Advances in artificial intelligence (AI) have powered many new technologies in the realms of natural language processing (e.g. Siri or Alexa) and computer vision (object detection and classification in videos and images, e.g. self-driving cars). I am particularly interested in the use of such machine learning systems for the analysis of medical images. While the field of radiology is working with digital images since a long time, the related discipline of pathology is only recently undergoing the digital transformation. Here, we are dealing with patient specimens in the form of tissue or cells for the study of disease. Recently, whole slide image scanners are available, that enable the rapid digitization of traditional stained glass slides into digital gigapixel images. The availability of digital images coupled with new and powerful AI methods gives rise to computational pathology which is concerned with the development of novel decision support systems as a way to further personalized medicine efforts and enable differential diagnosis systems for early detection and characterization of diseases such as cancer.
For my Gateway Fellowship project I could win the support of Prof. Jun Sakuma from the University of Tsukuba in Japan. His Machine Learning and Data Mining lab is very much theory focused while I come from a more practical bioinformatics background. The study and subsequent integration of foundational new ideas into established state-of-the-art approaches is a way to synthesize novel and powerful applications. As such, I want to investigate the potential of very scalable but inefficient transformer architectures that currently dominate many other areas of computer vision research but could not yet be successfully applied to medical images due to their sheer size. In Japan, there is the opportunity to work on a distributed network of hospitals to enable federated learning, which would split the computational load across many instances, thus giving me the optimal conditions for this project.
Decreasing the carbon dioxide (CO2) emissions is one of the most urgent global challenges. Electrochemical methods are highly desirable for that, because they can convert CO2 and electric energy to valuable compounds in a sustainable way, if the electricity is obtained from renewable sources. Several metal surfaces catalyze the electrochemical carbon dioxide reduction reaction (CO2RR). However, they suffer from poor selectivity, which means that they produce a mixture of compounds instead of one valuable product. Therefore, surface functionalization with polymers gained attention, because it increases the selectivity of metal-based electrocatalysts. However, the underlying mechanisms are poorly understood, especially, because of a severe lack of knowledge on the local catalyst environment under operating conditions. One of those unknown parameters is the local pH value, which defines how basic or acidic the catalyst environment is. Within the Gateway Fellowship project "Polymer-Induced Selectivity Enhancement of the CO2 Reduction Reaction on Copper and Gold - The Influence of the Local pH Value" being conducted at Leiden University under the supervision of Prof. Marc Koper and Prof. Lars Jeuken, I will functionalize polymers with pH sensitive, fluorescent dyes and coat them onto gold and copper electrodes. These polymers will allow to follow changes of the local pH value by fluorescence microscopy. These pH changes will be correlated to selectivity changes. This will add significant new knowledge on the mechanistic processes occurring at polymer-coated electrodes and may contribute to the rational design of selective CO2RR electrocatalyst.
Due to anthropogenic activities, coral reefs worldwide are under severe stress, which in many cases has led to so-called "phase shifts," a change from the dominance of stony corals to other reef taxa such as macroalgae, sponges, or other cnidarians. However, the effects of these phase shifts are poorly understood, so there is a need to understand how future reef states will be structured and function.
The Gateway Fellowship project is being conducted on Okinawa, Japan, at the University of the Ryukyus in collaboration with Prof. James Reimer, as the island is particularly affected by anthropogenic stressors. Therefore, the goal of this project is to investigate the composition of the benthic community at reef sites that are structured to varying degrees by anthropogenic impacts. A holistic approach will be taken, combining visual methods with a state-of-the-art eDNA metabarcoding assay to assess the biodiversity.
This will provide insight into how anthropogenic stress has structured these benthic communities. This will not only provide predictions for the future of Okinawan coral reefs under increasing anthropogenic stress and global climate change, but also for other stressed reefs worldwide, providing a toolkit for implementing management strategies.