Research
Research Presentation
Our study results suggests that atrophy percentage in the taken population had negative correlation with the age showing subset A (age 40-65) having higher atrophy percentage than subset B (age 65-90) when normalized to their age and eICV. Neuroshield was able to detect atrophic changes as low as 0.55% and at the earliest age of 41 years. This study highlights that atrophic changes related to dementia are age independent and volumetry can help detect it at its earliest.
Research Presentation
This study highlighted that female had accelerated atrophic changes (upto 30%) and as early as 42 years whereas males showed atrophic changes (upto 17%) as late as 50 years of age. The study indicates that females are more susceptible to early atrophic changes with higher frequency in age group of 40-50 compared to males. In conclusion the age brackets for Dementia screening needs to be revised and adjusted not just by age but also by gender to detect earlier changes with the help of volumetric analysis.
Quantitative MRI has been proven to aid in identification of subtle volumetric changes in the brain. Studies have stated regional and global differences in shape, size, and volume between Caucasian and eastern population. Chinese, Korean, and Japanese populations have also shown significant differences in brain shape and size between western and eastern population. Objective was to study the differences between Indian and Caucasian Population.
Data had normal distribution between ages with skewness coefficient of 0.05.The age and gender matched comparison of Indian (group 1) and Caucasian (group 2) brain and intracranial volumes (ICV) showed significant differences. The average volumes for Indian were 1122.48 ml (whole brain) and 1339.75 m. (ICV) as compared to 1222.58 mil (whole brain) and 1482.87 ml (ICV) in Caucasians. One-way Anova for the brain and ICV were found significant at p<0.5.
White Paper
White Paper
Building MRI-Based Volumetric Analysis References for the Indian Population-
A White Paper on Advancing Precision Healthcare
White Paper
Building MRI-Based Volumetric Analysis References for the Indian Population-
A White Paper on Advancing Precision Healthcare
.333
Research Poster
Worldwide, about 4-5 million deaths (9 percent) occur due to stroke. Stroke is the leading cause for neurological dysfunction resulting in considerable morbidity and mortality and holds the 6th position in the list of causes for reduced DALYS (Disability Adjusted Life Years). It’s categorized into two types: ischemic and hemorrhagic. Till date manual segmentation remains the gold standard in segmenting the stroke region of interest for every scan. This is a time-consuming process and inefficient in accurately identifying the ROIs. This work explores the hypothesis to develop an accurate automated stroke segmentation model. The 2D U-NET architecture used in segmenting the ROIs is based on the format to include the lesion size, lesion volume and their locations in the left and right hemisphere of the brain, and cortical and subcortical brain regions. The cohort consisted of single and multiple ROIs and were further bifurcated based on the volumes of these lesions. Based on this information we optimized our network into 5 different models keeping in mind all the information about the lesion size and volume. Eventually the average dice score obtained was highest for the network that included the combination of smaller and larger lesion, and Gd-T1w MRI scans containing the stroke lesion but no information of its size. The dice score for this model was 0.822 on the testing set. This result shows that considering the lesion sizes and volumes can help in obtaining a precise and automated segmentation model and can be the base work to further localize and classify the lesions.
Journal Publication
We developed a 3D CNN model for automatically detecting the ICH from head CT scans. The screening tool was tested in 20 cases and trained on 200 head CT scans, with 99 normal head CT and 101 CT scans with some type of ICH. The final model performed with 90% sensitivity, 70% specificity, and 80% accuracy. Our study reveals that the automated screening tool exhibits a commendable level of accuracy and sensitivity in detecting ICH from the head CT scans.
Traumatic brain injury (TBI) often results in midline shift (MLS) that is a critical indicator of the severity and prognosis of head injuries. Automated analysis of MLS from head computed tomography (CT) scans using artificial intelligence (AI) techniques has gained much attention in the past decade and has shown promise in improving diagnostic efficiency and accuracy. This review aims to summarize the current state of research on AI-based approaches for MLS analysis in TBI cases, identify the methodologies employed, evaluate the performance of the algorithms, and draw conclusions regarding their potential clinical applicability. A comprehensive literature search was conducted, identifying 15 distinctive publications. The identified articles were analyzed for their focus on MLS detection and quantification using AI techniques, including their choice of AI algorithms, dataset characteristics, and methodology. The reviewed articles covered various aspects related to MLS detection and quantification, employing deep neural networks trained on two-dimensional or three-dimensional CT imaging datasets. The dataset sizes ranged from 11 patients’ CT scans to 25,000 CT images. The performance of the AI algorithms exhibited variations in accuracy, sensitivity, and specificity, with sensitivity ranging from 70 to 100%, and specificity ranging from 73 to 97.4%. AI-based approaches utilizing deep neural networks have demonstrated potential in the automated detection and quantification of MLS in TBI cases. However, different researchers have used different techniques; hence, critical comparison is difficult. Further research and standardization of evaluation protocols are needed to establish the reliability and generalizability of these AI algorithms for MLS detection and quantification in clinical practice. The findings highlight the importance of AI techniques in improving MLS diagnosis and guiding clinical decision-making in TBI management.
Traumatic brain injury (TBI) is not only an acute condition but also a chronic disease with long-term consequences. Intracranial hematomas are considered the primary consequences that occur in TBI and may have devastating effects that may lead to mass effect on the brain and eventually cause secondary brain injury. Emergent detection of hematoma in computed tomography (CT) scans and assessment of three major determinants, namely, location, volume, and size, is crucial for prognosis and decision-making, and artificial intelligence (AI) using deep learning techniques, such as convolutional neural networks (CNN) has received extended attention after demonstrations that it could perform at least as well as humans in imaging classification tasks. This article conducts a comparative review of medical and technological literature to update and establish evidence as to how technology can be utilized rightly for increasing the efficiency of the clinical workflow in emergency cases. A systematic and comprehensive literature search was conducted in the electronic database of PubMed and Google Scholar from 2013 to 2023 to identify studies related to the automated detection of intracranial hemorrhage (ICH). Inclusion and exclusion criteria were set to filter out the most relevant articles. We identified 15 studies on the development and validation of computer-assisted screening and analysis algorithms that used head CT scans. Our review shows that AI algorithms can prioritize radiology worklists to reduce time to screen for ICH in the head scans sufficiently and may also identify subtle ICH overlooked by radiologists, and that automated ICH detection tool holds promise for introduction into routine clinical practice.
Forthcoming
3D CNN-based Automated Detection of Midline Shift in Traumatic Brain Injury Cases from Head CT scans
In this study, we sought to determine the accuracy and the prognostic value of our screening tool that automatically detects MLS on computed tomography (CT) images in patients with traumatic brain Injuries (TBI). The study enrolled TBI cases who presented at the Department of Neurosurgery, All India Institute of Medical Sciences, New Delhi. The developed 3D CNN model was trained using 176 scans and was tested on 20 Head CTs to determine the accuracy and sensitivity of the model. The screening tool was correctly able to detect 7/10 MLS cases and 4/10 non-MLS cases. The model showed an accuracy of 55% with high specificity (70%) and moderate sensitivity of 40%.
Studies prove the correlation between Body Fat distribution and insulin resistance which is a major risk factor for Type 2 diabetes and cardiovascular diseases (CVD). Educating individuals with more accurate measures of fat distribution outside fat percentage and body mass index (BMI) along with preventive solutions to susceptible conditions encourage better lifestyle choices and routines. Essential fat compartments that constitute the total fat distribution are visceral adipose tissue (VAT), superficial subcutaneous adipose tissue (SSAT) and deep subcutaneous adipose tissue (DSAT) which can be measured using whole-body MRI from head to foot. We propose a two-stage solution: rapid Dixon sequence acquisition, fat compartment segmentation. A clinically standard and predefined protocol is designed to automate the acquisition with optimal pulse sequence parameters to satisfy any time constraint. Two separate fully convolutional networks (UNet) with attention gates trained on our in-house dataset of 53 patients are used to segment VAT and SAT respectively. Further, the SAT segment is sub-classified into SSAT and DSAT by detecting the fascia superficialis using modified level sets. The models are capable of segmenting VAT, DSAT, and SSAT from head to foot without any manual intervention. Our method achieves a dice score of 0.868 for SAT segmentation and 0.9107 for VAT segmentation. The whole pipeline from data acquisition to reporting can be completed in under 20 minutes. Furthermore, our experiments show that our approach to estimating the segmentations are better than similar deep learning models trained on abdomen MRI. Our study demonstrates a use case of how MRI as a modality can be used outside of a typical clinical setting and set up as an upstream imaging solution to make it a more accessible tool for health evaluation/screening for the public.
Type 2 Diabetes Mellitus (DM) is a chronic condition that impairs the way the body processes blood sugar(glucose). Over 10 percent of the US population is known to be affected by Type 2 DM as of 2018, and almost quarter of them are unaware or undiagnosed, thus, making early detection and treatment of diabetes an important step in mitigating the associated health risks. Previous studies show that waist circumference and waist-height ratio are found to be better indicators of diabetes than BMI. These measures of central obesity create great interest to study different measures of body fat distribution. The main objective of this study is to provide evidence to prove that variables derived from the DXA(Dual-energy X-ray absorptiometry) analysis including regional fat distribution profiles are better indicators of DM when compared to conventional metrics such as Body Mass Index(BMI). A multi-class classification is performed using Random Forest Classifier to classify patients as ‘Normal’, ‘Prediabetic’ or ‘Diabetic’ across various subsets of data obtained from the NHANES diabetes cohort. Feature selection techniques such as ANOVA/Chi-square, Recursive Feature Eliminations(RFE) and intrinsic feature importance scores from the classifier were used to filter the most important features. It was observed that fat distribution features from DXA can be used as a viable alternative to conventional metrics in the detection of DM. Notably, head fat percentage was proven to be a prominent feature to identify DM. Thus, our study demonstrates the potential of fat distribution variables as a potential standalone or surrogate biomarker for Type 2 DM.
Dual-energy X-ray absorptiometry (DXA) derived measures of lean mass demonstrate strong associations with magnetic resonance imaging (MRI) derived measures of muscle volume (MV) in cross-sectional studies, however, few studies have compared changes in response to an intervention. The purpose of this study was to determine the accuracy of DXA at detecting changes in lean mass, using MRI-derived MV as a reference standard. 10 male and 16 female subjects (29.2 ± 9.5 years) underwent DXA and MRI scans before and after a 10-week resistance training intervention. DXA thigh lean mass was compared to MRI mid-thigh MV, and percent change in size was compared between MRI and DXA. There was a strong correlation between measures cross-sectionally (r = 0.89) in agreement with previous investigations. However, there was a modest correlation of percentage change over time between methods (r = 0.49). Bland-Altman plots revealed that the amount of random error increased as the magnitude of the change from baseline increased. DXA measures of change in lean mass were modestly associated with MRI measures of change in MV. While there are several advantages to using DXA for the measurement of lean mass, the inability to accurately detect changes over time calls into question its use in clinical trials.