Self-supervised learning for characterising histomorphological diversity and spatial RNA expression prediction across 23 human tissue types.

As vast histological archives are digitised, there is a pressing need to be able to associate specific tissue substructures and incident pathology to disease outcomes without arduous annotation. Here, we learn self-supervised representations using a Vision Transformer, trained on 1.7 M histology images across 23 healthy tissues in 838 donors from the Genotype Tissue Expression consortium (GTEx). Using these representations, we can automatically segment tissues into their constituent tissue substructures and pathology proportions across thousands of whole slide images, outperforming other self-supervised methods (43% increase in silhouette score). Additionally, we can detect and quantify histological pathologies present, such as arterial calcification (AUROC = 0.93) and identify missing calcification diagnoses. Finally, to link gene expression to tissue morphology, we introduce RNAPath, a set of models trained on 23 tissue types that can predict and spatially localise individual RNA expression levels directly from H&E histology (mean genes significantly regressed = 5156, FDR 1%). We validate RNAPath spatial predictions with matched ground truth immunohistochemistry for several well characterised control genes, recapitulating their known spatial specificity. Together, these results demonstrate how self-supervised machine learning when applied to vast histological archives allows researchers to answer questions about tissue pathology, its spatial organisation and the interplay between morphological tissue variability and gene expression.

An automatic entropy method to efficiently mask histology whole-slide images.

Tissue segmentation of histology whole-slide images (WSI) remains a critical task in automated digital pathology workflows for both accurate disease diagnosis and deep phenotyping for research purposes. This is especially challenging when the tissue structure of biospecimens is relatively porous and heterogeneous, such as for atherosclerotic plaques. In this study, we developed a unique approach called 'EntropyMasker' based on image entropy to tackle the fore- and background segmentation (masking) task in histology WSI. We evaluated our method on 97 high-resolution WSI of human carotid atherosclerotic plaques in the Athero-Express Biobank Study, constituting hematoxylin and eosin and 8 other staining types. Using multiple benchmarking metrics, we compared our method with four widely used segmentation methods: Otsu's method, Adaptive mean, Adaptive Gaussian and slideMask and observed that our method had the highest sensitivity and Jaccard similarity index. We envision EntropyMasker to fill an important gap in WSI preprocessing, machine learning image analysis pipelines, and enable disease phenotyping beyond the field of atherosclerosis.

Improving Augmented Reality Through Deep Learning: Real-time Instrument Delineation in Robotic Renal Surgery.

Several barriers prevent the integration and adoption of augmented reality (AR) in robotic renal surgery despite the increased availability of virtual three-dimensional (3D) models. Apart from correct model alignment and deformation, not all instruments are clearly visible in AR. Superimposition of a 3D model on top of the surgical stream, including the instruments, can result in a potentially hazardous surgical situation. We demonstrate real-time instrument detection during AR-guided robot-assisted partial nephrectomy and show the generalization of our algorithm to AR-guided robot-assisted kidney transplantation. We developed an algorithm using deep learning networks to detect all nonorganic items. This algorithm learned to extract this information for 65 927 manually labeled instruments on 15 100 frames. Our setup, which runs on a standalone laptop, was deployed in three different hospitals and used by four different surgeons. Instrument detection is a simple and feasible way to enhance the safety of AR-guided surgery. Future investigations should strive to optimize efficient video processing to minimize the 0.5-s delay currently experienced. General AR applications also need further optimization, including detection and tracking of organ deformation, for full clinical implementation.