Northwestern University resource and education development initiatives to advance collaborative artificial intelligence across the learning health system.

Introduction: The rapid development of artificial intelligence (AI) in healthcare has exposed the unmet need for growing a multidisciplinary workforce that can collaborate effectively in the learning health systems. Maximizing the synergy among multiple teams is critical for Collaborative AI in Healthcare. Methods: We have developed a series of data, tools, and educational resources for cultivating the next generation of multidisciplinary workforce for Collaborative AI in Healthcare. We built bulk-natural language processing pipelines to extract structured information from clinical notes and stored them in common data models. We developed multimodal AI/machine learning (ML) tools and tutorials to enrich the toolbox of the multidisciplinary workforce to analyze multimodal healthcare data. We have created a fertile ground to cross-pollinate clinicians and AI scientists and train the next generation of AI health workforce to collaborate effectively. Results: Our work has democratized access to unstructured health information, AI/ML tools and resources for healthcare, and collaborative education resources. From 2017 to 2022, this has enabled studies in multiple clinical specialties resulting in 68 peer-reviewed publications. In 2022, our cross-discipline efforts converged and institutionalized into the Center for Collaborative AI in Healthcare. Conclusions: Our Collaborative AI in Healthcare initiatives has created valuable educational and practical resources. They have enabled more clinicians, scientists, and hospital administrators to successfully apply AI methods in their daily research and practice, develop closer collaborations, and advanced the institution-level learning health system.

A panoptic segmentation dataset and deep-learning approach for explainable scoring of tumor-infiltrating lymphocytes.

Tumor-Infiltrating Lymphocytes (TILs) have strong prognostic and predictive value in breast cancer, but their visual assessment is subjective. To improve reproducibility, the International Immuno-oncology Working Group recently released recommendations for the computational assessment of TILs that build on visual scoring guidelines. However, existing resources do not adequately address these recommendations due to the lack of annotation datasets that enable joint, panoptic segmentation of tissue regions and cells. Moreover, existing deep-learning methods focus entirely on either tissue segmentation or cell nuclei detection, which complicates the process of TILs assessment by necessitating the use of multiple models and reconciling inconsistent predictions. We introduce PanopTILs, a region and cell-level annotation dataset containing 814,886 nuclei from 151 patients, openly accessible at: sites.google.com/view/panoptils . Using PanopTILs we developed MuTILs, a neural network optimized for assessing TILs in accordance with clinical recommendations. MuTILs is a concept bottleneck model designed to be interpretable and to encourage sensible predictions at multiple resolutions. Using a rigorous internal-external cross-validation procedure, MuTILs achieves an AUROC of 0.93 for lymphocyte detection and a DICE coefficient of 0.81 for tumor-associated stroma segmentation. Our computational score closely matched visual scores from 2 pathologists (Spearman R = 0.58-0.61, p < 0.001). Moreover, computational TILs scores had a higher prognostic value than visual scores, independent of TNM stage and patient age. In conclusion, we introduce a comprehensive open data resource and a modeling approach for detailed mapping of the breast tumor microenvironment.

Use of Patient-Reported Outcome Measures to Assess the Effectiveness of Hybrid Psychiatric Visits.

OBJECTIVE: Little empirical evidence exists to support the effectiveness of hybrid psychiatric care, defined as care delivered through a combination of telephone, videoconferencing, and in-person visits. The authors aimed to investigate the effectiveness of hybrid psychiatric care compared with outpatient waitlist groups, assessed with patient-reported outcome measures (PROMs). METHOD: Participants were recruited from an adult psychiatry clinic waitlist on which the most common primary diagnoses were unipolar depression, generalized anxiety disorder, and bipolar disorder. Patients (N=148) were randomly assigned to one of two waitlist groups that completed PROMs once or monthly before treatment initiation. PROMs were used to assess symptoms of depression (Patient Health Questionnaire-9 [PHQ-9]), anxiety (Generalized Anxiety Disorder-7 [GAD-7]), and daily psychological functioning (Brief Adjustment Scale-6 [BASE-6]). Patient measures were summarized descriptively with means, medians, and SDs and then compared by using the Kruskal-Wallis test; associated effect sizes were calculated. PROM scores for patients who received hybrid psychiatric treatment during a different period (N=272) were compared with scores of the waitlist groups. RESULTS: PROM assessments of patients who engaged in hybrid care indicated significant improvements in symptom severity compared with the waitlist groups, regardless of the number of PROMs completed while patients were on the waitlist. Between the hybrid care and waitlist groups, the effect size for the PHQ-9 score was moderate (d=0.66); effect sizes were small for the GAD-7 (d=0.46) and BASE-6 (d=0.45) scores. CONCLUSIONS: The findings indicate the clinical effectiveness of hybrid care and that PROMs can be used to assess this effectiveness.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.