Prediction of MYCN Gene Amplification in Pediatric Neuroblastomas: Development of a Deep Learning-Based Tool for Automatic Tumor Segmentation and Comparative Analysis of Computed Tomography-Based Radiomics Features Harmonization.

OBJECTIVE: MYCN oncogene amplification is closely linked to high-grade neuroblastoma with poor prognosis. Accurate quantification is essential for risk assessment, which guides clinical decision making and disease management. This study proposes an end-to-end deep-learning framework for automatic tumor segmentation of pediatric neuroblastomas and radiomics features-based classification of MYCN gene amplification. METHODS: Data from pretreatment contrast-enhanced computed tomography scans and MYCN status from 47 cases of pediatric neuroblastomas treated at a tertiary children's hospital from 2009 to 2020 were reviewed. Automated tumor segmentation and grading pipeline includes (1) a modified U-Net for tumor segmentation; (2) extraction of radiomic textural features; (3) feature-based ComBat harmonization for removal of variabilities across scanners; (4) feature selection using 2 approaches, namely, ( a ) an ensemble approach and ( b ) stepwise forward-and-backward selection method using logistic regression classifier; and (5) radiomics features-based classification of MYCN gene amplification using machine learning classifiers. RESULTS: Median train/test Dice score for modified U-Net was 0.728/0.680. The top 3 features from the ensemble approach were neighborhood gray-tone difference matrix (NGTDM) busyness, NGTDM strength, and gray-level run-length matrix (GLRLM) low gray-level run emphasis, whereas those from the stepwise approach were GLRLM low gray-level run emphasis, GLRLM high gray-level run emphasis, and NGTDM coarseness. The top-performing tumor classification algorithm achieved a weighted F1 score of 97%, an area under the receiver operating characteristic curve of 96.9%, an accuracy of 96.97%, and a negative predictive value of 100%. Harmonization-based tumor classification improved the accuracy by 2% to 3% for all classifiers. CONCLUSION: The proposed end-to-end framework achieved high accuracy for MYCN gene amplification status classification.

An end-end deep learning framework for lesion segmentation on multi-contrast MR images-an exploratory study in a rat model of traumatic brain injury.

Traumatic brain injury (TBI) engenders traumatic necrosis and penumbra-areas of secondary neural injury which are crucial targets for therapeutic interventions. Segmenting manually areas of ongoing changes like necrosis, edema, hematoma, and inflammation is tedious, error-prone, and biased. Using the multi-parametric MR data from a rodent model study, we demonstrate the effectiveness of an end-end deep learning global-attention-based UNet (GA-UNet) framework for automatic segmentation and quantification of TBI lesions. Longitudinal MR scans (2 h, 1, 3, 7, 14, 30, and 60 days) were performed on eight Sprague-Dawley rats after controlled cortical injury was performed. TBI lesion and sub-regions segmentation was performed using 3D-UNet and GA-UNet. Dice statistics (DSI) and Hausdorff distance were calculated to assess the performance. MR scan variations-based (bias, noise, blur, ghosting) data augmentation was performed to develop a robust model.Training/validation median DSI for U-Net was 0.9368 with T2w and MPRAGE inputs, whereas GA-UNet had 0.9537 for the same. Testing accuracies were higher for GA-UNet than U-Net with a DSI of 0.8232 for the T2w-MPRAGE inputs.Longitudinally, necrosis remained constant while oligemia and penumbra decreased, and edema appearing around day 3 which increased with time. GA-UNet shows promise for multi-contrast MR image-based segmentation/quantification of TBI in large cohort studies.

CT-based morphologic and radiomics features for the classification of MYCN gene amplification status in pediatric neuroblastoma.

PURPOSE: MYCN onco-gene amplification in neuroblastoma confers patients to the high-risk disease category for which prognosis is poor and more aggressive multimodal treatment is indicated. This retrospective study leverages machine learning techniques to develop a computed tomography (CT)-based model incorporating semantic and non-semantic features for non-invasive prediction of MYCN amplification status in pediatric neuroblastoma. METHODS: From 2009 to 2020, 54 pediatric patients treated for neuroblastoma at a specialized children's hospital with pre-treatment contrast-enhanced CT and MYCN status were identified (training cohort, n = 44; testing cohort, n = 10). Six morphologic features and 107 quantitative gray-level texture radiomics features extracted from manually drawn volume-of-interest were analyzed. Following feature selection and class balancing, the final predictive model was developed with eXtreme Gradient Boosting (XGBoost) algorithm. Accumulated local effects (ALE) plots were used to explore main effects of the predictive features. Tumor texture maps were also generated for visualization of radiomics features. RESULTS: One morphologic and 2 radiomics features were selected for model building. The XGBoost model from the training cohort yielded an area under the receiver operating characteristics curve (AUC-ROC) of 0.930 (95% CI, 0.85-1.00), optimized F1-score of 0.878, and Matthews correlation coefficient (MCC) of 0.773. Evaluation on the testing cohort returned AUC-ROC of 0.880 (95% CI, 0.64-1.00), optimized F1-score of 0.933, and MCC of 0.764. ALE plots and texture maps showed higher "GreyLevelNonUniformity" values, lower "Strength" values, and higher number of image-defined risk factors contribute to higher predicted probability of MYCN amplification. CONCLUSION: The machine learning model reliably classified MYCN amplification in pediatric neuroblastoma and shows potential as a surrogate imaging biomarker.

Rodent Abdominal Adipose Tissue Imaging by MR.

Rodents including rats and mice are important models to study obesity, diabetes, and metabolic syndrome in a preclinical setting. Translational and longitudinal imaging of these rodents permit investigation of metabolic diseases and identification of imaging biomarkers suitable for clinical translation. Here we describe the imaging protocols for achieving quantitative abdominal imaging in small animals followed by segmentation and quantification of fat volumes.

Narciclasine attenuates diet-induced obesity by promoting oxidative metabolism in skeletal muscle.

Obesity develops when caloric intake exceeds metabolic needs. Promoting energy expenditure represents an attractive approach in the prevention of this fast-spreading epidemic. Here, we report a novel pharmacological strategy in which a natural compound, narciclasine (ncls), attenuates diet-induced obesity (DIO) in mice by promoting energy expenditure. Moreover, ncls promotes fat clearance from peripheral metabolic tissues, improves blood metabolic parameters in DIO mice, and protects these mice from the loss of voluntary physical activity. Further investigation suggested that ncls achieves these beneficial effects by promoting a shift from glycolytic to oxidative muscle fibers in the DIO mice thereby enhancing mitochondrial respiration and fatty acid oxidation (FAO) in the skeletal muscle. Moreover, ncls strongly activates AMPK signaling specifically in the skeletal muscle. The beneficial effects of ncls treatment in fat clearance and AMPK activation were faithfully reproduced in vitro in cultured murine and human primary myotubes. Mechanistically, ncls increases cellular cAMP concentration and ADP/ATP ratio, which further lead to the activation of AMPK signaling. Blocking AMPK signaling through a specific inhibitor significantly reduces FAO in myotubes. Finally, ncls also enhances mitochondrial membrane potential and reduces the formation of reactive oxygen species in cultured myotubes.

Multi-echo susceptibility-weighted imaging and histology of open-field blast-induced traumatic brain injury in a rat model.

Blast-induced traumatic brain injury is on the rise, predominantly as a result of the use of improvised explosive devices, resulting in undesirable neuropsychological dysfunctions, as demonstrated in both animals and humans. This study investigated the effect of open-field blast injury on the rat brain using multi-echo, susceptibility-weighted imaging (SWI). Multi-echo SWI provided phase maps with better signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), making it a sensitive technique for brain injury. Male Sprague-Dawley rats were subjected to a survivable blast of 180 kPa. The visibility of blood vessels of varying sizes improved with multi-echo SWI. Reduced signal intensity from major vessels post-blast indicates increased deoxyhaemoglobin. Relative cerebral blood flow was computed from filtered phase SWI images using inferred changes in oxygen saturation from major blood vessels. Cerebral blood flow decreased significantly at day 3 and day 5 post-blast compared with that pre-blast. This was substantiated by the upregulation of ß-amyloid precursor protein (ß-APP), a marker of ischaemia, in the neuronal perikaya of the cerebral cortex, as observed by immunofluorescence, and in the cortical tissue by western blot analysis. Our findings indicate the presence of brain ischaemia in post-blast acute phase of injury with possible recovery subsequently. Our results from cerebrovascular imaging, histology and staining provide an insight into the ischaemic state of the brain post-blast and may be useful for prognosis and outcome.

Quantification of abdominal fat depots in rats and mice during obesity and weight loss interventions.

BACKGROUND & AIMS: Obesity is a leading healthcare issue contributing to metabolic diseases. There is a great interest in non-invasive approaches for quantitating abdominal fat in obese animals and humans. In this work, we propose an automated method to distinguish and quantify subcutaneous and visceral adipose tissues (SAT and VAT) in rodents during obesity and weight loss interventions. We have also investigated the influence of different magnetic resonance sequences and sources of variability in quantification of fat depots. MATERIALS AND METHODS: High-fat diet fed rodents were utilized for investigating the changes during obesity, exercise, and calorie restriction interventions (N = 7/cohort). Imaging was performed on a 7T Bruker ClinScan scanner using fast spin echo (FSE) and Dixon imaging methods to estimate the fat depots. Finally, we quantified the SAT and VAT volumes between the L1-L5 lumbar vertebrae using the proposed automatic hybrid geodesic region-based curve evolution algorithm. RESULTS: Significant changes in SAT and VAT volumes (p<0.01) were observed between the pre- and post-intervention measurements. The SAT and VAT were 44.22±9%, 21.06±1.35% for control, -17.33±3.07%, -15.09±1.11% for exercise, and 18.56±2.05%, -3.9±0.96% for calorie restriction cohorts, respectively. The fat quantification correlation between FSE (with and without water suppression) sequences and Dixon for SAT and VAT were 0.9709, 0.9803 and 0.9955, 0.9840 respectively. The algorithm significantly reduced the computation time from 100 sec/slice to 25 sec/slice. The pre-processing, data-derived contour placement and avoidance of strong background-image boundary improved the convergence accuracy of the proposed algorithm. CONCLUSIONS: We developed a fully automatic segmentation algorithm to quantitate SAT and VAT from abdominal images of rodents, which can support large cohort studies. We additionally identified the influence of non-algorithmic variables including cradle disturbance, animal positioning, and MR sequence on the fat quantification. There were no large variations between FSE and Dixon-based estimation of SAT and VAT.

Fat storage-inducing transmembrane protein 2 is required for normal fat storage in adipose tissue.

Triglycerides within the cytosol of cells are stored in a phylogenetically conserved organelle called the lipid droplet (LD). LDs can be formed at the endoplasmic reticulum, but mechanisms that regulate the formation of LDs are incompletely understood. Adipose tissue has a high capacity to form lipid droplets and store triglycerides. Fat storage-inducing transmembrane protein 2 (FITM2/FIT2) is highly expressed in adipocytes, and data indicate that FIT2 has an important role in the formation of LDs in cells, but whether FIT2 has a physiological role in triglyceride storage in adipose tissue remains unproven. Here we show that adipose-specific deficiency of FIT2 (AF2KO) in mice results in progressive lipodystrophy of white adipose depots and metabolic dysfunction. In contrast, interscapular brown adipose tissue of AF2KO mice accumulated few but large LDs without changes in cellular triglyceride levels. High fat feeding of AF2KO mice or AF2KO mice on the genetically obese ob/ob background accelerated the onset of lipodystrophy. At the cellular level, primary adipocyte precursors of white and brown adipose tissue differentiated in vitro produced fewer but larger LDs without changes in total cellular triglyceride or triglyceride biosynthesis. These data support the conclusion that FIT2 plays an essential, physiological role in fat storage in vivo.

Comparison of 3-segmentation techniques for intraventricular and intracerebral hemorrhages in unenhanced computed tomography scans.

OBJECTIVES: The Clot Lysis Evaluating Accelerated Resolution of Intraventricular Hemorrhage Trial phase III is a multicenter, randomized clinical trial in the management and treatment of subjects with small intracerebral hemorrhage and large intraventricular hemorrhage. Accurate localization, segmentation, and quantification of hemorrhage are necessary for decision making and treatment. Our studies are aimed at developing algorithms for accurate and automatic hemorrhage segmentation for this trial. METHODS: Two hundred one computed tomography scans of 41 patients with 2.5- to 10-mm slice thickness from 10 hospitals were used. Techniques based on thresholding, clustering, and graph theory modified using textural energy-based normalization were used along with preprocessing (filtering, skull stripping) and postprocessing (artifact removal). The segmented results of each method are compared with the ground truths. RESULTS: The median sensitivity, specificity, and dice statistical index (DSI) are 86.19%, 99.94%, and 0.8655 for modified thresholding; 83.23%, 99.93%, and 0.8410 for modified fuzzy C-means; and 87.28%, 99.81%, and 0.7917 for modified normalized cut method, respectively. The preprocessing and postprocessing enhanced the DSI by 10% and 3%, respectively. Usage of textural energy along with the Hounsfield value in the modified methods increased the DSI by about 8% to 10%. The methods reduced the time needed for processing from 20 to 30 minutes to 2 to 3 minutes per case. CONCLUSIONS: The modified thresholding provided the highest accuracy, least computation time, and implementation complexity compared with other 2 methods. The method reduces the time to localize and segment the hemorrhagic regions and also provides quantitative information that is critical to precise therapeutic decision making.