Dataset Information

Deep Learning Detection of Aneurysm Clips for Magnetic Resonance Imaging Safety.

ABSTRACT: Flagging the presence of metal devices before a head MRI scan is essential to allow appropriate safety checks. There is an unmet need for an automated system which can flag aneurysm clips prior to MRI appointments. We assess the accuracy with which a machine learning model can classify the presence or absence of an aneurysm clip on CT images. A total of 280 CT head scans were collected, 140 with aneurysm clips visible and 140 without. The data were used to retrain a pre-trained image classification neural network to classify CT localizer images. Models were developed using fivefold cross-validation and then tested on a holdout test set. A mean sensitivity of 100% and a mean accuracy of 82% were achieved. Predictions were explained using SHapley Additive exPlanations (SHAP), which highlighted that appropriate regions of interest were informing the models. Models were also trained from scratch to classify three-dimensional CT head scans. These did not exceed the sensitivity of the localizer models. This work illustrates an application of computer vision image classification to enhance current processes and improve patient safety.

SUBMITTER: Courtman M

PROVIDER: S-EPMC10976925 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep Learning Detection of Aneurysm Clips for Magnetic Resonance Imaging Safety.

Courtman Megan M Kim Daniel D Wit Huub H Wang Hongrui H Sun Lingfen L Ifeachor Emmanuel E Mullin Stephen S Thurston Mark M

Journal of imaging informatics in medicine 20240112 1

Flagging the presence of metal devices before a head MRI scan is essential to allow appropriate safety checks. There is an unmet need for an automated system which can flag aneurysm clips prior to MRI appointments. We assess the accuracy with which a machine learning model can classify the presence or absence of an aneurysm clip on CT images. A total of 280 CT head scans were collected, 140 with aneurysm clips visible and 140 without. The data were used to retrain a pre-trained image classificat ...[more]

PMID: 38343241

Similar Datasets

Project description:Background The purpose of this study was to develop a deep learning-based system with a cascade feature pyramid network for the detection and classification of breast lesions in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Methods This retrospective study enrolled 191 consecutive patients with pathological confirmed breast lesions who underwent preoperative magnetic resonance imaging (MRI) at the Second Affiliated Hospital of Xi’an Jiaotong University. Patients were randomly divided into a training set comprising 153 patients with 126 malignant and 27 benign lesions and a validation set containing 38 patients with 31 malignant and 7 benign lesions under 5-fold cross-validation. Two radiologists annotated the location and classification of all lesions. After augmentation with pseudo-color image fusion, MRI images were fed into the developed cascade feature pyramid network system, feature pyramid network, and faster region-based convolutional neural network (CNN) for breast lesion detection and classification, respectively. The performance on large (>2 cm) and small (≤2 cm) breast lesions was further evaluated. Average precision (AP), mean AP, F1-score, sensitivity, and false positives were used to evaluate different systems. Cohen’s kappa scores were calculated to assess agreement between different systems, and Student’s t-test and the Holm-Bonferroni method were used to compare multiple groups. Results The cascade feature pyramid network system outperformed the other systems with a mean AP and highest sensitivity of 0.826±0.051 and 0.970±0.014 (at 0.375 false positives), respectively. The F1-score of the cascade feature pyramid network in real detection was also superior to that of the other systems at both the slice and patient levels. The mean AP values of the cascade feature pyramid network reached 0.779±0.152 and 0.790±0.080 in detecting large and small lesions, respectively. Especially for small lesions, the cascade feature pyramid network achieved the best performance in detecting benign and malignant breast lesions at both the slice and patient levels. Conclusions The deep learning-based system with the developed cascade feature pyramid network has the potential to detect and classify breast lesions on DCE-MRI, especially small lesions.

Project description:BackgroundThe effect of diagnosing Graves' ophthalmopathy (GO) through traditional measurement and observation in medical imaging is not ideal. This study aimed to develop and validate deep learning (DL) models that could be applied to the diagnosis of GO based on magnetic resonance imaging (MRI) and compare them to traditional measurement and judgment of radiologists.MethodsA total of 199 clinically verified consecutive GO patients and 145 normal controls undergoing MRI were retrospectively recruited, of whom 240 were randomly assigned to the training group and 104 to the validation group. Areas of superior, inferior, medial, and lateral rectus muscles and all rectus muscles on coronal planes were calculated respectively. Logistic regression models based on areas of extraocular muscles were built to diagnose GO. The DL models named ResNet101 and Swin Transformer with T1-weighted MRI without contrast as input were used to diagnose GO and the results were compared to the radiologist's diagnosis only relying on MRI T1-weighted scans.ResultsAreas on the coronal plane of each muscle in the GO group were significantly greater than those in the normal group. In the validation group, the areas under the curve (AUCs) of logistic regression models by superior, inferior, medial, and lateral rectus muscles and all muscles were 0.897 [95% confidence interval (CI): 0.833-0.949], 0.705 (95% CI: 0.598-0.804), 0.799 (95% CI: 0.712-0.876), 0.681 (95% CI: 0.567-0.776), and 0.905 (95% CI: 0.843-0.955). ResNet101 and Swin Transformer achieved AUCs of 0.986 (95% CI: 0.977-0.994) and 0.936 (95% CI: 0.912-0.957), respectively. The accuracy, sensitivity, and specificity of ResNet101 were 0.933, 0.979, and 0.869, respectively. The accuracy, sensitivity, and specificity of Swin Transformer were 0.851, 0.817, and 0.898, respectively. The ResNet101 model yielded higher AUC than models of all muscles and radiologists (0.986 vs. 0.905, 0.818; P<0.001).ConclusionsThe DL models based on MRI T1-weighted scans could accurately diagnose GO, and the application of DL systems in MRI may improve radiologists' performance in diagnosing GO and early detection.

Project description:BackgroundSeveral deep learning-based techniques have been developed for prostate cancer (PCa) detection using multiparametric magnetic resonance imaging (mpMRI), but few of them have been rigorously evaluated relative to radiologists' performance or whole-mount histopathology (WMHP).PurposeTo compare the performance of a previously proposed deep learning algorithm, FocalNet, and expert radiologists in the detection of PCa on mpMRI with WMHP as the reference.Study typeRetrospective, single-center study.SubjectsA total of 553 patients (development cohort: 427 patients; evaluation cohort: 126 patients) who underwent 3-T mpMRI prior to radical prostatectomy from October 2010 to February 2018.Field strength/sequence3-T, T2-weighted imaging and diffusion-weighted imaging.AssessmentFocalNet was trained on the development cohort to predict PCa locations by detection points, with a confidence value for each point, on the evaluation cohort. Four fellowship-trained genitourinary (GU) radiologists independently evaluated the evaluation cohort to detect suspicious PCa foci, annotate detection point locations, and assign a five-point suspicion score (1: least suspicious, 5: most suspicious) for each annotated detection point. The PCa detection performance of FocalNet and radiologists were evaluated by the lesion detection sensitivity vs. the number of false-positive detections at different thresholds on suspicion scores. Clinically significant lesions: Gleason Group (GG) ≥ 2 or pathological size ≥ 10 mm. Index lesions: the highest GG and the largest pathological size (secondary).Statistical testsBootstrap hypothesis test for the detection sensitivity between radiologists and FocalNet.ResultsFor the overall differential detection sensitivity, FocalNet was 5.1% and 4.7% below the radiologists for clinically significant and index lesions, respectively; however, the differences were not statistically significant (P = 0.413 and P = 0.282, respectively).Data conclusionFocalNet achieved slightly lower but not statistically significant PCa detection performance compared with GU radiologists. Compared with radiologists, FocalNet demonstrated similar detection performance for a highly sensitive setting (suspicion score ≥ 1) or a highly specific setting (suspicion score = 5), while lower performance in between.Level of evidence3 TECHNICAL EFFICACY STAGE: 2.

Project description:ObjectiveLocalization of focal epilepsy is critical for surgical treatment of refractory seizures. There remains a great need for noninvasive techniques to localize seizures for surgical decision-making. We investigate the use of deep learning using resting state functional magnetic resonance imaging (RS-fMRI) to identify the hemisphere of seizure onset in temporal lobe epilepsy (TLE) patients.MethodsA total of 2132 healthy controls and 32 preoperative TLE patients were studied. All participants underwent structural MRI and RS-fMRI. Healthy control data were used to generate training samples for a three-dimensional convolutional neural network (3DCNN). RS-fMRI was synthetically altered in randomly lateralized regions in the healthy control participants. The model was then trained to classify the hemisphere containing synthetic noise. Finally, the model was tested on TLE patients to assess its performance for detecting biological seizure onset zones, and gradient-weighted class activation mapping (Grad-CAM) identified the strongest predictive regions.ResultsThe 3DCNN classified healthy control hemispheres known to contain synthetic noise with 96% accuracy, and TLE hemispheres clinically identified to be seizure onset zones with 90.6% accuracy. Grad-CAM identified a range of temporal, frontal, parietal, and subcortical regions that were strong anatomical predictors of the seizure onset zone, and the resting state networks that colocalized with Grad-CAM results included default mode, medial temporal, and dorsal attention networks. Lastly, in an analysis of a subset of patients with postsurgical outcomes, the 3DCNN leveraged a more focal set of regions to achieve classification in patients with Engel Class >I compared to Engel Class I.SignificanceNoninvasive techniques capable of localizing the seizure onset zone could improve presurgical planning in patients with intractable epilepsy. We have demonstrated the ability of deep learning to identify the correct hemisphere of the seizure onset zone in TLE patients using RS-fMRI with high accuracy. This approach represents a novel technique of seizure lateralization that could improve preoperative surgical planning.

Project description:BackgroundVentricular volumetry using a short-axis stack of two-dimensional (D) cine balanced steady-state free precession (bSSFP) sequences is crucial in any cardiac magnetic resonance imaging (MRI) examination. This task becomes particularly challenging in children due to multiple breath-holds.ObjectiveTo assess the diagnostic performance of accelerated 3-RR cine MRI sequences using deep learning reconstruction compared with standard 2-D cine bSSFP sequences.Material and methodsTwenty-nine consecutive patients (mean age 11 ± 5, median 12, range 1-17 years) undergoing cardiac MRI were scanned with a conventional segmented 2-D cine and a deep learning accelerated cine (three heartbeats) acquisition on a 1.5-tesla scanner. Short-axis volumetrics were performed (semi-)automatically in both datasets retrospectively by two experienced readers who visually assessed image quality employing a 4-point grading scale. Scan times and image quality were compared using the Wilcoxon rank-sum test. Volumetrics were assessed with linear regression and Bland-Altman analyses, and measurement agreement with intraclass correlation coefficient (ICC).ResultsMean acquisition time was significantly reduced with the 3-RR deep learning cine compared to the standard cine sequence (45.5 ± 13.8 s vs. 218.3 ± 44.8 s; P < 0.001). No significant differences in biventricular volumetrics were found. Left ventricular (LV) mass was increased in the deep learning cine compared with the standard cine sequence (71.4 ± 33.1 g vs. 69.9 ± 32.5 g; P < 0.05). All volumetric measurements had an excellent agreement with ICC > 0.9 except for ejection fraction (EF) (LVEF 0.81, RVEF 0.73). The image quality of deep learning cine images was decreased for end-diastolic and end-systolic contours, papillary muscles, and valve depiction (2.9 ± 0.5 vs. 3.5 ± 0.4; P < 0.05).ConclusionDeep learning cine volumetrics did not differ significantly from standard cine results except for LV mass, which was slightly overestimated with deep learning cine. Deep learning cine sequences result in a significant reduction in scan time with only slightly lower image quality.

Dataset Information

Deep Learning Detection of Aneurysm Clips for Magnetic Resonance Imaging Safety.

Publications

Deep Learning Detection of Aneurysm Clips for Magnetic Resonance Imaging Safety.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets