Dataset Information

Artificial Intelligence System Approaching Neuroradiologist-level Differential Diagnosis Accuracy at Brain MRI.

ABSTRACT: Background Although artificial intelligence (AI) shows promise across many aspects of radiology, the use of AI to create differential diagnoses for rare and common diseases at brain MRI has not been demonstrated. Purpose To evaluate an AI system for generation of differential diagnoses at brain MRI compared with radiologists. Materials and Methods This retrospective study tested performance of an AI system for probabilistic diagnosis in patients with 19 common and rare diagnoses at brain MRI acquired between January 2008 and January 2018. The AI system combines data-driven and domain-expertise methodologies, including deep learning and Bayesian networks. First, lesions were detected by using deep learning. Then, 18 quantitative imaging features were extracted by using atlas-based coregistration and segmentation. Third, these image features were combined with five clinical features by using Bayesian inference to develop probability-ranked differential diagnoses. Quantitative feature extraction algorithms and conditional probabilities were fine-tuned on a training set of 86 patients (mean age, 49 years ± 16 [standard deviation]; 53 women). Accuracy was compared with radiology residents, general radiologists, neuroradiology fellows, and academic neuroradiologists by using accuracy of top one, top two, and top three differential diagnoses in 92 independent test set patients (mean age, 47 years ± 18; 52 women). Results For accuracy of top three differential diagnoses, the AI system (91% correct) performed similarly to academic neuroradiologists (86% correct; P = .20), and better than radiology residents (56%; P < .001), general radiologists (57%; P < .001), and neuroradiology fellows (77%; P = .003). The performance of the AI system was not affected by disease prevalence (93% accuracy for common vs 85% for rare diseases; P = .26). Radiologists were more accurate at diagnosing common versus rare diagnoses (78% vs 47% across all radiologists; P < .001). Conclusion An artificial intelligence system for brain MRI approached overall top one, top two, and top three differential diagnoses accuracy of neuroradiologists and exceeded that of less-specialized radiologists. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Zaharchuk in this issue.

SUBMITTER: Rauschecker AM

PROVIDER: S-EPMC7263320 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundParkinson's disease (PD) is the second most common neurodegenerative disease. An objective diagnosis method is urgently needed in clinical practice. In this study, deep learning and radiomics techniques were studied to automatically diagnose PD from healthy controls (HCs).Methods155 PD patients and 154 HCs were randomly divided into a training set (246 patients) and a testing set (63 patients). The brain subregions identification and segmentation were automatically performed with a VB-net, and radiomics features of billateral thalamus, caudatum, putamen and pallidum were extracted. Five independent machine learning classifiers [Support Vector Machine (SVM), Stochastic gradient descent (SGD), random forest (RF), quadratic discriminant analysis (QDA) and decision tree (DT)] were trained on the training set, and validated on the testing. Delong test was used to compare the performance of different models.ResultsOur VB-net could automatically identify and segment the brain into 109 regions. 2,264 radiomics features were automatically extracted from the billateral thalamus, caudatum, putamen or pallidum of each patient. After four step of features dimensionality reduction, Delong tests showed that the SVM model based on combined features had the best performance, with AUCs of 0.988 (95% CI: 0.979 ~ 0.998, specificity = 91.1%, sensitivity =100%, accuracy = 89.4% and precision = 88.2%) and 0.976 (95% CI: 0.942 ~ 1.000, specificity = 100%, sensitivity = 87.1%, accuracy = 93.5% and precision = 88.6%) in the training set and testing set, respectively. Decision curve analysis showed that the clinical benefit of the line graph model was high.ConclusionThe SVM model based on combined features could be used to diagnose PD with high accuracy. Our fully automatic model could rapidly process the MRI data and distinguish PD and HCs in one minute. It greatly improved the diagnostic efficiency and has a great potential value in clinical practice to help the early diagnosis of PD.

Project description:BACKGROUND. Potential approaches for abbreviated knee MRI, including prospective acceleration with deep learning, have achieved limited clinical implementation. OBJECTIVE. The objective of this study was to evaluate the interreader agreement between conventional knee MRI and a 5-minute 3D quantitative double-echo steady-state (qDESS) sequence with automatic T2 mapping and deep learning super-resolutionaugmentation and to compare the diagnostic performance of the two methods regarding findings from arthroscopic surgery. METHODS. Fifty-one patients with knee pain underwent knee MRI that included an additional 3D qDESS sequence with automatic T2 mapping. Fourier interpolation was followed by prospective deep learning super resolution to enhance qDESS slice resolution twofold. A musculoskeletal radiologist and a radiology resident performed independent retrospective evaluations of articular cartilage, menisci, ligaments, bones, extensor mechanism, and synovium using conventional MRI. Following a 2-month washout period, readers reviewed qDESS images alone followed by qDESS with the automatic T2 maps. Interreader agreement between conventional MRI and qDESS was computed using percentage agreement and Cohen kappa. The sensitivity and specificity of conventional MRI, qDESS alone, and qDESS plus T2 mapping were compared with arthroscopic findings using exact McNemar tests. RESULTS. Conventional MRI and qDESS showed 92% agreement in evaluating all tissues. Kappa was 0.79 (95% CI, 0.76-0.81) across all imaging findings. In 43 patients who underwent arthroscopy, sensitivity and specificity were not significantly different (p = .23 to > .99) between conventional MRI (sensitivity, 58-93%; specificity, 27-87%) and qDESS alone (sensitivity, 54-90%; specificity, 23-91%) for cartilage, menisci, ligaments, and synovium. For grade 1 cartilage lesions, sensitivity and specificity were 33% and 56%, respectively, for conventional MRI; 23% and 53% for qDESS (p = .81); and 46% and 39% for qDESS with T2 mapping (p = .80). For grade 2A lesions, values were 27% and 53% for conventional MRI, 26% and 52% for qDESS (p = .02), and 58% and 40% for qDESS with T2 mapping (p < .001). CONCLUSION. The qDESS method prospectively augmented with deep learning showed strong interreader agreement with conventional knee MRI and near-equivalent diagnostic performance regarding arthroscopy. The ability of qDESS to automatically generate T2 maps increases sensitivity for cartilage abnormalities. CLINICAL IMPACT. Using prospective artificial intelligence to enhance qDESS image quality may facilitate an abbreviated knee MRI protocol while generating quantitative T2 maps.

Project description:BackgroundUltrasound is widely used for detecting thyroid nodules in clinical practice. This retrospective study aimed to assess the diagnostic efficacy of the American College of Radiology Thyroid Imaging Reporting and Data System (ACR-TIRADS), S-Detect, and elastography of the carotid artery for suspicious thyroid nodules and to determine the complementary value of artificial intelligence and elastography.MethodsBetween January 2021 and November 2021, 101 consecutive patients with 138 thyroid nodules were enrolled in The First Hospital of China Medical University. All nodules were evaluated using ACR-TIRADS categories (TR), S-Detect, and elastography, and then the diagnostic performance of the different methods and the combined assessment were compared. The inclusion criteria were the following: (I) TR3, TR4, and TR5 nodules, which were defined as "suspicious nodules"; (II) patients who had surgical or cytopathological results after ultrasound examination; and (III) voluntary enrollment in this study. Meanwhile, the exclusion criteria were the following: (I) TR1 and TR2 nodules, (II) patients who had undergone fine-needle aspiration before ultrasound examination, and (III) inconclusive cytologic findings.ResultsA total of 71 patients (12 men and 59 women) with 94 suspicious thyroid nodules (42 benign nodules and 52 malignant nodules) were finally included in this study. S-Detect had a significantly better sensitivity than did ACR-TIRADS [S-Detect: 98.1%, 95% confidence interval (CI): 89.7-100.0%; ACR-TIRADS: 84.6%, 95% CI: 71.9-93.1%; P=0.036], but its specificity was much lower (S-Detect: 19.0%; 95% CI: 8.6-34.1%; ACR-TIRADS: 40.5%, 95% CI: 25.6-56.7%; P=0.032). The accuracy was not significantly different between S-Detect (62.8%; 95% CI: 52.2-72.5%) and ACR-TIRADS (64.9%; 95% CI: 54.4-74.5%) (P=0.761). The elasticity contrast index (ECI) was not definitively useful in identifying suspicious thyroid nodules (P=0.592). Compared with the use of ACR-TIRADS and S-Detect alone, the specificity (45.2%; 95% CI: 29.8-61.3%), positive predictive value (65.2%; 95% CI: 52.4-76.5%), accuracy (66.0%; 95% CI: 55.5-75.4%), and the area under the receiver operating characteristic curve (0.640; 95% CI: 0.534-0.736) of their combination were higher but not significantly so.ConclusionsAt present, S-Detect cannot replace manual diagnosis, and the value of elastography of the carotid artery in diagnosing suspected thyroid nodules remains unclear.

Project description:BackgroundLess experienced clinicians sometimes make misdiagnosis of hip fractures. We developed computer-aided diagnosis (CAD) system for hip fractures on plain X-rays using a deep learning model trained on a large dataset. In this study, we examined whether the accuracy of the diagnosis of hip fracture of the residents could be improved by using this system.MethodsA deep convolutional neural network approach was used for machine learning. Pytorch 1.3 and Fast.ai 1.0 were applied as frameworks, and an EfficientNet-B4 model (a pre-trained ImageNet model) was used. We handled the 5295 X-rays from the patients with femoral neck fracture or femoral trochanteric fracture from 2009 to 2019. We excluded cases in which the bilateral hips were not included within an image range, and cases of femoral shaft fracture and periprosthetic fracture. Finally, we included 5242 AP pelvic X-rays from 4851 cases. We divided these 5242 images into two images per image, and prepared 5242 images including fracture site and 5242 images without fracture site. Thus, a total of 10,484 images were used for machine learning. The accuracy, sensitivity, specificity, F-value, and area under the curve (AUC) were assessed. Gradient-weighted class activation mapping (Grad-CAM) was used to conceptualize the basis for the diagnosis of the fracture by the deep learning algorithm. Secondly, we conducted a controlled experiment with clinicians. Thirty-one residents;young doctors within 2 years of graduation from medical school who rotate through various specialties, were tested using 300 hip fracture images that were randomly extracted from the dataset. We evaluated the diagnostic accuracy with and without the use of the CAD system for each of the 300 images.ResultsThe accuracy, sensitivity, specificity, F-value, and AUC were 96.1, 95.2, 96.9%, 0.961, and 0.99, respectively, with the correct diagnostic basis generated by Grad-CAM. In the controlled experiment, the diagnostic accuracy of the residents significantly improved when they used the CAD system.ConclusionsWe developed a newly CAD system with a deep learning algorithm from a relatively large dataset from multiple institutions. Our system achieved high diagnostic performance. Our system improved the diagnostic accuracy of residents for hip fractures.Level of evidenceLevel III, Foundational evidence, before-after study.Clinical relevancehigh.

Project description:BackgroundArtificial intelligence (AI) for gastric cancer diagnosis has been discussed in recent years. The role of AI in early gastric cancer is more important than in advanced gastric cancer since early gastric cancer is not easily identified in clinical practice. However, to our knowledge, past syntheses appear to have limited focus on the populations with early gastric cancer.ObjectiveThe purpose of this study is to evaluate the diagnostic accuracy of AI in the diagnosis of early gastric cancer from endoscopic images.MethodsWe conducted a systematic review from database inception to June 2020 of all studies assessing the performance of AI in the endoscopic diagnosis of early gastric cancer. Studies not concerning early gastric cancer were excluded. The outcome of interest was the diagnostic accuracy (comprising sensitivity, specificity, and accuracy) of AI systems. Study quality was assessed on the basis of the revised Quality Assessment of Diagnostic Accuracy Studies. Meta-analysis was primarily based on a bivariate mixed-effects model. A summary receiver operating curve and a hierarchical summary receiver operating curve were constructed, and the area under the curve was computed.ResultsWe analyzed 12 retrospective case control studies (n=11,685) in which AI identified early gastric cancer from endoscopic images. The pooled sensitivity and specificity of AI for early gastric cancer diagnosis were 0.86 (95% CI 0.75-0.92) and 0.90 (95% CI 0.84-0.93), respectively. The area under the curve was 0.94. Sensitivity analysis of studies using support vector machines and narrow-band imaging demonstrated more consistent results.ConclusionsFor early gastric cancer, to our knowledge, this was the first synthesis study on the use of endoscopic images in AI in diagnosis. AI may support the diagnosis of early gastric cancer. However, the collocation of imaging techniques and optimal algorithms remain unclear. Competing models of AI for the diagnosis of early gastric cancer are worthy of future investigation.Trial registrationPROSPERO CRD42020193223; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=193223.

Project description:BackgroundScreening patients for eligibility for clinical trials is labor intensive. It requires abstraction of data elements from multiple components of the longitudinal health record and matching them to inclusion and exclusion criteria for each trial. Artificial intelligence (AI) systems have been developed to improve the efficiency and accuracy of this process.ObjectiveThis study aims to evaluate the ability of an AI clinical decision support system (CDSS) to identify eligible patients for a set of clinical trials.MethodsThis study included the deidentified data from a cohort of patients with breast cancer seen at the medical oncology clinic of an academic medical center between May and July 2017 and assessed patient eligibility for 4 breast cancer clinical trials. CDSS eligibility screening performance was validated against manual screening. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value for eligibility determinations were calculated. Disagreements between manual screeners and the CDSS were examined to identify sources of discrepancies. Interrater reliability between manual reviewers was analyzed using Cohen (pairwise) and Fleiss (three-way) κ, and the significance of differences was determined by Wilcoxon signed-rank test.ResultsIn total, 318 patients with breast cancer were included. Interrater reliability for manual screening ranged from 0.60-0.77, indicating substantial agreement. The overall accuracy of breast cancer trial eligibility determinations by the CDSS was 87.6%. CDSS sensitivity was 81.1% and specificity was 89%.ConclusionsThe AI CDSS in this study demonstrated accuracy, sensitivity, and specificity of greater than 80% in determining the eligibility of patients for breast cancer clinical trials. CDSSs can accurately exclude ineligible patients for clinical trials and offer the potential to increase screening efficiency and accuracy. Additional research is needed to explore whether increased efficiency in screening and trial matching translates to improvements in trial enrollment, accruals, feasibility assessments, and cost.

Dataset Information

Artificial Intelligence System Approaching Neuroradiologist-level Differential Diagnosis Accuracy at Brain MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets