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. Each radiograph with a lung cancer had at least one malignant nodule confirmed by CT and pathologic examination. Twelve radiologists from the four centers independently analyzed the chest radiographs and marked regions of interest. Commercially available deep learning-based computer-aided detection software separately trained, tested, and validated with 19 330 radiographs was used to find suspicious nodules. The radiologists then reviewed the images with the assistance of DCNN software. The sensitivity and number of false-positive findings per image of DCNN software, radiologists alone, and radiologists with the use of DCNN software were analyzed by using logistic regression and Poisson regression. Results The average sensitivity of radiologists improved (from 65.1% [1375 of 2112; 95% confidence interval {CI}: 62.0%, 68.1%] to 70.3% [1484 of 2112; 95% CI: 67.2%, 73.1%], P < .001) and the number of false-positive findings per radiograph declined (from 0.2 [488 of 2400; 95% CI: 0.18, 0.22] to 0.18 [422 of 2400; 95% CI: 0.16, 0.2], P < .001) when the radiologists re-reviewed radiographs with the DCNN software. 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.

Flow-suppressed hyperpolarized 13 C chemical shift imaging using velocity-optimized bipolar gradient in mouse liver tumors at 9.4 T.

PURPOSE: To optimize and investigate the influence of bipolar gradients for flow suppression in metabolic quantification of hyperpolarized 13 C chemical shift imaging (CSI) of mouse liver at 9.4 T. METHODS: The trade-off between the amount of flow suppression using bipolar gradients and T2* effect from static spins was simulated. A free induction decay CSI sequence with alternations between the flow-suppressed and non-flow-suppressed acquisitions for each repetition time was developed and was applied to liver tumor-bearing mice via injection of hyperpolarized [1-13 C] pyruvate. RESULTS: The in vivo results from flow suppression using the velocity-optimized bipolar gradient were comparable with the simulation results. The vascular signal was adequately suppressed and signal loss in stationary tissue was minimized. Application of the velocity-optimized bipolar gradient to tumor-bearing mice showed reduction in the vessel-derived pyruvate signal contamination, and the average lactate/pyruvate ratio increased by 0.095 (P < 0.05) in the tumor region after flow suppression. CONCLUSION: Optimization of the bipolar gradient is essential because of the short 13 C T2* and high signal in venous flow in the mouse liver. The proposed velocity-optimized bipolar gradient can suppress the vascular signal, minimizing T2*-related signal loss in stationary tissues at 9.4 T. Magn Reson Med 78:1674-1682, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

An indirect method for in vivo T2 mapping of [1-13 C] pyruvate using hyperpolarized 13 C CSI.

An indirect method for in vivo T2 mapping of 13 C-labeled metabolites using T2 and T2 * information of water protons obtained a priori is proposed. The T2 values of 13 C metabolites are inferred using the relationship to T2 ' of coexisting 1 H and the T2 * of 13 C metabolites, which is measured using routine hyperpolarized 13 C CSI data. The concept is verified with phantom studies. Simulations were performed to evaluate the extent of T2 estimation accuracy due to errors in the other measurements. Also, bias in the 13 C T2 * estimation from the 13 C CSI data was studied. In vivo experiments were performed from the brains of normal rats and a rat with C6 glioma. Simulation results indicate that the proposed method provides accurate and unbiased 13 C T2 values within typical experimental settings. The in vivo studies found that the estimated T2 of [1-13 C] pyruvate using the indirect method was longer in tumor than in normal tissues and gave values similar to previous reports. This method can estimate localized T2 relaxation times from multiple voxels using conventional hyperpolarized 13 C CSI and can potentially be used with time resolved fast CSI.

Detection of Ureteral Stones in Kidney Ureter Bladder Radiography: Usefulness of Digital Post-processing.

PURPOSE: Kidney, Ureter, and Bladder radiography (KUB) has frequently been used in suspected urolithiasis, but its performance is known to be lower than that of Computed Tomography (CT). This study aimed to investigate the diagnostic performance of digitally KUB in the detection of ureteral stones. MATERIALS AND METHODS: Thirty patients who underwent digital KUB and CT were included in this retrospective study. The original digital KUB underwent post-processing that involved noise estimation, reduction, and whitening in improving the visibility of ureteral stones. Thus, 60 digital original or post-processed KUB images were obtained and ordered randomly for blinded review. After a period, a second review was performed after unblinding stone laterality. The detection rates were evaluated at both initial and second reviews, using CT as a reference standard. The objective (size) and subjective (visibility) parameters of ureteral stones were analyzed. Fisher's exact test was used to compare the detection sensitivity between the original and post-processed KUB data set. Visibility analysis was assessed with a paired t-test. The correlation of stone size between CT and digital KUB data sets was assessed with the Pearson's correlation test. RESULTS: The detection rate was higher for most reviewers once stone laterality was provided and was non-significantly better for the post-processed KUB images (p > 0.05). There was no significant difference in stone size among CT and digital KUB data sets. In all reviews, visibility grade was higher in the post-processed KUB images, irrespective of whether stone laterality was provided. CONCLUSION: Digital post-processing of KUB yielded higher visibility of ureteral stones and could improve stone detection, especially when stone laterality was available. Thus, digitally post-processed KUB can be an excellent modality for detecting ureteral stones and measuring their exact size.

Metabolite-selective hyperpolarized (13)C imaging using extended chemical shift displacement at 9.4T.

PURPOSE: To develop a technique for frequency-selective hyperpolarized (13)C metabolic imaging in ultra-high field strength which exploits the broad spatial chemical shift displacement in providing spectral and spatial selectivity. METHODS: The spatial chemical shift displacement caused by the slice-selection gradient was utilized in acquiring metabolite-selective images. Interleaved images of different metabolites were acquired by reversing the polarity of the slice-selection gradient at every repetition time, while using a low-bandwidth radio-frequency excitation pulse to alternatingly shift the displaced excitation bands outside the imaging subject. Demonstration of this technique is presented using (1)H phantom and in vivo mouse renal hyperpolarized (13)C imaging experiments with conventional chemical shift imaging and fast low-angle shot sequences. RESULTS: From phantom and in vivo mouse studies, the spectral selectivity of the proposed method is readily demonstrated using results of chemical shift spectroscopic imaging, which displayed clearly delineated images of different metabolites. Imaging results using the proposed method without spectral encoding also showed effective separation while also providing high spatial resolution. CONCLUSION: This method provides a way to acquire spectrally selective hyperpolarized (13)C metabolic images in a simple implementation, and with potential ability to support combination with more elaborate readout methods for faster imaging.

Computer-aided detection of metastatic brain tumors using magnetic resonance black-blood imaging.

OBJECTIVES: The objective of this study was to develop a computer-aided detection system for automated brain metastases detection using magnetic resonance black-blood imaging and compare its applicability with conventional magnetization-prepared rapid gradient echo (MP-RAGE) imaging. MATERIALS AND METHODS: Twenty-six patients with brain metastases were imaged with a contrast-enhanced, 3-dimensional, whole-brain magnetic resonance black-blood pulse sequence. Approval from the institutional review board and informed consent from the patients were obtained. Preprocessing steps included B1 inhomogeneity correction and brain extraction. The computer-aided detection system used 3-dimensional template matching, which measured normalized cross-correlation coefficient to generate possible metastases candidates. An artificial neural network was used for classification after various volume features were extracted. The same detection procedure was tested with contrast-enhanced MP-RAGE, which was also acquired from the same patients. RESULTS: The performance of the proposed detection method was measured by the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity values. In the black-blood case, detection process displayed an AUROC of 0.9355, a sensitivity value of 81.1%, and a specificity value of 98.2%. Magnetization-prepared rapid gradient echo data showed an AUROC of 0.6508, a sensitivity value of 30.2%, and a specificity value of 99.97%. CONCLUSIONS: The results demonstrate that accurate automated detection of metastatic brain tumors using contrast-enhanced black-blood imaging sequence is possible compared with using conventional contrast-enhanced MP-RAGE sequence.