Deep Learning-Based Algorithm for Automatic Detection of Pulmonary Embolism in Chest CT Angiograms.

PURPOSE: Since the prompt recognition of acute pulmonary embolism (PE) and the immediate initiation of treatment can significantly reduce the risk of death, we developed a deep learning (DL)-based application aimed to automatically detect PEs on chest computed tomography angiograms (CTAs) and alert radiologists for an urgent interpretation. Convolutional neural networks (CNNs) were used to design the application. The associated algorithm used a hybrid 3D/2D UNet topology. The training phase was performed on datasets adequately distributed in terms of vendors, patient age, slice thickness, and kVp. The objective of this study was to validate the performance of the algorithm in detecting suspected PEs on CTAs. METHODS: The validation dataset included 387 anonymized real-world chest CTAs from multiple clinical sites (228 U.S. cities). The data were acquired on 41 different scanner models from five different scanner makers. The ground truth (presence or absence of PE on CTA images) was established by three independent U.S. board-certified radiologists. RESULTS: The algorithm correctly identified 170 of 186 exams positive for PE (sensitivity 91.4% [95% CI: 86.4-95.0%]) and 184 of 201 exams negative for PE (specificity 91.5% [95% CI: 86.8-95.0%]), leading to an accuracy of 91.5%. False negative cases were either chronic PEs or PEs at the limit of subsegmental arteries and close to partial volume effect artifacts. Most of the false positive findings were due to contrast agent-related fluid artifacts, pulmonary veins, and lymph nodes. CONCLUSIONS: The DL-based algorithm has a high degree of diagnostic accuracy with balanced sensitivity and specificity for the detection of PE on CTAs.

Validation of a Deep Learning Tool in the Detection of Intracranial Hemorrhage and Large Vessel Occlusion.

Purpose: Recently developed machine-learning algorithms have demonstrated strong performance in the detection of intracranial hemorrhage (ICH) and large vessel occlusion (LVO). However, their generalizability is often limited by geographic bias of studies. The aim of this study was to validate a commercially available deep learning-based tool in the detection of both ICH and LVO across multiple hospital sites and vendors throughout the U.S. Materials and Methods: This was a retrospective and multicenter study using anonymized data from two institutions. Eight hundred fourteen non-contrast CT cases and 378 CT angiography cases were analyzed to evaluate ICH and LVO, respectively. The tool's ability to detect and quantify ICH, LVO, and their various subtypes was assessed among multiple CT vendors and hospitals across the United States. Ground truth was based off imaging interpretations from two board-certified neuroradiologists. Results: There were 255 positive and 559 negative ICH cases. Accuracy was 95.6%, sensitivity was 91.4%, and specificity was 97.5% for the ICH tool. ICH was further stratified into the following subtypes: intraparenchymal, intraventricular, epidural/subdural, and subarachnoid with true positive rates of 92.9, 100, 94.3, and 89.9%, respectively. ICH true positive rates by volume [small (<5 mL), medium (5-25 mL), and large (>25 mL)] were 71.8, 100, and 100%, respectively. There were 156 positive and 222 negative LVO cases. The LVO tool demonstrated an accuracy of 98.1%, sensitivity of 98.1%, and specificity of 98.2%. A subset of 55 randomly selected cases were also assessed for LVO detection at various sites, including the distal internal carotid artery, middle cerebral artery M1 segment, proximal middle cerebral artery M2 segment, and distal middle cerebral artery M2 segment with an accuracy of 97.0%, sensitivity of 94.3%, and specificity of 97.4%. Conclusion: Deep learning tools can be effective in the detection of both ICH and LVO across a wide variety of hospital systems. While some limitations were identified, specifically in the detection of small ICH and distal M2 occlusion, this study highlights a deep learning tool that can assist radiologists in the detection of emergent findings in a variety of practice settings.

Intravoxel incoherent motion and dynamic contrast-enhanced MRI for differentiation between hepatocellular adenoma and focal nodular hyperplasia.

OBJECTIVE: To examine if intravoxel incoherent motion (IVIM) and dynamic contrast-enhanced MRI (DCE-MRI) can be used as new and supplemental MRI techniques to differentiate hepatocellular adenomas (HCAs) from focal nodular hyperplasias (FNHs) and analyse if diffusion parameter apparent diffusion coefficient (ADC) and IVIM parameter true diffusion coefficient (D) differ in doing so. METHODS: This prospective study included 21 patients (8 HCAs and 13 FNHs) who underwent a specifically designed MRI scanning protocol, including series for analysis of IVIM (four b-values 0, 10, 150 and 800 s mm-2) and DCE-MRI. On a dedicated workstation, identical regions of interest were placed in parametric maps of Ktrans, Ve, D and ADC in each lesion for quantification. Diagnostic accuracy was assessed using receiver operating characteristics analysis. Time-intensity curves (TICs) were classified in different types. RESULTS: HCAs had significantly lower values for Ktrans (mean 1.45 vs 2.68 min-1; p = 0.029) and D (mean 1.02 × 10-3 vs 1.22 × 10-3 mm2 s-1; p = 0.033). Both parameters showed good diagnostic accuracy of 76%. TIC analysis could not differentiate between HCAs and FNHs. CONCLUSION: In this exploratory study, Ktrans and D were able to differentiate HCAs from FNHs in most cases, whereas Ve, ADC and TIC analysis were not. Advances in knowledge: Histological differences between HCAs and FNHs can be quantified on MRI using Ktrans and D.