Fast and scalable search of whole-slide images via self-supervised deep learning.

The adoption of digital pathology has enabled the curation of large repositories of gigapixel whole-slide images (WSIs). Computationally identifying WSIs with similar morphologic features within large repositories without requiring supervised training can have significant applications. However, the retrieval speeds of algorithms for searching similar WSIs often scale with the repository size, which limits their clinical and research potential. Here we show that self-supervised deep learning can be leveraged to search for and retrieve WSIs at speeds that are independent of repository size. The algorithm, which we named SISH (for self-supervised image search for histology) and provide as an open-source package, requires only slide-level annotations for training, encodes WSIs into meaningful discrete latent representations and leverages a tree data structure for fast searching followed by an uncertainty-based ranking algorithm for WSI retrieval. We evaluated SISH on multiple tasks (including retrieval tasks based on tissue-patch queries) and on datasets spanning over 22,000 patient cases and 56 disease subtypes. SISH can also be used to aid the diagnosis of rare cancer types for which the number of available WSIs is often insufficient to train supervised deep-learning models.

Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media.

Pathologists are responsible for rapidly providing a diagnosis on critical health issues. Challenging cases benefit from additional opinions of pathologist colleagues. In addition to on-site colleagues, there is an active worldwide community of pathologists on social media for complementary opinions. Such access to pathologists worldwide has the capacity to improve diagnostic accuracy and generate broader consensus on next steps in patient care. From Twitter we curate 13,626 images from 6,351 tweets from 25 pathologists from 13 countries. We supplement the Twitter data with 113,161 images from 1,074,484 PubMed articles. We develop machine learning and deep learning models to (i) accurately identify histopathology stains, (ii) discriminate between tissues, and (iii) differentiate disease states. Area Under Receiver Operating Characteristic (AUROC) is 0.805-0.996 for these tasks. We repurpose the disease classifier to search for similar disease states given an image and clinical covariates. We report precision@k = 1 = 0.7618 ± 0.0018 (chance 0.397 ± 0.004, mean ±stdev ). The classifiers find that texture and tissue are important clinico-visual features of disease. Deep features trained only on natural images (e.g., cats and dogs) substantially improved search performance, while pathology-specific deep features and cell nuclei features further improved search to a lesser extent. We implement a social media bot (@pathobot on Twitter) to use the trained classifiers to aid pathologists in obtaining real-time feedback on challenging cases. If a social media post containing pathology text and images mentions the bot, the bot generates quantitative predictions of disease state (normal/artifact/infection/injury/nontumor, preneoplastic/benign/low-grade-malignant-potential, or malignant) and lists similar cases across social media and PubMed. Our project has become a globally distributed expert system that facilitates pathological diagnosis and brings expertise to underserved regions or hospitals with less expertise in a particular disease. This is the first pan-tissue pan-disease (i.e., from infection to malignancy) method for prediction and search on social media, and the first pathology study prospectively tested in public on social media. We will share data through http://pathobotology.org . We expect our project to cultivate a more connected world of physicians and improve patient care worldwide.

Scaling of cytoskeletal organization with cell size in Drosophila.

Spatially organized macromolecular complexes are essential for cell and tissue function, but the mechanisms that organize micron-scale structures within cells are not well understood. Microtubule-based structures such as mitotic spindles scale with cell size, but less is known about the scaling of actin structures within cells. Actin-rich denticle precursors cover the ventral surface of the Drosophila embryo and larva and provide templates for cuticular structures involved in larval locomotion. Using quantitative imaging and statistical modeling, we demonstrate that denticle number and spacing scale with cell length over a wide range of cell sizes in embryos and larvae. Denticle number and spacing are reduced under space-limited conditions, and both features robustly scale over a 10-fold increase in cell length during larval growth. We show that the relationship between cell length and denticle spacing can be recapitulated by specific mathematical equations in embryos and larvae and that accurate denticle spacing requires an intact microtubule network and the microtubule minus end-binding protein, Patronin. These results identify a novel mechanism of micro-tubule-dependent actin scaling that maintains precise patterns of actin organization during tissue growth.

DeepScope: Nonintrusive Whole Slide Saliency Annotation and Prediction from Pathologists at the Microscope.

Modern digital pathology departments have grown to produce whole-slide image data at petabyte scale, an unprecedented treasure chest for medical machine learning tasks. Unfortunately, most digital slides are not annotated at the image level, hindering large-scale application of supervised learning. Manual labeling is prohibitive, requiring pathologists with decades of training and outstanding clinical service responsibilities. This problem is further aggravated by the United States Food and Drug Administration's ruling that primary diagnosis must come from a glass slide rather than a digital image. We present the first end-to-end framework to overcome this problem, gathering annotations in a nonintrusive manner during a pathologist's routine clinical work: (i) microscope-specific 3D-printed commodity camera mounts are used to video record the glass-slide-based clinical diagnosis process; (ii) after routine scanning of the whole slide, the video frames are registered to the digital slide; (iii) motion and observation time are estimated to generate a spatial and temporal saliency map of the whole slide. Demonstrating the utility of these annotations, we train a convolutional neural network that detects diagnosis-relevant salient regions, then report accuracy of 85.15% in bladder and 91.40% in prostate, with 75.00% accuracy when training on prostate but predicting in bladder, despite different pathologists examining the different tissues. When training on one patient but testing on another, AUROC in bladder is 0.79±0.11 and in prostate is 0.96±0.04. Our tool is available at https://bitbucket.org/aschaumberg/deepscope.

The complete genome sequence of Clostridium indolis DSM 755(T.).

Clostridium indolis DSM 755(T) is a bacterium commonly found in soils and the feces of birds and mammals. Despite its prevalence, little is known about the ecology or physiology of this species. However, close relatives, C. saccharolyticum and C. hathewayi, have demonstrated interesting metabolic potentials related to plant degradation and human health. The genome of C. indolis DSM 755(T) reveals an abundance of genes in functional groups associated with the transport and utilization of carbohydrates, as well as citrate, lactate, and aromatics. Ecologically relevant gene clusters related to nitrogen fixation and a unique type of bacterial microcompartment, the CoAT BMC, are also detected. Our genome analysis suggests hypotheses to be tested in future culture based work to better understand the physiology of this poorly described species.

Draft Genome Sequence of Pseudomonas azotifigens Strain DSM 17556T (6H33bT), a Nitrogen Fixer Strain Isolated from a Compost Pile.

Pseudomonas azotifigens strain 6H33b(T) is a nitrogen fixer isolated from a hyperthermal compost pile in 2005 by Hatayama and collaborators. Here we report the draft genome, which has an estimated size of 5.0 Mb, exhibits an average G+C content of 66.73%, and is predicted to encode 4,536 protein-coding genes and 100 RNA genes.