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.

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 β-amyloid precursor protein (β-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.

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.