Maria Babak: The development of DEPLOY represents a significant advancement in neuro-oncology diagnostics

Maria Babak shared a post by The Babak Lab, on LinkedIn:

“Congratulations to Danh-Tai Hoang, PhD, Eldad Shulman, Rust Turakulov PhD, and the entire team on the remarkable achievement showcased in their recent publication in Nature! The development of DEPLOY represents a significant advancement in neuro-oncology diagnostics, addressing critical challenges and paving the way for more precise and efficient diagnosis of CNS tumors. No doubt, DEPLOY will have a huge impact on improving patient outcomes in diagnosing and treating CNS tumors. Brilliant work! ”

Quoting The Babak Lab‘s post:

“Scientific Wednesday: Revolutionizing Central Nervous System Tumor Diagnosis: Deep Learning Meets Histopathology and Methylation Data

Exciting news in the field of neuro-oncology! We want to share groundbreaking research from Danh-Tai Hoang, PhD, Eldad Shulman, Rust Turakulov PhD, and their team, as featured in their recent publication in Nature Portfolio, ‘Prediction of DNA methylation-based tumor types from histopathology in central nervous system tumors with deep learning.’

Central nervous system (CNS) tumors pose a significant diagnostic challenge, where precision is paramount for optimal treatment. Enter ‘DEPLOY’ – Deep lEarning from histoPathoLOgy and methYlation – a cutting-edge solution devised to enhance diagnostic accuracy while bypassing the limitations associated with DNA methylation profiling.

DEPLOY operates through three interconnected components:

Direct Model: By analyzing slide images, DEPLOY directly classifies CNS tumors, accelerating the diagnostic process and eliminating the need for laborious DNA methylation profiling.

Indirect Model: Leveraging histopathology images, this component generates predictions for DNA methylation beta values, offering an indirect yet effective means of utilizing methylation data for tumor classification.

Demographic-based Model: DEPLOY incorporates routinely available patient demographics into the classification process, further enhancing its accuracy in discerning tumor types.

The efficacy of DEPLOY is validated through rigorous testing. The model accurately predicts beta values from histopathology images and achieves remarkable results in predicting tumor categories across multiple external datasets, with an overall accuracy of 95% and a balanced accuracy of 91% on confidently predicted samples.

These findings underscore the transformative potential of DEPLOY in clinical settings. By providing rapid and precise tumor classification within a clinically relevant timeframe, DEPLOY stands poised to revolutionize CNS tumor diagnosis. With its integration of deep learning technology and histopathology imaging, DEPLOY offers a glimpse into the future of personalized medicine, empowering pathologists to make informed decisions swiftly and accurately.

Excited to see how DEPLOY shapes the future of neuro-oncology! ”

Read further.
Source: Maria Babak/LinkedIn and The Babak Lab/LinkedIn

Dr. Maria (Masha) Babak is the Head of The Babak Lab and an Assistant Professor at the City University of Hong Kong. She earned her Ph.D. in bioinorganic chemistry from the University of Vienna in 2014. From 2015 to 2020, Dr. Babak was a postdoctoral research fellow at the National University of Singapore under the mentorship of Prof. Wee Han Ang, where she developed a strong passion for drug discovery and drug target identification. In November 2020, she joined the City University of Hong Kong as an assistant professor. Dr. Babak received the Graeme Hanson-AsBIC Early Career Award in 2022.

Her research interests are at the intersection of chemistry, biology, and medicine, with a focus on the discovery and preclinical development of anticancer drugs for resistant and aggressive cancers with limited treatment options, such as malignant pleural mesothelioma and brain metastases.