New DDLS Fellow: Kimmo Kartasalo
The SciLifeLab & Wallenberg National Program for Data-Driven Life Science (DDLS) continues to recruit outstanding early career group leaders, both nationally and internationally. Meet our latest Fellow Kimmo Kartasalo from Karolinska Institutet. He will be joining the DDLS Precision medicine and diagnostics research area.
Kimmo studied engineering at the Tampere University in Finland, with an initial focus on biotech, but couldn’t resist the pull of data science and graduated with a Master’s degree in signal processing. He obtained his doctoral degree in 2021 from the same university, focusing on bioimage informatics under the supervision of Pekka Ruusuvuori. Kimmo’s doctoral thesis handled the use of computational methods for 3D analysis and AI-based processing of tissue samples, and was awarded as the best thesis of the year by the Finnish Society for Bioinformatics. During his PhD, he also conducted extended research visits to Uppsala University and Karolinska Institutet, which he later joined as a postdoc.
How do you think your expertise can contribute to the program?
I have a decade of experience in applying machine learning, AI and high-performance computing to biomedical applications, and can contribute to the program and the supporting infrastructure with my knowledge of these key technologies. I am also a co-founder of a spin-off company from Karolinska, Clinsight AB, which aims to bring some of the research output to routine clinical use in the form of certified medical devices, and could share my experiences with other Fellows who have identified some of their research as having immediate translational potential.
Shortly describe your research in an easy to understand way.
AI and machine learning offer new precision medicine opportunities, for example in pathology, where digital tissue scanning generates vast image data for better cancer diagnostics and treatment. My group develops AI tools to enhance pathology efficiency, accuracy, and reproducibility, automating tasks and aiding pathologists. By developing AI-based decision support tools, routine tasks can be partially or fully automated, and a tireless “digital colleague” provided to pathologists who struggle with an increasing workload and the demand for more extensive and precise quantification. We also integrate image, molecular, and clinical data to build AI models capable of estimating the most likely future course of an individual’s disease and predicting optimal therapeutic options in a manner not possible with current approaches. Our key skills include large-scale image analysis, deep learning, and high-performance computing, and we rely on a network of international clinical collaborations to ensure broad applicability of the developed technologies.
How do you think the program and interactions with the other DDLS-Fellows will benefit you?
Apart from the obvious role of the DDLS funding for my research, the infrastructure developed with the needs of our Fellows in mind, in particular the supercomputer Berzelius, is an enabling key factor for my planned research. Interaction with the other Fellows has already also provided me with some “tricks of the trade” and lessons learned by more senior Fellows when it comes to the practicalities and strategic decisions involved in starting and running a research group. I believe this network of peers at a similar career stage will be a uniquely valuable resource in this respect. Moreover, while we study a wide range of scientific questions, we face similar methodological challenges when it comes to the demands of data-driven research and will be able to share solutions or identify new application areas e.g. for the kind of AI technology I am developing.
Name one thing that people generally do not know about you.
As a teenager, I raced go-karts competitively (occasionally even sharing the track with some of the drivers who went on to later become F1 and rally stars). Needless to say, I didn’t become a Flying Finn and Stockholm will have to do in place of Monte Carlo. In my defense amid the current climate crisis, I have never owned a car, though, and cycling and running have always been my preferred modes of transport off the race circuit.
Where do you see yourself in five years regarding the DDLS aspect?
In five years, I hope my first PhD students have celebrated their degrees and we have published a string of exciting studies during a time, when every day brings something new and unexpected in the field of AI. I also hope some of the research findings have evolved to a stage where they’ve become a part of the daily work of pathologists and are contributing positively to patients’ lives.
In one word, describe how you feel about becoming a DDLS-Fellow.
Curious!
