Lung Nodule Malignancy Prediction in Sequential CT Scans: Summary of ISBI 2018 Challenge.

Lung cancer is by far the leading cause of cancer death in the US. Recent studies have demonstrated the effectiveness of screening using low dose CT (LDCT) in reducing lung cancer related mortality. While lung nodules are detected with a high rate of sensitivity, this exam has a low specificity rate and it is still difficult to separate benign and malignant lesions. The ISBI 2018 Lung Nodule Malignancy Prediction Challenge, developed by a team from the Quantitative Imaging Network of the National Cancer Institute, was focused on the prediction of lung nodule malignancy from two sequential LDCT screening exams using automated (non-manual) algorithms. We curated a cohort of 100 subjects who participated in the National Lung Screening Trial and had established pathological diagnoses. Data from 30 subjects were randomly selected for training and the remaining was used for testing. Participants were evaluated based on the area under the receiver operating characteristic curve (AUC) of nodule-wise malignancy scores generated by their algorithms on the test set. The challenge had 17 participants, with 11 teams submitting reports with method description, mandated by the challenge rules. Participants used quantitative methods, resulting in a reporting test AUC ranging from 0.698 to 0.913. The top five contestants used deep learning approaches, reporting an AUC between 0.87 - 0.91. The team's predictor did not achieve significant differences from each other nor from a volume change estimate (p =.05 with Bonferroni-Holm's correction).

Quantitative Relationships Between Individual Lower-Limb Muscle Volumes and Jump and Sprint Performances of Basketball Players.

Xie, T, Crump, KB, Ni, R, Meyer, CH, Hart, JM, Blemker, SS, and Feng, X. Quantitative relationships between individual lower-limb muscle volumes and jump and sprint performances of basketball players. J Strength Cond Res 34(3): 623-631, 2020-Lower body skeletal muscles play an essential role in athletic performance; however, because of the difficulty in obtaining detailed information of each individual muscle, the quantitative relationships between individual muscle volumes and performance are not well studied. The aim of this study was to accurately measure individual muscle volumes and identify the muscles with strong correlations with jump and sprint performance metrics for basketball players. Ten male varsity basketball players and 8 club players were scanned using magnetic resonance imaging (MRI) and instructed to perform various jump and sprint tests. The volumes of all lower-limb muscles were calculated from MRI and normalized by body surface area to reduce the effect of the body size differences. In analysis, feature selection was first used to identify the most relevant muscles, followed by correlation analysis to quantify the relationships between the selected muscles and each performance metric. Vastus medialis and semimembranosus were found to be the most relevant muscles for jump while adductor longus and vastus medialis were selected for sprint. Strong correlations (r = 0.664-0.909) between the selected muscles and associated performance tests were found for varsity players, and moderate correlations (r = -0.203 to 0.635) were found for club players. One possible application is that for well-trained varsity players, a targeted training scheme focusing on the selected muscles may be an effective method to further improve jump and sprint performances.

Automatic segmentation of all lower limb muscles from high-resolution magnetic resonance imaging using a cascaded three-dimensional deep convolutional neural network.

High-resolution magnetic resonance imaging with fat suppression can obtain accurate anatomical information of all 35 lower limb muscles and individual segmentation can facilitate quantitative analysis. However, due to limited contrast and edge information, automatic segmentation of the muscles is very challenging, especially for athletes whose muscles are all well developed and more compact than the average population. Deep convolutional neural network (DCNN)-based segmentation methods showed great promise in many clinical applications, however, a direct adoption of DCNN to lower limb muscle segmentation is challenged by the large three-dimensional (3-D) image size and lack of the direct usage of muscle location information. We developed a cascaded 3-D DCNN model with the first step to localize each muscle using low-resolution images and the second step to segment it using cropped high-resolution images with individually trained networks. The workflow was optimized to account for different characteristics of each muscle for improved accuracy and reduced training and testing time. A testing augmentation technique was proposed to smooth the segmentation contours. The segmentation performance of 14 muscles was within interobserver variability and 21 were slightly worse than humans.