Deep Learning for Pediatric Posterior Fossa Tumor Detection and Classification: A Multi-Institutional Study.

BACKGROUND AND PURPOSE: Posterior fossa tumors are the most common pediatric brain tumors. MR imaging is key to tumor detection, diagnosis, and therapy guidance. We sought to develop an MR imaging-based deep learning model for posterior fossa tumor detection and tumor pathology classification. MATERIALS AND METHODS: The study cohort comprised 617 children (median age, 92 months; 56% males) from 5 pediatric institutions with posterior fossa tumors: diffuse midline glioma of the pons (n = 122), medulloblastoma (n = 272), pilocytic astrocytoma (n = 135), and ependymoma (n = 88). There were 199 controls. Tumor histology served as ground truth except for diffuse midline glioma of the pons, which was primarily diagnosed by MR imaging. A modified ResNeXt-50-32x4d architecture served as the backbone for a multitask classifier model, using T2-weighted MRIs as input to detect the presence of tumor and predict tumor class. Deep learning model performance was compared against that of 4 radiologists. RESULTS: Model tumor detection accuracy exceeded an AUROC of 0.99 and was similar to that of 4 radiologists. Model tumor classification accuracy was 92% with an F1 score of 0.80. The model was most accurate at predicting diffuse midline glioma of the pons, followed by pilocytic astrocytoma and medulloblastoma. Ependymoma prediction was the least accurate. Tumor type classification accuracy and F1 score were higher than those of 2 of the 4 radiologists. CONCLUSIONS: We present a multi-institutional deep learning model for pediatric posterior fossa tumor detection and classification with the potential to augment and improve the accuracy of radiologic diagnosis.

Physician self-referral and imaging use appropriateness: negative cervical spine MRI frequency as an assessment metric.

BACKGROUND AND PURPOSE: Imaging self-referral is increasingly cited as a contributor to diagnostic imaging overuse. The purpose of this study was to determine whether ownership of MR imaging equipment by ordering physicians influences the frequency of negative cervical spine MR imaging findings. MATERIALS AND METHODS: A retrospective review was performed of 500 consecutive cervical spine MRIs ordered by 2 separate referring-physician groups serving the same geographic community. The first group owned the scanners used and received technical fees for their use, while the second group did not. Final reports were reviewed, and for each group, the percentage of negative study findings and the frequency of abnormalities were calculated. The number of concomitant shoulder MRIs was recorded. RESULTS: Five hundred MRIs meeting inclusion criteria were reviewed (250 with financial interest, 250 with no financial interest). Three hundred fifty-two had negative findings (190 with financial interest, 162 with no financial interest); there were 17.3% more scans with negative findings in the financial interest group (P = .006). Among scans with positive findings, there was no significant difference in the mean number of lesions per scan, controlled for age (1.90 with financial interest, 2.19 with no financial interest; P = .23). Patients in the financial interest group were more likely to undergo concomitant shoulder MR imaging (24 with financial interest, 11 with no financial interest; P = .02). CONCLUSIONS: Cervical spine MRIs referred by physicians with a financial interest in the imaging equipment used were significantly more likely to have negative findings. There was otherwise a highly similar distribution and severity of disease between the 2 patient samples. Patients in the financial interest group were more likely to undergo concomitant shoulder MR imaging.

Global health imaging curriculum in radiology residency programs: the fundamentals.

Recent advances in imaging technology have created new opportunities for medical imaging to improve health care in resource-restricted countries around the world. Radiology residents are increasingly interested in global health and imaging outreach, yet infrastructure and opportunities for international outreach are limited. With the recent change in the ABR exam schedule, residents now have more flexibility in the fourth year of training to pursue elective interests, including participation in global health projects. Creating a formalized global health imaging curriculum will improve the quality, quantity, and overall impact of initiatives undertaken by residents and their training programs. A curriculum is proposed that provides content, opportunities for global health project development, and established metrics for effective evaluation and assessment. Four components considered integral to a global health imaging curriculum are described: (1) global and public health education; (2) targeted travel medicine education; (3) basic imaging proficiency; and (4) practice attitudes and accountability. Methods are presented of differentiating curricula to increase applicability across the spectrum of training programs that vary in available resources. A blueprint is presented for formalizing a global health curriculum or elective rotation within a program, as well as a resource for residents, radiologists, and organizations to make a meaningful impact on global health.

Fiber type composition and maximum shortening velocity of muscles crossing the human shoulder.

A study of the fiber type composition of fourteen muscles spanning the human glenohumeral joint was carried out with the purpose of determining the contribution of fiber types to overall muscle cross-sectional area (CSA) and to estimate the maximum shortening velocity (V(max)) of those muscles. Muscle biopsies were procured from 4 male cadavers (mean age 50) within 24 hr of death, snap frozen, mounted, and transversely sectioned (10 microm). Slides were stained for myofibrillar ATPase after alkaline preincubation. Photoimages were taken of defined areas (100 fibers) using the Bioquant system, and fiber type and CSA were measured from these images. Staining for mATPase produced three different fiber types: slow-oxidative (SO), fast-oxidative-glycolytic (FOG), and fast-glycolytic (FG). On average, the muscle fiber type composition ranged from 22 to 40% of FG, from 17 to 51% of FOG, and from 23 to 56% of SO. Twelve out of the 14 muscles had average SO proportions ranging from 35 to 50%. V(max) was calculated from the fiber type contribution relative to CSA and shortening velocity values taken from the literature. The maximum velocities of shortening presented here provide a physiological basis for the development of human shoulder musculoskeletal models suitable for predicting muscle forces for functionally relevant tasks encompassing conditions of muscle shortening and lengthening.