Dr. Bishesh Khanal

Founding ChairpersonBoard of Directors Research Scientist

Medical Image Analysis|Computer Vision|Natural Language Processing|Low-cost Medical Imaging|Healthcare AI for LMICs

Former Executive Director at NAAMII
Full-time Research Scientist leading the TOGAI research group at NAAMII
Specializes in computer vision and NLP for low-resource settings relevant to Low and Middle-Income Countries (LMICs)

Dr. Bishesh Khanal is a full-time Research Scientist at NAAMII, where he leads the TOGAI research group focused on transforming global health through AI. His research pushes the boundaries of machine learning and artificial intelligence with applications relevant to Low and Middle-Income Countries. At TOGAI, his team develops biomedical computer vision methods for low-cost medical imaging solutions, including smartphone-based diagnostics. They also advance Natural Language Processing for Nepali language to enable chatbots, voice bots, and automated clinical report processing for healthcare applications. Dr. Khanal's work emphasizes clinical translational research projects relevant to resource-constrained settings, bridging cutting-edge AI research with practical healthcare solutions for underserved populations.

Publications

2026

The AI Pyramid A Conceptual Framework for Workforce Capability in the Age of AI

Alok Khatri, Bishesh Khanal

Pre-Prints

Dr. Bishesh Khanal

Publications

The AI Pyramid A Conceptual Framework for Workforce Capability in the Age of AI

Mapping the potential and limitations of using generative AI technologies to address socio-economic challenges in LMICs

Transforming healthcare through just, equitable and quality driven artificial intelligence solutions in South Asia

Assistive Artificial Intelligence in Epilepsy and Its Impact on Epilepsy Care in Low- and Middle-Income Countries

Multimodal Lead-Specific Modeling of ECG for Low-Cost Pulmonary Hypertension Assessment

NLPineers@ NLU of Devanagari Script Languages 2025: Hate speech detection using ensembling of BERT-based models

TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models

Deep-learning assisted detection and quantification of (oo) cysts of Giardia and Cryptosporidium on smartphone microscopy images

Investigating the Robustness of Vision Transformers against Label Noise in Medical Image Classification

AI-Assisted Cervical Cancer Screening

VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blocks

How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?

Emerging Avenue of Artificial Intelligence and Ethical Considerations

Synthetic Boost: Leveraging Synthetic Data for Enhanced Vision-Language Segmentation in Echocardiography

Exploring transfer learning in medical image segmentation using vision-language models

FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining

M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Tasks

Benchmarking Encoder-Decoder Architectures for Biplanar X-ray to 3D Bone Shape Reconstruction

Investigating the impact of class-dependent label noise in medical image classification

Fast fetal head compounding from multi-view 3D ultrasound

Distributed, Collaborative, and Federated Learning, and Affordable AI and Healthcare for Resource Diverse Global Health

Challenges of Deep Learning Methods for COVID-19 Detection Using Public Datasets

COVID-19-related Nepali Tweets Classification in a Low Resource Setting

FixMatchSeg: Fixing FixMatch for Semi-Supervised Semantic Segmentation

Label Geometry Aware Discriminator for Conditional Generative Networks

COVID-19 control strategies and intervention effects in resource limited settings: a modeling study

Machine-Learning-Assisted Analysis of Colorimetric Assays on Paper Analytical Devices

Evaluation and Comparison of Accurate Automated Spinal Curvature Estimation Algorithms with Spinal Anterior-posterior X-Ray Images: The AASCE2019 Challenge

Towards automated extraction of 2D standard fetal head planes from 3D ultrasound acquisitions: A clinical evaluation and quality assessment comparison

Uncertainty Estimation in Deep 2D Echocardiography Segmentation

Ensemble U-Net model for efficient polyp segmentation

Complete Fetal Head Compounding from Multi-View 3D Ultrasound

Complete Fetal Head Compounding from Multi-View 3D Ultrasound

Automatic Cobb Angle Detection using Vertebra Detector and Vertebra Corners Regression

Image Reconstruction in a Manifold of Image Patches: Application to Whole-fetus Ultrasound Imaging

Towards whole placenta segmentation at late gestation using multi-view ultrasound images

Confident Head Circumference Measurement from Ultrasound with Real-time Feedback for Sonographers

Adapted and Oversegmenting Graphs: Application to Geometric Deep Learning