Search

PurposeTo use machine learning tools and leverage big data informatics to statistically model the variation in the area of lumbar neural foramina in a large asymptomatic population.Materials and methodsBy using an electronic health record and imaging archive, lumbar MRI studies in 645 male (mean age, 50.07 years) and 511 female (mean age, 48.23 years) patients between 20 and 80 years old were identified. Machine learning algorithms were used to delineate lumbar neural foramina autonomously and measure their areas. The relationship between neural foraminal area and patient age, sex, and height was studied by using multivariable linear regression.ResultsNeural foraminal areas correlated directly with patient height and inversely with patient age. The associations involved were statistically significant (P < .01).ConclusionBy using machine learning and big data techniques, a linear model encoding variation in lumbar neural foraminal areas in asymptomatic individuals has been established. This model can be used to make quantitative assessments of neural foraminal areas in patients by comparing them to the age-, sex-, and height-adjusted population averages.© RSNA, 2019Supplemental material is available for this article.

Head computed tomography (CT) is instrumental for managing patients of all ages. However, its low dose radiation may pose a low but non-zero risk of tumor induction in pediatric patients. Here, we present a systematic literature review on the estimated incidence of brain tumor induction from head CT exams performed on children and adolescents. MEDLINE was searched using an electronic protocol and bibliographic searches to identify articles related to CT, cancer, and epidemiology or risk assessment. Sixteen studies that predicted or measured head CT-related neoplasm incidence or mortality were identified and reviewed. Epidemiological studies consistently cited increased tumor incidence in pediatric patients (ages 0-18) exposed to head CTs. Excess relative risk of new brain tumor averaged 1.29 (95% confidence interval, 0.66-1.93) for pediatric patients exposed to one or more head CTs. Tumor incidence increased with number of pediatric head CTs in a dose-dependent manner, with measurable excess incidence even after a single scan. Converging evidence from epidemiological studies supported a small excess risk of brain tumor incidence after even a single CT exam in pediatric patients. However, refined epidemiological methods are needed to control for confounding variables that may contribute to reverse causation, such as patients with pre-existing cancer or cancer susceptibility. CT remains an invaluable technology that should be utilized so long as there is clinical indication for the study and the radiation dose is as small as reasonably achievable.

Objectives  Superior semicircular canal dehiscence (SSCD) results from a defect in the middle cranial fossa floor. One challenge during SSCD repair is the lack of a consistent landmark. This study proposes a reference point above the external auditory canal at the level of the zygoma as the inferior craniectomy edge during surgery. Design  This is a retrospective review of patients with SSCD. Setting/Participants  A total of 72 cases of SSCD in 60 patients were repaired via a middle fossa approach at a single institution. Main Outcome Measures  The distance from the proposed reference point to the dehiscence was statistically analyzed using Shapiro-Wilk's goodness-of-fit test and Student's t -test. Results  Average distance for all patients was 28.84 ± 2.22 mm (range: 22.96-33.43). Average distance for females was 29.08 mm (range: 24.56-33.43) versus 28.26 mm (range: 22.96-32.36) for males. There was no difference in distance by sex ( p  = 0.174). The distance measurements followed a normal distribution with 95% of the patients between 24.49 and 33.10 mm. Conclusion  This study analyzed a potential reference point during a middle fossa approach for SSCD surgery. The distance from this reference point to the SSCD was found to be consistent and may serve as a readily identifiable landmark in localizing the dehiscence.

Superior semicircular canal dehiscence (SSCD) describes a pathological aperture at the level of the arcuate eminence. Techniques for quantifying defect size are described with most studies using two-dimensional lengths that underestimate the pathology. The objective of this study is to describe a novel method of measurement that combines manual segmentation of high-resolution computed tomography (HRCT) images of the temporal bone and a morphological skeletonization transform to calculate dehiscence volume. Images were imported into a freely available image segmentation tool: ITK-SNAP (version 3.4.0; available at: http://www.itksnap.org/) software. Coronal and sagittal planes were used to outline the dehiscence in all slices demonstrating the defect using the paintbrush tool. A morphological skeletonization transform derived a single-pixel thick representation of the original delineation. This "sheet" of voxels overlaid the dehiscence. Volume was calculated by counting the number of nonzero image voxels within this "sheet" and multiplying this number by the volume (mm3) of each voxel. A total of 70 cases of SSCD were identified. Overall, mean volume was 0.88 mm3 (standard deviation: 0.57, range: 0.11-2.27). We present a novel technique for measuring SSCD, which we believe provides a more accurate representation of the pathology, and has the potential to standardize measurement of SSCD.

The development of quantitative imaging biomarkers in medicine requires automatic delineation of relevant anatomical structures using available imaging data. However, this task is complicated in clinical medicine due to the variation in scanning parameters and protocols, even within a single medical center. Existing literature on automatic image segmentation using MR data is based on the analysis of highly homogenous images obtained using a fixed set of pulse sequence parameters (TR/TE). Unfortunately, algorithms that operate on fixed scanning parameters do not avail themselves to real-world daily clinical use due to the existing variation in scanning parameters and protocols. Thus, it is necessary to develop algorithmic techniques that can address the challenge of MR image segmentation using real clinical data. Toward this goal, we developed a multi-parametric ensemble learning technique to automatically detect and segment lumbar vertebral bodies using MR images of the spine. We use spine imaging data to illustrate our techniques since low back pain is an extremely common condition and a typical spine clinic evaluates patients that have been referred with a wide range of scanning parameters. This method was designed with special emphasis on robustness so that it can perform well despite the inherent variation in scanning protocols. Specifically, we show how a single multi-parameter ensemble model trained with manually labeled T2 scans can autonomously segment vertebral bodies on scans with echo times varying between 24 and 147 ms and relaxation times varying between 1500 and 7810 ms. Furthermore, even though the model was trained using T2-MR imaging data, it can accurately segment vertebral bodies on T1-MR and CT, further demonstrating the robustness and versatility of our methodology. We believe that robust segmentation techniques, such as the one presented here, are necessary for translating computer assisted diagnosis into everyday clinical practice.