Higher weight in partially leptin-resistant db/+ mice is associated with positive effects on bone.

Absence of leptin confers metabolic dysfunction resulting in morbid obesity. Bone growth and maturation are also impaired. Partial leptin resistance is more common than leptin deficiency and, when induced by feeding mice a high fat diet, often has a negative effect on bone. Here, we used a genetic model to investigate the skeletal effects of partial and total leptin resistance in mice. This was accomplished by comparing the skeletal phenotypes of 17-week-old female C57Bl6/J wild-type (WT) mice, partial leptin receptor-deficient (db/+) mice and leptin receptor-deficient (db/db) mice (n = 7-8/group), all fed a standard diet. Compared to WT mice, db/db mice were dramatically heavier and hyperleptinemic. These mice were also hypogonadal, hyperglycemic, osteopenic and had lower serum levels of bone turnover markers, osteocalcin and C-terminal telopeptide of type I collagen (CTX). Compared to WT mice, db/+ mice were 14% heavier, had 149% more abdominal white adipose tissue, and were mildly hyperglycemic. db/+ mice did not differ from WT mice in uterine weight or serum levels of markers of bone turnover, although there was a trend for lower osteocalcin. At the bone microarchitectural level, db/+ mice differed from WT mice in having more massive femurs and a trend (P = 0.072) for larger vertebrae. These findings suggest that db/+ mice fed a normal mouse diet compensate for partial leptin resistance by increasing white adipose tissue mass which results in higher leptin levels. Our findings suggest that db/+ mice are a useful diet-independent model for studying the effects of partial leptin resistance on the skeleton.

Severe Zinc Deficiency Impairs Accrual of Bone in Rapidly Growing Rats That Is Partially Corrected Following Short-term Zinc Repletion.

Zinc (Zn) deficiency impairs bone growth. However, the precise skeletal effects of varying levels of Zn deficiency and response to subsequent Zn repletion on the growing skeleton are incompletely understood. To address this gap in knowledge, we investigated the effects of dietary Zn ((severe deficiency (< 0.5 mg Zn/kg diet) and short-term Zn repletion (30 mg/kg diet), marginal deficiency (6 mg Zn/kg diet)) on bone mass, density, and cortical and cancellous bone microarchitecture in growing male Sprague Dawley rats. Marginal Zn intake for 42 days had no effect on bone mass or cortical and cancellous bone microarchitecture. Twenty-one days of severe Zn deficiency lowered serum osteocalcin and C terminal telopeptide of type I collagen (CTX-1), decreased tibial bone mineral content and density, and lowered cross-sectional volume, cortical volume, and cortical thickness in tibial diaphysis as compared to both Zn-adequate (30 mg/kg diet) and pair-fed controls. Severe Zn deficiency similarly lowered cancellous bone volume in proximal tibial metaphysis. Zn repletion (10 days) accelerated weight gain, indicative of catch-up growth, normalized CTX-1 and osteocalcin, but did not normalize bone mass (unadjusted and adjusted for body weight) or cortical and cancellous bone microarchitecture. In summary, severe but not marginal Zn deficiency in rapidly growing rats impaired acquisition of cortical and cancellous bone, resulting in abnormalities in bone microarchitecture. Zn repletion accelerated weight gain compared to Zn-adequate controls but absence of a compensatory increase in serum osteocalcin or bone mass suggests Zn repletion may be insufficient to fully counteract the detrimental effects of prior Zn deficiency on skeletal growth.

Leptin and environmental temperature as determinants of bone marrow adiposity in female mice.

Bone marrow adipose tissue (BMAT) levels are higher in distal femur metaphysis of female mice housed at thermoneutral (32°C) than in mice housed at 22°C, as are abdominal white adipose tissue (WAT) mass, and serum leptin levels. We performed two experiments to explore the role of increased leptin in temperature-enhanced accrual of BMAT. First, we supplemented 6-week-old female C57BL/6J (B6) mice with leptin for 2 weeks at 10 µg/d using a subcutaneously implanted osmotic pump. Controls consisted of ad libitum (ad lib) fed mice and mice pair fed to match food intake of leptin-supplemented mice. The mice were maintained at 32°C for the duration of treatment. At necropsy, serum leptin in leptin-supplemented mice did not differ from ad lib mice, suggesting suppression of endogenous leptin production. In support, Ucp1 expression in BAT, percent body fat, and abdominal WAT mass were lower in leptin-supplemented mice. Leptin-supplemented mice also had lower BMAT and higher bone formation in distal femur metaphysis compared to the ad lib group, changes not replicated by pair-feeding. In the second experiment, BMAT response was evaluated in 6-week-old female B6 wild type (WT), leptin-deficient ob/ob and leptin-treated (0.3 µg/d) ob/ob mice housed at 32°C for the 2-week duration of the treatment. Compared to mice sacrificed at baseline (22°C), BMAT increased in ob/ob mice as well as WT mice, indicating a leptin independent response to increased temperature. However, infusion of ob/ob mice with leptin, at a dose rate having negligible effects on either energy metabolism or serum leptin levels, attenuated the increase in BMAT. In summary, increased housing temperature and increased leptin have independent but opposing effects on BMAT in mice.

Impact of measurement method on interobserver variability of apparent diffusion coefficient of lesions in prostate MRI.

PURPOSE: To compare the inter-observer variability of apparent diffusion coefficient (ADC) values of prostate lesions measured by 2D-region of interest (ROI) with and without specific measurement instruction. METHODS: Forty lesions in 40 patients who underwent prostate MR followed by targeted prostate biopsy were evaluated. A multi-reader study (10 readers) was performed to assess the agreement of ADC values between 2D-ROI without specific instruction and 2D-ROI with specific instruction to place a 9-pixel size 2D-ROI covering the lowest ADC area. The computer script generated multiple overlapping 9-pixel 2D-ROIs within a 3D-ROI encompassing the entire lesion placed by a single reader. The lowest mean ADC values from each 2D-small-ROI were used as reference values. Inter-observer agreement was assessed using the Bland-Altman plot. Intraclass correlation coefficient (ICC) was assessed between ADC values measured by 10 readers and the computer-calculated reference values. RESULTS: Ten lesions were benign, 6 were Gleason score 6 prostate carcinoma (PCa), and 24 were clinically significant PCa. The mean±SD ADC reference value by 9-pixel-ROI was 733 ± 186 (10-6 mm2/s). The 95% limits of agreement of ADC values among readers were better with specific instruction (±112) than those without (±205). ICC between reader-measured ADC values and computer-calculated reference values ranged from 0.736-0.949 with specific instruction and 0.349-0.919 without specific instruction. CONCLUSION: Interobserver agreement of ADC values can be improved by indicating a measurement method (use of a specific ROI size covering the lowest ADC area).

Determining age and sex-specific distribution of pancreatic whole-gland CT attenuation using artificial intelligence aided image segmentation: Associations with body composition and pancreatic cancer risk.

BACKGROUND & AIMS: Increased intrapancreatic fat is associated with pancreatic diseases; however, there are no established objective diagnostic criteria for fatty pancreas. On non-contrast computed tomography (CT), adipose tissue shows negative Hounsfield Unit (HU) attenuations (-150 to -30 HU). Using whole organ segmentation on non-contrast CT, we aimed to describe whole gland pancreatic attenuation and establish 5th and 10th percentile thresholds across a spectrum of age and sex. Subsequently, we aimed to evaluate the association between low pancreatic HU and risk of pancreatic ductal adenocarcinoma (PDAC). METHODS: The whole pancreas was segmented in 19,456 images from 469 non-contrast CT scans. A convolutional neural network was trained to assist pancreas segmentation. Mean pancreatic HU, volume, and body composition metrics were calculated. The lower 5th and 10th percentile for mean pancreatic HU were identified, examining the association with age and sex. Pre-diagnostic CT scans from patients who later developed PDAC were compared to cancer-free controls. RESULTS: Less than 5th percentile mean pancreatic HU was significantly associated with increase in BMI (OR 1.07; 1.03-1.11), visceral fat (OR 1.37; 1.15-1.64), total abdominal fat (OR 1.12; 1.03-1.22), and diabetes mellitus type 1 (OR 6.76; 1.68-27.28). Compared to controls, pre-diagnostic scans in PDAC cases had lower mean whole gland pancreatic HU (-0.2 vs 7.8, p = 0.026). CONCLUSION: In this study, we report age and sex-specific distribution of pancreatic whole-gland CT attenuation. Compared to controls, mean whole gland pancreatic HU is significantly lower in the pre-diagnostic phase of PDAC.

Deep Learning Improves the Temporal Reproducibility of Aortic Measurement.

Imaging-based measurements form the basis of surgical decision making in patients with aortic aneurysm. Unfortunately, manual measurement suffer from suboptimal temporal reproducibility, which can lead to delayed or unnecessary intervention. We tested the hypothesis that deep learning could improve upon the temporal reproducibility of CT angiography-derived thoracic aortic measurements in the setting of imperfect ground-truth training data. To this end, we trained a standard deep learning segmentation model from which measurements of aortic volume and diameter could be extracted. First, three blinded cardiothoracic radiologists visually confirmed non-inferiority of deep learning segmentation maps with respect to manual segmentation on a 50-patient hold-out test cohort, demonstrating a slight preference for the deep learning method (p < 1e-5). Next, reproducibility was assessed by evaluating measured change (coefficient of reproducibility and standard deviation) in volume and diameter values extracted from segmentation maps in patients for whom multiple scans were available and whose aortas had been deemed stable over time by visual assessment (n = 57 patients, 206 scans). Deep learning temporal reproducibility was superior for measures of both volume (p < 0.008) and diameter (p < 1e-5) and reproducibility metrics compared favorably with previously reported values of manual inter-rater variability. Our work motivates future efforts to apply deep learning to aortic evaluation.

A Deep Learning Tool for Automated Radiographic Measurement of Acetabular Component Inclination and Version After Total Hip Arthroplasty.

BACKGROUND: Inappropriate acetabular component angular position is believed to increase the risk of hip dislocation after total hip arthroplasty. However, manual measurement of these angles is time consuming and prone to interobserver variability. The purpose of this study was to develop a deep learning tool to automate the measurement of acetabular component angles on postoperative radiographs. METHODS: Two cohorts of 600 anteroposterior (AP) pelvis and 600 cross-table lateral hip postoperative radiographs were used to develop deep learning models to segment the acetabular component and the ischial tuberosities. Cohorts were manually annotated, augmented, and randomly split to train-validation-test data sets on an 8:1:1 basis. Two U-Net convolutional neural network models (one for AP and one for cross-table lateral radiographs) were trained for 50 epochs. Image processing was then deployed to measure the acetabular component angles on the predicted masks for anatomical landmarks. Performance of the tool was tested on 80 AP and 80 cross-table lateral radiographs. RESULTS: The convolutional neural network models achieved a mean Dice similarity coefficient of 0.878 and 0.903 on AP and cross-table lateral test data sets, respectively. The mean difference between human-level and machine-level measurements was 1.35° (σ = 1.07°) and 1.39° (σ = 1.27°) for the inclination and anteversion angles, respectively. Differences of 5° or more between human-level and machine-level measurements were observed in less than 2.5% of cases. CONCLUSION: We developed a highly accurate deep learning tool to automate the measurement of angular position of acetabular components for use in both clinical and research settings. LEVEL OF EVIDENCE: III.

Generative Adversarial Networks to Synthesize Missing T1 and FLAIR MRI Sequences for Use in a Multisequence Brain Tumor Segmentation Model.

Background Missing MRI sequences represent an obstacle in the development and use of deep learning (DL) models that require multiple inputs. Purpose To determine if synthesizing brain MRI scans using generative adversarial networks (GANs) allows for the use of a DL model for brain lesion segmentation that requires T1-weighted images, postcontrast T1-weighted images, fluid-attenuated inversion recovery (FLAIR) images, and T2-weighted images. Materials and Methods In this retrospective study, brain MRI scans obtained between 2011 and 2019 were collected, and scenarios were simulated in which the T1-weighted images and FLAIR images were missing. Two GANs were trained, validated, and tested using 210 glioblastomas (GBMs) (Multimodal Brain Tumor Image Segmentation Benchmark [BRATS] 2017) to generate T1-weighted images from postcontrast T1-weighted images and FLAIR images from T2-weighted images. The quality of the generated images was evaluated with mean squared error (MSE) and the structural similarity index (SSI). The segmentations obtained with the generated scans were compared with those obtained with the original MRI scans using the dice similarity coefficient (DSC). The GANs were validated on sets of GBMs and central nervous system lymphomas from the authors' institution to assess their generalizability. Statistical analysis was performed using the Mann-Whitney, Friedman, and Dunn tests. Results Two hundred ten GBMs from the BRATS data set and 46 GBMs (mean patient age, 58 years ± 11 [standard deviation]; 27 men [59%] and 19 women [41%]) and 21 central nervous system lymphomas (mean patient age, 67 years ± 13; 12 men [57%] and nine women [43%]) from the authors' institution were evaluated. The median MSE for the generated T1-weighted images ranged from 0.005 to 0.013, and the median MSE for the generated FLAIR images ranged from 0.004 to 0.103. The median SSI ranged from 0.82 to 0.92 for the generated T1-weighted images and from 0.76 to 0.92 for the generated FLAIR images. The median DSCs for the segmentation of the whole lesion, the FLAIR hyperintensities, and the contrast-enhanced areas using the generated scans were 0.82, 0.71, and 0.92, respectively, when replacing both T1-weighted and FLAIR images; 0.84, 0.74, and 0.97 when replacing only the FLAIR images; and 0.97, 0.95, and 0.92 when replacing only the T1-weighted images. Conclusion Brain MRI scans generated using generative adversarial networks can be used as deep learning model inputs in case MRI sequences are missing. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Zhong in this issue. An earlier incorrect version of this article appeared online. This article was corrected on April 12, 2021.

Deep Learning Artificial Intelligence Model for Assessment of Hip Dislocation Risk Following Primary Total Hip Arthroplasty From Postoperative Radiographs.

BACKGROUND: Dislocation is a common complication following total hip arthroplasty (THA), and accounts for a high percentage of subsequent revisions. The purpose of this study is to illustrate the potential of a convolutional neural network model to assess the risk of hip dislocation based on postoperative anteroposterior pelvis radiographs. METHODS: We retrospectively evaluated radiographs for a cohort of 13,970 primary THAs with 374 dislocations over 5 years of follow-up. Overall, 1490 radiographs from dislocated and 91,094 from non-dislocated THAs were included in the analysis. A convolutional neural network object detection model (YOLO-V3) was trained to crop the images by centering on the femoral head. A ResNet18 classifier was trained to predict subsequent hip dislocation from the cropped imaging. The ResNet18 classifier was initialized with ImageNet weights and trained using FastAI (V1.0) running on PyTorch. The training was run for 15 epochs using 10-fold cross validation, data oversampling, and augmentation. RESULTS: The hip dislocation classifier achieved the following mean performance (standard deviation): accuracy = 49.5 (4.1%), sensitivity = 89.0 (2.2%), specificity = 48.8 (4.2%), positive predictive value = 3.3 (0.3%), negative predictive value = 99.5 (0.1%), and area under the receiver operating characteristic curve = 76.7 (3.6%). Saliency maps demonstrated that the model placed the greatest emphasis on the femoral head and acetabular component. CONCLUSION: Existing prediction methods fail to identify patients at high risk of dislocation following THA. Our radiographic classifier model has high sensitivity and negative predictive value, and can be combined with clinical risk factor information for rapid assessment of risk for dislocation following THA. The model further suggests radiographic locations which may be important in understanding the etiology of prosthesis dislocation. Importantly, our model is an illustration of the potential of automated imaging artificial intelligence models in orthopedics. LEVEL OF EVIDENCE: Level III.

Complete abdomen and pelvis segmentation using U-net variant architecture.

PURPOSE: Organ segmentation of computed tomography (CT) imaging is essential for radiotherapy treatment planning. Treatment planning requires segmentation not only of the affected tissue, but nearby healthy organs-at-risk, which is laborious and time-consuming. We present a fully automated segmentation method based on the three-dimensional (3D) U-Net convolutional neural network (CNN) capable of whole abdomen and pelvis segmentation into 33 unique organ and tissue structures, including tissues that may be overlooked by other automated segmentation approaches such as adipose tissue, skeletal muscle, and connective tissue and vessels. Whole abdomen segmentation is capable of quantifying exposure beyond a handful of organs-at-risk to all tissues within the abdomen. METHODS: Sixty-six (66) CT examinations of 64 individuals were included in the training and validation sets and 18 CT examinations from 16 individuals were included in the test set. All pixels in each examination were segmented by image analysts (with physician correction) and assigned one of 33 labels. Segmentation was performed with a 3D U-Net variant architecture which included residual blocks, and model performance was quantified on 18 test cases. Human interobserver variability (using semiautomated segmentation) was also reported on two scans, and manual interobserver variability of three individuals was reported on one scan. Model performance was also compared to several of the best models reported in the literature for multiple organ segmentation. RESULTS: The accuracy of the 3D U-Net model ranges from a Dice coefficient of 0.95 in the liver, 0.93 in the kidneys, 0.79 in the pancreas, 0.69 in the adrenals, and 0.51 in the renal arteries. Model accuracy is within 5% of human segmentation in eight of 19 organs and within 10% accuracy in 13 of 19 organs. CONCLUSIONS: The CNN approaches the accuracy of human tracers and on certain complex organs displays more consistent prediction than human tracers. Fully automated deep learning-based segmentation of CT abdomen has the potential to improve both the speed and accuracy of radiotherapy dose prediction for organs-at-risk.

Effects of Propranolol on Bone, White Adipose Tissue, and Bone Marrow Adipose Tissue in Mice Housed at Room Temperature or Thermoneutral Temperature.

Growing female mice housed at room temperature (22°C) weigh the same but differ in body composition compared to mice housed at thermoneutrality (32°C). Specifically, mice housed at room temperature have lower levels of white adipose tissue (WAT). Additionally, bone marrow adipose tissue (bMAT) and cancellous bone volume fraction in distal femur metaphysis are lower in room temperature-housed mice. The metabolic changes induced by sub-thermoneutral housing are associated with lower leptin levels in serum and higher levels of Ucp1 gene expression in brown adipose tissue. Although the precise mechanisms mediating adaptation to sub-thermoneutral temperature stress remain to be elucidated, there is evidence that increased sympathetic nervous system activity acting via ß-adrenergic receptors plays an important role. We therefore evaluated the effect of the non-specific ß-blocker propranolol (primarily ß1 and ß2 antagonist) on body composition, femur microarchitecture, and bMAT in growing female C57BL/6 mice housed at either room temperature or thermoneutral temperature. As anticipated, cancellous bone volume fraction, WAT and bMAT were lower in mice housed at room temperature. Propranolol had small but significant effects on bone microarchitecture (increased trabecular number and decreased trabecular spacing), but did not attenuate premature bone loss induced by room temperature housing. In contrast, propranolol treatment prevented housing temperature-associated differences in WAT and bMAT. To gain additional insight, we evaluated a panel of genes in tibia, using an adipogenesis PCR array. Housing temperature and treatment with propranolol had exclusive as well as shared effects on gene expression. Of particular interest was the finding that room temperature housing reduced, whereas propranolol increased, expression of the gene for acetyl-CoA carboxylase (Acacb), the rate-limiting step for fatty acid synthesis and a key regulator of ß-oxidation. Taken together, these findings provide evidence that increased activation of ß1 and/or ß2 receptors contributes to reduced bMAT by regulating adipocyte metabolism, but that this pathway is unlikely to be responsible for premature cancellous bone loss in room temperature-housed mice.

Fully Automated Segmentation of Head CT Neuroanatomy Using Deep Learning.

PURPOSE: To develop a deep learning model that segments intracranial structures on head CT scans. MATERIALS AND METHODS: In this retrospective study, a primary dataset containing 62 normal noncontrast head CT scans from 62 patients (mean age, 73 years; age range, 27-95 years) acquired between August and December 2018 was used for model development. Eleven intracranial structures were manually annotated on the axial oblique series. The dataset was split into 40 scans for training, 10 for validation, and 12 for testing. After initial training, eight model configurations were evaluated on the validation dataset and the highest performing model was evaluated on the test dataset. Interobserver variability was reported using multirater consensus labels obtained from the test dataset. To ensure that the model learned generalizable features, it was further evaluated on two secondary datasets containing 12 volumes with idiopathic normal pressure hydrocephalus (iNPH) and 30 normal volumes from a publicly available source. Statistical significance was determined using categorical linear regression with P < .05. RESULTS: Overall Dice coefficient on the primary test dataset was 0.84 ± 0.05 (standard deviation). Performance ranged from 0.96 ± 0.01 (brainstem and cerebrum) to 0.74 ± 0.06 (internal capsule). Dice coefficients were comparable to expert annotations and exceeded those of existing segmentation methods. The model remained robust on external CT scans and scans demonstrating ventricular enlargement. The use of within-network normalization and class weighting facilitated learning of underrepresented classes. CONCLUSION: Automated segmentation of CT neuroanatomy is feasible with a high degree of accuracy. The model generalized to external CT scans as well as scans demonstrating iNPH.Supplemental material is available for this article.© RSNA, 2020.

Thermoneutral housing attenuates premature cancellous bone loss in male C57BL/6J mice.

Mice are a commonly used model to investigate aging-related bone loss but, in contrast to humans, mice exhibit cancellous bone loss prior to skeletal maturity. The mechanisms mediating premature bone loss are not well established. However, our previous work in female mice suggests housing temperature is a critical factor. Premature cancellous bone loss was prevented in female C57BL/6J mice by housing the animals at thermoneutral temperature (where basal rate of energy production is at equilibrium with heat loss). In the present study, we determined if the protective effects of thermoneutral housing extend to males. Male C57BL/6J mice were housed at standard room temperature (22°C) or thermoneutral (32°C) conditions from 5 (rapidly growing) to 16 (slowly growing) weeks of age. Mice housed at room temperature exhibited reductions in cancellous bone volume fraction in distal femur metaphysis and fifth lumbar vertebra; these effects were abolished at thermoneutral conditions. Mice housed at thermoneutral temperature had higher levels of bone formation in distal femur (based on histomorphometry) and globally (serum osteocalcin), and lower global levels of bone resorption (serum C-terminal telopeptide of type I collagen) compared to mice housed at room temperature. Thermoneutral housing had no impact on bone marrow adiposity but resulted in higher abdominal white adipose tissue and serum leptin. The overall magnitude of room temperature housing-induced cancellous bone loss did not differ between male (current study) and female (published data) mice. These findings highlight housing temperature as a critical experimental variable in studies using mice of either sex to investigate aging-related changes in bone metabolism.

A Survey of Deep-Learning Applications in Ultrasound: Artificial Intelligence-Powered Ultrasound for Improving Clinical Workflow.

Ultrasound is the most commonly used imaging modality in clinical practice because it is a nonionizing, low-cost, and portable point-of-care imaging tool that provides real-time images. Artificial intelligence (AI)-powered ultrasound is becoming more mature and getting closer to routine clinical applications in recent times because of an increased need for efficient and objective acquisition and evaluation of ultrasound images. Because ultrasound images involve operator-, patient-, and scanner-dependent variations, the adaptation of classical machine learning methods to clinical applications becomes challenging. With their self-learning ability, deep-learning (DL) methods are able to harness exponentially growing graphics processing unit computing power to identify abstract and complex imaging features. This has given rise to tremendous opportunities such as providing robust and generalizable AI models for improving image acquisition, real-time assessment of image quality, objective diagnosis and detection of diseases, and optimizing ultrasound clinical workflow. In this report, the authors review current DL approaches and research directions in rapidly advancing ultrasound technology and present their outlook on future directions and trends for DL techniques to further improve diagnosis, reduce health care cost, and optimize ultrasound clinical workflow.

Effects of Alcohol and Estrogen Receptor Blockade Using ICI 182,780 on Bone in Ovariectomized Rats.

BACKGROUND: Estrogen signaling is essential for the sexual dimorphism of the skeleton, is required for normal bone remodeling balance in adults, and may influence the skeletal response to alcohol. High levels of alcohol consumption lower bone mass in ovary-intact but not ovariectomized (ovx) rats. However, the extremely rapid rate of bone loss immediately following ovx may obscure the effects of alcohol. We therefore determined (i) whether heavy alcohol consumption (35% caloric intake) influences bone in sexually mature ovx rats with established cancellous osteopenia and (ii) whether ICI 182,780 (ICI), a potent estrogen receptor signaling antagonist, alters the skeletal response to alcohol. METHODS: Three weeks following ovx, rats were randomized into 5 groups, (i) baseline, (ii) control + vehicle, (iii) control + ICI, (iv) ethanol (EtOH) + vehicle, or (v) EtOH + ICI, and treated accordingly for 4 weeks. Dual-energy X-ray absorptiometry, microcomputed tomography, blood measurements of markers of bone turnover, and gene expression in femur and uterus were used to evaluate response to alcohol and ICI. RESULTS: Rats consuming alcohol had lower bone mass and increased fat mass. Bone microarchitecture of the tibia and gene expression in femur were altered; specifically, there was reduced accrual of cortical bone, net loss of cancellous bone, and differential expression of 19/84 genes related to bone turnover. Furthermore, osteocalcin, a marker of bone turnover, was lower in alcohol-fed rats. ICI had no effect on weight gain, body composition, or cortical bone. ICI reduced cancellous bone loss and serum CTX-1, a biochemical marker of bone resorption; alcohol antagonized the latter 2 responses. Neither alcohol nor ICI affected uterine weight or gene expression. CONCLUSIONS: Alcohol exaggerated bone loss in ovx rats in the presence or absence of estrogen receptor blockade with ICI. The negligible effect of alcohol on uterus and limited effects of ICI on bone in alcohol-fed ovx rats suggest that estrogen receptor signaling plays a limited role in the action of alcohol on bone in a rat model for chronic alcohol abuse.

RIL-Contour: a Medical Imaging Dataset Annotation Tool for and with Deep Learning.

Deep-learning algorithms typically fall within the domain of supervised artificial intelligence and are designed to "learn" from annotated data. Deep-learning models require large, diverse training datasets for optimal model convergence. The effort to curate these datasets is widely regarded as a barrier to the development of deep-learning systems. We developed RIL-Contour to accelerate medical image annotation for and with deep-learning. A major goal driving the development of the software was to create an environment which enables clinically oriented users to utilize deep-learning models to rapidly annotate medical imaging. RIL-Contour supports using fully automated deep-learning methods, semi-automated methods, and manual methods to annotate medical imaging with voxel and/or text annotations. To reduce annotation error, RIL-Contour promotes the standardization of image annotations across a dataset. RIL-Contour accelerates medical imaging annotation through the process of annotation by iterative deep learning (AID). The underlying concept of AID is to iteratively annotate, train, and utilize deep-learning models during the process of dataset annotation and model development. To enable this, RIL-Contour supports workflows in which multiple-image analysts annotate medical images, radiologists approve the annotations, and data scientists utilize these annotations to train deep-learning models. To automate the feedback loop between data scientists and image analysts, RIL-Contour provides mechanisms to enable data scientists to push deep newly trained deep-learning models to other users of the software. RIL-Contour and the AID methodology accelerate dataset annotation and model development by facilitating rapid collaboration between analysts, radiologists, and engineers.

MANAGEMENT AND OUTCOMES OF GIANT PROLACTINOMA: A SERIES OF 71 PATIENTS.

Objective: To describe outcomes of patients with giant prolactinoma (≥4 cm) and identify predictors of therapeutic response. Methods: In this retrospective study, complete biochemical and structural response were defined as prolactin (PRL) ≤25 ng/mL and no visible tumor at follow-up, respectively. Results: Giant prolactinoma (median size, 4.8 cm [range, 4 to 9.8 cm]; median PRL, 5,927 ng/mL [range, 120 to 100,000 ng/mL]) was diagnosed in 71 patients. Treatments included: dopamine agonists (DAs) (n = 70, 99%), surgery (n = 30, 42%), radiation (n = 10, 14%), and somatostatin analogs (n = 2, 3%). Patients treated with DA monotherapy were older compared with those who received subsequent therapies (47 years vs. 28 years; P = .003) but had similar initial PRL and tumor size. Surgically managed patients were younger compared with the nonsurgical group (35 years vs. 46 years; P = .02) and had lower initial PRL (3,121 ng/mL vs. 6,920 ng/mL; P = .02), yet they had similar tumor response. Hypopituitarism was more common following surgery compared to medical management: adrenal insufficiency (69% vs. 27%; P<.001), hypothyroidism (67% vs. 38%; P = .02), growth hormone deficiency (24% vs. 6%; P = .04), and diabetes insipidus (17% vs. 3%; P = .04). Therapeutic response did not correlate with sex, age, initial PRL, tumor size, or first-line therapy mode. At median follow-up of 4.8 years, the median PRL was 18.3 ng/mL (range, 0.6 to 12,680 ng/mL), and final volume was 0.9 cm3 (range, 0 to 43.0 cm3). In those with available data, 36/65 (55%) patients achieved PRL normalization, and 16/61 (26%) had no visible tumor at follow-up. Conclusion: Most patients with giant prolactinoma have excellent response to DA. Sex, age, initial PRL, and tumor size do not predict therapeutic response. Abbreviations: BRC = bromocriptine; CAB = cabergoline; CSF = cerebrospinal fluid; DA = dopamine agonist; MRI = magnetic resonance imaging; PRL = prolactin.

Phases of Metabolic and Soft Tissue Changes in Months Preceding a Diagnosis of Pancreatic Ductal Adenocarcinoma.

BACKGROUND & AIMS: Identifying metabolic abnormalities that occur before pancreatic ductal adenocarcinoma (PDAC) diagnosis could increase chances for early detection. We collected data on changes in metabolic parameters (glucose, serum lipids, triglycerides; total, low-density, and high-density cholesterol; and total body weight) and soft tissues (abdominal subcutaneous fat [SAT], adipose tissue, visceral adipose tissue [VAT], and muscle) from patients 5 years before the received a diagnosis of PDAC. METHODS: We collected data from 219 patients with a diagnosis of PDAC (patients) and 657 healthy individuals (controls) from the Rochester Epidemiology Project, from 2000 through 2015. We compared metabolic profiles of patients with those of age- and sex-matched controls, constructing temporal profiles of fasting blood glucose, serum lipids including triglycerides, cholesterol profiles, and body weight and temperature for 60 months before the diagnosis of PDAC (index date). To construct the temporal profile of soft tissue changes, we collected computed tomography scans from 68 patients, comparing baseline (>18 months before diagnosis) areas of SAT, VAT, and muscle at L2/L3 vertebra with those of later scans until time of diagnosis. SAT and VAT, isolated from healthy individuals, were exposed to exosomes isolated from PDAC cell lines and analyzed by RNA sequencing. SAT was collected from KRAS+/LSLG12D P53flox/flox mice with PDACs, C57/BL6 (control) mice, and 5 patients and analyzed by histology and immunohistochemistry. RESULTS: There were no significant differences in metabolic or soft tissue features of patients vs controls until 30 months before PDAC diagnosis. In the 30 to 18 months before PDAC diagnosis (phase 1, hyperglycemia), a significant proportion of patients developed hyperglycemia, compared with controls, without soft tissue changes. In the 18 to 6 months before PDAC diagnosis (phase 2, pre-cachexia), patients had significant increases in hyperglycemia and decreases in serum lipids, body weight, and SAT, with preserved VAT and muscle. In the 6 to 0 months before PDAC diagnosis (phase 3, cachexia), a significant proportion of patients had hyperglycemia compared with controls, and patients had significant reductions in all serum lipids, SAT, VAT, and muscle. We believe the patients had browning of SAT, based on increases in body temperature, starting 18 months before PDAC diagnosis. We observed expression of uncoupling protein 1 (UCP1) in SAT exposed to PDAC exosomes, SAT from mice with PDACs, and SAT from all 5 patients but only 1 of 4 controls. CONCLUSIONS: We identified 3 phases of metabolic and soft tissue changes that precede a diagnosis of PDAC. Loss of SAT starts 18 months before PDAC identification, and is likely due to browning. Overexpression of UCP1 in SAT might be a biomarker of early-stage PDAC, but further studies are needed.

Automated Abdominal Segmentation of CT Scans for Body Composition Analysis Using Deep Learning.

Purpose To develop and evaluate a fully automated algorithm for segmenting the abdomen from CT to quantify body composition. Materials and Methods For this retrospective study, a convolutional neural network based on the U-Net architecture was trained to perform abdominal segmentation on a data set of 2430 two-dimensional CT examinations and was tested on 270 CT examinations. It was further tested on a separate data set of 2369 patients with hepatocellular carcinoma (HCC). CT examinations were performed between 1997 and 2015. The mean age of patients was 67 years; for male patients, it was 67 years (range, 29-94 years), and for female patients, it was 66 years (range, 31-97 years). Differences in segmentation performance were assessed by using two-way analysis of variance with Bonferroni correction. Results Compared with reference segmentation, the model for this study achieved Dice scores (mean ± standard deviation) of 0.98 ± 0.03, 0.96 ± 0.02, and 0.97 ± 0.01 in the test set, and 0.94 ± 0.05, 0.92 ± 0.04, and 0.98 ± 0.02 in the HCC data set, for the subcutaneous, muscle, and visceral adipose tissue compartments, respectively. Performance met or exceeded that of expert manual segmentation. Conclusion Model performance met or exceeded the accuracy of expert manual segmentation of CT examinations for both the test data set and the hepatocellular carcinoma data set. The model generalized well to multiple levels of the abdomen and may be capable of fully automated quantification of body composition metrics in three-dimensional CT examinations. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Chang in this issue.