Learning representations for image-based profiling of perturbations.

Measuring the phenotypic effect of treatments on cells through imaging assays is an efficient and powerful way of studying cell biology, and requires computational methods for transforming images into quantitative data. Here, we present an improved strategy for learning representations of treatment effects from high-throughput imaging, following a causal interpretation. We use weakly supervised learning for modeling associations between images and treatments, and show that it encodes both confounding factors and phenotypic features in the learned representation. To facilitate their separation, we constructed a large training dataset with images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN. We evaluated our strategy on three publicly available Cell Painting datasets, and observed that the Cell Painting CNN improves performance in downstream analysis up to 30% with respect to classical features, while also being more computationally efficient.

Reproducible image-based profiling with Pycytominer.

Technological advances in high-throughput microscopy have facilitated the acquisition of cell images at a rapid pace, and data pipelines can now extract and process thousands of image-based features from microscopy images. These features represent valuable single-cell phenotypes that contain information about cell state and biological processes. The use of these features for biological discovery is known as image-based or morphological profiling. However, these raw features need processing before use and image-based profiling lacks scalable and reproducible open-source software. Inconsistent processing across studies makes it difficult to compare datasets and processing steps, further delaying the development of optimal pipelines, methods, and analyses. To address these issues, we present Pycytominer, an open-source software package with a vibrant community that establishes an image-based profiling standard. Pycytominer has a simple, user-friendly Application Programming Interface (API) that implements image-based profiling functions for processing high-dimensional morphological features extracted from microscopy images of cells. Establishing Pycytominer as a standard image-based profiling toolkit ensures consistent data processing pipelines with data provenance, therefore minimizing potential inconsistencies and enabling researchers to confidently derive accurate conclusions and discover novel insights from their data, thus driving progress in our field.

Intrinsic mesoscale properties of a Polycomb protein underpin heterochromatin fidelity.

Little is understood about how the two major types of heterochromatin domains (HP1 and Polycomb) are kept separate. In the yeast Cryptococcus neoformans, the Polycomb-like protein Ccc1 prevents deposition of H3K27me3 at HP1 domains. Here we show that phase separation propensity underpins Ccc1 function. Mutations of the two basic clusters in the intrinsically disordered region or deletion of the coiled-coil dimerization domain alter phase separation behavior of Ccc1 in vitro and have commensurate effects on formation of Ccc1 condensates in vivo, which are enriched for PRC2. Notably, mutations that alter phase separation trigger ectopic H3K27me3 at HP1 domains. Supporting a direct condensate-driven mechanism for fidelity, Ccc1 droplets efficiently concentrate recombinant C. neoformans PRC2 in vitro whereas HP1 droplets do so only weakly. These studies establish a biochemical basis for chromatin regulation in which mesoscale biophysical properties play a key functional role.

Health in All Education: A Transdisciplinary Learning Outcomes Framework.

Historical and recent population health issues necessitate the goal of educating and preparing a transdisciplinary workforce with population health knowledge and competence to be able to develop, implement, and evaluate innovative and feasible solutions that not only address multifaceted community health problems downstream but also to be able to predict and prevent those factors that contribute to an inequitable health burden upstream. To identify where population health education is already shared among multiple disciplines, the Centers for Disease Control and Prevention's Academic Partnerships to Improve Health program conceptualized the Health In All Education initiative that was implemented in partnership with the Association for Prevention Teaching and Research. The purpose of the initiative was to (1) show the importance of integrating population health principles into higher-education transdisciplinary practices; (2) discuss examples of Centers for Disease Control and Prevention collaboration with disciplines related to public health (i.e., economics, environmental engineering, health informatics, health law and policy, social work, liberal education in general education); and (3) explore opportunities to promote transdisciplinary learning to prepare for collaborative, interprofessional practice in population health. This article introduces the Health in All Education Learning Outcomes Framework, a set of shared population health concepts identified on the basis of discipline-representative consensus. The following domains were identified as having transdisciplinary applicability on the basis of established public health curricula, competency, and learning outcome models: determinants of health, evidence-based approaches, population health focus, interprofessional practice, community collaboration, environmental health, occupational health, global health, diversity/cultural competence, health systems, finance and budgeting, and health law and policy.

Medical Service Quality and Office Rent Premiums: Reputation Spillovers.

Location spillovers are a common theme in real estate and urban economics research, but this is the first test on the relationship between hospital service quality and the demand for proximate medical office space. We hypothesize that hospitals with reputations for high quality service represent an opportunity for physicians, and other service providers, to benefit from reputation spillovers. Further, the reputation benefit is capitalized into the practices' willingness to pay for proximate office locations, thereby driving up the rental rates for nearby space. We find that distance from, and overall quality ranking of the hospital, both independent and in concert, are significantly linked to the base rents. The degradation in rent with distance is significantly greater when the hospital is ranked high in overall service quality, supporting the notion that a rent premium is linked to the high-quality hospital rather than simply an artifact of the neighborhood.

CellProfiler 4: improvements in speed, utility and usability.

BACKGROUND: Imaging data contains a substantial amount of information which can be difficult to evaluate by eye. With the expansion of high throughput microscopy methodologies producing increasingly large datasets, automated and objective analysis of the resulting images is essential to effectively extract biological information from this data. CellProfiler is a free, open source image analysis program which enables researchers to generate modular pipelines with which to process microscopy images into interpretable measurements. RESULTS: Herein we describe CellProfiler 4, a new version of this software with expanded functionality. Based on user feedback, we have made several user interface refinements to improve the usability of the software. We introduced new modules to expand the capabilities of the software. We also evaluated performance and made targeted optimizations to reduce the time and cost associated with running common large-scale analysis pipelines. CONCLUSIONS: CellProfiler 4 provides significantly improved performance in complex workflows compared to previous versions. This release will ensure that researchers will have continued access to CellProfiler's powerful computational tools in the coming years.

Deepometry, a framework for applying supervised and weakly supervised deep learning to imaging cytometry.

Deep learning offers the potential to extract more than meets the eye from images captured by imaging flow cytometry. This protocol describes the application of deep learning to single-cell images to perform supervised cell classification and weakly supervised learning, using example data from an experiment exploring red blood cell morphology. We describe how to acquire and transform suitable input data as well as the steps required for deep learning training and inference using an open-source web-based application. All steps of the protocol are provided as open-source Python as well as MATLAB runtime scripts, through both command-line and graphic user interfaces. The protocol enables a flexible and friendly environment for morphological phenotyping using supervised and weakly supervised learning and the subsequent exploration of the deep learning features using multi-dimensional visualization tools. The protocol requires 40 h when training from scratch and 1 h when using a pre-trained model.

Objective assessment of stored blood quality by deep learning.

Stored red blood cells (RBCs) are needed for life-saving blood transfusions, but they undergo continuous degradation. RBC storage lesions are often assessed by microscopic examination or biochemical and biophysical assays, which are complex, time-consuming, and destructive to fragile cells. Here we demonstrate the use of label-free imaging flow cytometry and deep learning to characterize RBC lesions. Using brightfield images, a trained neural network achieved 76.7% agreement with experts in classifying seven clinically relevant RBC morphologies associated with storage lesions, comparable to 82.5% agreement between different experts. Given that human observation and classification may not optimally discern RBC quality, we went further and eliminated subjective human annotation in the training step by training a weakly supervised neural network using only storage duration times. The feature space extracted by this network revealed a chronological progression of morphological changes that better predicted blood quality, as measured by physiological hemolytic assay readouts, than the conventional expert-assessed morphology classification system. With further training and clinical testing across multiple sites, protocols, and instruments, deep learning and label-free imaging flow cytometry might be used to routinely and objectively assess RBC storage lesions. This would automate a complex protocol, minimize laboratory sample handling and preparation, and reduce the impact of procedural errors and discrepancies between facilities and blood donors. The chronology-based machine-learning approach may also improve upon humans' assessment of morphological changes in other biomedically important progressions, such as differentiation and metastasis.

Efficacy of enhanced emergency department discharge for chronic hypertension management - Results of a randomized controlled trial.

INTRODUCTION: AchieveBP is a randomized controlled trial (RCT) of an education intervention for patients with chronic hypertension who have uncontrolled blood pressure (BP) at discharge from an urban emergency department (ED). The study examined efficacy and moderators of an educational intervention in an RCT on BP control at 180-day post-intervention. METHODS: Participants were recruited from a single, urban ED and randomized to receive or not to receive hypertension education. To minimize potential bias, participants were all started on an evidence-based anti-hypertensive regimen and medications were dispensed directly to participants by the study team. Bivariate analysis was performed to examine differences in sociodemographic characteristics between patients achieving BP control and those who did not. Paired t-test was used to compare the difference of systolic and diastolic BP between baseline and 180 days post-discharge. Multiple logistic regression analysis examined interaction of covariates and intervention on achieving BP control. RESULTS: One hundred and thirty-nine participants were randomized into the study. All were African-American with a mean age of 47.6 (SD = 10.8) years; 51% were male, 63% had smoked cigarettes and 15% had diabetes. A total of 66 patients completed the study (47.4%), 44 of whom (67%) achieved BP control. However, there was no difference in BP reduction or control between the two groups. Age and smoking status showed moderation effects on intervention efficacy. CONCLUSION: Despite a neutral effect of our intervention, a high level of BP control was achieved overall, suggesting that the ED may be a viable location for efforts aimed at reducing the impact of chronic hypertension in predominantly African American communities.

Keras R-CNN: library for cell detection in biological images using deep neural networks.

BACKGROUND: A common yet still manual task in basic biology research, high-throughput drug screening and digital pathology is identifying the number, location, and type of individual cells in images. Object detection methods can be useful for identifying individual cells as well as their phenotype in one step. State-of-the-art deep learning for object detection is poised to improve the accuracy and efficiency of biological image analysis. RESULTS: We created Keras R-CNN to bring leading computational research to the everyday practice of bioimage analysts. Keras R-CNN implements deep learning object detection techniques using Keras and Tensorflow ( https://github.com/broadinstitute/keras-rcnn ). We demonstrate the command line tool's simplified Application Programming Interface on two important biological problems, nucleus detection and malaria stage classification, and show its potential for identifying and classifying a large number of cells. For malaria stage classification, we compare results with expert human annotators and find comparable performance. CONCLUSIONS: Keras R-CNN is a Python package that performs automated cell identification for both brightfield and fluorescence images and can process large image sets. Both the package and image datasets are freely available on GitHub and the Broad Bioimage Benchmark Collection.

Label-Free Leukemia Monitoring by Computer Vision.

Acute lymphoblastic leukemia (ALL) is the most common childhood cancer. While there are a number of well-recognized prognostic biomarkers at diagnosis, the most powerful independent prognostic factor is the response of the leukemia to induction chemotherapy (Campana and Pui: Blood 129 (2017) 1913-1918). Given the potential for machine learning to improve precision medicine, we tested its capacity to monitor disease in children undergoing ALL treatment. Diagnostic and on-treatment bone marrow samples were labeled with an ALL-discriminating antibody combination and analyzed by imaging flow cytometry. Ignoring the fluorescent markers and using only features extracted from bright-field and dark-field cell images, a deep learning model was able to identify ALL cells at an accuracy of >88%. This antibody-free, single cell method is cheap, quick, and could be adapted to a simple, laser-free cytometer to allow automated, point-of-care testing to detect slow early responders. Adaptation to other types of leukemia is feasible, which would revolutionize residual disease monitoring. © 2020 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Publisher Correction: Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

nucleAIzer: A Parameter-free Deep Learning Framework for Nucleus Segmentation Using Image Style Transfer.

Single-cell segmentation is typically a crucial task of image-based cellular analysis. We present nucleAIzer, a deep-learning approach aiming toward a truly general method for localizing 2D cell nuclei across a diverse range of assays and light microscopy modalities. We outperform the 739 methods submitted to the 2018 Data Science Bowl on images representing a variety of realistic conditions, some of which were not represented in the training data. The key to our approach is that during training nucleAIzer automatically adapts its nucleus-style model to unseen and unlabeled data using image style transfer to automatically generate augmented training samples. This allows the model to recognize nuclei in new and different experiments efficiently without requiring expert annotations, making deep learning for nucleus segmentation fairly simple and labor free for most biological light microscopy experiments. It can also be used online, integrated into CellProfiler and freely downloaded at www.nucleaizer.org. A record of this paper's transparent peer review process is included in the Supplemental Information.

Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl.

Segmenting the nuclei of cells in microscopy images is often the first step in the quantitative analysis of imaging data for biological and biomedical applications. Many bioimage analysis tools can segment nuclei in images but need to be selected and configured for every experiment. The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction. Top participants in the challenge succeeded in this task, developing deep-learning-based models that identified cell nuclei across many image types and experimental conditions without the need to manually adjust segmentation parameters. This represents an important step toward configuration-free bioimage analysis software tools.

Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images.

Identifying nuclei is often a critical first step in analyzing microscopy images of cells and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluation metrics for nucleus segmentation do not satisfactorily capture error modes that are relevant in cellular images. We present an evaluation framework to measure accuracy, types of errors, and computational efficiency; and use it to compare deep learning strategies and classical approaches. We publicly release a set of 23,165 manually annotated nuclei and source code to reproduce experiments and run the proposed evaluation methodology. Our evaluation framework shows that deep learning improves accuracy and can reduce the number of biologically relevant errors by half. © 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Scientific Community Image Forum: A discussion forum for scientific image software.

Forums and email lists play a major role in assisting scientists in using software. Previously, each open-source bioimaging software package had its own distinct forum or email list. Although each provided access to experts from various software teams, this fragmentation resulted in many scientists not knowing where to begin with their projects. Thus, the scientific imaging community lacked a central platform where solutions could be discussed in an open, software-independent manner. In response, we introduce the Scientific Community Image Forum, where users can pose software-related questions about digital image analysis, acquisition, and data management.

DoGNet: A deep architecture for synapse detection in multiplexed fluorescence images.

Neuronal synapses transmit electrochemical signals between cells through the coordinated action of presynaptic vesicles, ion channels, scaffolding and adapter proteins, and membrane receptors. In situ structural characterization of numerous synaptic proteins simultaneously through multiplexed imaging facilitates a bottom-up approach to synapse classification and phenotypic description. Objective automation of efficient and reliable synapse detection within these datasets is essential for the high-throughput investigation of synaptic features. Convolutional neural networks can solve this generalized problem of synapse detection, however, these architectures require large numbers of training examples to optimize their thousands of parameters. We propose DoGNet, a neural network architecture that closes the gap between classical computer vision blob detectors, such as Difference of Gaussians (DoG) filters, and modern convolutional networks. DoGNet is optimized to analyze highly multiplexed microscopy data. Its small number of training parameters allows DoGNet to be trained with few examples, which facilitates its application to new datasets without overfitting. We evaluate the method on multiplexed fluorescence imaging data from both primary mouse neuronal cultures and mouse cortex tissue slices. We show that DoGNet outperforms convolutional networks with a low-to-moderate number of training examples, and DoGNet is efficiently transferred between datasets collected from separate research groups. DoGNet synapse localizations can then be used to guide the segmentation of individual synaptic protein locations and spatial extents, revealing their spatial organization and relative abundances within individual synapses. The source code is publicly available: https://github.com/kulikovv/dognet.

Splenic Angiosarcoma Diagnosed on Bone Marrow Biopsy: Case Report and Literature Review.

Primary splenic angiosarcoma carries a poor prognosis and is among the rarest forms of malignancy. An overwhelming majority of patients with splenic angiosarcoma will develop metastases. However, osseous metastatic disease is rare. We present an 83 year old hispanic female who was diagnosed with primary splenic angiosarcoma on bone marrow biopsy performed for a hematologic workup. We highlight key historical, laboratory, imaging, and pathological features of splenic angiosarcoma. The synthesis of both imaging features and clinical history is essential for establishing early diagnosis in these patients.

CellProfiler 3.0: Next-generation image processing for biology.

CellProfiler has enabled the scientific research community to create flexible, modular image analysis pipelines since its release in 2005. Here, we describe CellProfiler 3.0, a new version of the software supporting both whole-volume and plane-wise analysis of three-dimensional (3D) image stacks, increasingly common in biomedical research. CellProfiler's infrastructure is greatly improved, and we provide a protocol for cloud-based, large-scale image processing. New plugins enable running pretrained deep learning models on images. Designed by and for biologists, CellProfiler equips researchers with powerful computational tools via a well-documented user interface, empowering biologists in all fields to create quantitative, reproducible image analysis workflows.