Edvard Pedersen

Pavitra Chauhan, Mohsen Gamal Saad Askar, Kristian Svendsen et al.

The translation of clinical decision support system (CDSS) tools from research settings into the clinic is often non-existent, partly because the focus tends to be on training machine learning models rather than tool development using the model for inference. To develop a CDSS tool that can be deployed in the clinical workflow, there is a need to integrate, validate, and test the tool on the Electronic Health Record (EHR) systems that store and manage patient data. Not surprisingly, it is rarely possible for researchers to get the necessary access to an EHR system due to legal restrictions pertaining to the protection of data privacy in patient records. We propose an architecture for using synthetic data in EHR systems to make CDSS tool development and testing much easier. In this study, the architecture is implemented in the SyntHIR system. SyntHIR has three noteworthy architectural features enabling (i) integration with synthetic data generators, (ii) data interoperability, and (iii) tool transportability. The translational value of this approach was evaluated through two primary steps. First, a working proof-of-concept of a machine learning-based CDSS tool was developed using data from patient registries in Norway. Second, the transportability of this CDSS tool was demonstrated by successfully deploying it in Norway's largest EHR system vendor (DIPS). These findings showcase the value of the SyntHIR architecture as a useful reference model to accelerate the translation of "bench to bedside" research of CDSS tools.

Nikita Shvetsov, Morten Grønnesby, Edvard Pedersen et al.

Increased levels of tumor infiltrating lymphocytes (TILs) in cancer tissue indicate favourable outcomes in many types of cancer. Manual quantification of immune cells is inaccurate and time consuming for pathologists. Our aim is to leverage a computational solution to automatically quantify TILs in whole slide images (WSIs) of standard diagnostic haematoxylin and eosin stained sections (H&E slides) from lung cancer patients. Our approach is to transfer an open source machine learning method for segmentation and classification of nuclei in H&E slides trained on public data to TIL quantification without manual labeling of our data. Our results show that additional augmentation improves model transferability when training on few samples/limited tissue types. Models trained with sufficient samples/tissue types do not benefit from our additional augmentation policy. Further, the resulting TIL quantification correlates to patient prognosis and compares favorably to the current state-of-the-art method for immune cell detection in non-small lung cancer (current standard CD8 cells in DAB stained TMAs HR 0.34 95% CI 0.17-0.68 vs TILs in HE WSIs: HoVer-Net PanNuke Aug Model HR 0.30 95% CI 0.15-0.60, HoVer-Net MoNuSAC Aug model HR 0.27 95% CI 0.14-0.53). Moreover, we implemented a cloud based system to train, deploy and visually inspect machine learning based annotation for H&E slides. Our pragmatic approach bridges the gap between machine learning research, translational clinical research and clinical implementation. However, validation in prospective studies is needed to assert that the method works in a clinical setting.

Álvaro Martínez Fernández, Lars Ailo Bongo, Edvard Pedersen

Visualizations are an essential part of biomedical analysis result interpretation. Often, interactive networks are used to visualize the data. However, the high interconnectivity, and high dimensionality of the data often results in information overload, making it hard to interpret the results. To address the information overload problem, existing solutions typically either use data reduction, reduced interactivity, or expensive hardware. We propose using the affordable Oculus Quest Virtual Reality (VR) headset for interactive visualization of large-scale biological networks. We present the design and implementation of our solution, GeneNet VR, and we evaluate its scalability and usability using large gene-to-gene interaction networks. We achieve the 72 FPS required by the Oculus performance guidelines for the largest of our networks (2693 genes) using both a GPU and the Oculus Quest standalone. We found from our interviews with biomedical researchers that GeneNet VR is innovative, interesting, and easy to use for novice VR users. We believe affordable hardware like the Oculus Quest has a big potential for biological data analysis. However, additional work is required to evaluate its benefits to improve knowledge discovery for real data analysis use cases. GeneNet VR is open-sourced: https://github.com/kolibrid/GeneNet-VR. A video demonstrating GeneNet VR used to explore large biological networks: https://youtu.be/N4QDZiZqVNY.