MEDICAL IMAGING / LANGUAGE / GRAPH LEARNING
I study how images, language, and prior knowledge can help when supervision is limited. My current work combines CT anatomy, SPECT uptake, and clinical report context for quantitative theranostics. Earlier studies explore word senses in low-resource translation and graph representations for text classification.
01 / SELECTED RESEARCH
3 featured studies
CURRENT RESEARCH
Combining SPECT uptake, CT anatomy, and clinical report information to segment organs and tumors without task-specific supervised segmentation training.
Low-resource language learning
Using unsupervised sense induction to improve lexical choices in English-to-Indic statistical machine translation, evaluated across five translation directions.
Graph representation learning
Comparing gated, convolutional, and attention-based graph models that represent each document independently, with experiments on AG News, IMDB, and DBpedia.
02 / PUBLICATION RECORD
Conference abstract · 2026 · First author · Current research
Journal of Nuclear Medicine · SNMMI Annual Meeting · 2026;67(Supplement 1):261107
Chaurasia U, Abu-Mahfouz A, Rangbulla M, Qi K, Laforest R, Prasad V, Jha AK. A Large-Language Model-Guided Unsupervised Segmentation Method for Lu-177 DOTATATE/PSMA SPECT/CT Images. Journal of Nuclear Medicine. 2026;67(Supplement 1):261107. https://jnm.snmjournals.org/content/67/supplement_1/261107
Journal article · 2023 · Co-author
IETE Journal of Research · 69(12):8848–8858 · Online first: July 2022
Saxena S, Chaurasia U, Bansal N, Daniel P. Improved Unsupervised Statistical Machine Translation via Unsupervised Word Sense Disambiguation for a Low-Resource and Indic Languages. IETE Journal of Research. 2023;69(12):8848–8858. https://doi.org/10.1080/03772063.2022.2098189
Conference paper · 2022 · Co-author
IEEE ASSIC 2022 · International Conference on Advancements in Smart, Secure and Intelligent Computing · pp. 227–231
Pandian S, Chaurasia U, Ranjan S, Saxena S. Comparative Study of Inductive Graph Neural Network Models for Text Classification. 2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC). 2022:227–231. https://doi.org/10.1109/ASSIC55218.2022.10088315
03 / ADDITIONAL PUBLICATIONS
pp. 30–36 · Co-author
A collaborative study of texture-based local binary pattern features and feature selection for MRI-based brain tumor classification.
We combined color-space preprocessing, principal component analysis, LBP feature extraction, and support vector machine classification, with a deep neural network comparison. In these experiments, the SVM achieved 98.4% accuracy and the neural network achieved 98.6%.
Read the publisher recordGuleria V, Verma A, Dhenkawat R, Chaurasia U, Singh NP. Brain Tumor Detection Using Texture-Based LBP Feature on MRI Images Using Feature Selection Technique. In: Artificial Intelligence, Blockchain, Computing and Security, Volume 1. CRC Press; 2023:30–36. https://doi.org/10.1201/9781003393580-6
Selected Papers from ADCIS 2022, Volume 1 · pp. 201–213 · First author
An earlier study of image-processing and support vector machine approaches for COVID-19 classification using CT, chest X-ray, and ultrasound datasets.
We studied image-processing and SVM-based classification across three separate datasets: CT, chest X-ray, and ultrasound.
Read the publisher recordChaurasia U, Dhenkawat R, Verma PK, Singh NP. COVID Prediction Using Different Modality of Medical Imaging. In: Advances in Data-Driven Computing and Intelligent Systems. Springer; 2023:201–213. https://doi.org/10.1007/978-981-99-3250-4_15