Background: Artificial intelligence (AI) is fast becoming the tool of choice for scalable and reliable analysis of medical images. However, constraints in sharing medical data outside the institutional or geographical space, as well as difficulties in getting AI models and modeling platforms to work across different environments, have led to a “reproducibility crisis” in digital medicine. Methods: This study details the implementation of a web platform that can be used to mitigate these challenges by orchestrating a digital pathology AI pipeline, from raw data to model inference, entirely on the local machine. We discuss how this federated platform provides governed access to data by consuming the Application Program Interfaces exposed by cloud storage services, allows the addition of user-defined annotations, facilitates active learning for training models iteratively, and provides model inference computed directly in the web browser at practically zero cost. The latter is of particular relevance to clinical workflows because the code, including the AI model, travels to the user's data, which stays private to the governance domain where it was acquired. Results: We demonstrate that the web browser can be a means of democratizing AI and advancing data socialization in medical imaging backed by consumer-facing cloud infrastructure such as Box.com. As a case study, we test the accompanying platform end-to-end on a large dataset of digital breast cancer tissue microarray core images. We also showcase how it can be applied in contexts separate from digital pathology by applying it to a radiology dataset containing COVID-19 computed tomography images. Conclusions: The platform described in this report resolves the challenges to the findable, accessible, interoperable, reusable stewardship of data and AI models by integrating with cloud storage to maintain user-centric governance over the data. It also enables distributed, federated computation for AI inference over those data and proves the viability of client-side AI in medical imaging. Availability: The open-source application is publicly available at https://episphere.github.io/path, with a short video demonstration at https://youtu.be/z59jToy2TxE.

Context: Diseases of the hematopoietic system such as leukemia is diagnosed using bone marrow samples. The cell type distribution plays a major role but requires manual analysis of different cell types in microscopy images. Aims: Automated analysis of bone marrow samples requires detection and classification of different cell types. In this work, we propose and compare algorithms for cell localization, which is a key component in automated bone marrow analysis. Settings and Design: We research fully supervised detection architectures but also propose and evaluate several techniques utilizing weak annotations in a segmentation network. We further incorporate typical cell-like artifacts into our analysis. Whole slide microscopy images are acquired from the human bone marrow samples and annotated by expert hematologists. Subjects and Methods: We adapt and evaluate state-of-the-art detection networks. We further propose to utilize the popular U-Net for cell detection by applying suitable preprocessing steps to the annotations. Statistical Analysis Used: Evaluations are performed on a held-out dataset using multiple metrics based on the two different matching algorithms. Results: The results show that the detection of cells in hematopoietic images using state-of-the-art detection networks yields very accurate results. U-Net-based methods are able to slightly improve detection results using adequate preprocessing – despite artifacts and weak annotations. Conclusions: In this work, we propose, U-Net-based cell detection methods and compare with state-of-the-art detection methods for the localization of hematopoietic cells in high-resolution bone marrow images. We show that even with weak annotations and cell-like artifacts, cells can be localized with high precision.

Background: Tumor heterogeneity is increasingly being recognized as a major source of variability in the histopathological assessment of drug responses. Quantitative analysis of immunohistochemistry (IHC) and immunofluorescence (IF) images using biomarkers that capture spatialpatterns of distinct tumor biology and drug concentration in tumors is of high interest to the field. Methods: We have developed an image analysis pipeline to measure drug response using IF and IHC images along spatial gradients of local drug release from a tumor-implantable drug delivery microdevice. The pipeline utilizes a series of user-interactive python scripts and CellProfiler pipelines with custom modules to perform image and spatial analysis of regions of interest within whole-slide images. Results: Worked examples demonstrate that intratumor measurements such as apoptosis, cell proliferation, and immune cell population density can be quantitated in a spatially and drug concentration-dependent manner, establishing in vivo profiles of pharmacodynamics and pharmacokinetics in tumors. Conclusions: Spatial image analysis of tumor response along gradients of local drug release is achievable in high throughput. The major advantage of this approach is the use of spatially aware annotation tools to correlate drug gradients with drug effects in tumors in vivo.