Intraoperative margin assessment for basal cell carcinoma with deep learning and histologic tumor mapping to surgical site

Successful treatment of solid cancers relies on complete surgical excision of the tumor either for definitive treatment or before adjuvant therapy. Intraoperative and postoperative radial sectioning, the most common form of margin assessment, can lead to incomplete excision and increase the risk of recurrence and repeat procedures. Mohs Micrographic Surgery is associated with complete removal of basal cell and squamous cell carcinoma through real-time margin assessment of 100% of the peripheral and deep margins. Real-time assessment in many tumor types is constrained by tissue size, complexity, and specimen processing / assessment time during general anesthesia. We developed an artificial intelligence platform to reduce the tissue preprocessing and histological assessment time through automated grossing recommendations, mapping and orientation of tumor to the surgical specimen. Using basal cell carcinoma as a model system, results demonstrate that this approach can address surgical laboratory efficiency bottlenecks for rapid and complete intraoperative margin assessment.

Potential to Enhance Large Scale Molecular Assessments of Skin Photoaging through Virtual Inference of Spatial Transcriptomics from Routine Staining

The advent of spatial transcriptomics technologies has heralded a renaissance in research to advance our understanding of the spatial cellular and transcriptional heterogeneity within tissues. Spatial transcriptomics allows investigation of the interplay between cells, molecular pathways, and the surrounding tissue architecture and can help elucidate developmental trajectories, disease pathogenesis, and various niches in the tumor microenvironment. Photoaging is the histological and molecular skin damage resulting from chronic/acute sun exposure and is a major risk factor for skin cancer. Spatial transcriptomics technologies hold promise for improving the reliability of evaluating photoaging and developing new therapeutics. Challenges to current methods include limited focus on dermal elastosis variations and reliance on self-reported measures, which can introduce subjectivity and inconsistency. Spatial transcriptomics offers an opportunity to assess photoaging objectively and reproducibly in studies of carcinogenesis and discern the effectiveness of therapies that intervene in photoaging and preventing cancer. Evaluation of distinct histological architectures using highly-multiplexed spatial technologies can identify specific cell lineages that have been understudied due to their location beyond the depth of UV penetration. However, the cost and interpatient variability using state-of-the-art assays such as the 10x Genomics Spatial Transcriptomics assays limits the scope and scale of large-scale molecular epidemiologic studies. Here, we investigate the inference of spatial transcriptomics information from routine hematoxylin and eosin-stained (H&E) tissue slides. We employed the Visium CytAssist spatial transcriptomics assay to analyze over 18,000 genes at a 50-micron resolution for four patients from a cohort of 261 skin specimens collected adjacent to surgical resection sites for basal cell and squamous cell keratinocyte tumors. The spatial transcriptomics data was co-registered with 40x resolution whole slide imaging (WSI) information. We developed machine learning models that achieved a macro-averaged median AUC and F1 score of 0.80 and 0.61 and Spearman coefficient of 0.60 in inferring transcriptomic profiles across the slides, and accurately captured biological pathways across various tissue architectures.

A deep learning algorithm to detect cutaneous squamous cell carcinoma on frozen sections in Mohs micrographic surgery: A retrospective assessment

Intraoperative margin analysis is crucial for the successful removal of cutaneous squamous cell carcinomas (cSCC). Artificial intelligence technologies (AI) have previously demonstrated potential for facilitating rapid and complete tumour removal using intraoperative margin assessment for basal cell carcinoma. However, the varied morphologies of cSCC present challenges for AI margin assessment. The aim of this study was to develop and evaluate the accuracy of an AI algorithm for real-time histologic margin analysis of cSCC. To do this, a retrospective cohort study was conducted using frozen cSCC section slides. These slides were scanned and annotated, delineating benign tissue structures, inflammation and tumour to develop an AI algorithm for real-time margin analysis. A convolutional neural network workflow was used to extract histomorphological features predictive of cSCC. This algorithm demonstrated proof of concept for identifying cSCC with high accuracy, highlighting the potential for integration of AI into the surgical workflow. Incorporation of AI algorithms may improve efficiency and completeness of real-time margin assessment for cSCC removal, particularly in cases of moderately and poorly differentiated tumours/neoplasms. Further algorithmic improvement incorporating surrounding tissue context is necessary to remain sensitive to the unique epidermal landscape of well-differentiated tumours, and to map tumours to their original anatomical position/orientation.

Spatial Omics Driven Crossmodal Pretraining Applied to Graph-based Deep Learning for Cancer Pathology Analysis

Graph-based deep learning has shown great promise in cancer histopathology image analysis by contextualizing complex morphology and structure across whole slide images to make high quality downstream outcome predictions (ex: prognostication). These methods rely on informative representations (i.e., embeddings) of image patches comprising larger slides, which are used as node attributes in slide graphs. Spatial omics data, including spatial transcriptomics, is a novel paradigm offering a wealth of detailed information. Pairing this data with corresponding histological imaging localized at 50-micron resolution, may facilitate the development of algorithms which better appreciate the morphological and molecular underpinnings of carcinogenesis. Here, we explore the utility of leveraging spatial transcriptomics data with a contrastive crossmodal pretraining mechanism to generate deep learning models that can extract molecular and histological information for graph-based learning tasks. Performance on cancer staging, lymph node metastasis prediction, survival prediction, and tissue clustering analyses indicate that the proposed methods bring improvement to graph based deep learning models for histopathological slides compared to leveraging histological information from existing schemes, demonstrating the promise of mining spatial omics data to enhance deep learning for pathology workflows.

Utility of Retrospective Molecular Analysis in Diagnostically Challenging Mesenchymal Neoplasms

Introduction: Molecular analysis plays a growing role in the diagnosis of mesenchymal neoplasms. The aim of this study was to retrospectively apply broad, multiplex molecular assays (a solid tumor targeted next-generation sequencing [NGS]) assay and single nucleotide polymorphism [SNP] microarray) to selected tumors, exploring the current utility and limitations. Methods: We searched our database (2010-2020) for diagnostically challenging mesenchymal neoplasms. After histologic review of available slides, tissue blocks were selected for NGS, SNP microarray, or both. DNA and RNA were extracted using the AllPrep DNA/RNA FFPE Kit Protocol on the QIAcube instrument. The NGS platform used was the TruSight Tumor 170 (TST-170). For SNP array, copy number variant (CNV) analysis was performed using the OncoScanTM CNV Plus Assay. Results: DNA/RNA was successfully extracted from 50% of tumors (n = 10/20). Specimens not successfully extracted included 6 core biopsies, 3 incisional biopsies, and 1 resection; 4 were decalcified (3 hydrochloric acid, 1 ethylenediaminetetraacetic acid). Higher tumor proportion and number of tumor cells were parameters positively associated with sufficient DNA/RNA extraction whereas necrosis and decalcification were negatively associated with sufficient extraction. Molecular testing helped reach a definitive diagnosis in 50% of tumors (n = 5/10). Conclusions: Although the overall utility of this approach is limited, these molecular panels can be helpful in detecting a specific "driver" alteration.

Use of molecular testing results to analyze the overuse of atypia of undetermined significance in thyroid cytology

INTRODUCTION

The suggested atypia of undetermined significance (AUS) rate for thyroid fine-needle aspiration biopsies is 10% or less. Prompted by a high institutional AUS rate, we examined using molecular testing results (MTR) as a potential quality metric tool to reduce the AUS rate. We correlated MTR with AUS cytologic findings, surgical pathology follow-up, and individual pathologist AUS rates.

MATERIALS AND METHODS

Demographic data, cytologic diagnoses, MTR, and surgical pathology diagnoses were retrospectively obtained. MTR were classified as either positive or negative. AUS rates and MTR proportions were compared among pathologists. The cytomorphologic features of 143 AUS cases were assessed and correlated with MTR.

RESULTS

Between 2017 and 2022, 710 of 3247 thyroid fine-needle aspirations were classified as AUS, with a yearly average rate of 22% (range = 19%-26%). AUS cases included: 331 (47%) with architectural atypia; 204 (29%) with oncocytic (Hürthle cell) atypia; 99 (14%) with combined architectural and cytologic atypia; and 76 (10%) with isolated cytologic atypia. Most AUS cases with molecular testing had negative MTR (360/492, 73%). AUS with cytologic atypia had higher positive MTR risk (logarithm of odds ratio = 1.27, 95% credible interval [0.5-2.04], P = 0.001). The average positive MTR rate by pathologist was 21.5% (range 0%-35%); higher positive MTR rates had better correlation with subsequent neoplastic/malignant histologic diagnoses. The MTR sensitivity for malignant disease was 89% and the negative predictive value was 91%.

CONCLUSIONS

MTR analysis reveals the importance of cytologic atypia as a determinant of malignancy risk in AUS cases. Periodic analysis of MTR data alongside individual pathologist AUS rates can help refine diagnostic criteria and potentially reduce AUS overuse.

Feasibility of Inferring Spatial Transcriptomics from Single-Cell Histological Patterns for Studying Colon Cancer Tumor Heterogeneity

Background

Spatial transcriptomics involves studying the spatial organization of gene expression within tissues, offering insights into the molecular diversity of tumors. While spatial gene expression is commonly amalgamated from 1-10 cells across 50-micron spots, recent methods have demonstrated the capability to disaggregate this information at subspot resolution by leveraging both expression and histological patterns. However, elucidating such information from histology alone presents a significant challenge but if solved can better permit spatial molecular analysis at cellular resolution for instances where Visium data is not available, reducing study costs. This study explores integrating single-cell histological and transcriptomic data to infer spatial mRNA expression patterns in whole slide images collected from a cohort of stage pT3 colorectal cancer patients. A cell graph neural network algorithm was developed to align histological information extracted from detected cells with single cell RNA patterns through optimal transport methods, facilitating the analysis of cellular groupings and gene relationships. This approach leveraged spot-level expression as an intermediary to co-map histological and transcriptomic information at the single-cell level.

Results

Our study demonstrated that single-cell transcriptional heterogeneity within a spot could be predicted from histological markers extracted from cells detected within a spot. Furthermore, our model exhibited proficiency in delineating overarching gene expression patterns across whole-slide images. This approach compared favorably to traditional patch-based computer vision methods as well as other methods which did not incorporate single cell expression during the model fitting procedures. Topological nuances of single-cell expression within a Visium spot were preserved using the developed methodology.

Conclusion

This innovative approach augments the resolution of spatial molecular assays utilizing histology as a sole input through synergistic co-mapping of histological and transcriptomic datasets at the single-cell level, anchored by spatial transcriptomics. While initial results are promising, they warrant rigorous validation. This includes collaborating with pathologists for precise spatial identification of distinct cell types and utilizing sophisticated assays, such as Xenium, to attain deeper subcellular insights.

The Overlooked Role of Specimen Preparation in Bolstering Deep Learning-Enhanced Spatial Transcriptomics Workflows

The application of deep learning methods to spatial transcriptomics has shown promise in unraveling the complex relationships between gene expression patterns and tissue architecture as they pertain to various pathological conditions. Deep learning methods that can infer gene expression patterns directly from tissue histomorphology can expand the capability to discern spatial molecular markers within tissue slides. However, current methods utilizing these techniques are plagued by substantial variability in tissue preparation and characteristics, which can hinder the broader adoption of these tools. Furthermore, training deep learning models using spatial transcriptomics on small study cohorts remains a costly endeavor. Necessitating novel tissue preparation processes enhance assay reliability, resolution, and scalability. This study investigated the impact of an enhanced specimen processing workflow for facilitating a deep learning-based spatial transcriptomics assessment. The enhanced workflow leveraged the flexibility of the Visium CytAssist assay to permit automated H&E staining (e.g., Leica Bond) of tissue slides, whole-slide imaging at 40x-resolution, and multiplexing of tissue sections from multiple patients within individual capture areas for spatial transcriptomics profiling. Using a cohort of thirteen pT3 stage colorectal cancer (CRC) patients, we compared the efficacy of deep learning models trained on slide prepared using an enhanced workflow as compared to the traditional workflow which leverages manual tissue staining and standard imaging of tissue slides. Leveraging Inceptionv3 neural networks, we aimed to predict gene expression patterns across matched serial tissue sections, each stemming from a distinct workflow but aligned based on persistent histological structures. Findings indicate that the enhanced workflow considerably outperformed the traditional spatial transcriptomics workflow. Gene expression profiles predicted from enhanced tissue slides also yielded expression patterns more topologically consistent with the ground truth. This led to enhanced statistical precision in pinpointing biomarkers associated with distinct spatial structures. These insights can potentially elevate diagnostic and prognostic biomarker detection by broadening the range of spatial molecular markers linked to metastasis and recurrence. Future endeavors will further explore these findings to enrich our comprehension of various diseases and uncover molecular pathways with greater nuance. Combining deep learning with spatial transcriptomics provides a compelling avenue to enrich our understanding of tumor biology and improve clinical outcomes. For results of the highest fidelity, however, effective specimen processing is crucial, and fostering collaboration between histotechnicians, pathologists, and genomics specialists is essential to herald this new era in spatial transcriptomics-driven cancer research.

Large-scale validation study of an improved semiautonomous urine cytology assessment tool: AutoParis-X

BACKGROUND

Adopting a computational approach for the assessment of urine cytology specimens has the potential to improve the efficiency, accuracy, and reliability of bladder cancer screening, which has heretofore relied on semisubjective manual assessment methods. As rigorous, quantitative criteria and guidelines have been introduced for improving screening practices (e.g., The Paris System for Reporting Urinary Cytology), algorithms to emulate semiautonomous diagnostic decision-making have lagged behind, in part because of the complex and nuanced nature of urine cytology reporting.

METHODS

In this study, the authors report on the development and large-scale validation of a deep-learning tool, AutoParis-X, which can facilitate rapid, semiautonomous examination of urine cytology specimens.

RESULTS

The results of this large-scale, retrospective validation study indicate that AutoParis-X can accurately determine urothelial cell atypia and aggregate a wide variety of cell-related and cluster-related information across a slide to yield an atypia burden score, which correlates closely with overall specimen atypia and is predictive of Paris system diagnostic categories. Importantly, this approach accounts for challenges associated with the assessment of overlapping cell cluster borders, which improve the ability to predict specimen atypia and accurately estimate the nuclear-to-cytoplasm ratio for cells in these clusters.

CONCLUSIONS

The authors developed a publicly available, open-source, interactive web application that features a simple, easy-to-use display for examining urine cytology whole-slide images and determining the level of atypia in specific cells, flagging the most abnormal cells for pathologist review. The accuracy of AutoParis-X (and other semiautomated digital pathology systems) indicates that these technologies are approaching clinical readiness and necessitates full evaluation of these algorithms in head-to-head clinical trials.

Examining longitudinal markers of bladder cancer recurrence through a semiautonomous machine learning system for quantifying specimen atypia from urine cytology

BACKGROUND

Urine cytology is generally considered the primary approach for screening for recurrence of bladder cancer. However, it is currently unclear how best to use cytological examinations for assessment and early detection of recurrence, beyond identifying a positive finding that requires more invasive methods to confirm recurrence and decide on therapeutic options. Because screening programs are frequent, and can be burdensome, finding quantitative means to reduce this burden for patients, cytopathologists, and urologists is an important endeavor and can improve both the efficiency and reliability of findings. Additionally, identifying ways to risk-stratify patients is crucial for improving quality of life while reducing the risk of future recurrence or progression of the cancer.

METHODS

In this study, a computational machine learning tool, AutoParis-X, was leveraged to extract imaging features from urine cytology examinations longitudinally to study the predictive potential of urine cytology for assessing recurrence risk. This study examined how the significance of imaging predictors changes over time before and after surgery to determine which predictors and time periods are most relevant for assessing recurrence risk.

RESULTS

Results indicate that imaging predictors extracted using AutoParis-X can predict recurrence as well or better than traditional cytological/histological assessments alone and that the predictiveness of these features is variable across time, with key differences in overall specimen atypia identified immediately before tumor recurrence.

CONCLUSIONS

Further research will clarify how computational methods can be effectively used in high-volume screening programs to improve recurrence detection and complement traditional modes of assessment.

Assessment of emerging pretraining strategies in interpretable multimodal deep learning for cancer prognostication

BACKGROUND

Deep learning models can infer cancer patient prognosis from molecular and anatomic pathology information. Recent studies that leveraged information from complementary multimodal data improved prognostication, further illustrating the potential utility of such methods. However, current approaches: 1) do not comprehensively leverage biological and histomorphological relationships and 2) make use of emerging strategies to "pretrain" models (i.e., train models on a slightly orthogonal dataset/modeling objective) which may aid prognostication by reducing the amount of information required for achieving optimal performance. In addition, model interpretation is crucial for facilitating the clinical adoption of deep learning methods by fostering practitioner understanding and trust in the technology.

METHODS

Here, we develop an interpretable multimodal modeling framework that combines DNA methylation, gene expression, and histopathology (i.e., tissue slides) data, and we compare performance of crossmodal pretraining, contrastive learning, and transfer learning versus the standard procedure.

RESULTS

Our models outperform the existing state-of-the-art method (average 11.54% C-index increase), and baseline clinically driven models (average 11.7% C-index increase). Model interpretations elucidate consideration of biologically meaningful factors in making prognosis predictions.

DISCUSSION

Our results demonstrate that the selection of pretraining strategies is crucial for obtaining highly accurate prognostication models, even more so than devising an innovative model architecture, and further emphasize the all-important role of the tumor microenvironment on disease progression.

Paired-agent imaging as a rapid en face margin screening method in Mohs micrographic surgery

Background

Mohs micrographic surgery is a procedure used for non-melanoma skin cancers that has 97-99% cure rates largely owing to 100% margin analysis enabled by en face sectioning with real-time, iterative histologic assessment. However, the technique is limited to small and aggressive tumors in high-risk areas because the histopathological preparation and assessment is very time intensive. To address this, paired-agent imaging (PAI) can be used to rapidly screen excised specimens and identify tumor positive margins for guided and more efficient microscopic evaluation.

Methods

A mouse xenograft model of human squamous cell carcinoma (n = 8 mice, 13 tumors) underwent PAI. Targeted (ABY-029, anti-epidermal growth factor receptor (EGFR) affibody molecule) and untargeted (IRDye 680LT carboxylate) imaging agents were simultaneously injected 3-4 h prior to surgical tumor resection. Fluorescence imaging was performed on main, unprocessed excised specimens and en face margins (tissue sections tangential to the deep margin surface). Binding potential (BP) - a quantity proportional to receptor concentration - and targeted fluorescence signal were measured for each, and respective mean and maximum values were analyzed to compare diagnostic ability and contrast. The BP and targeted fluorescence of the main specimen and margin samples were also correlated with EGFR immunohistochemistry (IHC).

Results

PAI consistently outperformed targeted fluorescence alone in terms of diagnostic ability and contrast-to-variance ratio (CVR). Mean and maximum measures of BP resulted in 100% accuracy, while mean and maximum targeted fluorescence signal offered 97% and 98% accuracy, respectively. Moreover, maximum BP had the greatest average CVR for both main specimen and margin samples (average 1.7 ± 0.4 times improvement over other measures). Fresh tissue margin imaging improved similarity with EGFR IHC volume estimates compared to main specimen imaging in line profile analysis; and margin BP specifically had the strongest concordance (average 3.6 ± 2.2 times improvement over other measures).

Conclusions

PAI was able to reliably distinguish tumor from normal tissue in fresh en face margin samples using the single metric of maximum BP. This demonstrated the potential for PAI to act as a highly sensitive screening tool to eliminate the extra time wasted on real-time pathological assessment of low-risk margins.

Identification of Spatial Proteomic Signatures of Colon Tumor Metastasis: A Digital Spatial Profiling Approach

Over 150,000 Americans are diagnosed with colorectal cancer (CRC) every year, and annually >50,000 individuals are estimated to die of CRC, necessitating improvements in screening, prognostication, disease management, and therapeutic options. CRC tumors are removed en bloc with surrounding vasculature and lymphatics. Examination of regional lymph nodes at the time of surgical resection is essential for prognostication. Developing alternative approaches to indirectly assess recurrence risk would have utility in cases where lymph node yield is incomplete or inadequate. Spatially dependent, immune cell-specific (eg, tumor-infiltrating lymphocytes), proteomic, and transcriptomic expression patterns inside and around the tumor-the tumor immune microenvironment-can predict nodal/distant metastasis and probe the coordinated immune response from the primary tumor site. The comprehensive characterization of tumor-infiltrating lymphocytes and other immune infiltrates is possible using highly multiplexed spatial omics technologies, such as the GeoMX Digital Spatial Profiler. In this study, machine learning and differential co-expression analyses helped identify biomarkers from Digital Spatial Profiler-assayed protein expression patterns inside, at the invasive margin, and away from the tumor, associated with extracellular matrix remodeling (eg, granzyme B and fibronectin), immune suppression (eg, forkhead box P3), exhaustion and cytotoxicity (eg, CD8), Programmed death ligand 1-expressing dendritic cells, and neutrophil proliferation, among other concomitant alterations. Further investigation of these biomarkers may reveal independent risk factors of CRC metastasis that can be formulated into low-cost, widely available assays.

A deep learning algorithm to detect cutaneous squamous cell carcinoma on frozen sections in Mohs micrographic surgery: a retrospective assessment

Importance

Intraoperative margin analysis is crucial for the successful removal of cutaneous squamous cell carcinomas (cSCC). Artificial intelligence technologies (AI) have previously demonstrated potential for facilitating rapid and complete tumor removal using intraoperative margin assessment for basal cell carcinoma. However, the varied morphologies of cSCC present challenges for AI margin assessment.

Objective

To develop and evaluate the accuracy of an AI algorithm for real-time histologic margin analysis of cSCC.

Design

A retrospective cohort study was conducted using frozen cSCC section slides and adjacent tissues.

Setting

This study was conducted in a tertiary care academic center.

Participants

Patients undergoing Mohs micrographic surgery for cSCC between January and March 2020.

Exposures

Frozen section slides were scanned and annotated, delineating benign tissue structures, inflammation, and tumor to develop an AI algorithm for real-time margin analysis. Patients were stratified by tumor differentiation status. Epithelial tissues including epidermis and hair follicles were annotated for moderate-well to well differentiated cSCC tumors. A convolutional neural network workflow was used to extract histomorphological features predictive of cSCC at 50-micron resolution.

Main Outcomes and Measures

The performance of the AI algorithm in identifying cSCC at 50-micron resolution was reported using the area under the receiver operating characteristic curve. Accuracy was also reported by tumor differentiation status and by delineation of cSCC from epidermis. Model performance using histomorphological features alone was compared to architectural features (i.e., tissue context) for well-differentiated tumors.

Results

The AI algorithm demonstrated proof of concept for identifying cSCC with high accuracy. Accuracy differed by differentiation status, driven by challenges in separating cSCC from epidermis using histomorphological features alone for well-differentiated tumors. Consideration of broader tissue context through architectural features improved the ability to delineate tumor from epidermis.

Conclusions and Relevance

Incorporating AI into the surgical workflow may improve efficiency and completeness of real-time margin assessment for cSCC removal, particularly in cases of moderately and poorly differentiated tumors/neoplasms. Further algorithmic improvement is necessary to remain sensitive to the unique epidermal landscape of well-differentiated tumors, and to map tumors to their original anatomical position/orientation. Future studies should assess the efficiency improvements and cost benefits and address other confounding pathologies such as inflammation and nuclei.

Funding sources

JL is supported by NIH grants R24GM141194, P20GM104416 and P20GM130454. Support for this work was also provided by the Prouty Dartmouth Cancer Center development funds.

Key Points

Question: How can the efficiency and accuracy of real-time intraoperative margin analysis for the removal of cutaneous squamous cell carcinoma (cSCC) be improved, and how can tumor differentiation be incorporated into this approach?Findings: A proof-of-concept deep learning algorithm was trained, validated, and tested on frozen section whole slide images (WSI) for a retrospective cohort of cSCC cases, demonstrating high accuracy in identifying cSCC and related pathologies. Histomorphology alone was found to be insufficient to delineate tumor from epidermis in histologic identification of well-differentiated cSCC. Incorporation of surrounding tissue architecture and shape improved the ability to delineate tumor from normal tissue.Meaning: Integrating artificial intelligence into surgical procedures has the potential to enhance the thoroughness and efficiency of intraoperative margin analysis for cSCC removal. However, accurately accounting for the epidermal tissue based on the tumor's differentiation status requires specialized algorithms that consider the surrounding tissue context. To meaningfully integrate AI algorithms into clinical practice, further algorithmic refinement is needed, as well as the mapping of tumors to their original surgical site, and evaluation of the cost and efficacy of these approaches to address existing bottlenecks.

GRANDPA: GeneRAtive network sampling using degree and property augmentation applied to the analysis of partially confidential healthcare networks

Protecting medical privacy can create obstacles in the analysis and distribution of healthcare graphs and statistical inferences accompanying them. We pose a graph simulation model which generates networks using degree and property augmentation and provide a flexible R package that allows users to create graphs that preserve vertex attribute relationships and approximating the retention of topological properties observed in the original graph (e.g., community structure). We illustrate our proposed algorithm using a case study based on Zachary's karate network and a patient-sharing graph generated from Medicare claims data in 2019. In both cases, we find that community structure is preserved, and normalized root mean square error between cumulative distributions of the degrees across the generated and the original graphs is low (0.0508 and 0.0514 respectively).

Inferring spatial transcriptomics markers from whole slide images to characterize metastasis-related spatial heterogeneity of colorectal tumors: A pilot study

Over 150 000 Americans are diagnosed with colorectal cancer (CRC) every year, and annually over 50 000 individuals will die from CRC, necessitating improvements in screening, prognostication, disease management, and therapeutic options. Tumor metastasis is the primary factor related to the risk of recurrence and mortality. Yet, screening for nodal and distant metastasis is costly, and invasive and incomplete resection may hamper adequate assessment. Signatures of the tumor-immune microenvironment (TIME) at the primary site can provide valuable insights into the aggressiveness of the tumor and the effectiveness of various treatment options. Spatially resolved transcriptomics technologies offer an unprecedented characterization of TIME through high multiplexing, yet their scope is constrained by cost. Meanwhile, it has long been suspected that histological, cytological, and macroarchitectural tissue characteristics correlate well with molecular information (e.g., gene expression). Thus, a method for predicting transcriptomics data through inference of RNA patterns from whole slide images (WSI) is a key step in studying metastasis at scale. In this work, we collected tissue from 4 stage-III (pT3) matched colorectal cancer patients for spatial transcriptomics profiling. The Visium spatial transcriptomics (ST) assay was used to measure transcript abundance for 17 943 genes at up to 5000 55-micron (i.e., 1-10 cells) spots per patient sampled in a honeycomb pattern, co-registered with hematoxylin and eosin (H&E) stained WSI. The Visium ST assay can measure expression at these spots through tissue permeabilization of mRNAs, which are captured through spatially (i.e., x-y positional coordinates) barcoded, gene specific oligo probes. WSI subimages were extracted around each co-registered Visium spot and were used to predict the expression at these spots using machine learning models. We prototyped and compared several convolutional, transformer, and graph convolutional neural networks to predict spatial RNA patterns at the Visium spots under the hypothesis that the transformer- and graph-based approaches better capture relevant spatial tissue architecture. We further analyzed the model's ability to recapitulate spatial autocorrelation statistics using SPARK and SpatialDE. Overall, the results indicate that the transformer- and graph-based approaches were unable to outperform the convolutional neural network architecture, though they exhibited optimal performance for relevant disease-associated genes. Initial findings suggest that different neural networks that operate on different scales are relevant for capturing distinct disease pathways (e.g., epithelial to mesenchymal transition). We add further evidence that deep learning models can accurately predict gene expression in whole slide images and comment on understudied factors which may increase its external applicability (e.g., tissue context). Our preliminary work will motivate further investigation of inference for molecular patterns from whole slide images as metastasis predictors and in other applications.

Uncovering additional predictors of urothelial carcinoma from voided urothelial cell clusters through a deep learning-based image preprocessing technique

BACKGROUND

Urine cytology is commonly used as a screening test for high-grade urothelial carcinoma for patients with risk factors or hematuria and is an essential step in longitudinal monitoring of patients with previous bladder cancer history. However, the semisubjective nature of current reporting systems for urine cytology (e.g., The Paris System) can hamper reproducibility. For instance, the incorporation of urothelial cell clusters into the classification schema is still an item of debate and perplexity among expert cytopathologists because several previous works have disputed their diagnostic relevance.

METHODS

In this work, an automated preprocessing tool for urothelial cell cluster assessment was developed that divides urothelial cell clusters into meaningful components for downstream assessment (ie, population-based studies, workflow automation).

RESULTS

In this work, an automated preprocessing tool for urothelial cell cluster assessment was developed that divides urothelial cell clusters into meaningful components for downstream assessment (ie, population-based studies, workflow automation). Results indicate that cell cluster atypia (i.e., defined by whether the cell cluster harbored multiple atypical cells, thresholded by a minimum number of cells), cell border overlap and smoothness, and total number of clusters are important markers of specimen atypia when considering assessment of urothelial cell clusters.

CONCLUSIONS

Markers established through techniques to separate cell clusters may have wider applicability for the design and implementation of machine learning approaches for urine cytology assessment.

Predictors of Gastrostomy Tube Placement in Head and Neck Cancer Patients at a Rural Tertiary Care Hospital

Background Head and neck cancer is a leading cause of cancer. Treatment often requires surgical resection, free-flap reconstruction, radiation, and/or chemotherapy. Tumor burden and pain may limit swallowing and impair nutrition, increasing complications and mortality. Patients commonly require gastrostomy tubes (G-tube), but predicting which patients are in need remains elusive. This study identifies predictors of G-tube among head and neck cancer patients undergoing immediate free-flap reconstruction.

Methods Institutional Review Board approval was obtained. Retrospective database review was performed of patients at 18 years of age or older with head and neck cancer who underwent resection with immediate free-flap reconstruction from 2011 to 2019. Patients who underwent nonfree-flap or delayed reconstruction or with mortality within 7 days postoperatively were excluded. Patient demographics and comorbidities, tumor/treatment characteristics, and need for G-tube were analyzed to identify univariate and multivariate predictors.

Results In total, 107 patients were included and 72 required G-tube placement. On multivariate analysis, tracheostomy (odds ratio [OR]: 81.78; confidence interval [CI]: 7.43–1,399.92; p < 0.01), anterolateral thigh flap reconstruction (OR: 16.18; CI: 1.14–429.66; p = 0.04), and age 65 years or younger (OR: 9.35; CI: 1.47–89.11; p = 0.02) were predictors of G-tube placement.

Conclusion Head and neck cancer treatment commonly involves extensive resection, reconstruction, and/or chemoradiation. These patients are at high risk for malnutrition and need G-tube. Determining who requires a pre- or postoperative G-tube remains a challenge. In this study, the need for tracheostomy or ALT flap reconstruction and age 65 years or younger were predictive of postoperative G-tube placement. Future research will guide a multidisciplinary perioperative pathway to facilitate the optimization of nutrition management.

Functional Reorganization of the Mesial Frontal Premotor Cortex in Patients With Supplementary Motor Area Seizures

BACKGROUND

Direct cortical stimulation of the mesial frontal premotor cortex, including the supplementary motor area (SMA), is challenging in humans. Limited access to these brain regions impedes understanding of human premotor cortex functional organization and somatotopy.

OBJECTIVE

To test whether seizure onset within the SMA was associated with functional remapping of mesial frontal premotor areas in a cohort of patients with epilepsy who underwent awake brain mapping after implantation of interhemispheric subdural electrodes.

METHODS

Stimulation trials from 646 interhemispheric subdural electrodes were analyzed and compared between patients who had seizure onset in the SMA (n = 13) vs patients who had seizure onset outside of the SMA (n = 12). 1:1 matching with replacement between SMA and non-SMA data sets was used to ensure similar spatial distribution of electrodes. Centroids and 95% confidence regions were computed for clustered head, trunk, upper extremity, lower extremity, and vision responses. A generalized linear mixed-effects model was used to test for significant differences in the resulting functional maps. Clinical, radiographic, and histopathologic data were reviewed.

RESULTS

After analyzing direct cortical stimulation trials from interhemispheric electrodes, we found significant displacement of the head and trunk responses in SMA compared with non-SMA patients ( P < .01 for both). These differences remained significant after accounting for structural lesions, preexisting motor deficits, and seizure outcome.

CONCLUSION

The somatotopy of the mesial frontal premotor regions is significantly altered in patients who have SMA-onset seizures compared with patients who have seizure onset outside of the SMA, suggesting that functional remapping can occur in these brain regions.

Applications of artificial intelligence in orthopaedic surgery

The practice of medicine is rapidly transforming as a result of technological breakthroughs. Artificial intelligence (AI) systems are becoming more and more relevant in medicine and orthopaedic surgery as a result of the nearly exponential growth in computer processing power, cloud based computing, and development, and refining of medical-task specific software algorithms. Because of the extensive role of technologies such as medical imaging that bring high sensitivity, specificity, and positive/negative prognostic value to management of orthopaedic disorders, the field is particularly ripe for the application of machine-based integration of imaging studies, among other applications. Through this review, we seek to promote awareness in the orthopaedics community of the current accomplishments and projected uses of AI and ML as described in the literature. We summarize the current state of the art in the use of ML and AI in five key orthopaedic disciplines: joint reconstruction, spine, orthopaedic oncology, trauma, and sports medicine.

Large-scale longitudinal comparison of urine cytological classification systems reveals potential early adoption of The Paris System criteria

INTRODUCTION

Urine cytology is used to screen for urothelial carcinoma in patients with hematuria or risk factors (eg, smoking, industrial dye exposure) and is an essential clinical triage and longitudinal monitoring tool for patients with known bladder cancer. However, urine cytology is semisubjective and thus susceptible to issues including specimen quality, interobserver variability, and "hedging" towards equivocal ("atypical") diagnoses. These factors limit the predictive value of urine cytology and increase reliance on invasive procedures (cystoscopy). The Paris System for Reporting Urine Cytology (TPS) was formulated to provide more quantitative/reproducible endpoints with well-defined criteria for urothelial atypia. TPS is often compared to other assessment techniques to justify its adoption. TPS results in decreased use of the atypical category and better reproducibility. Previous reports comparing diagnoses pre- and post-TPS have not considered temporal differences between diagnoses made under prior systems and TPS. By aggregating across time, studies may underestimate the magnitude of differences between assessment methods.

MATERIALS AND METHODS

We conducted a large-scale longitudinal reassessment of urine cytology using TPS criteria from specimens collected from 2008 to 2018, prior to the mid-2018 adoption of TPS at an academic medical center.

RESULTS

Findings indicate that differences in atypical assignment were largest at the start of the period and these differences progressively decreased towards insignificance just prior to TPS implementation.

CONCLUSIONS

This finding suggests that cytopathologists had begun to utilize the quantitative TPS criteria prior to official adoption, which may more broadly inform adoption strategies, communication, and understanding for evolving classification systems in cytology.

Predictors of gastrostomy tube placement in patients with head and neck cancer undergoing resection and flap-based reconstruction: systematic review and meta-analysis

BACKGROUND

Nutritional status may be impaired in patients with head and neck cancer undergoing surgical treatment, often necessitating gastrostomy tube (G-tube) placement. Identifying which patients will require a G-tube remains a challenge. This study identifies predictors of G-tube requirement in patients undergoing tumor resection and reconstruction with pedicled or free flaps.

METHODS

Systematic review of the PubMed, Cochrane, and Scopus databases was performed of English language articles, discussing risk factors of perioperative G-tube placement among patients >18 years. Data on patient, tumor, and treatment factors, as well as need for G-tube, were collected. Univariable meta-analysis was conducted to identify predictors for G-tube placement.

RESULTS

Eleven studies (1,112 patients) met inclusion criteria. Overall pooled prevalence of postoperative G-tube placement was 25%. Patients with advanced cancer stage IV/recurrence were more likely to require a G-tube (OR 2.81 [CI 1.03-7.69]; p<0.05), as were those who had undergone preoperative radiation (OR 3.55 [CI 2.03-6.20], p<0.05). Reconstruction with a radial forearm free flap was associated with a lower need for G-tube versus rectus abdominis (OR 0.25 [CI 0.08-0.83], p=0.02) and latissimus dorsi flap (OR 0.21 [CI 0.04-1.09], p=0.06). There was no difference in G-tube placement between those receiving pedicled flaps versus free flaps (OR 1.54 [CI 0.38-6.20], p=0.54).

CONCLUSIONS

Among patients with head and neck cancer undergoing resection with immediate pedicled or free flap reconstruction, advanced tumor stage and history of prior radiation therapy are associated with increased likelihood of G-tube placement. More randomized controlled trials are needed to develop a decision-making algorithm.

Passive order auditing associated with reductions in red blood cell utilization: National blood shortage experience

BACKGROUND

Decreased blood collection during the Coronavirus Disease 2019 (COVID-19) pandemic resulted in long-term red blood cell (RBC) shortages in the United States. In an effort to conserve RBCs, the existing passive alert system for auditing inpatient transfusions was modified to activate at a lower hemoglobin threshold (6.5 g/dL instead of 7.0 g/dL for stable, nonbleeding inpatients) during a 9-month shortage at an academic medical center. Hemoglobin levels prior to RBC transfusions were compared for inpatients receiving RBC transfusions to determine whether RBC utilization changed during the intervention.

STUDY DESIGN AND METHODS

This retrospective study compared the number of single-unit RBC transfusions and hemoglobin levels prior to RBC transfusion among inpatients during the 9 months of the intervention (Period 2, 06/01/2021-2/28/2022) to the same period of the previous year (Period 1, 06/01/2020-2/28/2021).

RESULTS

Overall full unit RBC transfusions to inpatients decreased by 15% from 5182 to 4421. Of all transfusions, 50.3% and 49.8% were single-unit RBC transfusions in Period 1 and Period 2, respectively. The incidence rate difference and incidence rate ratio of single RBC units transfused per 1000 patient days were significantly decreased (p = 0.0007). The average pre-transfusion hemoglobin level significantly decreased from 7.18 g/dL to 7.05 g/dL (p = 0.0002), largely due to significant decreases in hemoglobin transfusion triggers for adult inpatient ward transfusions.

DISCUSSION

Modification of the passive alert system was associated with significantly decreased RBC utilization during a long-term RBC shortage. Modification of transfusion criteria recommended by passive alerts may be a feasible option to decrease RBC utilization at centers during long-term RBC shortages.

Machine Learning Approaches for Hospital Acquired Pressure Injuries: A Retrospective Study of Electronic Medical Records

Background

Many machine learning heuristics integrate well with Electronic Medical Record (EMR) systems yet often fail to surpass traditional statistical models for biomedical applications.

Objective

We sought to compare predictive performances of 12 machine learning and traditional statistical techniques to predict the occurrence of Hospital Acquired Pressure Injuries (HAPI).

Methods

EMR information was collected from 57,227 hospitalizations acquired from Dartmouth Hitchcock Medical Center (April 2011 to December 2016). Twelve classification algorithms, chosen based upon classic regression and recent machine learning techniques, were trained to predict HAPI incidence and performance was assessed using the Area Under the Receiver Operating Characteristic Curve (AUC).

Results

Logistic regression achieved a performance (AUC = 0.91 ± 0.034) comparable to the other machine learning approaches. We report discordance between machine learning derived predictors compared to the traditional statistical model. We visually assessed important patient-specific factors through Shapley Additive Explanations.

Conclusions

Machine learning models will continue to inform clinical decision-making processes but should be compared to traditional modeling approaches to ensure proper utilization. Disagreements between important predictors found by traditional and machine learning modeling approaches can potentially confuse clinicians and need to be reconciled. These developments represent important steps forward in developing real-time predictive models that can be integrated into EMR systems to reduce unnecessary harm.

Comparison of Symptoms and Antibody Response Following Administration of Moderna or Pfizer SARS-CoV-2 Vaccines

CONTEXT. –

Moderna (mRNA-1272) and Pfizer (BNT162b2) SARS-CoV-2 vaccines demonstrate favorable safety and efficacy profiles, but direct comparison data is lacking.

OBJECTIVE. –

To determine the vaccines' side effect profiles and expected antibody responses. This data may help personalize vaccine selection and identify individuals with a suboptimal vaccine response.

DESIGN. –

One hundred forty-nine healthy, largely seronegative adults were assigned Moderna (n=79) or Pfizer (n=70). Following the second dose, participants completed a survey documenting their side effects. Serum was collected 0-4 days prior to dose 2, 14±4 days, 30±4 days, 90±10 days, and 180±20 days after dose 2. Convalescent serum specimens were collected 32-54 days from donors after a polymerase chain reaction (PCR)-confirmed SARS-CoV-2 infection (n=20). Anti-spike antibodies were measured using the Roche Diagnostics Elecys anti-SARS-CoV-2 S assay on a Roche cobas e801 instrument.

RESULTS. –

Participants receiving the Moderna vaccine experienced side effects with greater frequency and severity. Both vaccines elicited a robust antibody response but median signal was higher in Moderna recipients. Symptom severity decreased with age. Antibody response in Pfizer recipients negatively correlated with age. Antibody response decreased after 6 months (84% reduction in Moderna, 79% Pfizer), but values remained greater than for convalescent donors. Antibody response did not correlate with gender or symptom severity.

CONCLUSIONS. –

Moderna may be preferred in individuals in need of greater immune stimulation (e.g. older individuals) while Pfizer may be preferred in those concerned about vaccine reactions. Anti-spike antibody signal varies by vaccine, so specific reference intervals will be needed to identify individuals with a suboptimal response.

Mixed Effects Machine Learning Models for Colon Cancer Metastasis Prediction using Spatially Localized Immuno-Oncology Markers

Spatially resolved characterization of the transcriptome and proteome promises to provide further clarity on cancer pathogenesis and etiology, which may inform future clinical practice through classifier development for clinical outcomes. However, batch effects may potentially obscure the ability of machine learning methods to derive complex associations within spatial omics data. Profiling thirty-five stage three colon cancer patients using the GeoMX Digital Spatial Profiler, we found that mixed-effects machine learning (MEML) methods† may provide utility for overcoming significant batch effects to communicate key and complex disease associations from spatial information. These results point to further exploration and application of MEML methods within the spatial omics algorithm development life cycle for clinical deployment.

Using Satellite Images and Deep Learning to Identify Associations Between County-Level Mortality and Residential Neighborhood Features Proximal to Schools: A Cross-Sectional Study

What is the relationship between mortality and satellite images as elucidated through the use of Convolutional Neural Networks? Background: Following a century of increase, life expectancy in the United States has stagnated and begun to decline in recent decades. Using satellite images and street view images, prior work has demonstrated associations of the built environment with income, education, access to care, and health factors such as obesity. However, assessment of learned image feature relationships with variation in crude mortality rate across the United States has been lacking. Objective: We sought to investigate if county-level mortality rates in the U.S. could be predicted from satellite images. Methods: Satellite images of neighborhoods surrounding schools were extracted with the Google Static Maps application programming interface for 430 counties representing ~68.9% of the US population. A convolutional neural network was trained using crude mortality rates for each county in 2015 to predict mortality. Learned image features were interpreted using Shapley Additive Feature Explanations, clustered, and compared to mortality and its associated covariate predictors. Results: Predicted mortality from satellite images in a held-out test set of counties was strongly correlated to the true crude mortality rate (Pearson r = 0.72). Direct prediction of mortality using a deep learning model across a cross-section of 430 U.S. counties identified key features in the environment (e.g., sidewalks, driveways, and hiking trails) associated with lower mortality. Learned image features were clustered, and we identified 10 clusters that were associated with education, income, geographical region, race, and age. Conclusions: The application of deep learning techniques to remotely-sensed features of the built environment can serve as a useful predictor of mortality in the United States. Although we identified features that were largely associated with demographic information, future modeling approaches that directly identify image features associated with health-related outcomes have the potential to inform targeted public health interventions.

Using molecular testing to improve the management of thyroid nodules with indeterminate cytology: an institutional experience with review of molecular alterations

INTRODUCTION

Molecular testing has helped clinicians and cytopathologists to further categorize indeterminate thyroid fine needle aspiration (FNA) specimens. The purpose of the present study was to evaluate the accuracy of commercially available molecular tests, review their effects on patient treatment, and correlate the molecular alterations with the histologic findings.

MATERIALS AND METHODS

A pathology laboratory information system search identified thyroid FNAs performed at our institution between January 1, 2015 and June 30, 2020. The results of surgical follow-up and ancillary molecular testing were collected. We evaluated the accuracy of these tests and whether they could reduce the number of surgeries performed.

RESULTS

Our laboratory information system search identified 510 cases reported as atypia of undetermined significance, 94 as suspicious for follicular neoplasm, and 44 as suspicious for follicular neoplasm, Hurthle cell type. Of the specimens, 343 had no ancillary molecular testing, 146 were sent for ThyGenX/ThyraMIR, and 136 were sent for ThyroSeq. Of the patients without molecular testing, 50.4% had undergone follow-up surgery compared with 30.8% after ThyGenX/ThyraMIR and 38.2% after ThyroSeq testing, resulting in 38.9% and 24.2% fewer surgeries and an odds ratio of 0.04 (95% confidence interval, 0.00-0.33) and 0.14 (95% confidence interval, 0.01-0.95), respectively. For ThyGenX/ThyraMIR testing, the risk of malignancy for high and moderate to high risk alterations was 80%, 28.6% for moderate and low to moderate risk alterations, and 23.1% for low risk alterations. For ThyroSeq, the risk of malignancy was 87.5% for high risk alterations, 36.8% for intermediate to high risk alterations, 27.3% for intermediate risk alterations, and 0% for low risk alterations. The areas under the curve for ThyGenX/ThyraMIR and ThyroSeq testing were 0.65 and 0.85, respectively.

CONCLUSIONS

These findings suggest that, at our institution, both ThygenX/ThyraMIR and ThyroSeq can be used to effectively stratify cytology specimens based on the risk of malignancy and reduce the number of surgeries performed at our institution.

MethylSPWNet and MethylCapsNet: Biologically Motivated Organization of DNAm Neural Networks, Inspired by Capsule Networks

DNA methylation (DNAm) alterations have been heavily implicated in carcinogenesis and the pathophysiology of diseases through upstream regulation of gene expression. DNAm deep-learning approaches are able to capture features associated with aging, cell type, and disease progression, but lack incorporation of prior biological knowledge. Here, we present modular, user-friendly deep-learning methodology and software, MethylCapsNet and MethylSPWNet, that group CpGs into biologically relevant capsules-such as gene promoter context, CpG island relationship, or user-defined groupings-and relate them to diagnostic and prognostic outcomes. We demonstrate these models' utility on 3,897 individuals in the classification of central nervous system (CNS) tumors. MethylCapsNet and MethylSPWNet provide an opportunity to increase DNAm deep-learning analyses' interpretability by enabling a flexible organization of DNAm data into biologically relevant capsules.

Atypia of undetermined significance in thyroid cytology: Nuclear atypia and architectural atypia are associated with different molecular alterations and risks of malignancy

BACKGROUND

The Bethesda System for Reporting Thyroid Cytopathology contains an atypia of undetermined significance (AUS) category with heterogeneous and distinct inclusion criteria. The purpose of this study was to investigate differences in malignancy rates and molecular alterations based on the presence of different criteria.

METHODS

A laboratory information search was conducted to identify thyroid fine-needle aspiration specimens signed out as AUS. The cases were reclassified as architectural atypia (3A), cytologic atypia (3C), both architectural and cytologic atypia (3B), or Hürthle cell aspirate (3H). Surgical follow-up and concurrent molecular test results, if available, were collected.

RESULTS

Five hundred ten specimens, including 258 reclassified as 3A, 40 reclassified as 3B, 119 reclassified as 3C, and 86 reclassified as 3H, were identified. The risks of malignancy for the subcategories were 13.4%, 26.3%, 44.1%, and 13.8%, respectively. Additionally, BRAF V600E mutations were more prevalent in specimens with cytologic atypia (3B/3C), whereas low-risk alterations, including KRAS, PTEN, and PAX8-PPARy2, were more prevalent in those with architectural atypia (3A).

CONCLUSIONS

Subdividing AUS specimens on the basis of the type of atypia can yield categories associated with distinct molecular alterations and risks of malignancy.

A large-scale internal validation study of unsupervised virtual trichrome staining technologies on nonalcoholic steatohepatitis liver biopsies

Non-alcoholic steatohepatitis (NASH) is a fatty liver disease characterized by accumulation of fat in hepatocytes with concurrent inflammation and is associated with morbidity, cirrhosis and liver failure. After extraction of a liver core biopsy, tissue sections are stained with hematoxylin and eosin (H&E) to grade NASH activity, and stained with trichrome to stage fibrosis. Methods to computationally transform one stain into another on digital whole slide images (WSI) can lessen the need for additional physical staining besides H&E, reducing personnel, equipment, and time costs. Generative adversarial networks (GAN) have shown promise for virtual staining of tissue. We conducted a large-scale validation study of the viability of GANs for H&E to trichrome conversion on WSI (n = 574). Pathologists were largely unable to distinguish real images from virtual/synthetic images given a set of twelve Turing Tests. We report high correlation between staging of real and virtual stains ([Formula: see text]; 95% CI: 0.84-0.88). Stages assigned to both virtual and real stains correlated similarly with a number of clinical biomarkers and progression to End Stage Liver Disease (Hazard Ratio HR = 2.06, 95% CI: 1.36-3.12, p < 0.001 for real stains; HR = 2.02, 95% CI: 1.40-2.92, p < 0.001 for virtual stains). Our results demonstrate that virtual trichrome technologies may offer a software solution that can be employed in the clinical setting as a diagnostic decision aid.

Evaluating the mediating effects of perceived vulnerability to disease in the relation between disgust and contamination-based OCD

Contamination-based obsessive-compulsive disorder (OCD) is thought to develop and be maintained by excessive propensity to experience disgust, particularly in response to perceived contaminants, and dysfunctional threat appraisals pertaining to illness. The present studies attempted to integrate these lines of research by testing the degree to which contamination-based OCD is associated with individual differences in disgust propensity and sensitivity, affective distress in response to perceived contaminants, and perceived threat of illness. In Study 1, a convenience sample of 185 adults completed self-report scales assessing obsessive-compulsive symptoms, disgust propensity and sensitivity, germ aversion, and perceived infectability. Multivariate regression showed that disgust propensity and germ aversion were the only significant predictors of contamination-based obsessions and compulsions. Exploratory analyses suggested that there was a significant indirect effect of disgust propensity on contamination-based obsessions and compulsions via germ aversion. Findings from Study 1 were replicated using a sample of twenty-six obsessive-compulsive participants. Despite the substantially smaller sample, the proportion of the total effects attributable to the mediating effect of germ aversion was comparable, consistent with a significant partial mediation in both samples. These results together suggest that contamination-based OCD symptoms are likely maintained and motivated by basic affective processes.

Gradual polyploid genome evolution revealed by pan-genomic analysis of Brachypodium hybridum and its diploid progenitors

Our understanding of polyploid genome evolution is constrained because we cannot know the exact founders of a particular polyploid. To differentiate between founder effects and post polyploidization evolution, we use a pan-genomic approach to study the allotetraploid Brachypodium hybridum and its diploid progenitors. Comparative analysis suggests that most B. hybridum whole gene presence/absence variation is part of the standing variation in its diploid progenitors. Analysis of nuclear single nucleotide variants, plastomes and k-mers associated with retrotransposons reveals two independent origins for B. hybridum, ~1.4 and ~0.14 million years ago. Examination of gene expression in the younger B. hybridum lineage reveals no bias in overall subgenome expression. Our results are consistent with a gradual accumulation of genomic changes after polyploidization and a lack of subgenome expression dominance. Significantly, if we did not use a pan-genomic approach, we would grossly overestimate the number of genomic changes attributable to post polyploidization evolution.

PyMethylProcess-convenient high-throughput preprocessing workflow for DNA methylation data

SUMMARY

Performing highly parallelized preprocessing of methylation array data using Python can accelerate data preparation for downstream methylation analyses, including large scale production-ready machine learning pipelines. We present a highly reproducible, scalable pipeline (PyMethylProcess) that can be quickly set-up and deployed through Docker and PIP.

AVAILABILITY AND IMPLEMENTATION

Project Home Page: https://github.com/Christensen-Lab-Dartmouth/PyMethylProcess. Available on PyPI (pymethylprocess), Docker (joshualevy44/pymethylprocess).

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Don't dismiss logistic regression: the case for sensible extraction of interactions in the era of machine learning

BACKGROUND

Machine learning approaches have become increasingly popular modeling techniques, relying on data-driven heuristics to arrive at its solutions. Recent comparisons between these algorithms and traditional statistical modeling techniques have largely ignored the superiority gained by the former approaches due to involvement of model-building search algorithms. This has led to alignment of statistical and machine learning approaches with different types of problems and the under-development of procedures that combine their attributes. In this context, we hoped to understand the domains of applicability for each approach and to identify areas where a marriage between the two approaches is warranted. We then sought to develop a hybrid statistical-machine learning procedure with the best attributes of each.

METHODS

We present three simple examples to illustrate when to use each modeling approach and posit a general framework for combining them into an enhanced logistic regression model building procedure that aids interpretation. We study 556 benchmark machine learning datasets to uncover when machine learning techniques outperformed rudimentary logistic regression models and so are potentially well-equipped to enhance them. We illustrate a software package, InteractionTransformer, which embeds logistic regression with advanced model building capacity by using machine learning algorithms to extract candidate interaction features from a random forest model for inclusion in the model. Finally, we apply our enhanced logistic regression analysis to two real-word biomedical examples, one where predictors vary linearly with the outcome and another with extensive second-order interactions.

RESULTS

Preliminary statistical analysis demonstrated that across 556 benchmark datasets, the random forest approach significantly outperformed the logistic regression approach. We found a statistically significant increase in predictive performance when using hybrid procedures and greater clarity in the association with the outcome of terms acquired compared to directly interpreting the random forest output.

CONCLUSIONS

When a random forest model is closer to the true model, hybrid statistical-machine learning procedures can substantially enhance the performance of statistical procedures in an automated manner while preserving easy interpretation of the results. Such hybrid methods may help facilitate widespread adoption of machine learning techniques in the biomedical setting.

MethylNet: an automated and modular deep learning approach for DNA methylation analysis

BACKGROUND

DNA methylation (DNAm) is an epigenetic regulator of gene expression programs that can be altered by environmental exposures, aging, and in pathogenesis. Traditional analyses that associate DNAm alterations with phenotypes suffer from multiple hypothesis testing and multi-collinearity due to the high-dimensional, continuous, interacting and non-linear nature of the data. Deep learning analyses have shown much promise to study disease heterogeneity. DNAm deep learning approaches have not yet been formalized into user-friendly frameworks for execution, training, and interpreting models. Here, we describe MethylNet, a DNAm deep learning method that can construct embeddings, make predictions, generate new data, and uncover unknown heterogeneity with minimal user supervision.

RESULTS

The results of our experiments indicate that MethylNet can study cellular differences, grasp higher order information of cancer sub-types, estimate age and capture factors associated with smoking in concordance with known differences.

CONCLUSION

The ability of MethylNet to capture nonlinear interactions presents an opportunity for further study of unknown disease, cellular heterogeneity and aging processes.

PathFlowAI: A High-Throughput Workflow for Preprocessing, Deep Learning and Interpretation in Digital Pathology

The diagnosis of disease often requires analysis of a biopsy. Many diagnoses depend not only on the presence of certain features but on their location within the tissue. Recently, a number of deep learning diagnostic aids have been developed to classify digitized biopsy slides. Clinical workflows often involve processing of more than 500 slides per day. But, clinical use of deep learning diagnostic aids would require a preprocessing workflow that is cost-effective, flexible, scalable, rapid, interpretable, and transparent. Here, we present such a workflow, optimized using Dask and mixed precision training via APEX, capable of handling any patch-level or slide level classification and prediction problem. The workflow uses a flexible and fast preprocessing and deep learning analytics pipeline, incorporates model interpretation and has a highly storage-efficient audit trail. We demonstrate the utility of this package on the analysis of a prototypical anatomic pathology specimen, liver biopsies for evaluation of hepatitis from a prospective cohort. The preliminary data indicate that PathFlowAI may become a cost-effective and time-efficient tool for clinical use of Artificial Intelligence (AI) algorithms.

PolyCRACKER, a robust method for the unsupervised partitioning of polyploid subgenomes by signatures of repetitive DNA evolution

BACKGROUND

Our understanding of polyploid genomes is limited by our inability to definitively assign sequences to a specific subgenome without extensive prior knowledge like high resolution genetic maps or genome sequences of diploid progenitors. In theory, existing methods for assigning sequences to individual species from metagenome samples could be used to separate subgenomes in polyploid organisms, however, these methods rely on differences in coarse genome properties like GC content or sequences from related species. Thus, these approaches do not work for subgenomes where gross features are indistinguishable and related genomes are lacking. Here we describe a method that uses rapidly evolving repetitive DNA to circumvent these limitations.

RESULTS

By using short, repetitive, DNA sequences as species-specific signals we separated closely related genomes from test datasets and subgenomes from two polyploid plants, tobacco and wheat, without any prior knowledge.

CONCLUSION

This approach is ideal for separating the subgenomes of polyploid species with unsequenced or unknown progenitor genomes.

A novel, mild, specific and indirect maleimido-based radioiodolabeling method. Radiolabeling of analogs derived from parathyroid hormone (PTH) and PTH-related protein (PTHrP)

In an effort to design a mild, non-oxidative and site-specific means of radiolabeling bioactive molecules we have employed maleimido-sulfhydryl chemistry to produce bioactive hormone radioligands. We have prepared two novel radioiodolabeled reagents, 3'-maleimidopropanoyl-3-125I-tyramide and its retro analog, N-maleoyl-N'-3-(4-hydroxy-3-125I-phenyl)propanoyl ethylenediamide, by either oxidative radioiodination of the precursors or radiolabeling of the phenolic component prior to its incorporation into the radiolabeling reagents. These reagents were then used to radiolabel analogs of parathyroid hormone (PTH) and parathyroid hormone-related protein (PTHrP) in an efficient way, yielding reaction mixtures which were easily purified. The radioligands obtained are stable upon storage and bind in a reversible manner to a single population of binding sites displaying affinity in the low nanomolar range. The potencies of these analogs are comparable to the non-modified PTH and PTHrP analogs. This study demonstrates the utility of the novel maleimido-based indirect radioiodination approach and highlights some of its advantages over either direct oxidative procedures or acylation using the Bolton-Hunter reagent.

Solid-phase synthesis and biologic activity of human parathyroid hormone (1-84)

We have chemically synthesized the full-length, 84 amino acid, human parathyroid hormone (hPTH) on a greater than 100 mg scale by the Merrifield solid-phase technique of stepwise peptide synthesis using a benzhydrylamine support. The peptide was purified by high-performance liquid chromatography and found to be greater than 96% pure. The authenticity or the sequence of the synthetic peptide was confirmed by repetitive Edman degradation. Furthermore, tryptic digestion of hPTH generated the predicted fragments. The synthetic full-length hormone was evaluated for biologic activity in assays of PTH receptor binding and stimulation of adenylate cyclase activity (using bovine renal cortical membranes and rat and human bone cells). Synthetic hPTH (1-84) was found to be highly potent in binding to PTH receptors (Kb = 1-25 nM) and stimulating adenylate cyclase (Km = 1-14 nM). The availability of significant quantities of synthetic full-length hPTH and future analogs will permit widespread use in multiple in vitro and in vivo assays to delineate their spectrum of biologic properties. Available supplies of the synthetic hormone will also enable evaluation of the effectiveness of PTH antagonists at inhibiting the action of native sequence hormone at its receptors.

Optically efficient free-space folded perfect shuffle network

A light-efficient folded perfect shuffle network is described. Two-dimensional (2-D) raster encoding of the processing element nodes is used to accommodate large arrays with simple imaging optics. The network uses 2-D arrays of lenslets and prisms to correct for magnification and replication losses. Simulation results show the required prism arrays to be of low complexity and suggest that the network is tolerant to imperfections in the prism parameters.

Primary structure of peptides and ion channels. Role of amino acid side chains in voltage gating of melittin channels

Melittin produces a voltage-dependent increase in the conductance of planar lipid bilayers. The conductance increases when the side of the membrane to which melittin has been added (cis-side) is made positive. This paper reports observations on the effect of modifying two positively charged amino acid residues within the NH2-terminal region of the molecule: lysine at position 7 (K7), and the NH2-terminal glycine (G1). We have synthesized melittin analogues in which K7 is replaced by asparagine (K7-N), G1 is blocked by a formyl group (G1-f), and in which both modifications of the parent compound were introduced (G1-f, K7-N). The time required to reach peak conductance during a constant voltage pulse was shorter in membranes exposed to the analogues than in membranes modified by melittin. The apparent number of monomers producing a conducting unit for [K7-N]-melittin and [G1-f]-melittin, eight, was found to be greater than the one for [G1-f], K7-N]-melittin and for melittin itself, four. The apparent gating charge per monomer was less for the analogues, 0.5-0.3 than for melittin, one. Essentially similar results were obtained with melittin analogues in which the charge on K7 or G1 or both was blocked by an uncharged N-linked spin label. These results show that the positive charges in the NH2-terminal region of melittin play a major but not exclusive role in the voltage gating of melittin channels in bilayers.

The bovine renal parathyroid hormone (PTH) receptor has equal affinity for two different amino acid sequences: the receptor binding domains of PTH and PTH-related protein are located within the 14-34 region

Previous studies examining the interaction of PTH and PTH-related protein (PTHrP) with target tissue have for the most part emphasized the similarity between the two hormones in binding to and activating receptors. This observation that two peptides with limited homology have equal affinities for the same receptor is unusual. In this report we investigated two aspects of PTH/PTHrP-receptor interactions. First, the nonhomologous 14-34 regions of PTH and PTHrP were synthesized and evaluated. Second, hybrid peptides containing the 7-18 fragment of one hormone combined with the 19-34 region of the other hormone were studied to determine whether interactions between these two regions are required for receptor recognition. All four peptides were examined in bovine renal cortical membrane and rat osteosarcoma (ROS 17/2.8) cell PTH-binding and PTH-stimulated adenylate cyclase assays. The results indicate that the receptor-binding domains of PTH and PTHrP lie outside of the 1-13 region, the region containing sequence homology shared by the two hormones, and that two peptides of different amino acid sequence bind with equal affinity to the bovine renal PTH receptor. However, in the absence of the N-terminal region, the rat bone PTH receptor displays a preference for the C-terminal (19-34 sequence) region of PTHrP.

Removal of partial agonism from parathyroid hormone (PTH)-related protein-(7-34)NH2 by substitution of PTH amino acids at positions 10 and 11

PTHrP(7-34)NH2 and [D-Trp12]PTHrP(7-34)NH2 have previously been shown to be shown to be more potent antagonists than the corresponding PTH peptide, [Tyr34]bPTH(7-34)NH2. However, these peptides also display partial agonism for adenylate cyclase activity in ROS 17/2.8 cells. In this study, design of a pure potent antagonist of PTH and PTHrP by removal of agonism from PTHrP(7-34)NH2 with retention of antagonist potency was accomplished. Since [Tyr34]bPTH(7-34)NH2 lacks agonist activity, we introduced two amino acids native to the PTH sequence into their respective positions in PTHrP and the potent D-Trp12 analog. [Asn10Leu11]- and [Asn10,leu11,D-Trp12]-PTHrP(7-34)NH2 were found to be 23- and 26-fold more potent as antagonists in ROS cells than PTHrP(7-34)NH2 and [D-Trp12]PTHrP(7-34)NH2, respectively. In addition, these peptides did not display partial agonism, even in an assay based on highly responsive cells pretreated with dexamethasone and pertussis toxin. In contrast, when the PTHrP sequence Asp10,Lys11 was inserted into [Tyr34]hPTH(7-34)NH2, antagonist potency declined by more than 6-fold and PTH-like agonist activity was installed. These results demonstrate that the activation domain of both PTH and PTHrP can be extended to include the 1-12 region and that the 10-12 region, in addition to the N-terminal hexapeptide, is important not only for receptor binding but also for hormonal signal transduction.

Modifications of position 12 in parathyroid hormone and parathyroid hormone related protein: toward the design of highly potent antagonists

Truncated N-terminal fragments of parathyroid hormone (PTH), [Tyr34]bovine PTH(7-34)NH2, and parathyroid hormone related protein (PTHrP), PTHrP(7-34)NH2, inhibit [Nle8,18,[125I]iodo-Tyr34]-bPTH(1-34)NH2 binding and PTH-stimulated adenylate cyclase in bone and kidney assays. However, the receptor interactions of these peptides are 2-3 orders of magnitude weaker than those of their agonist counterparts. To produce an antagonist with increased receptor-binding affinity but lacking agonist-like properties, structure-function studies were undertaken. Glycine at position 12 (present in all homologues of PTH and in PTHrP), which is predicted in both hormones to participate in a beta-turn, was examined by substituting conformational reporters, such as D- or L-Ala, Pro, and alpha-aminoisobutyric acid (Aib), in both agonist and antagonist analogues. Except for N-substituted amino acids, which substantially diminished potency, substitutions were well tolerated, indicating that this site can accept a wide latitude of modifications. To augment receptor avidity, hydrophobic residues compatible with helical secondary structure were introduced. Incorporation of the nonnatural amino acids D-Trp, D-alpha-naphthylalanine (D-alpha-Nal), or D-beta-Nal into either [Tyr34]bPTH(7-34)NH2 or [Nle8,18,Tyr34]bPTH(7-34)NH2 resulted in antagonists that were about 10-fold more active than their respective 7-34 parent compound. Similarly, [D-Trp12]PTHrP(7-34)NH2 was 6 times more potent than the unsubstituted peptide but retained partial agonistic properties, although markedly reduced, similar to PTHrP(7-34)NH2. The antagonistic potentiating effect was configurationally specific.(ABSTRACT TRUNCATED AT 250 WORDS)

Renal and adrenal adenosine 3',5'-monophosphate production and corticosteroid secretion in response to synthetic chicken parathyroid hormone-(1-34)

The activity of synthetic chicken (c) PTH-(1-34) amide was tested in dispersed chicken and rat kidney and adrenocortical cells. In the adrenal cells the effect of intact cPTH was also evaluated. In chicken kidney cells, the time- and dose-response patterns of cAMP production were similar for cPTH-(1-34) amide and human (h) PTH-(1-34), whereas rat kidney cells were considerably more sensitive to hPTH-(1-34) than to cPTH-(1-34) amide. The agonist effects of both hPTH-(1-34) and cPTH-(1-34) amide in kidney cells were inhibited by the bovine PTH-(3-34) analog. In chicken adrenocortical cells, cPTH-(1-34) amide stimulated cAMP production and steroid secretion. This action of the peptide was inhibited by bovine PTH-(3-34) and hPTH-(1-34), which by themselves showed no agonist effects. The maximal response of steroid secretion to cPTH-(1-34) amide was significantly lower than that to ACTH, but intact cPTH (supplied as a semipurified parathyroid extract) stimulated steriodogenesis to the same extent as ACTH. In rat adrenocortical cells, intact cPTH stimulated both cAMP formation and steriodogenesis, but cPTH-(1-34) amine showed no agonist effect. The action of the intact hormone in the rat adrenal could be inhibited by cPTH-(1-34) amide. The present results demonstrate the interaction of cPTH-(1-34) with kidney and adrenocortical cells of either chicken or rat. The cAMP and steroidogenic responses of the adrenocortical cells to PTH appear to be dependent (completely in the rat and partially in the chicken) on some sequence beyond the 1-34 region.