PeopleofSuperintelligence

Researcher

Farzad Khalvati

Farzad Khalvati is a medical-imaging AI researcher whose lab at the Hospital for Sick Children builds multimodal tools for early diagnosis, prognosis and treatment planning, with brain tumors in children as a central case. He earned a B.Sc. in computer engineering at the University of Tehran in 1998 and a PhD in electrical and computer engineering at the University of Waterloo in 2009, then held research posts at Sunnybrook Research Institute and the Lunenfeld-Tanenbaum Research Institute. In 2020, he joined SickKids as endowed chair of machine learning and AI, and in 2021 he became an associate professor at the University of Toronto and a Faculty Affiliate of the Vector Institute. His team builds MRI models that read the genetic features of pediatric low-grade gliomas, and a 2025 Communications Medicine paper reported an area under the ROC curve of 0.772 for BRAF status from whole-brain FLAIR images. Since 2025, he is Director of Radiology AI at SickKids, where he also directs the IMICS Lab.

Timeline

  1. 1994–2009

    Engineering degrees from Tehran to Waterloo

    He earns a B.Sc. in computer engineering from the University of Tehran in 1998, an M.A.Sc. in electrical and computer engineering from the University of Waterloo in 2003, and a PhD in the same field at Waterloo in 2009. The University of Waterloo Commercialization Office selects and patents his dissertation on image analysis.

  2. 2013–2017

    Postdoc and scientist at Sunnybrook

    After working as an imaging and AI scientist in the biomedical industry, he spends 2013 to 2014 as a postdoctoral fellow in Imaging Research at the Sunnybrook Research Institute in Toronto. He stays on as a Junior Scientist there until 2017.

  3. 2017

    Radiomics for lung cancer prognosis

    In 2017, he is the corresponding author of "Radiomics-based Prognosis Analysis for Non-Small Cell Lung Cancer" in Scientific Reports, written with Yucheng Zhang, Anastasia Oikonomou, Alexander Wong and Masoom A. Haider. The study uses CT images of 112 patients to predict recurrence, death and recurrence-free survival, and finds Random Forest models and Principal Component Analysis the best modeling and feature selection methods.

  4. 2017–2020

    Endowed chair at SickKids

    He is a Staff Scientist at the Lunenfeld-Tanenbaum Research Institute of Sinai Health System from 2017 to 2020. In 2020, he joins the Hospital for Sick Children as endowed chair of Machine Learning and AI.

  5. 2021–2022

    Associate professor and Vector affiliate

    In 2021, he becomes an Associate Professor in the Department of Medical Imaging at the University of Toronto and a Faculty Affiliate of the Vector Institute. In 2022, he takes cross appointments in Computer Science and in Mechanical and Industrial Engineering.

  6. 2022–2023

    Reading glioma genetics from MRI

    In 2022, Canadian Cancer Society-funded work in his lab uses AI on MRI scans to give a non-invasive, fast look at the genetic features of slow-growing gliomas, the most common childhood brain cancer. In 2023, his lab predicts glioma type nearly 90% of the time for the two most common pediatric low-grade glioma subtypes and about 80% when less common subtypes are included.

  7. 2025

    Multimodal models for glioma markers

    In 2025, he coauthors a Scientific Reports paper with Sara Ketabi that trains a multimodal contrastive learning model on 3D brain MRI scans and radiology reports and reaches 87.7% test classification performance on genetic markers of pediatric low-grade glioma. In a Communications Medicine paper coauthored with Kareem Kudus, a model that assesses BRAF status from whole-brain FLAIR MRI reaches a one-vs-rest area under the ROC curve of 0.772 after pretraining on segmentation.

  8. Since 2025

    Director of Radiology AI

    In 2025, he becomes Director of Radiology AI in the Department of Diagnostic & Interventional Radiology at SickKids, where he is also a Senior Scientist, holds the Endowed Chair in Medical Imaging and AI, and directs the IMICS Lab. His lab builds explainable multimodal AI that joins medical images with radiology reports and clinical data for diagnosis, prognosis and treatment planning. He also works with the University of Toronto's Department of Near and Middle Eastern Civilizations on applying AI to Persian literature.

Career

  1. Since 2020Hospital for Sick ChildrenEndowed Chair of Machine Learning and AI; Endowed Chair in Medical Imaging and AI, Director of Radiology AI
  2. From 2021Vector InstituteFaculty Affiliate
  3. 2017–2020Sinai Health SystemStaff Scientist
  4. 2013–2017University of TorontoPostdoctoral Fellow, Junior Scientist

Education

  1. 2009University of WaterlooPhD
  2. 2003University of WaterlooM.A.Sc.
  3. 1998University of TehranB.Sc.

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes University of Toronto. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University of Toronto. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes University of Toronto. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.
  4. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Vector Institute. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Farzad Khalvati yet. Send us a free-licensed photo.

  1. Farzad Khalvati | SickKids Directory sickkids.ca. Checked 21 October 2026.
  2. Dr. Khavati Appointed as the Endowed Chair in Medical Imaging at Sickkids/UT Medical Imaging | Medical Imaging medical-imaging.utoronto.ca. Checked 21 October 2026.
  3. Radiomics-based Prognosis Analysis for Non-Small Cell Lung Cancer | Scientific Reports nature.com. Checked 21 October 2026.
  4. Farzad Khalvati - Vector Institute for Artificial Intelligence vectorinstitute.ai. Checked 21 October 2026.
  5. Revolutionizing brain cancer diagnosis | Canadian Cancer Society cancer.ca. Checked 21 October 2026.
  6. An Image is Worth a Thousand Diagnostic Variables: Developing AI-based solutions for precision medicine – IMS Magazine imsmagazine.com. Checked 21 October 2026.
  7. Multimodal contrastive learning for enhanced explainability in pediatric brain tumor molecular diagnosis | Scientific Reports nature.com. Checked 21 October 2026.
  8. Segmentation-free pretherapeutic assessment of BRAF-status in pediatric low-grade gliomas | Communications Medicine nature.com. Checked 21 October 2026.
  9. Meeting MI - Radiologists Behind AI: Dr. Farzad Khalvati, Chair in Medical Imaging and Artificial Intelligence, SickKids | Medical Imaging medical-imaging.utoronto.ca. Checked 21 October 2026.