. Twenty-three AVM patients who were evaluated for radiosurgery and underwent multi-parametric MRI/MRA were included. A hybrid semi-automated and manual approach was used to label MRI/MRAs with arteries, veins, brain parenchyma, cerebral spinal fluid (CSF), and embolized vessels. Next, these labels were used to train a convolutional neural network to perform this task. Imaging from 17 patients (6362 image slices) was used for training, and 6 patients (1224 slices) for validation. Performance was evaluated by Dice Similarity Coefficient (DSC). Classification performance was good for arteries, veins, brain parenchyma, and CSF, with DSCs of 0.86, 0.91, 0.98, and 0.91, respectively in the validation image set. Performance was lower for embolized vessels, with a DSC of 0.75. This demonstrates the proof of principle that accurate, high-resolution cerebrovascular-anatomical maps can be generated from multiparametric MRI/MRA. Clinical validation of their utility in radiosurgery planning is warranted.
| S-EPMC8763944 | biostudies-literature
Project description:Background The methods for assessing knee osteoarthritis (OA) do not provide enough comprehensive information to make robust and accurate outcome predictions. Purpose To develop a deep learning (DL) prediction model for risk of OA progression by using knee radiographs in patients who underwent total knee replacement (TKR) and matched control patients who did not undergo TKR. Materials and Methods In this retrospective analysis that used data from the OA Initiative, a DL model on knee radiographs was developed to predict both the likelihood of a patient undergoing TKR within 9 years and Kellgren-Lawrence (KL) grade. Study participants included a case-control matched subcohort between 45 and 79 years. Patients were matched to control patients according to age, sex, ethnicity, and body mass index. The proposed model used a transfer learning approach based on the ResNet34 architecture with sevenfold nested cross-validation. Receiver operating characteristic curve analysis and conditional logistic regression assessed model performance for predicting probability and risk of TKR compared with clinical observations and two binary outcome prediction models on the basis of radiographic readings: KL grade and OA Research Society International (OARSI) grade. Results Evaluated were 728 participants including 324 patients (mean age, 64 years ± 8 [standard deviation]; 222 women) and 324 control patients (mean age, 64 years ± 8; 222 women). The prediction model based on DL achieved an area under the receiver operating characteristic curve (AUC) of 0.87 (95% confidence interval [CI]: 0.85, 0.90), outperforming a baseline prediction model by using KL grade with an AUC of 0.74 (95% CI: 0.71, 0.77; P < .001). The risk for TKR increased with probability that a person will undergo TKR from the DL model (odds ratio [OR], 7.7; 95% CI: 2.3, 25; P < .001), KL grade (OR, 1.92; 95% CI: 1.17, 3.13; P = .009), and OARSI grade (OR, 1.20; 95% CI: 0.41, 3.50; P = .73). Conclusion The proposed deep learning model better predicted risk of total knee replacement in osteoarthritis than did binary outcome models by using standard grading systems. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Richardson in this issue.
| S-EPMC7434649 | biostudies-literature
Project description:We address the problem of prostate lesion detection, localization, and segmentation in T2W magnetic resonance (MR) images. We train a deep convolutional encoder-decoder architecture to simultaneously segment the prostate, its anatomical structure, and the malignant lesions. To incorporate the 3D contextual spatial information provided by the MRI series, we propose a novel 3D sliding window approach, which preserves the 2D domain complexity while exploiting 3D information. Experiments on data from 19 patients provided for the public by the Initiative for Collaborative Computer Vision Benchmarking (I2CVB) show that our approach outperforms traditional pattern recognition and machine learning approaches by a significant margin. Particularly, for the task of cancer detection and localization, the system achieves an average AUC of 0.995, an accuracy of 0.894, and a recall of 0.928. The proposed mono-modal deep learning-based system performs comparably to other multi-modal MR-based systems. It could improve the performance of a radiologist in prostate cancer diagnosis and treatment planning.
| S-EPMC6737129 | biostudies-literature
Project description:BACKGROUND:Deep learning algorithms are increasingly used for automatic medical imaging analysis and cardiac chamber segmentation. Especially in congenital heart disease, obtaining a sufficient number of training images and data anonymity issues remain of concern. METHODS:Progressive generative adversarial networks (PG-GAN) were trained on cardiac magnetic resonance imaging (MRI) frames from a nationwide prospective study to generate synthetic MRI frames. These synthetic frames were subsequently used to train segmentation networks (U-Net) and the quality of the synthetic training images, as well as the performance of the segmentation network was compared to U-Net-based solutions trained entirely on patient data. RESULTS:Cardiac MRI data from 303 patients with Tetralogy of Fallot were used for PG-GAN training. Using this model, we generated 100,000 synthetic images with a resolution of 256?×?256 pixels in 4-chamber and 2-chamber views. All synthetic samples were classified as anatomically plausible by human observers. The segmentation performance of the U-Net trained on data from 42 separate patients was statistically significantly better compared to the PG-GAN based training in an external dataset of 50 patients, however, the actual difference in segmentation quality was negligible (<?1% in absolute terms for all models). CONCLUSION:We demonstrate the utility of PG-GANs for generating large amounts of realistically looking cardiac MRI images even in rare cardiac conditions. The generated images are not subject to data anonymity and privacy concerns and can be shared freely between institutions. Training supervised deep learning segmentation networks on this synthetic data yielded similar results compared to direct training on original patient data.
| S-EPMC7542728 | biostudies-literature
Project description:Background and objectiveMagnetic resonance (MR) imaging is increasingly used in studies of speech as it enables non-invasive visualisation of the vocal tract and articulators, thus providing information about their shape, size, motion and position. Extraction of this information for quantitative analysis is achieved using segmentation. Methods have been developed to segment the vocal tract, however, none of these also fully segment any articulators. The objective of this work was to develop a method to fully segment multiple groups of articulators as well as the vocal tract in two-dimensional MR images of speech, thus overcoming the limitations of existing methods.MethodsFive speech MR image sets (392 MR images in total), each of a different healthy adult volunteer, were used in this work. A fully convolutional network with an architecture similar to the original U-Net was developed to segment the following six regions in the image sets: the head, soft palate, jaw, tongue, vocal tract and tooth space. A five-fold cross-validation was performed to investigate the segmentation accuracy and generalisability of the network. The segmentation accuracy was assessed using standard overlap-based metrics (Dice coefficient and general Hausdorff distance) and a novel clinically relevant metric based on velopharyngeal closure.ResultsThe segmentations created by the method had a median Dice coefficient of 0.92 and a median general Hausdorff distance of 5mm. The method segmented the head most accurately (median Dice coefficient of 0.99), and the soft palate and tooth space least accurately (median Dice coefficients of 0.92 and 0.93 respectively). The segmentations created by the method correctly showed 90% (27 out of 30) of the velopharyngeal closures in the MR image sets.ConclusionsAn automatic method to fully segment multiple groups of articulators as well as the vocal tract in two-dimensional MR images of speech was successfully developed. The method is intended for use in clinical and non-clinical speech studies which involve quantitative analysis of the shape, size, motion and position of the vocal tract and articulators. In addition, a novel clinically relevant metric for assessing the accuracy of vocal tract and articulator segmentation methods was developed.
| S-EPMC7732702 | biostudies-literature