Radiology
-
Background Fluorine 18 (18F)-fluorodeoxyglucose (FDG) PET/CT is a routine tool for staging patients with lymphoma and lung cancer. Purpose To evaluate configurations of deep convolutional neural networks (CNNs) to localize and classify uptake patterns of whole-body 18F-FDG PET/CT images in patients with lung cancer and lymphoma. Materials and Methods This was a retrospective analysis of consecutive patients with lung cancer or lymphoma referred to a single center from August 2011 to August 2013. ⋯ Anatomic localization accuracy of the CNN was 2543 of 2639 (96.4%; 95% CI: 95.5%, 97.1%) for body part, 2292 of 2639 (86.9%; 95% CI: 85.3%, 88.5%) for region (ie, organ), and 2149 of 2639 (81.4%; 95% CI: 79.3%-83.5%) for subregion. Conclusion The fully automated anatomic localization and classification of fluorine 18-fluorodeoxyglucose PET uptake patterns in foci suspicious and nonsuspicious for cancer in patients with lung cancer and lymphoma by using a convolutional neural network is feasible and achieves high diagnostic performance when both CT and PET images are used. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Froelich and Salavati in this issue.
-
Background Detection of cerebral lesions at MRI may benefit from a chemically stable and more sensitively detected gadolinium-based contrast agent (GBCA). Gadopiclenol, a macrocyclic GBCA with at least twofold higher relaxivity, is currently undergoing clinical trials in humans. Purpose To determine the relationship between MRI contrast enhancement and the injected dose of gadopiclenol in a glioma rat model compared with those of conventional GBCA at label dose. ⋯ Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Tweedle in this issue.
-
Multicenter Study
Deep Convolutional Neural Network-based Software Improves Radiologist Detection of Malignant Lung Nodules on Chest Radiographs.
Background Multicenter studies are required to validate the added benefit of using deep convolutional neural network (DCNN) software for detecting malignant pulmonary nodules on chest radiographs. Purpose To compare the performance of radiologists in detecting malignant pulmonary nodules on chest radiographs when assisted by deep learning-based DCNN software with that of radiologists or DCNN software alone in a multicenter setting. Materials and Methods Investigators at four medical centers retrospectively identified 600 lung cancer-containing chest radiographs and 200 normal chest radiographs. ⋯ For the 12 radiologists in this study, 104 of 2400 radiographs were positively changed (from false-negative to true-positive or from false-positive to true-negative) using the DCNN, while 56 of 2400 radiographs were changed negatively. Conclusion Radiologists had better performance with deep convolutional network software for the detection of malignant pulmonary nodules on chest radiographs than without. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Jacobson in this issue.
-
Background Deep learning (DL) algorithms are gaining extensive attention for their excellent performance in image recognition tasks. DL models can automatically make a quantitative assessment of complex medical image characteristics and achieve increased accuracy in diagnosis with higher efficiency. Purpose To determine the feasibility of using a DL approach to predict clinically negative axillary lymph node metastasis from US images in patients with primary breast cancer. ⋯ Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Bae in this issue.
-
Comparative Study
MRI T2 Mapping of the Knee Providing Synthetic Morphologic Images: Comparison to Conventional Turbo Spin-Echo MRI.
Background Use of a T2 mapping sequence in addition to the conventional knee MRI protocol increases sensitivity to early cartilage lesions but is time consuming. Purpose To test the in vitro validity of quantitative data from an accelerated parallel T2 mapping sequence (combined generalized autocalibrating partially parallel acquisition and model-based accelerated relaxometry by iterative nonlinear inversion [GRAPPATINI]) of the knee and to compare in vivo synthetic images generated with this sequence with those generated with conventional morphologic sequences. Materials and Methods T2 estimations with GRAPPATINI were validated in vitro in comparison with T2 estimations with routine multisection multiecho and reference standard single-section single-echo spin-echo T2 mapping sequences by using a Bland-Altman plot. ⋯ The rates of findings were not different between synthetic and conventional image sets (all P ≥ .07) except for two items (femoral trochlear cartilage [3.0% vs 0.3%, P = .006] and joint effusion [0.3% vs 2.7%, P = .005]). Conclusion This T2 mapping sequence yields, in one acquisition, accurate T2 values and synthetic morphologic images that are comparable with those obtained with conventional turbo spin-echo sequences. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Fritz in this issue.