A comprehensive AI model development framework for consistent Gleason grading.

BACKGROUND: Artificial Intelligence(AI)-based solutions for Gleason grading hold promise for pathologists, while image quality inconsistency, continuous data integration needs, and limited generalizability hinder their adoption and scalability. METHODS: We present a comprehensive digital pathology workflow for AI-assisted Gleason grading. It incorporates A!MagQC (image quality control), A!HistoClouds (cloud-based annotation), Pathologist-AI Interaction (PAI) for continuous model improvement, Trained on Akoya-scanned images only, the model utilizes color augmentation and image appearance migration to address scanner variations. We evaluate it on Whole Slide Images (WSI) from another five scanners and conduct validations with pathologists to assess AI efficacy and PAI. RESULTS: Our model achieves an average F1 score of 0.80 on annotations and 0.71 Quadratic Weighted Kappa on WSIs for Akoya-scanned images. Applying our generalization solution increases the average F1 score for Gleason pattern detection from 0.73 to 0.88 on images from other scanners. The model accelerates Gleason scoring time by 43% while maintaining accuracy. Additionally, PAI improve annotation efficiency by 2.5 times and led to further improvements in model performance. CONCLUSIONS: This pipeline represents a notable advancement in AI-assisted Gleason grading for improved consistency, accuracy, and efficiency. Unlike previous methods limited by scanner specificity, our model achieves outstanding performance across diverse scanners. This improvement paves the way for its seamless integration into clinical workflows.

Gleason grading is a well-accepted diagnostic standard to assess the severity of prostate cancer in patients' tissue samples, based on how abnormal the cells in their prostate tumor look under a microscope. This process can be complex and time-consuming. We explore how artificial intelligence (AI) can help pathologists perform Gleason grading more efficiently and consistently. We build an AI-based system which automatically checks image quality, standardizes the appearance of images from different equipment, learns from pathologists' feedback, and constantly improves model performance. Testing shows that our approach achieves consistent results across different equipment and improves efficiency of the grading process. With further testing and implementation in the clinic, our approach could potentially improve prostate cancer diagnosis and management.

Quantitative image-based collagen structural features predict the reversibility of hepatitis C virus-induced liver fibrosis post antiviral therapies.

The novel targeted therapeutics for hepatitis C virus (HCV) in last decade solved most of the clinical needs for this disease. However, despite antiviral therapies resulting in sustained virologic response (SVR), a challenge remains where the stage of liver fibrosis in some patients remains unchanged or even worsens, with a higher risk of cirrhosis, known as the irreversible group. In this study, we provided novel tissue level collagen structural insight into early prediction of irreversible cases via image based computational analysis with a paired data cohort (of pre- and post-SVR) following direct-acting-antiviral (DAA)-based treatment. Two Photon Excitation and Second Harmonic Generation microscopy was used to image paired biopsies from 57 HCV patients and a fully automated digital collagen profiling platform was developed. In total, 41 digital image-based features were profiled where four key features were discovered to be strongly associated with fibrosis reversibility. The data was validated for prognostic value by prototyping predictive models based on two selected features: Collagen Area Ratio and Collagen Fiber Straightness. We concluded that collagen aggregation pattern and collagen thickness are strong indicators of liver fibrosis reversibility. These findings provide the potential implications of collagen structural features from DAA-based treatment and paves the way for a more comprehensive early prediction of reversibility using pre-SVR biopsy samples to enhance timely medical interventions and therapeutic strategies. Our findings on DAA-based treatment further contribute to the understanding of underline governing mechanism and knowledge base of structural morphology in which the future non-invasive prediction solution can be built upon.

Automatic DNA replication tract measurement to assess replication and repair dynamics at the single-molecule level.

MOTIVATION: DNA fibre assay has a potential application in genomic medicine, cancer and stem cell research at the single-molecule level. A major challenge for the clinical and research implementation of DNA fibre assays is the slow speed in which manual analysis takes place as it limits the clinical actionability. While automatic detection of DNA fibres speeds up this process considerably, current publicly available software have limited features in terms of their user interface for manual correction of results, which in turn limit their accuracy and ability to account for atypical structures that may be important in diagnosis or investigative studies. We recognize that core improvements can be made to the GUI to allow for direct interaction with automatic results to preserve accuracy as well as enhance the versatility of automatic DNA fibre detection for use in variety of situations. RESULTS: To address the unmet needs of diverse DNA fibre analysis investigations, we propose DNA Stranding, an open-source software that is able to perform accurate fibre length quantification (13.22% mean relative error) and fibre pattern recognition (R > 0.93) with up to six fibre patterns supported. With the graphical interface, we developed, user can conduct semi-automatic analyses which benefits from the advantages of both automatic and manual processes to improve workflow efficiency without compromising accuracy. AVAILABILITY AND IMPLEMENTATION: The software package is available at https://github.com/lgole/DNAStranding. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Constructing and optimizing 3D atlases from 2D data with application to the developing mouse brain.

3D imaging data necessitate 3D reference atlases for accurate quantitative interpretation. Existing computational methods to generate 3D atlases from 2D-derived atlases result in extensive artifacts, while manual curation approaches are labor-intensive. We present a computational approach for 3D atlas construction that substantially reduces artifacts by identifying anatomical boundaries in the underlying imaging data and using these to guide 3D transformation. Anatomical boundaries also allow extension of atlases to complete edge regions. Applying these methods to the eight developmental stages in the Allen Developing Mouse Brain Atlas (ADMBA) led to more comprehensive and accurate atlases. We generated imaging data from 15 whole mouse brains to validate atlas performance and observed qualitative and quantitative improvement (37% greater alignment between atlas and anatomical boundaries). We provide the pipeline as the MagellanMapper software and the eight 3D reconstructed ADMBA atlases. These resources facilitate whole-organ quantitative analysis between samples and across development.

The research community needs precise, reliable 3D atlases of organs to pinpoint where biological structures and processes are located. For instance, these maps are essential to understand where specific genes are turned on or off, or the spatial organization of various groups of cells over time. For centuries, atlases have been built by thinly 'slicing up' an organ, and then precisely representing each 2D layer. Yet this approach is imperfect: each layer may be accurate on its own, but inevitable mismatches appear between the slices when viewed in 3D or from another angle. Advances in microscopy now allow entire organs to be imaged in 3D. Comparing these images with atlases could help to detect subtle differences that indicate or underlie disease. However, this is only possible if 3D maps are accurate and do not feature mismatches between layers. To create an atlas without such artifacts, one approach consists in starting from scratch and manually redrawing the maps in 3D, a labor-intensive method that discards a large body of well-established atlases. Instead, Young et al. set out to create an automated method which could help to refine existing 'layer-based' atlases, releasing software that anyone can use to improve current maps. The package was created by harnessing eight atlases in the Allen Developing Mouse Brain Atlas, and then using the underlying anatomical images to resolve discrepancies between layers or fill out any missing areas. Known as MagellanMapper, the software was extensively tested to demonstrate the accuracy of the maps it creates, including comparison to whole-brain imaging data from 15 mouse brains. Armed with this new software, researchers can improve the accuracy of their atlases, helping them to understand the structure of organs at the level of the cell and giving them insight into a broad range of human disorders.

Quantitative stain-free imaging and digital profiling of collagen structure reveal diverse survival of triple negative breast cancer patients.

BACKGROUND: Stromal and collagen biology has a significant impact on tumorigenesis and metastasis. Collagen is a major structural extracellular matrix component in breast cancer, but its role in cancer progression is the subject of historical debate. Collagen may represent a protective layer that prevents cancer cell migration, while increased stromal collagen has been demonstrated to facilitate breast cancer metastasis. METHODS: Stromal remodeling is characterized by collagen fiber restructuring and realignment in stromal and tumoral areas. The patients in our study were diagnosed with triple-negative breast cancer in Singapore General Hospital from 2003 to 2015. We designed novel image processing and quantification pipelines to profile collagen structures using numerical imaging parameters. Our solution differentiated the collagen into two distinct modes: aggregated thick collagen (ATC) and dispersed thin collagen (DTC). RESULTS: Extracted parameters were significantly associated with bigger tumor size and DCIS association. Of numerical parameters, ATC collagen fiber density (CFD) and DTC collagen fiber length (CFL) were of significant prognostic value for disease-free survival and overall survival for the TNBC patient cohort. Using these two parameters, we built a predictive model to stratify the patients into four groups. CONCLUSIONS: Our study provides a novel insight for the quantitation of collagen in the tumor microenvironment and will help predict clinical outcomes for TNBC patients. The identified collagen parameters, ATC CFD and DTC CFL, represent a new direction for clinical prognosis and precision medicine. We also compared our result with benign samples and DICS samples to get novel insight about the TNBC heterogeneity. The improved understanding of collagen compartment of TNBC may provide insights into novel targets for better patient stratification and treatment.

Obeticholic Acid Modulates Serum Metabolites and Gene Signatures Characteristic of Human NASH and Attenuates Inflammation and Fibrosis Progression in Ldlr-/-.Leiden Mice.

Concerns have been raised about whether preclinical models sufficiently mimic molecular disease processes observed in nonalcoholic steatohepatitis (NASH) patients, bringing into question their translational value in studies of therapeutic interventions in the process of NASH/fibrosis. We investigated the representation of molecular disease patterns characteristic for human NASH in high-fat diet (HFD)-fed Ldlr-/-.Leiden mice and studied the effects of obeticholic acid (OCA) on these disease profiles. Multiplatform serum metabolomic profiles and genome-wide liver transcriptome from HFD-fed Ldlr-/-.Leiden mice were compared with those of NASH patients. Mice were profiled at the stage of mild (24 weeks HFD) and severe (34 weeks HFD) fibrosis, and after OCA intervention (24-34 weeks; 10 mg/kg/day). Effects of OCA were analyzed histologically, biochemically, by immunohistochemistry, using deuterated water technology (de novo collagen formation), and by its effect on the human-based transcriptomics and metabolomics signatures. The transcriptomics and metabolomics profile of Ldlr-/-.Leiden mice largely reflected the molecular signature of NASH patients. OCA modulated the expression of these molecular profiles and quenched specific proinflammatory-profibrotic pathways. OCA attenuated specific facets of cellular inflammation in liver (F4/80-positive cells) and reduced crown-like structures in adipose tissue. OCA reduced de novo collagen formation and attenuated further progression of liver fibrosis, but did not reduce fibrosis below the level before intervention. Conclusion: HFD-fed Ldlr-/-.Leiden mice recapitulate molecular transcriptomic and metabolomic profiles of NASH patients, and these signatures are modulated by OCA. Intervention with OCA in developing fibrosis reduces collagen deposition and de novo synthesis but does not resolve already manifest fibrosis in the period studied. These data show that human molecular signatures can be used to evaluate the translational character of preclinical models for NASH.

Membrane tension controls adhesion positioning at the leading edge of cells.

Cell migration is dependent on adhesion dynamics and actin cytoskeleton remodeling at the leading edge. These events may be physically constrained by the plasma membrane. Here, we show that the mechanical signal produced by an increase in plasma membrane tension triggers the positioning of new rows of adhesions at the leading edge. During protrusion, as membrane tension increases, velocity slows, and the lamellipodium buckles upward in a myosin II-independent manner. The buckling occurs between the front of the lamellipodium, where nascent adhesions are positioned in rows, and the base of the lamellipodium, where a vinculin-dependent clutch couples actin to previously positioned adhesions. As membrane tension decreases, protrusion resumes and buckling disappears, until the next cycle. We propose that the mechanical signal of membrane tension exerts upstream control in mechanotransduction by periodically compressing and relaxing the lamellipodium, leading to the positioning of adhesions at the leading edge of cells.

Cortical forces and CDC-42 control clustering of PAR proteins for Caenorhabditis elegans embryonic polarization.

Cell polarization enables zygotes to acquire spatial asymmetry, which in turn patterns cellular and tissue axes during development. Local modification in the actomyosin cytoskeleton mediates spatial segregation of partitioning-defective (PAR) proteins at the cortex, but how mechanical changes in the cytoskeleton are transmitted to PAR proteins remains elusive. Here we uncover a role of actomyosin contractility in the remodelling of PAR proteins through cortical clustering. During embryonic polarization in Caenorhabditis elegans, actomyosin contractility and the resultant cortical tension stimulate clustering of PAR-3 at the cortex. Clustering of atypical protein kinase C (aPKC) is supported by PAR-3 clusters and is antagonized by activation of CDC-42. Cortical clustering is associated with retardation of PAR protein exchange at the cortex and with effective entrainment of advective cortical flows. Our findings delineate how cytoskeleton contractility couples the cortical clustering and long-range displacement of PAR proteins during polarization. The principles described here would apply to other pattern formation processes that rely on local modification of cortical actomyosin and PAR proteins.

OpenSegSPIM: a user-friendly segmentation tool for SPIM data.

UNLABELLED: OpenSegSPIM is an open access and user friendly 3D automatic quantitative analysis tool for Single Plane Illumination Microscopy data. The software is designed to extract, in a user-friendly way, quantitative relevant information from SPIM image stacks, such as the number of nuclei or cells. It provides quantitative measurement (volume, sphericity, distance, intensity) on Light Sheet Fluorescent Microscopy images. AVAILABILITY AND IMPLEMENTATION: freely available from http://www.opensegspim.weebly.com Source code and binaries under BSD License. CONTACT: lgole@imcb.a-star.edu.sg or wmyu@imcb.a-star.edu.sg or sohail.ahmed@imb.a-star.edu.sg SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A tapered channel microfluidic device for comprehensive cell adhesion analysis, using measurements of detachment kinetics and shear stress-dependent motion.

We have developed a method for studying cellular adhesion by using a custom-designed microfluidic device with parallel non-connected tapered channels. The design enables investigation of cellular responses to a large range of shear stress (ratio of 25) with a single input flow-rate. For each shear stress, a large number of cells are analyzed (500-1500 cells), providing statistically relevant data within a single experiment. Besides adhesion strength measurements, the microsystem presented in this paper enables in-depth analysis of cell detachment kinetics by real-time videomicroscopy. It offers the possibility to analyze adhesion-associated processes, such as migration or cell shape change, within the same experiment. To show the versatility of our device, we examined quantitatively cell adhesion by analyzing kinetics, adhesive strength and migration behaviour or cell shape modifications of the unicellular model cell organism Dictyostelium discoideum at 21 °C and of the human breast cancer cell line MDA-MB-231 at 37 °C. For both cell types, we found that the threshold stresses, which are necessary to detach the cells, follow lognormal distributions, and that the detachment process follows first order kinetics. In addition, for particular conditions' cells are found to exhibit similar adhesion threshold stresses, but very different detachment kinetics, revealing the importance of dynamics analysis to fully describe cell adhesion. With its rapid implementation and potential for parallel sample processing, such microsystem offers a highly controllable platform for exploring cell adhesion characteristics in a large set of environmental conditions and cell types, and could have wide applications across cell biology, tissue engineering, and cell screening.

A quorum-sensing factor in vegetative Dictyostelium discoideum cells revealed by quantitative migration analysis.

BACKGROUND: Many cells communicate through the production of diffusible signaling molecules that accumulate and once a critical concentration has been reached, can activate or repress a number of target genes in a process termed quorum sensing (QS). In the social amoeba Dictyostelium discoideum, QS plays an important role during development. However little is known about its effect on cell migration especially in the growth phase. METHODS AND FINDINGS: To investigate the role of cell density on cell migration in the growth phase, we use multisite timelapse microscopy and automated cell tracking. This analysis reveals a high heterogeneity within a given cell population, and the necessity to use large data sets to draw reliable conclusions on cell motion. In average, motion is persistent for short periods of time (t ≤ 5 min), but normal diffusive behavior is recovered over longer time periods. The persistence times are positively correlated with the migrated distances. Interestingly, the migrated distance decreases as well with cell density. The adaptation of cell migration to cell density highlights the role of a secreted quorum sensing factor (QSF) on cell migration. Using a simple model describing the balance between the rate of QSF generation and the rate of QSF dilution, we were able to gather all experimental results into a single master curve, showing a sharp cell transition between high and low motile behaviors with increasing QSF. CONCLUSION: This study unambiguously demonstrates the central role played by QSF on amoeboid motion in the growth phase.