Attention 3D U-NET for dose distribution prediction of high-dose-rate brachytherapy of cervical cancer: Direction modulated brachytherapy tandem applicator.

BACKGROUND: Direction Modulated Brachytherapy (DMBT) enables conformal dose distributions. However, clinicians may face challenges in creating viable treatment plans within a fast-paced clinical setting, especially for a novel technology like DMBT, where cumulative clinical experience is limited. Deep learning-based dose prediction methods have emerged as effective tools for enhancing efficiency. PURPOSE: To develop a voxel-wise dose prediction model using an attention-gating mechanism and a 3D UNET for cervical cancer high-dose-rate (HDR) brachytherapy treatment planning with DMBT six-groove tandems with ovoids or ring applicators. METHODS: A multi-institutional cohort of 122 retrospective clinical HDR brachytherapy plans treated to a prescription dose in the range of 4.8-7.0 Gy/fraction was used. A DMBT tandem model was constructed and incorporated onto a research version of BrachyVision Treatment Planning System (BV-TPS) as a 3D solid model applicator and retrospectively re-planned all cases by seasoned experts. Those plans were randomly divided into 64:16:20 as training, validating, and testing cohorts, respectively. Data augmentation was applied to the training and validation sets to increase the size by a factor of 4. An attention-gated 3D UNET architecture model was developed to predict full 3D dose distributions based on high-risk clinical target volume (CTVHR) and organs at risk (OARs) contour information. The model was trained using the mean absolute error loss function, Adam optimization algorithm, a learning rate of 0.001, 250 epochs, and a batch size of eight. In addition, a baseline UNET model was trained similarly for comparison. The model performance was evaluated on the testing dataset by analyzing the outcomes in terms of mean dose values and derived dose-volume-histogram indices from 3D dose distributions and comparing the generated dose distributions against the ground-truth dose distributions using dose statistics and clinically meaningful dosimetric indices. RESULTS: The proposed attention-gated 3D UNET model showed competitive accuracy in predicting 3D dose distributions that closely resemble the ground-truth dose distributions. The average values of the mean absolute errors were 1.82 ± 29.09 Gy (vs. 6.41 ± 20.16 Gy for a baseline UNET) in CTVHR, 0.89 ± 1.25 Gy (vs. 0.94 ± 3.96 Gy for a baseline UNET) in the bladder, 0.33 ± 0.67 Gy (vs. 0.53 ± 1.66 Gy for a baseline UNET) in the rectum, and 0.55 ± 1.57 Gy (vs. 0.76 ± 2.89 Gy for a baseline UNET) in the sigmoid. The results showed that the mean absolute error (MAE) for the bladder, rectum, and sigmoid were 0.22 ± 1.22 Gy (3.62%) (p = 0.015), 0.21 ± 1.06 Gy (2.20%) (p = 0.172), and -0.03 ± 0.54 Gy (1.13%) (p = 0.774), respectively. The MAE for D90, V100%, and V150% of the CTVHR were 0.46 ± 2.44 Gy (8.14%) (p = 0.018), 0.57 ± 11.25% (5.23%) (p = 0.283), and -0.43 ± 19.36% (4.62%) (p = 0.190), respectively. The proposed model needs less than 5 s to predict a full 3D dose distribution of 64 × 64 × 64 voxels for any new patient plan, thus making it sufficient for near real-time applications and aiding with decision-making in the clinic. CONCLUSIONS: Attention gated 3D-UNET model demonstrated a capability in predicting voxel-wise dose prediction, in comparison to 3D UNET, for DMBT intracavitary brachytherapy planning. The proposed model could be used to obtain dose distributions for near real-time decision-making before DMBT planning and quality assurance. This will guide future automated planning, making the workflow more efficient and clinically viable.

Evaluation of circulating plasma miR-9, miR-29a, miR-192, and miR-375 as potential biomarkers for predicting prediabetes and type 2 diabetes in Nepali adult population.

Circulating plasma miRNAs have emerged as potential early predictors of glucometabolic disorders. However, their biomarker potential remains unvalidated in populations with diverse genetic backgrounds, races, and ethnicities. This study aims to validate the biomarker potential of plasma miR-9, miR-29a, miR-192, and miR-375 for early detection of prediabetes and type 2 diabetes mellitus (T2DM) in Nepali populations that represent distinct genetic backgrounds, races, and ethnicities. A total of 46 adults, categorized into healthy controls (n = 25), prediabetes (n = 9), and T2DM (n = 12) groups, were enrolled. Baseline sociodemographic, anthropometric, and clinical characteristics were collected. Fold change in plasma expression of all four miRNAs was quantified using RT-qPCR against the RNU6B reference gene. Their biomarker potential was determined by receiver operating characteristic (ROC) curve analysis. Multivariate discriminant function and hierarchical cluster analyses were used to evaluate the effectiveness of the miRNA panel in reclassifying study participants who were initially categorized according to their glucose tolerance status. Plasma expression of all four miRNAs was significantly upregulated in T2DM patients compared to normoglycemic controls. Furthermore, the expression of only miR-29a and miR-375 was upregulated in T2DM patients than in prediabetic individuals. Notably, only miR-192 expression was significantly upregulated in prediabetic individuals than in the normoglycemic controls. The miRNA expression profiles had the potential of reclassifying the participants into three original groups with an accuracy of 69.6 %. ROC curve analysis identified miR-192 as the predictor for both prediabetes and T2DM, while miR-9, miR-29a, miR-192, and miR-375 were predictive only for T2DM. The specific set of miRNA combinations significantly improved their predictive accuracy. This study validates the early predictive biomarker potential of plasma miR-9, miR-29a, miR-192, and miR-375 also in the Nepali population and paves the way for future translational studies to validate their utility in clinical laboratories.

Dengue virus infection during window period of consecutive outbreaks in Nepal and assessment of clinical parameters.

Nepal is an endemic country for dengue infection with rolling of every 3 year's clear cyclic outbreaks with exponential growth since 2019 outbreak and the virus gearing towards the non-foci temperate hill regions. However, the information regarding circulating serotype and genotype is not frequent. This research discusses on the clinical features, diagnosis, epidemiology, circulating serotype and genotype among 61 dengue suspected cases from different hospitals of Nepal during the window period 2017-2018 between the two outbreaks of 2016 and 2019. E-gene sequences from PCR positive samples were subjected to phylogenetic analysis under time to most recent common ancestor tree using Markov Chain Monte Carlo (MCMC) and BEAST v2.5.1. Both evolution and genotypes were determined based on the phylogenetic tree. Serotyping by Real-time PCR and Nested PCR showed the co-circulation of all the 3 serotypes of dengue in the year 2017 and only DENV-2 in 2018. Genotype V for DENV-1 and Cosmopolitan Genotype IVa for DENV-2 were detected. The detected Genotype V of DENV-1 in Terai was found close to Indian genotype while Cosmopolitan IVa of DENV-2 found spreading to geographically safe hilly region (now gripped to 9 districts) was close to South-East Asia. The genetic drift of DENV-2 is probably due to climate change and rapid viral evolution which could be a representative model for high altitude shift of the infection. Further, the increased primary infection indicates dengue venturing to new populations. Platelets count together with Aspartate transaminase and Aalanine transaminase could serve as important clinical markers to support clinical diagnosis. The study will support future dengue virology and epidemiology in Nepal.

Random Change-Point Non-linear Mixed Effects Model for left-censored longitudinal data: An application to HIV surveillance.

A change-point model is essential in longitudinal data to infer an individual specific time to an event that induces a change of trend. However, in general, change points are not known for population-based data. We present an unknown change-point model that fits the linear and non-linear mixed effects for pre- and post-change points. We address the left-censored observations. Through stochastic approximation expectation maximization (SAEM) with the Metropolis Hasting sampler, we fit a random change-point non-linear mixed effects model. We apply our method on the longitudinal viral load (VL) data reported to the HIV surveillance registry from New York City.

Stochastic Version of EM Algorithm for Nonlinear Random Change-Point Models.

Random effect change-point models are commonly used to infer individual-specific time of event that induces trend change of longitudinal data. Linear models are often employed before and after the change point. However, in applications such as HIV studies, a mechanistic nonlinear model can be derived for the process based on the underlying data-generation mechanisms and such nonlinear model may provide better ``predictions". In this article, we propose a random change-point model in which we model the longitudinal data by segmented nonlinear mixed effect models. Inference wise, we propose a maximum likelihood solution where we use the Stochastic Expectation-Maximization (StEM) algorithm coupled with independent multivariate rejection sampling through Gibbs's sampler. We evaluate the method with simulations to gain insights.