Loading Events


Lunch Pitches with Anders Garpebring, Sophia Harlid and Jian-Feng Mao

To encourage cross pollination of ideas between researchers from different disciplines, IceLab hosts interdisciplinary research lunches with the vision of allowing ideas to meet and mate. During the Lunch Pitch Season, the creative lunches take place at KBC on a Wednesday.
Place: KBC Glasburen
Time: Wednesday 27 March at 12:00.

Pitch 1: Anders Garpebring: Image Processing for AI Made Easy

Associate Professor, combined with clinical employment at Department of Diagnostics and Intervention, unit Radiation Physics

The development and deployment of artificial intelligence (AI) models for image processing tasks require extensive preprocessing of image data to ensure it meets the requisite format and quality standards. This preparatory phase is critical, as it directly influences the performance and accuracy of AI models. However, it is often marked by complexity and labor-intensive procedures that can impede efficiency and scalability.

To address these challenges, we have developed Hero, an innovative graphical user interface designed to streamline the process of image data preparation and model deployment. Hero is a user-friendly platform that allows users to construct pre-processing and post-processing pipelines through intuitive drawing of workflows, significantly reducing the technical barrier traditionally associated with these tasks. Additionally, Hero provides functionality for seamless deployment of trained models by employing a drag-and-drop mechanism, facilitating a smoother transition from model development to operational use. Finally, Hero is equipped to handle large batches of data, enabling the application of defined workflows on extensive datasets efficiently. This capability is particularly beneficial for projects requiring the processing of vast amounts of image data, ensuring both time and resource optimization.

With Hero, we hope to simplify the preparatory stages of image data formatting and quality enhancement as well as accelerate the model deployment process. Through its graphical interface, we want Hero to democratize access to advanced image processing techniques, making it an invaluable tool for researchers, developers, and practitioners aiming to leverage AI in their work with minimal technical hurdles.

What I am looking for: Researchers interested in using Hero and providing feedback. Also interested in collaborations that can result in improving or extending the software.

Pitch 2: Sophia Harlid: Exposure assessment during sensitive time periods – a key to understanding breast cancer risk?

Research Fellow, Department of Diagnostics and Intervention, unit: Oncology
Breast cancer etiology may be driven by disruptions and changes in breast tissue during critical windows of susceptibility such as puberty, menopause, and pregnancy. For example: during pregnancy, the breast tissue undergoes several critical stages of development and maturation, controlled by hormonal fluctuations. This makes the gland sensitive to environmental exposures e.g., through contact with chemicals that interact with hormone receptors which could increase breast cancer risk. Effects triggered by such exposures could also serve as mediators between exposure and breast cancer development. In my work I am investigating the effect of exposures during pregnancy to infer their effect on premenopausal breast cancer risk. The project involves register and biobank studies, as well as the setup of a new cohort.

Interested in: Potential collaborations that could help us setup a proof-of-concept study using animal models. Any additional feedback or discussion will also be very welcome.


Pitch 3: Jian-Feng Mao: Deep-learning (DL) guided identification of LTR retrotransposon

Associate Professor, Department of Plant Physiology, Umeå Plant Science Centre, Umea University


Long Terminal Repeat retrotransposons (LTR-RTs) are pervasive and a dominant component in plant genomes, playing pivotal roles in functional variation, genome plasticity, and evolutionary processes. Despite their significance, the computational resources required for LTR-RT identification remain substantial, particularly for large genomes such as those of wheat (5-15 Gb) and conifers (10-40 Gb). To address this, we have developed a deep-learning (DL) guided method for LTR-RT identification, named LTR-checker. This tool offers competitive precision, reduced computational demands, and enhanced flexibility. This study underscores the exciting potential of DL applications in genomics. The new method is publicly available at: https://github.com/morningsun77/ltr_checker.

Interested in: We aim to unravel the complexity in plant genomes, by developing highly efficient computational tools. We are looking for collaboration from both plant biologists (to pinpoint critical research questions) and computer scientists (to integrate the latest advancements in computing technology).



Share This Post