53% and 2.1% of MUSE-DWEPI and SS-DWEPI, respectively; The corresponding methods root-mean-square errors were 0.58, 3.37, and 5.07 mm. WSR and KW tests showed no significant difference in the ADC measurement between these three DW-MRI methods for both healthy masseter muscles and neoplasms (P > .05). We observed improvement in spatial accuracy for MUSE-DWEPI with RPG in the head and neck region with a higher correlation (R2 = 0.791) compared with that for SS-DWEPI (R2 = 0.707) and MUSE-DWEPI (R2 = 0.745). MUSE-DWEPI with RPG significantly reduces the distortion compared with MUSE-DWEPI or conventional SS-DWEPI techniques, and the ADC values were similar.We investigated the performance of multiple radiomics feature extractors/software on predicting epidermal growth factor receptor mutation status in 228 patients with non-small cell lung cancer from publicly available data sets in The Cancer Imaging Archive. The imaging and clinical data were split into training (n = 105) and validation cohorts (n = 123). Terephthalic purchase Two of the most cited open-source feature extractors, IBEX (1563 features) and Pyradiomics (1319 features), and our in-house software, Columbia Image Feature Extractor (CIFE) (1160 features), were used to extract radiomics features. Univariate and multivariate analyses were performed sequentially to predict EGFR mutation status using each individual feature extractor. Our univariate analysis integrated an unsupervised clustering method to identify nonredundant and informative candidate features for the creation of prediction models by multivariate analyses. In training, unsupervised clustering-based univariate analysis identified 5, 6, and 4 features from IBEX, Pyradiomics, and CIFE as candidate features, respectively. Multivariate prediction models using these features from IBEX, Pyradiomics, and CIFE yielded similar areas under the receiver operating characteristic curve of 0.68, 0.67, and 0.69. However, in validation, areas under the receiver operating characteristic curve of multivariate prediction models from IBEX, Pyradiomics, and CIFE decreased to 0.54, 0.56 and 0.64, respectively. Different feature extractors select different radiomics features, which leads to prediction models with varying performance. However, correlation between those selected features from different extractors may indicate these features measure similar imaging phenotypes associated with similar biological characteristics. Overall, attention should be paid to the generalizability of individual radiomics features and radiomics prediction models.This retrospective study examined magnetic resonance imaging (MRI)-derived tumor sphericity (SPH) as a quantitative measure of breast tumor morphology, and investigated the association between SPH and reader-assessed morphological pattern (MP). In addition, association of SPH with pathologic complete response was evaluated in patients enrolled in an adaptively randomized clinical trial designed to rapidly identify new agents for breast cancer. All patients underwent MRI examinations at multiple time points during the treatment. SPH values from pretreatment (T0) and early-treatment (T1) were investigated in this study. MP on T0 dynamic contrast-enhanced MRI was ranked from 1 to 5 in 220 patients. Mean SPH values decreased with the increased order of MP. SPH was higher in patients with pathologic complete response than in patients without (difference at T0 0.04, 95% confidence interval [CI] 0.02-0.05, P less then .001; difference at T1 0.03, 95% CI 0.02-0.04, P less then .001). The area under the receiver operating characteristic curve was estimated as 0.61 (95% CI, 0.57-0.65) at T0 and 0.58 (95% CI, 0.55-0.62) at T1. When the analysis was performed by cancer subtype defined by hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) status, highest area under the receiver operating characteristic curve were observed in HR-/HER2+ 0.67 (95% CI, 0.54-0.80) at T0, and 0.63 (95% CI, 0.51-0.76) at T1. Tumor SPH showed promise to quantify MRI MPs and as a biomarker for predicting treatment outcome at pre- or early-treatment time points.Noninvasive diagnosis of lung cancer in early stages is one task where radiomics helps. Clinical practice shows that the size of a nodule has high predictive power for malignancy. In the literature, convolutional neural networks (CNNs) have become widely used in medical image analysis. We study the ability of a CNN to capture nodule size in computed tomography images after images are resized for CNN input. For our experiments, we used the National Lung Screening Trial data set. Nodules were labeled into 2 categories (small/large) based on the original size of a nodule. After all extracted patches were re-sampled into 100-by-100-pixel images, a CNN was able to successfully classify test nodules into small- and large-size groups with high accuracy. To show the generality of our discovery, we repeated size classification experiments using Common Objects in Context (COCO) data set. From the data set, we selected 3 categories of images, namely, bears, cats, and dogs. For all 3 categories a 5- × 2-fold cross-validation was performed to put them into small and large classes. The average area under receiver operating curve is 0.954, 0.952, and 0.979 for the bear, cat, and dog categories, respectively. Thus, camera image rescaling also enables a CNN to discover the size of an object. The source code for experiments with the COCO data set is publicly available in Github (https//github.com/VisionAI-USF/COCO_Size_Decoding/).We have previously characterized the reproducibility of brain tumor relative cerebral blood volume (rCBV) using a dynamic susceptibility contrast magnetic resonance imaging digital reference object across 12 sites using a range of imaging protocols and software platforms. As expected, reproducibility was highest when imaging protocols and software were consistent, but decreased when they were variable. Our goal in this study was to determine the impact of rCBV reproducibility for tumor grade and treatment response classification. We found that varying imaging protocols and software platforms produced a range of optimal thresholds for both tumor grading and treatment response, but the performance of these thresholds was similar. These findings further underscore the importance of standardizing acquisition and analysis protocols across sites and software benchmarking.