Segmenting and classifying tuberculosis, pneumonia and COVID-19 in chest X-rays
A deep learning pipeline that first isolates the lungs in a chest X-ray, then classifies the image as normal, tuberculosis, pneumonia or COVID-19.
Our research work
BigAI is built on research. Our founder, Dr Mahesh Maindarkar, has authored and co-authored more than 200 research papers, with recent work in AI for cardiovascular risk, medical imaging and explainable AI published in leading international journals.
200+ research papers by our founder
17 recent international journal papers listed below and on his faculty profile
2 published patents
MDPI best paper award, Healthcare 2022
Research areas
- Cardiovascular and stroke risk stratification
- Deep learning models that estimate cardiovascular and stroke risk in patients with conditions such as diabetes, Parkinson’s disease, rheumatoid arthritis, sleep apnoea and COVID-19.
- Medical image analysis
- Segmentation and classification of intravascular ultrasound, carotid ultrasound and chest X-ray images, including transformer and attention-based architectures.
- Explainable and unbiased AI
- Methods to make clinical AI transparent, and to detect and reduce bias before models are used on patients.
- Radiogenomics and precision medicine
- Combining imaging, genomics and polygenic risk scores to personalise risk prediction.
- Economics of AI in healthcare
- Where AI saves cost in diagnosis and treatment — work recognised with MDPI Healthcare’s 2022 best paper award.
- Machine learning and IoT for energy
- Energy harvesting and machine-learning control of solar plants, the subject of two published patents.
Research projects
View as case studies
Transformer models for coronary artery wall segmentation in intravascular ultrasound
A review of transformer and attention-based deep learning architectures for outlining coronary artery walls in IVUS images, and where they outperform earlier networks.
AI frameworks for cardiovascular and stroke risk in patients with comorbidities
A body of research on how AI can estimate cardiovascular and stroke risk in people with diabetes, Parkinson’s disease, rheumatoid arthritis, sleep apnoea and COVID-19.
Where AI saves money in healthcare: diagnosis versus treatment
An analysis of the economics of artificial intelligence across the healthcare pathway, recognised with MDPI Healthcare’s 2022 best paper award.
Machine learning and IoT for solar plant control and fault detection
A patented approach that combines IoT sensing with machine learning to control a solar plant, detect faults early and predict energy output.
Selected publications
Recent peer-reviewed journal papers co-authored by Dr Mahesh Maindarkar.
-
Segmentation and classification of tuberculosis, pneumonia and COVID-19 in chest images
-
AI-based cardiovascular and stroke risk assessment in women with autoimmune disorders
-
Non-invasive cardiovascular risk stratification in obstructive sleep apnoea using AI
-
Ultrasound radiomics and genomics (UltraAIGenomics) for cardiovascular risk
-
Polygenic risk scores for cardiovascular disease in an AI framework
-
Radiogenomics risk predictors in an explainable AI framework for clinical trials
-
Economics of artificial intelligence in healthcare: diagnosis vs. treatment (MDPI best paper award 2022)
-
Deep learning for cardiovascular and stroke risk in diabetic foot infection
-
Bias in AI systems for early detection of Parkinson’s disease
Patents
Published Indian patent applications.
RF rectenna for energy harvesting at 1.8 GHz to 5.8 GHz to reduce energy crises
Indian patent application 202021036496, published 4 March 2022
Machine learning and Internet of Things approach for solar plant control system and fault detection with energy prediction
Indian patent application 202021036499, published 4 March 2022
Research collaborations
We work with universities, hospitals and research institutes on joint projects, publications and student research.