Artificial intelligence for pancreatic cancer diagnosis

Work done in the lab of Prof. Anant Madabhushi at Case Western Reserve University (Now at Emory University)

About author

Shayan Monabbati is a final year PhD candidate in the Systems & Control Engineering program at Case Western Reserve University, Cleveland, Ohio. He received his bachelor of mechanical engineering from his hometown in Toronto, Canada. His research interests include the use of artificial intelligence tools to extract engineered subvisual features from routinely acquired medical imaging data for the diagnosis, prognosis, and prediction of different diseases. His current projects include an automated method for improved sensitivity in the diagnosis of pancreatobiliary tract adenocarcinomas from bile duct brushing cytopathology specimens and the characterization of the papillary thyroid tumor environment for improved prognosis using pathomic and genomic data.

Interview

How would you explain your research outcomes to the non-scientific community?

We were able to create an automated machine learning-based pipeline that can identify malignancies from high resolution images of patient biopsies from the bile duct, which is one of the rarest and deadliest forms of cancer. Our model is able to diagnose the most difficult cases without any false positives, which are often misdiagnosed and lead to unnecessary treatments for patients. We were able to improve the true positive rate from around 44% to 68% when compared to cytopathologist performance.

How do these findings contribute to your research area?

This research is primarily designed to serve as a clinical support tool for cytopathologists, especially those who specialize in the biliary and pancreatobiliary tracts. One of the most difficult challenges in this field is to diagnose patients with atypical cell morphologies, which have extremely subjective criteria for malignancy amongst experts. Our work will aid in being able to further stratify those cases into a definitive diagnosis so that the clinician can prescribe the best treatment available for the patient.

“Research is primarily designed to serve as a clinical support tool for cytopathologists, especially those who specialize in the biliary and pancreatobiliary tracts.”

What was the exciting moment during your research?

I think the first time I saw those Area Under the Curve (AUC) values hovering around 79% for validating the classifier on a novel set of images. It was the “eureka” moment, as it served as a sanity check that all the laborious pre-processing work and selection of machine learning algorithms were sufficient, and that no further deep learning networks were necessary.

What do you hope to do next?

We are currently collaborating with new partners at the Emory School of Medicine to further improve the robustness of our model by introducing multi-site data and the rest…must remain a secret for now!

Where do you seek scientific inspiration from?

From my parents to my extended family, I have no shortage of role models in all areas of STEM (science, tech, engineering, medicine). Anything I wanted to do, someone was there to help, especially my father. Since my freshman year of undergrad, I started volunteering in various labs in different fields. Four years later, I found my area.

How do you intend to help Indian science improve?

By doing research in our field, we hope to boost the awareness of the young generation via your platform. As the financial and pathological burdens of these diseases that can be detected early increases, it will require more brain power. I appreciate a platform like Biopatrika, which has a wider public and social media reach, and through which new minds could well be introduced to a field that many are unaware existed.

Reference

Monabbati, S, Leo, P, Bera, K, et al. Automated analysis of computerized morphological features of cell clusters associated with malignancy on bile duct brushing whole slide images. Cancer Med. 2022; 00: 1- 14. doi: 10.1002/cam4.5365

Copy Editor

Sukanya Madhwal

Ph.D. student at inStem Bangalore

Sukanya hails from a small town, kotdwara in Uttarakhand. She completed her Masters’ degree in Biotechnology from Banasthali Vidyapith, Rajasthan. After this, she served as a graduate teacher for one year at P.G. College, Kotdwara, Uttarakhand. In 2014, she qualified for the JGEEBILS exam conducted by NCBS/TIFR and joined as a Research Scholar (Ph.D. student) in Dr. Tina Mukherjee’s lab at inStem. Currently, she continued working as a bridging post-doc in Dr. Tina Mukherjee’s lab. Besides work, she loves reading non-fiction books, enjoys gardening, and cooking delicious food.

For interview related queries, write to us at interview.biopatrika@gmail.com