Abstract
Black-blood (BB) imaging is used to complement contrast-enhanced 3D gradient-echo (CE 3D-GRE) imaging for detecting brain metastases, requiring additional scan time. In this study, we proposed deep-learned 3D BB imaging with an auto-labelling technique and 3D convolutional neural networks for brain metastases detection without additional BB scan. Patients were randomly selected for training (29 sets) and testing (36 sets). Two neuroradiologists independently evaluated deep-learned and original BB images, assessing the degree of blood vessel suppression and lesion conspicuity. Vessel signals were effectively suppressed in all patients. The figure of merits, which indicate the diagnostic performance of radiologists, were 0.9708 with deep-learned BB and 0.9437 with original BB imaging, suggesting that the deep-learned BB imaging is highly comparable to the original BB imaging (difference was not significant; p = 0.2142). In per patient analysis, sensitivities were 100% for both deep-learned and original BB imaging; however, the original BB imaging indicated false positive results for two patients. In per lesion analysis, sensitivities were 90.3% for deep-learned and 100% for original BB images. There were eight false positive lesions on the original BB imaging but only one on the deep-learned BB imaging. Deep-learned 3D BB imaging can be effective for brain metastases detection.
Highlights
Brain metastases are the most common intracranial tumors and their prevalence has been increasing due to prolonged survival of cancer patients with improved systemic therapies[1]
BB imaging is often used as a complementary modality to CE 3D-GRE imaging for brain metastasis diagnosis, but in routine clinical settings, this requires an additional scan
Modern BB imaging has been much improved by advanced techniques such as improved motion-sensitized driven-equilibrium technique[6,30], the signal suppression of blood vessels is not yet perfect, leaving some blood vessels bright on BB images, which can result in false positive lesion
Summary
Brain metastases are the most common intracranial tumors and their prevalence has been increasing due to prolonged survival of cancer patients with improved systemic therapies[1]. Several studies have generated or transformed medical images with different contrasts, such as estimating CT images from MRI data and generating synthetic MRI7,8 These could reduce the number of scans needed for accurate diagnosis, thereby reducing the acquisition time. CNNs trained in this way could be used to obtain images from other images without the need for an additional scan These studies demonstrated the feasibility of generating or transforming medical images with different contrasts using CNNs. there can be a problem with using CNNs to directly transform CE 3D-GRE images into BB images because of the different contrast and quality of BB images. Training CNNs for directly transforming CE 3D-GRE images into BB images becomes inefficient, and blur artifacts can occur in the output images, thereby obscuring metastatic lesions because of the quality and contrast difference between the input (CE 3D-GRE) and label (BB) images (Supplementary Fig. S1)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
