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.

Single-cell landscape of functionally cured chronic hepatitis B patients reveals activation of innate and altered CD4-CTL-driven adaptive immunity.

BACKGROUND & AIMS: Hepatitis B surface antigen (HBsAg) loss or functional cure (FC) is considered the optimal therapeutic outcome for patients with chronic hepatitis B (CHB). However, the immune-pathological biomarkers and underlying mechanisms of FC remain unclear. In this study we comprehensively interrogate disease-associated cell states identified within intrahepatic tissue and matched PBMCs from patients with CHB or after FC, at the resolution of single cells, to provide novel insights into putative mechanisms underlying FC. METHODS: We combined single-cell transcriptomics (single-cell RNA sequencing) with multiparametric flow cytometry-based immune phenotyping, and multiplexed immunofluorescence to elucidate the immunopathological cell states associated with CHB vs. FC. RESULTS: We found that the intrahepatic environment in CHB and FC displays specific cell identities and molecular signatures that are distinct from those found in matched PBMCs. FC is associated with the emergence of an altered adaptive immune response marked by CD4 cytotoxic T lymphocytes, and an activated innate response represented by liver-resident natural killer cells, specific Kupffer cell subtypes and marginated neutrophils. Surprisingly, we found MHC class II-expressing hepatocytes in patients achieving FC, as well as low but persistent levels of covalently closed circular DNA and pregenomic RNA, which may play an important role in FC. CONCLUSIONS: Our study provides conceptually novel insights into the immuno-pathological control of HBV cure, and opens exciting new avenues for clinical management, biomarker discovery and therapeutic development. We believe that the discoveries from this study, as it relates to the activation of an innate and altered immune response that may facilitate sustained, low-grade inflammation, may have broader implications in the resolution of chronic viral hepatitis. IMPACT AND IMPLICATIONS: This study dissects the immuno-pathological cell states associated with functionally cured chronic hepatitis B (defined by the loss of HBV surface antigen or HBsAg). We identified the sustained presence of very low viral load, accessory antigen-presenting hepatocytes, adaptive-memory-like natural killer cells, and the emergence of helper CD4 T cells with cytotoxic or effector-like signatures associated with functional cure, suggesting previously unsuspected alterations in the adaptive immune response, as well as a key role for the innate immune response in achieving or maintaining functional cure. Overall, the insights generated from this study may provide new avenues for the development of alternative therapies as well as patient surveillance for better clinical management of chronic hepatitis B.

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.

Surgical Transplantation of Human RPE Stem Cell-Derived RPE Monolayers into Non-Human Primates with Immunosuppression.

Recent trials of retinal pigment epithelium (RPE) transplantation for the treatment of disorders such as age-related macular degeneration have been promising. However, limitations of existing strategies include the uncertain survival of RPE cells delivered by cell suspension and the inherent risk of uncontrolled cell proliferation in the vitreous cavity. Human RPE stem cell-derived RPE (hRPESC-RPE) transplantation can rescue vision in a rat model of retinal dystrophy and survive in the rabbit retina for at least 1 month. The present study placed hRPESC-RPE monolayers under the macula of a non-human primate model for 3 months. The transplant was able to recover in vivo and maintained healthy photoreceptors. Importantly, there was no evidence that subretinally transplanted monolayers underwent an epithelial-mesenchymal transition. Neither gliosis in adjacent retina nor epiretinal membranes were observed. These findings suggest that hRPESC-RPE monolayers are safe and may be a useful source for RPE cell replacement therapy.

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.

Sustained delivery of anti-VEGFs from thermogel depots inhibits angiogenesis without the need for multiple injections.

Anti-vascular endothelial growth factor (anti-VEGF) proteins are the gold-standard treatment for posterior eye segment proliferative vascular diseases such as Age-Related Macular Degeneration (AMD) and Diabetic Retinopathy (DR). However, the standard of care requires inconvenient monthly intravitreal injections. This underlies an unmet clinical need to develop alternative solutions for sustained delivery of biologics. In this paper, we demonstrated that anti-VEGFs can be encapsulated by a simple mild process into our polyurethane thermogel depots. By changing the hydrophilic-hydrophobic balance in the copolymer, anti-VEGF release rates can be modulated. The antibody in the thermogel partitions into protein domains which vary in size corresponding to the hydrophilicity balance of the polymer. Anti-VEGFs can be released in a relatively linear manner from the thermogel for up to 40 days in vitro. The encapsulated anti-VEGFs demonstrate anti-angiogenic bioactivity by inhibiting vessel outgrowth in rat ex vivo choroidal explants, and reducing vascular leakage in a VEGF-driven neovascularization rabbit model. In conclusion, we show that these thermogels can be tuned in terms of hydrophilicity and used for sustained delivery of bioactive anti-VEGFs. Physically cross-linked polyurethane thermoresponsive hydrogels could be a promising platform for sustained delivery of biologically active therapeutic proteins.

Geometric constraints alter cell arrangements within curved epithelial tissues.

Organ and tissue formation are complex three-dimensional processes involving cell division, growth, migration, and rearrangement, all of which occur within physically constrained regions. However, analyzing such processes in three dimensions in vivo is challenging. Here, we focus on the process of cellularization in the anterior pole of the early Drosophila embryo to explore how cells compete for space under geometric constraints. Using microfluidics combined with fluorescence microscopy, we extract quantitative information on the three-dimensional epithelial cell morphology. We observed a cellular membrane rearrangement in which cells exchange neighbors along the apical-basal axis. Such apical-to-basal neighbor exchanges were observed more frequently in the anterior pole than in the embryo trunk. Furthermore, cells within the anterior pole skewed toward the trunk along their long axis relative to the embryo surface, with maximum skew on the ventral side. We constructed a vertex model for cells in a curved environment. We could reproduce the observed cellular skew in both wild-type embryos and embryos with distorted morphology. Further, such modeling showed that cell rearrangements were more likely in ellipsoidal, compared with cylindrical, geometry. Overall, we demonstrate that geometric constraints can influence three-dimensional cell morphology and packing within epithelial tissues.

Quantitative 3D analysis of complex single border cell behaviors in coordinated collective cell migration.

Understanding the mechanisms of collective cell migration is crucial for cancer metastasis, wound healing and many developmental processes. Imaging a migrating cluster in vivo is feasible, but the quantification of individual cell behaviours remains challenging. We have developed an image analysis toolkit, CCMToolKit, to quantify the Drosophila border cell system. In addition to chaotic motion, previous studies reported that the migrating cells are able to migrate in a highly coordinated pattern. We quantify the rotating and running migration modes in 3D while also observing a range of intermediate behaviours. Running mode is driven by cluster external protrusions. Rotating mode is associated with cluster internal cell extensions that could not be easily characterized. Although the cluster moves slower while rotating, individual cells retain their mobility and are in fact slightly more active than in running mode. We also show that individual cells may exchange positions during migration.

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.

NeuronCyto II: An automatic and quantitative solution for crossover neural cells in high throughput screening.

Microscopy is a fundamental technology driving new biological discoveries. Today microscopy allows a large number of images to be acquired using, for example, High Throughput Screening (HTS) and 4D imaging. It is essential to be able to interrogate these images and extract quantitative information in an automated fashion. In the context of neurobiology, it is important to automatically quantify the morphology of neurons in terms of neurite number, length, branching and complexity, etc. One major issue in quantification of neuronal morphology is the "crossover" problem where neurites cross and it is difficult to assign which neurite belongs to which cell body. In the present study, we provide a solution to the "crossover" problem, the software package NeuronCyto II. NeuronCyto II is an interactive and user-friendly software package for automatic neurite quantification. It has a well-designed graphical user interface (GUI) with only a few free parameters allowing users to optimize the software by themselves and extract relevant quantitative information routinely. Users are able to interact with the images and the numerical features through the Result Inspector. The processing of neurites without crossover was presented in our previous work. Our solution for the "crossover" problem is developed based on our recently published work with directed graph theory. Both methods are implemented in NeuronCyto II. The results show that our solution is able to significantly improve the reliability and accuracy of the neurons displaying "crossover." NeuronCyto II is freely available at the website: https://sites.google.com/site/neuroncyto/, which includes user support and where software upgrades will also be placed in the future. © 2016 The Authors. Cytometry Part A Published by Wiley Periodicals, Inc. on behalf of ISAC.

A Graph-Theoretical Approach for Tracing Filamentary Structures in Neuronal and Retinal Images.

The aim of this study is about tracing filamentary structures in both neuronal and retinal images. It is often crucial to identify single neurons in neuronal networks, or separate vessel tree structures in retinal blood vessel networks, in applications such as drug screening for neurological disorders or computer-aided diagnosis of diabetic retinopathy. Both tasks are challenging as the same bottleneck issue of filament crossovers is commonly encountered, which essentially hinders the ability of existing systems to conduct large-scale drug screening or practical clinical usage. To address the filament crossovers' problem, a two-step graph-theoretical approach is proposed in this paper. The first step focuses on segmenting filamentary pixels out of the background. This produces a filament segmentation map used as input for the second step, where they are further separated into disjointed filaments. Key to our approach is the idea that the problem can be reformulated as label propagation over directed graphs, such that the graph is to be partitioned into disjoint sub-graphs, or equivalently, each of the neurons (vessel trees) is separated from the rest of the neuronal (vessel) network. This enables us to make the interesting connection between the tracing problem and the digraph matrix-forest theorem in algebraic graph theory for the first time. Empirical experiments on neuronal and retinal image datasets demonstrate the superior performance of our approach over existing methods.

Automatic white matter lesion segmentation using an adaptive outlier detection method.

White matter (WM) lesions are diffuse WM abnormalities that appear as hyperintense (bright) regions in cranial magnetic resonance imaging (MRI). WM lesions are often observed in older populations and are important indicators of stroke, multiple sclerosis, dementia and other brain-related disorders. In this paper, a new automated method for WM lesions segmentation is presented. In the proposed method, the presence of WM lesions is detected as outliers in the intensity distribution of the fluid-attenuated inversion recovery (FLAIR) MR images using an adaptive outlier detection approach. Outliers are detected using a novel adaptive trimmed mean algorithm and box-whisker plot. In addition, pre- and postprocessing steps are implemented to reduce false positives attributed to MRI artifacts commonly observed in FLAIR sequences. The approach is validated using the cranial MRI sequences of 38 subjects. A significant correlation (R=0.9641, P value=3.12×10(-3)) is observed between the automated approach and manual segmentation by radiologist. The accuracy of the proposed approach was further validated by comparing the lesion volumes computed using the automated approach and lesions manually segmented by an expert radiologist. Finally, the proposed approach is compared against leading lesion segmentation algorithms using a benchmark dataset.