Annalena Artinger

Pathology is undergoing a fundamental change as slide-based diagnostics transition toward digital workflows. Advances in whole slide imaging, data management, and computational analysis have created the basis for integrating artificial intelligence (AI) into diagnostic routines. However, the growing number of commercial digital pathology platforms poses challenges for selecting clinically suitable and regulatory-compliant solutions. A structured multi-source approach was conducted to identify commercially available digital pathology platforms. Vendor and sponsor lists from major digital pathology congresses, the Digital Pathology Association vendor catalog, and a structured web search were performed. Predefined eligibility criteria were applied to identify the relevant platforms. Suitable parameters were defined and validated by pathology and IT experts to then compare the included platforms, supplemented by direct vendor communication for selected implementation-related parameters, such as support and pricing modalities. Fourteen platforms met the eligibility criteria. Moderate variation was observed across platforms, particularly regarding deployment models, whole slide imaging (WSI) format compatibility, the integration of external AI algorithms, and reported pricing modalities. Based on the market analysis, six practical recommendations were derived to guide platform selection in routine diagnostic workflows. Pathology institutes are under increasing pressure to digitalize their workflows due to rising work volumes and workforce shortages. However, the market for digital pathology solutions is highly dynamic. To ensure sustainable acquisition decisions, the regulatory framework and the site-specific technical infrastructure must be considered. Furthermore, platforms that support the integration of third-party algorithms and offer broad compatibility with whole-slide image formats help to maintain long-term flexibility with regard to future algorithmic developments.

Cell nuclei interpretation is crucial in pathological diagnostics, especially in tumor specimens. A critical step in computational pathology is to detect and analyze individual nuclear properties using segmentation algorithms. Conventionally, a semantic segmentation network is used, where individual nuclear properties are derived after post-processing a segmentation mask. In this study, we focus on showing that an object-detection-based instance segmentation network, the Mask R-CNN, after integrating it with a Feature Pyramidal Network (FPN), gives mature and reliable results for nuclei detection without the need for additional post-processing. The results were analyzed using the Kumar dataset, a public dataset with over 20,000 nuclei annotations from various organs. The dice score of the baseline Mask R-CNN improved from 76% to 83% after integration with an FPN. This was comparable with the 82.6% dice score achieved by modern semantic-segmentation-based networks. Thus, evidence is provided that an end-to-end trainable detection-based instance segmentation algorithm with minimal post-processing steps can reliably be used for the detection and analysis of individual nuclear properties. This represents a relevant task for research and diagnosis in digital pathology, which can improve the automated analysis of histopathological images.

Angiogenesis is the process of new blood vessels growing from existing vasculature. Visualizing them as a three-dimensional (3D) model is a challenging, yet relevant, task as it would be of great help to researchers, pathologists, and medical doctors. A branching analysis on the 3D model would further facilitate research and diagnostic purposes. In this paper, a pipeline of vision algorithms is elaborated to visualize and analyze blood vessels in 3D from formalin-fixed paraffin-embedded (FFPE) granulation tissue sections with two different staining methods. First, a U-net neural network is used to segment blood vessels from the tissues. Second, image registration is used to align the consecutive images. Coarse registration using an image-intensity optimization technique, followed by finetuning using a neural network based on Spatial Transformers, results in an excellent alignment of images. Lastly, the corresponding segmented masks depicting the blood vessels are aligned and interpolated using the results of the image registration, resulting in a visualized 3D model. Additionally, a skeletonization algorithm is used to analyze the branching characteristics of the 3D vascular model. In summary, computer vision and deep learning is used to reconstruct, visualize and analyze a 3D vascular model from a set of parallel tissue samples. Our technique opens innovative perspectives in the pathophysiological understanding of vascular morphogenesis under different pathophysiological conditions and its potential diagnostic role.