BME Ph.D. Candidate Vibha Balaji Wins Prestigious Award from Society of Nuclear Medicine and Molecular Imaging
Content
The Society of Nuclear Medicine and Molecular Imaging (SNMMI) has selected doctoral candidate Vibha Balaji from the UMass Amherst Biomedical Engineering (BME) Department to receive its prestigious Alavi-Mandell Award for her paper on “Artificial Intelligence for PET and SPECT Image Enhancement,” published in The Journal of Nuclear Medicine - JNM. Balaji’s mentor is BME Professor Joyita Dutta, who is the principal investigator of the Biomedical Imaging and Data Science Lab and also the BME graduate program director and an adjunct in the Electrical and Computer Engineering (ECE) Department. See (24) The Journal of Nuclear Medicine - JNM: Overview | LinkedIn.
PET means positron emission tomography and SPECT stands for single photon emission computed tomography. They are both nuclear-medicine-imaging techniques that provide detailed anatomical, metabolic, and functional information, especially when combined with scans performed with computed-tomography and magnetic-resonance imaging.
According to the SNMMI, “The Alavi-Mandell Award is given to individuals who were the first author of a paper published in the JNM, were trainees at the time the published work was carried out, and made a major contribution to the completion of the work. The award is accompanied by a monetary reward, which is provided by the established fund.”
Balaji was the first author of the January 2024 JNM paper. Her co-authors were: UMass BME Post Doctoral Research Associate Tzu-An Song; Ph.D. student Masoud Malekzadeh of the UMass ECE department; Pedram Heidari from the Division of Nuclear Medicine and Molecular Imaging in the Department of Radiology at Massachusetts General Hospital in Boston; and Dutta.
Balaji and her co-authors explain that “This review article presents a comprehensive survey of state-of-the-art, artificial-intelligence (AI) methods for PET- and SPECT-image enhancement and seeks to identify emerging trends in this field. We focus on recent breakthroughs in AI-based PET- and SPECT-image denoising and deblurring.”
As Balaji and her colleagues say about the backdrop of their winning paper, “PET and SPECT are confounded by high-noise levels and low-spatial resolution, necessitating post-reconstruction-image enhancement to improve their quality and quantitative accuracy. AI models such as convolutional neural networks, U-Nets, and generative adversarial networks have shown promising outcomes in enhancing PET and SPECT images.”
The JNM paper adds that “Supervised deep-learning models have shown great potential in reducing radiotracer-dose and scan times without sacrificing image quality and diagnostic accuracy. However, the clinical utility of these methods is often limited by their need for corrupt [and unpaired] datasets for training. This has motivated research into unsupervised alternatives that can overcome this limitation by relying on only corrupt inputs or unpaired datasets to train models.”
The award-winning paper highlights recently published supervised and unsupervised efforts toward AI-based, PET- and SPECT-image enhancement. As the authors say, “We discuss cross-scanner and cross-protocol training efforts, which can greatly enhance the clinical translatability of AI-based, image-enhancement tools.”
The researchers say that their paper also aims to address the “looming question” of whether the improvements in image quality generated by AI models lead to actual clinical benefit.
“To this end,” the authors conclude, “we discuss works that have focused on task-specific, objective, clinical evaluation of AI models for image enhancement or incorporated clinical metrics into their loss functions to guide the image-generation process. Finally, we discuss emerging research directions, which include the exploration of novel training paradigms, curation of larger task-specific datasets, and objective clinical evaluation that will enable the realization of the full translation potential of these models in the future.”
The SNMMI had previously awarded Balaji a $5,000 Medical and Science Student Research Grant in the spring of 2023, and she scored a second-place finish in the competition for the SNMMI Physics, Instrumentation, and Data Sciences Council Young Investigator Awards in the summer of 2023. Balaji earned her M.S. from the Birla Institute of Technology and Science, Pilani, in Goa, India. (May 2025)