Focused active learning for histopathological image classification.

Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifacts, ambiguities, and class imbalances, as commonly seen in the medical field. The lack of precise uncertainty estimations leads to the acquisition of images with a low informative value. To address these challenges, we propose Focused Active Learning (FocAL), which combines a Bayesian Neural Network with Out-of-Distribution detection to estimate different uncertainties for the acquisition function. Specifically, the weighted epistemic uncertainty accounts for the class imbalance, aleatoric uncertainty for ambiguous images, and an OoD score for artifacts. We perform extensive experiments to validate our method on MNIST and the real-world Panda dataset for the classification of prostate cancer. The results confirm that other AL methods are 'distracted' by ambiguities and artifacts which harm the performance. FocAL effectively focuses on the most informative images, avoiding ambiguities and artifacts during acquisition. For both experiments, FocAL outperforms existing AL approaches, reaching a Cohen's kappa of 0.764 with only 0.69% of the labeled Panda data.

Translating prognostic quantification of c-MYC and BCL2 from tissue microarrays to whole slide images in diffuse large B-cell lymphoma using deep learning.

BACKGROUND: c-MYC and BCL2 positivity are important prognostic factors for diffuse large B-cell lymphoma. However, manual quantification is subject to significant intra- and inter-observer variability. We developed an automated method for quantification in whole-slide images of tissue sections where manual quantification requires evaluating large areas of tissue with possibly heterogeneous staining. We train this method using annotations of tumor positivity in smaller tissue microarray cores where expression and staining are more homogeneous and then translate this model to whole-slide images. METHODS: Our method applies a technique called attention-based multiple instance learning to regress the proportion of c-MYC-positive and BCL2-positive tumor cells from pathologist-scored tissue microarray cores. This technique does not require annotation of individual cell nuclei and is trained instead on core-level annotations of percent tumor positivity. We translate this model to scoring of whole-slide images by tessellating the slide into smaller core-sized tissue regions and calculating an aggregate score. Our method was trained on a public tissue microarray dataset from Stanford and applied to whole-slide images from a geographically diverse multi-center cohort produced by the Lymphoma Epidemiology of Outcomes study. RESULTS: In tissue microarrays, the automated method had Pearson correlations of 0.843 and 0.919 with pathologist scores for c-MYC and BCL2, respectively. When utilizing standard clinical thresholds, the sensitivity/specificity of our method was 0.743 / 0.963 for c-MYC and 0.938 / 0.951 for BCL2. For double-expressors, sensitivity and specificity were 0.720 and 0.974. When translated to the external WSI dataset scored by two pathologists, Pearson correlation was 0.753 & 0.883 for c-MYC and 0.749 & 0.765 for BCL2, and sensitivity/specificity was 0.857/0.991 & 0.706/0.930 for c-MYC, 0.856/0.719 & 0.855/0.690 for BCL2, and 0.890/1.00 & 0.598/0.952 for double-expressors. Survival analysis demonstrates that for progression-free survival, model-predicted TMA scores significantly stratify double-expressors and non double-expressors (p = 0.0345), whereas pathologist scores do not (p = 0.128). CONCLUSIONS: We conclude that proportion of positive stains can be regressed using attention-based multiple instance learning, that these models generalize well to whole slide images, and that our models can provide non-inferior stratification of progression-free survival outcomes.

Learning from crowds for automated histopathological image segmentation.

Automated semantic segmentation of histopathological images is an essential task in Computational Pathology (CPATH). The main limitation of Deep Learning (DL) to address this task is the scarcity of expert annotations. Crowdsourcing (CR) has emerged as a promising solution to reduce the individual (expert) annotation cost by distributing the labeling effort among a group of (non-expert) annotators. Extracting knowledge in this scenario is challenging, as it involves noisy annotations. Jointly learning the underlying (expert) segmentation and the annotators' expertise is currently a commonly used approach. Unfortunately, this approach is frequently carried out by learning a different neural network for each annotator, which scales poorly when the number of annotators grows. For this reason, this strategy cannot be easily applied to real-world CPATH segmentation. This paper proposes a new family of methods for CR segmentation of histopathological images. Our approach consists of two coupled networks: a segmentation network (for learning the expert segmentation) and an annotator network (for learning the annotators' expertise). We propose to estimate the annotators' behavior with only one network that receives the annotator ID as input, achieving scalability on the number of annotators. Our family is composed of three different models for the annotator network. Within this family, we propose a novel modeling of the annotator network in the CR segmentation literature, which considers the global features of the image. We validate our methods on a real-world dataset of Triple Negative Breast Cancer images labeled by several medical students. Our new CR modeling achieves a Dice coefficient of 0.7827, outperforming the well-known STAPLE (0.7039) and being competitive with the supervised method with expert labels (0.7723). The code is available at https://github.com/wizmik12/CRowd_Seg.

Image-based multiplex immune profiling of cancer tissues: translational implications. A report of the International Immuno-oncology Biomarker Working Group on Breast Cancer.

Recent advances in the field of immuno-oncology have brought transformative changes in the management of cancer patients. The immune profile of tumours has been found to have key value in predicting disease prognosis and treatment response in various cancers. Multiplex immunohistochemistry and immunofluorescence have emerged as potent tools for the simultaneous detection of multiple protein biomarkers in a single tissue section, thereby expanding opportunities for molecular and immune profiling while preserving tissue samples. By establishing the phenotype of individual tumour cells when distributed within a mixed cell population, the identification of clinically relevant biomarkers with high-throughput multiplex immunophenotyping of tumour samples has great potential to guide appropriate treatment choices. Moreover, the emergence of novel multi-marker imaging approaches can now provide unprecedented insights into the tumour microenvironment, including the potential interplay between various cell types. However, there are significant challenges to widespread integration of these technologies in daily research and clinical practice. This review addresses the challenges and potential solutions within a structured framework of action from a regulatory and clinical trial perspective. New developments within the field of immunophenotyping using multiplexed tissue imaging platforms and associated digital pathology are also described, with a specific focus on translational implications across different subtypes of cancer. © 2024 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Tissue Contamination Challenges the Credibility of Machine Learning Models in Real World Digital Pathology.

Machine learning (ML) models are poised to transform surgical pathology practice. The most successful use attention mechanisms to examine whole slides, identify which areas of tissue are diagnostic, and use them to guide diagnosis. Tissue contaminants, such as floaters, represent unexpected tissue. Although human pathologists are extensively trained to consider and detect tissue contaminants, we examined their impact on ML models. We trained 4 whole-slide models. Three operate in placenta for the following functions: (1) detection of decidual arteriopathy, (2) estimation of gestational age, and (3) classification of macroscopic placental lesions. We also developed a model to detect prostate cancer in needle biopsies. We designed experiments wherein patches of contaminant tissue are randomly sampled from known slides and digitally added to patient slides and measured model performance. We measured the proportion of attention given to contaminants and examined the impact of contaminants in the t-distributed stochastic neighbor embedding feature space. Every model showed performance degradation in response to one or more tissue contaminants. Decidual arteriopathy detection--balanced accuracy decreased from 0.74 to 0.69 ± 0.01 with addition of 1 patch of prostate tissue for every 100 patches of placenta (1% contaminant). Bladder, added at 10% contaminant, raised the mean absolute error in estimating gestational age from 1.626 weeks to 2.371 ± 0.003 weeks. Blood, incorporated into placental sections, induced false-negative diagnoses of intervillous thrombi. Addition of bladder to prostate cancer needle biopsies induced false positives, a selection of high-attention patches, representing 0.033 mm2, and resulted in a 97% false-positive rate when added to needle biopsies. Contaminant patches received attention at or above the rate of the average patch of patient tissue. Tissue contaminants induce errors in modern ML models. The high level of attention given to contaminants indicates a failure to encode biological phenomena. Practitioners should move to quantify and ameliorate this problem.

A population-level digital histologic biomarker for enhanced prognosis of invasive breast cancer.

Breast cancer is a heterogeneous disease with variable survival outcomes. Pathologists grade the microscopic appearance of breast tissue using the Nottingham criteria, which are qualitative and do not account for noncancerous elements within the tumor microenvironment. Here we present the Histomic Prognostic Signature (HiPS), a comprehensive, interpretable scoring of the survival risk incurred by breast tumor microenvironment morphology. HiPS uses deep learning to accurately map cellular and tissue structures to measure epithelial, stromal, immune, and spatial interaction features. It was developed using a population-level cohort from the Cancer Prevention Study-II and validated using data from three independent cohorts, including the Prostate, Lung, Colorectal, and Ovarian Cancer trial, Cancer Prevention Study-3, and The Cancer Genome Atlas. HiPS consistently outperformed pathologists in predicting survival outcomes, independent of tumor-node-metastasis stage and pertinent variables. This was largely driven by stromal and immune features. In conclusion, HiPS is a robustly validated biomarker to support pathologists and improve patient prognosis.

Automated Deep Learning-Based Diagnosis and Molecular Characterization of Acute Myeloid Leukemia Using Flow Cytometry.

The current flow cytometric analysis of blood and bone marrow samples for diagnosis of acute myeloid leukemia (AML) relies heavily on manual intervention in the processing and analysis steps, introducing significant subjectivity into resulting diagnoses and necessitating highly trained personnel. Furthermore, concurrent molecular characterization via cytogenetics and targeted sequencing can take multiple days, delaying patient diagnosis and treatment. Attention-based multi-instance learning models (ABMILMs) are deep learning models that make accurate predictions and generate interpretable insights regarding the classification of a sample from individual events/cells; nonetheless, these models have yet to be applied to flow cytometry data. In this study, we developed a computational pipeline using ABMILMs for the automated diagnosis of AML cases based exclusively on flow cytometric data. Analysis of 1820 flow cytometry samples shows that this pipeline provides accurate diagnoses of acute leukemia (area under the receiver operating characteristic curve [AUROC] 0.961) and accurately differentiates AML vs B- and T-lymphoblastic leukemia (AUROC 0.965). Models for prediction of 9 cytogenetic aberrancies and 32 pathogenic variants in AML provide accurate predictions, particularly for t(15;17)(PML::RARA) [AUROC 0.929], t(8;21)(RUNX1::RUNX1T1) (AUROC 0.814), and NPM1 variants (AUROC 0.807). Finally, we demonstrate how these models generate interpretable insights into which individual flow cytometric events and markers deliver optimal diagnostic utility, providing hematopathologists with a data visualization tool for improved data interpretation, as well as novel biological associations between flow cytometric marker expression and cytogenetic/molecular variants in AML. Our study is the first to illustrate the feasibility of using deep learning-based analysis of flow cytometric data for automated AML diagnosis and molecular characterization.

Automated Deep Learning-Based Diagnosis and Molecular Characterization of Acute Myeloid Leukemia using Flow Cytometry.

Current flow cytometric analysis of blood and bone marrow samples for diagnosis of acute myeloid leukemia (AML) relies heavily on manual intervention in both the processing and analysis steps, introducing significant subjectivity into resulting diagnoses and necessitating highly trained personnel. Furthermore, concurrent molecular characterization via cytogenetics and targeted sequencing can take multiple days, delaying patient diagnosis and treatment. Attention-based multi-instance learning models (ABMILMs) are deep learning models which make accurate predictions and generate interpretable insights regarding the classification of a sample from individual events/cells; nonetheless, these models have yet to be applied to flow cytometry data. In this study, we developed a computational pipeline using ABMILMs for the automated diagnosis of AML cases based exclusively on flow cytometric data. Analysis of 1,820 flow cytometry samples shows that this pipeline provides accurate diagnoses of acute leukemia [AUROC 0.961] and accurately differentiates AML versus B- and T-lymphoblastic leukemia [AUROC 0.965]. Models for prediction of 9 cytogenetic aberrancies and 32 pathogenic variants in AML provide accurate predictions, particularly for t(15;17)(PML::RARA) [AUROC 0.929], t(8;21)(RUNX1::RUNX1T1) [AUROC 0.814], and NPM1 variants [AUROC 0.807]. Finally, we demonstrate how these models generate interpretable insights into which individual flow cytometric events and markers deliver optimal diagnostic utility, providing hematopathologists with a data visualization tool for improved data interpretation, as well as novel biological associations between flow cytometric marker expression and cytogenetic/molecular variants in AML. Our study is the first to illustrate the feasibility of using deep learning-based analysis of flow cytometric data for automated AML diagnosis and molecular characterization.

Spatial analyses of immune cell infiltration in cancer: current methods and future directions: A report of the International Immuno-Oncology Biomarker Working Group on Breast Cancer.

Modern histologic imaging platforms coupled with machine learning methods have provided new opportunities to map the spatial distribution of immune cells in the tumor microenvironment. However, there exists no standardized method for describing or analyzing spatial immune cell data, and most reported spatial analyses are rudimentary. In this review, we provide an overview of two approaches for reporting and analyzing spatial data (raster versus vector-based). We then provide a compendium of spatial immune cell metrics that have been reported in the literature, summarizing prognostic associations in the context of a variety of cancers. We conclude by discussing two well-described clinical biomarkers, the breast cancer stromal tumor infiltrating lymphocytes score and the colon cancer Immunoscore, and describe investigative opportunities to improve clinical utility of these spatial biomarkers. © 2023 The Pathological Society of Great Britain and Ireland.

Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: A report of the International Immuno-Oncology Biomarker Working Group on Breast Cancer

The clinical significance of the tumor-immune interaction in breast cancer is now established, and tumor-infiltrating lymphocytes (TILs) have emerged as predictive and prognostic biomarkers for patients with triple-negative (estrogen receptor, progesterone receptor, and HER2-negative) breast cancer and HER2-positive breast cancer. How computational assessments of TILs might complement manual TIL assessment in trial and daily practices is currently debated. Recent efforts to use machine learning (ML) to automatically evaluate TILs have shown promising results. We review state-of-the-art approaches and identify pitfalls and challenges of automated TIL evaluation by studying the root cause of ML discordances in comparison to manual TIL quantification. We categorize our findings into four main topics: (1) technical slide issues, (2) ML and image analysis aspects, (3) data challenges, and (4) validation issues. The main reason for discordant assessments is the inclusion of false-positive areas or cells identified by performance on certain tissue patterns or design choices in the computational implementation. To aid the adoption of ML for TIL assessment, we provide an in-depth discussion of ML and image analysis, including validation issues that need to be considered before reliable computational reporting of TILs can be incorporated into the trial and routine clinical management of patients with triple-negative breast cancer. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

A comprehensive satellite-based assessment across the Pacific Arctic Distributed Biological Observatory shows widespread late-season sea surface warming and sea ice declines with significant influences on primary productivity.

Massive declines in sea ice cover and widespread warming seawaters across the Pacific Arctic region over the past several decades have resulted in profound shifts in marine ecosystems that have cascaded throughout all trophic levels. The Distributed Biological Observatory (DBO) provides sampling infrastructure for a latitudinal gradient of biological "hotspot" regions across the Pacific Arctic region, with eight sites spanning the northern Bering, Chukchi, and Beaufort Seas. The purpose of this study is two-fold: (a) to provide an assessment of satellite-based environmental variables for the eight DBO sites (including sea surface temperature (SST), sea ice concentration, annual sea ice persistence and the timing of sea ice breakup/formation, chlorophyll-a concentrations, primary productivity, and photosynthetically available radiation (PAR)) as well as their trends across the 2003-2020 time period; and (b) to assess the importance of sea ice presence/open water for influencing primary productivity across the region and for the eight DBO sites in particular. While we observe significant trends in SST, sea ice, and chlorophyll-a/primary productivity throughout the year, the most significant and synoptic trends for the DBO sites have been those during late summer and autumn (warming SST during October/November, later shifts in the timing of sea ice formation, and increases in chlorophyll-a/primary productivity during August/September). Those DBO sites where significant increases in annual primary productivity over the 2003-2020 time period have been observed include DBO1 in the Bering Sea (37.7 g C/m2/year/decade), DBO3 in the Chukchi Sea (48.0 g C/m2/year/decade), and DBO8 in the Beaufort Sea (38.8 g C/m2/year/decade). The length of the open water season explains the variance of annual primary productivity most strongly for sites DBO3 (74%), DBO4 in the Chukchi Sea (79%), and DBO6 in the Beaufort Sea (78%), with DBO3 influenced most strongly with each day of additional increased open water (3.8 g C/m2/year per day). These synoptic satellite-based observations across the suite of DBO sites will provide the legacy groundwork necessary to track additional and inevitable future physical and biological change across the region in response to ongoing climate warming.

Validation of a prediction system for risk of kidney allograft failure in pediatric kidney transplant recipients: An international observational study.

Predicting long-term kidney allograft failure is an unmet need for clinical care and clinical trial optimization in children. We aimed to validate a kidney allograft failure risk prediction system in a large international cohort of pediatric kidney transplant recipients. Patients from 20 centers in Europe and the United States, transplanted between 2004 and 2017, were included. Allograft assessment included estimated glomerular filtration rate, urine protein-to-creatinine ratio, circulating antihuman leukocyte antigen donor-specific antibody, and kidney allograft histology. Individual predictions of allograft failure were calculated using the integrative box (iBox) system. Prediction performances were assessed using discrimination and calibration. The allograft evaluations were performed in 706 kidney transplant recipients at a median time of 9.1 (interquartile range, 3.3-19.2) months posttransplant; mean estimated glomerular filtration rate was 68.7 ± 28.1 mL/min/1.73 m2, and median urine protein-to-creatinine ratio was 0.1 (0.0-0.4) g/g, and 134 (19.0%) patients had antihuman leukocyte antigen donor-specific antibodies. The iBox exhibited accurate calibration and discrimination for predicting the outcomes up to 10 years after evaluation, with a C-index of 0.81 (95% confidence interval, 0.75-0.87). This study confirms the generalizability of the iBox to predict long-term kidney allograft failure in children, with performances similar to those reported in adults. These results support the use of the iBox to improve patient monitoring and facilitate clinical trials in children.

A population-level computational histologic signature for invasive breast cancer prognosis.

Breast cancer is a heterogeneous disease with variable survival outcomes. Pathologists grade the microscopic appearance of breast tissue using the Nottingham criteria, which is qualitative and does not account for non-cancerous elements within the tumor microenvironment (TME). We present the Histomic Prognostic Signature (HiPS), a comprehensive, interpretable scoring of the survival risk incurred by breast TME morphology. HiPS uses deep learning to accurately map cellular and tissue structures in order to measure epithelial, stromal, immune, and spatial interaction features. It was developed using a population-level cohort from the Cancer Prevention Study (CPS)-II and validated using data from three independent cohorts, including the PLCO trial, CPS-3, and The Cancer Genome Atlas. HiPS consistently outperformed pathologists' performance in predicting survival outcomes, independent of TNM stage and pertinent variables. This was largely driven by stromal and immune features. In conclusion, HiPS is a robustly validated biomarker to support pathologists and improve prognosis.

Tissue contamination challenges the credibility of machine learning models in real world digital pathology.

Machine learning (ML) models are poised to transform surgical pathology practice. The most successful use attention mechanisms to examine whole slides, identify which areas of tissue are diagnostic, and use them to guide diagnosis. Tissue contaminants, such as floaters, represent unexpected tissue. While human pathologists are extensively trained to consider and detect tissue contaminants, we examined their impact on ML models. We trained 4 whole slide models. Three operate in placenta for 1) detection of decidual arteriopathy (DA), 2) estimation of gestational age (GA), and 3) classification of macroscopic placental lesions. We also developed a model to detect prostate cancer in needle biopsies. We designed experiments wherein patches of contaminant tissue are randomly sampled from known slides and digitally added to patient slides and measured model performance. We measured the proportion of attention given to contaminants and examined the impact of contaminants in T-distributed Stochastic Neighbor Embedding (tSNE) feature space. Every model showed performance degradation in response to one or more tissue contaminants. DA detection balanced accuracy decreased from 0.74 to 0.69 +/- 0.01 with addition of 1 patch of prostate tissue for every 100 patches of placenta (1% contaminant). Bladder, added at 10% contaminant raised the mean absolute error in estimating gestation age from 1.626 weeks to 2.371 +/ 0.003 weeks. Blood, incorporated into placental sections, induced false negative diagnoses of intervillous thrombi. Addition of bladder to prostate cancer needle biopsies induced false positives, a selection of high-attention patches, representing 0.033mm2, resulted in a 97% false positive rate when added to needle biopsies. Contaminant patches received attention at or above the rate of the average patch of patient tissue. Tissue contaminants induce errors in modern ML models. The high level of attention given to contaminants indicates a failure to encode biological phenomena. Practitioners should move to quantify and ameliorate this problem.

A Deep Learning Approach for Histology-Based Nucleus Segmentation and Tumor Microenvironment Characterization.

Microscopic examination of pathology slides is essential to disease diagnosis and biomedical research. However, traditional manual examination of tissue slides is laborious and subjective. Tumor whole-slide image (WSI) scanning is becoming part of routine clinical procedures and produces massive data that capture tumor histologic details at high resolution. Furthermore, the rapid development of deep learning algorithms has significantly increased the efficiency and accuracy of pathology image analysis. In light of this progress, digital pathology is fast becoming a powerful tool to assist pathologists. Studying tumor tissue and its surrounding microenvironment provides critical insight into tumor initiation, progression, metastasis, and potential therapeutic targets. Nucleus segmentation and classification are critical to pathology image analysis, especially in characterizing and quantifying the tumor microenvironment (TME). Computational algorithms have been developed for nucleus segmentation and TME quantification within image patches. However, existing algorithms are computationally intensive and time consuming for WSI analysis. This study presents Histology-based Detection using Yolo (HD-Yolo), a new method that significantly accelerates nucleus segmentation and TME quantification. We demonstrate that HD-Yolo outperforms existing WSI analysis methods in nucleus detection, classification accuracy, and computation time. We validated the advantages of the system on 3 different tissue types: lung cancer, liver cancer, and breast cancer. For breast cancer, nucleus features by HD-Yolo were more prognostically significant than both the estrogen receptor status by immunohistochemistry and the progesterone receptor status by immunohistochemistry. The WSI analysis pipeline and a real-time nucleus segmentation viewer are available at https://github.com/impromptuRong/hd_wsi.

Improving measurement-based care implementation in adult ambulatory psychiatry: a virtual focus group interview with multidisciplinary healthcare professionals.

BACKGROUND: Measurement-Based Care (MBC) is an evidence-based practice shown to enhance patient care. Despite being efficacious, MBC is not commonly used in practice. While barriers and facilitators of MBC implementation have been described in the literature, the type of clinicians and populations studied vary widely, even within the same practice setting. The current study aims to improve MBC implementation in adult ambulatory psychiatry by conducting focus group interviews while utilizing a novel virtual brainwriting premortem method. METHODS: Semi-structured focus group interviews were conducted with clinicians (n = 18) and staff (n = 7) to identify their current attitudes, facilitators, and barriers of MBC implementation in their healthcare setting. Virtual video-conferencing software was used to conduct focus groups, and based on transcribed verbatin, emergent barriers/facilitators and four themes were identified. Mixed methods approach was utilized for this study. Specifically, qualitative data was aggregated and re-coded separately by three doctoral-level coders. Quantitative analyses were conducted from a follow-up questionnaire surveying clinician attitudes and satisfaction with MBC. RESULTS: The clinician and staff focus groups resulted in 291 and 91 unique codes, respectively. While clinicians identified a similar number of barriers (40.9%) and facilitators (44.3%), staff identified more barriers (67%) than facilitators (24.7%) for MBC. Four themes emerged from the analysis; (1) a description of current status/neutral opinion on MBC; (2) positive themes that include benefits of MBC, facilitators, enablers, or reasons on why they conduct MBC in their practice, (3) negative themes that include barriers or issues that hinder them from incorporating MBC into their practice, and (4) requests and suggestions for future MBC implementation. Both participant groups raised more negative themes highlighting critical challenges to MBC implementation than positive themes. The follow-up questionnaire regarding MBC attitudes showed the areas that clinicians emphasized the most and the least in their clinical practice. CONCLUSION: The virtual brainwriting premortem focus groups provided critical information on the shortcomings and strengths of MBC in adult ambulatory psychiatry. Our findings underscore implementation challenges in healthcare settings and provide insight for both research and clinical practice in mental health fields. The barriers and facilitators identified in this study can inform future training to increase sustainability and better integrate MBC with positive downstream outcomes in patient care.

Machine learning classification of placental villous infarction, perivillous fibrin deposition, and intervillous thrombus.

INTRODUCTION: Placental parenchymal lesions are commonly encountered and carry significant clinical associations. However, they are frequently missed or misclassified by general practice pathologists. Interpretation of pathology slides has emerged as one of the most successful applications of machine learning (ML) in medicine with applications ranging from cancer detection and prognostication to transplant medicine. The goal of this study was to use a whole-slide learning model to identify and classify placental parenchymal lesions including villous infarctions, intervillous thrombi (IVT), and perivillous fibrin deposition (PVFD). METHODS: We generated whole slide images from placental discs examined at our institution with infarct, IVT, PVFD, or no macroscopic lesion. Slides were analyzed as a set of overlapping patches. We extracted feature vectors from each patch using a pretrained convolutional neural network (EfficientNetV2L). We trained a model to assign attention to each vector and used the attentions as weights to produce a pooled feature vector. The pooled vector was classified as normal or 1 of 3 lesions using a fully connected network. Patch attention was plotted to highlight informative areas of the slide. RESULTS: Overall balanced accuracy in a test set of held-out slides was 0.86 with receiver-operator characteristic areas under the curve of 0.917-0.993. Cases of PVFD were frequently miscalled as normal or infarcts, the latter possibly due to the perivillous fibrin found at the periphery of infarctions. We used attention maps to further understand some errors, including one most likely due to poor tissue fixation and processing. DISCUSSION: We used a whole-slide learning paradigm to train models to recognize three of the most common placental parenchymal lesions. We used attention maps to gain insight into model function, which differed from intuitive explanations.

SARS-CoV-2 omicron (B.1.1.529)-related COVID-19 sequelae in vaccinated and unvaccinated patients with cancer: results from the OnCovid registry.

BACKGROUND: COVID-19 sequelae can affect about 15% of patients with cancer who survive the acute phase of SARS-CoV-2 infection and can substantially impair their survival and continuity of oncological care. We aimed to investigate whether previous immunisation affects long-term sequelae in the context of evolving variants of concern of SARS-CoV-2. METHODS: OnCovid is an active registry that includes patients aged 18 years or older from 37 institutions across Belgium, France, Germany, Italy, Spain, and the UK with a laboratory-confirmed diagnosis of COVID-19 and a history of solid or haematological malignancy, either active or in remission, followed up from COVID-19 diagnosis until death. We evaluated the prevalence of COVID-19 sequelae in patients who survived COVID-19 and underwent a formal clinical reassessment, categorising infection according to the date of diagnosis as the omicron (B.1.1.529) phase from Dec 15, 2021, to Jan 31, 2022; the alpha (B.1.1.7)-delta (B.1.617.2) phase from Dec 1, 2020, to Dec 14, 2021; and the pre-vaccination phase from Feb 27 to Nov 30, 2020. The prevalence of overall COVID-19 sequelae was compared according to SARS-CoV-2 immunisation status and in relation to post-COVID-19 survival and resumption of systemic anticancer therapy. This study is registered with ClinicalTrials.gov, NCT04393974. FINDINGS: At the follow-up update on June 20, 2022, 1909 eligible patients, evaluated after a median of 39 days (IQR 24-68) from COVID-19 diagnosis, were included (964 [50·7%] of 1902 patients with sex data were female and 938 [49·3%] were male). Overall, 317 (16·6%; 95% CI 14·8-18·5) of 1909 patients had at least one sequela from COVID-19 at the first oncological reassessment. The prevalence of COVID-19 sequelae was highest in the pre-vaccination phase (191 [19·1%; 95% CI 16·4-22·0] of 1000 patients). The prevalence was similar in the alpha-delta phase (110 [16·8%; 13·8-20·3] of 653 patients, p=0·24), but significantly lower in the omicron phase (16 [6·2%; 3·5-10·2] of 256 patients, p<0·0001). In the alpha-delta phase, 84 (18·3%; 95% CI 14·6-22·7) of 458 unvaccinated patients and three (9·4%; 1·9-27·3) of 32 unvaccinated patients in the omicron phase had sequelae. Patients who received a booster and those who received two vaccine doses had a significantly lower prevalence of overall COVID-19 sequelae than unvaccinated or partially vaccinated patients (ten [7·4%; 95% CI 3·5-13·5] of 136 boosted patients, 18 [9·8%; 5·8-15·5] of 183 patients who had two vaccine doses vs 277 [18·5%; 16·5-20·9] of 1489 unvaccinated patients, p=0·0001), respiratory sequelae (six [4·4%; 1·6-9·6], 11 [6·0%; 3·0-10·7] vs 148 [9·9%; 8·4-11·6], p=0·030), and prolonged fatigue (three [2·2%; 0·1-6·4], ten [5·4%; 2·6-10·0] vs 115 [7·7%; 6·3-9·3], p=0·037). INTERPRETATION: Unvaccinated patients with cancer remain highly vulnerable to COVID-19 sequelae irrespective of viral strain. This study confirms the role of previous SARS-CoV-2 immunisation as an effective measure to protect patients from COVID-19 sequelae, disruption of therapy, and ensuing mortality. FUNDING: UK National Institute for Health and Care Research Imperial Biomedical Research Centre and the Cancer Treatment and Research Trust.

An Automated Pipeline for Differential Cell Counts on Whole-Slide Bone Marrow Aspirate Smears.

The pathologic diagnosis of bone marrow disorders relies in part on the microscopic analysis of bone marrow aspirate (BMA) smears and the manual counting of marrow nucleated cells to obtain a differential cell count (DCC). This manual process has significant limitations, including the analysis of only a small subset of optimal slide areas and nucleated cells, as well as interobserver variability due to differences in cell selection and classification. To address these shortcomings, we developed an automated machine learning-based pipeline for obtaining 11-component DCCs on whole-slide BMAs. This pipeline uses a sequential process of identifying optimal BMA regions with high proportions of marrow nucleated cells, detecting individual cells within these optimal areas, and classifying these cells into 1 of 11 DCC components. Convolutional neural network models were trained on 396,048 BMA region, 28,914 cell boundary, and 1,510,976 cell class images from manual annotations. The resulting automated pipeline produced 11-component DCCs that demonstrated a high statistical and diagnostic concordance with manual DCCs among a heterogeneous group of testing BMA slides with varying pathologies and cellularities. Additionally, we demonstrated that an automated analysis can reduce the intraslide variance in DCCs by analyzing the whole slide and marrow nucleated cells within all optimal regions. Finally, the pipeline outputs of region classification, cell detection, and cell classification can be visualized using whole-slide image analysis software. This study demonstrates the feasibility of a fully automated pipeline for generating DCCs on scanned whole-slide BMA images, with the potential for improving the current standard of practice for utilizing BMA smears in the laboratory analysis of hematologic disorders.

Community belongingness during COVID-19 predicts anxiety and depression treatment change in college students.

OBJECTIVE: Community belongingness has been shown to be related to mental health outcomes in college students; however, little work has evaluated whether community belongingness impacts treatment change, especially during the COVID-19 pandemic, when social isolation and mental health concerns are exacerbated. Accordingly, the current study evaluated community belongingness as a predictor of treatment change for anxiety and depression in a university counseling center. METHOD: Participants included 516 young adults with clinical levels of anxiety or depression who attended at least two individual therapy sessions at a university counseling center during fall 2020. Participants completed broad measures of psychosocial functioning at each session. RESULTS: Paired-samples t-tests indicated that students demonstrated significant decreases in anxiety and depression after just one session. Linear stepwise regressions revealed that community belongingness was a significant predictor of symptom improvement for both anxiety and depression. CONCLUSION: These results suggest improving community belongingness on college campuses may be a way to buffer mental health and improve treatment outcomes for students seeking psychological services. Specific clinical and educational recommendations for ways to improve community belongingness are discussed.