Spatial subcellular organelle networks in single cells.

Organelles play important roles in human health and disease, such as maintaining homeostasis, regulating growth and aging, and generating energy. Organelle diversity in cells not only exists between cell types but also between individual cells. Therefore, studying the distribution of organelles at the single-cell level is important to understand cellular function. Mesenchymal stem cells are multipotent cells that have been explored as a therapeutic method for treating a variety of diseases. Studying how organelles are structured in these cells can answer questions about their characteristics and potential. Herein, rapid multiplexed immunofluorescence (RapMIF) was performed to understand the spatial organization of 10 organelle proteins and the interactions between them in the bone marrow (BM) and umbilical cord (UC) mesenchymal stem cells (MSCs). Spatial correlations, colocalization, clustering, statistical tests, texture, and morphological analyses were conducted at the single cell level, shedding light onto the interrelations between the organelles and comparisons of the two MSC subtypes. Such analytics toolsets indicated that UC MSCs exhibited higher organelle expression and spatially spread distribution of mitochondria accompanied by several other organelles compared to BM MSCs. This data-driven single-cell approach provided by rapid subcellular proteomic imaging enables personalized stem cell therapeutics.

Explainable synthetic image generation to improve risk assessment of rare pediatric heart transplant rejection.

Expert microscopic analysis of cells obtained from frequent heart biopsies is vital for early detection of pediatric heart transplant rejection to prevent heart failure. Detection of this rare condition is prone to low levels of expert agreement due to the difficulty of identifying subtle rejection signs within biopsy samples. The rarity of pediatric heart transplant rejection also means that very few gold-standard images are available for developing machine learning models. To solve this urgent clinical challenge, we developed a deep learning model to automatically quantify rejection risk within digital images of biopsied tissue using an explainable synthetic data augmentation approach. We developed this explainable AI framework to illustrate how our progressive and inspirational generative adversarial network models distinguish between normal tissue images and those containing cellular rejection signs. To quantify biopsy-level rejection risk, we first detect local rejection features using a binary image classifier trained with expert-annotated and synthetic examples. We converted these local predictions into a biopsy-wide rejection score via an interpretable histogram-based approach. Our model significantly improves upon prior works with the same dataset with an area under the receiver operating curve (AUROC) of 98.84% for the local rejection detection task and 95.56% for the biopsy-rejection prediction task. A biopsy-level sensitivity of 83.33% makes our approach suitable for early screening of biopsies to prioritize expert analysis. Our framework provides a solution to rare medical imaging challenges currently limited by small datasets.