Search

Tyrosine kinase inhibitors (TKIs) targeting epidermal growth factor receptor (EGFR) are effective for many patients with lung cancer with EGFR mutations. However, not all patients are responsive to EGFR TKIs, including even those harboring EGFR-sensitizing mutations. In this study, we quantified the cells and cellular interaction features of the tumor microenvironment (TME) using routine H&E-stained biopsy sections. These TME features were used to develop a prediction model for survival benefit from EGFR TKI therapy in patients with lung adenocarcinoma and EGFR-sensitizing mutations in the Lung Cancer Mutation Consortium 1 (LCMC1) and validated in an independent LCMC2 cohort. In the validation data set, EGFR TKI treatment prolonged survival in the predicted-to-benefit group but not in the predicted-not-to-benefit group. Among patients treated with EGFR TKIs, the predicted-to-benefit group had prolonged survival outcomes compared with the predicted not-to- benefit group. The EGFR TKI survival benefit positively correlated with tumor- tumor interaction image features and negatively correlated with tumor-stroma interaction. Moreover, the tumor-stroma interaction was associated with higher activation of the hepatocyte growth factor/MET-mediated PI3K/AKT signaling pathway and epithelial-mesenchymal transition process, supporting the hypothesis of fibroblast-involved resistance to EGFR TKI treatment., Introduction Tyrosine kinase inhibitors (TKIs) of the epidermal growth factor receptor (EGFR) have shown survival improvements in the treatment of patients with EGFR-mutant lung cancer as first line therapy. Erlotinib, [...]

Genetic mouse models of skeletal abnormalities have demonstrated promise in the identification of phenotypes relevant to human skeletal diseases. Traditionally, phenotypes are assessed by manually examining radiographs, a tedious and potentially error-prone process. In response, this study developed a deep learning-based model that streamlines the measurement of murine bone lengths from radiographs in an accurate and reproducible manner. A bone detection and measurement pipeline utilizing the Keypoint R-CNN algorithm with an EfficientNet-B3 feature extraction backbone was developed to detect murine bone positions and measure their lengths. The pipeline was developed utilizing 94 X-ray images with expert annotations on the start and end position of each murine bone. The accuracy of our pipeline was evaluated on an independent dataset test with 592 images, and further validated on a previously published dataset of 21,300 mouse radiographs. The results showed that our model performed comparably to humans in measuring tibia and femur lengths (R2 > 0.92, p-value = 0) and significantly outperformed humans in measuring pelvic lengths in terms of precision and consistency. Furthermore, the model improved the precision and consistency of genetic association mapping results, identifying significant associations between genetic mutations and skeletal phenotypes with reduced variability. This study demonstrates the feasibility and efficiency of automated murine bone length measurement in the identification of mouse models of abnormal skeletal phenotypes. [ABSTRACT FROM AUTHOR]

PURPOSE: Osteosarcoma research advancement requires enhanced data integration across different modalities and sources. Current osteosarcoma research, encompassing clinical, genomic, protein, and tissue imaging data, is hindered by the siloed landscape of data generation and storage. MATERIALS AND METHODS: Clinical, molecular profiling, and tissue imaging data for 573 patients with pediatric osteosarcoma were collected from four public and institutional sources. A common data model incorporating standardized terminology was created to facilitate the transformation, integration, and load of source data into a relational database. On the basis of this database, a data commons accompanied by a user-friendly web portal was developed, enabling various data exploration and analytics functions. RESULTS: The Osteosarcoma Explorer (OSE) was released to the public in 2021. Leveraging a comprehensive and harmonized data set on the backend, the OSE offers a wide range of functions, including Cohort Discovery, Patient Dashboard, Image Visualization, and Online Analysis. Since its initial release, the OSE has experienced an increasing utilization by the osteosarcoma research community and provided solid, continuous user support. To our knowledge, the OSE is the largest (N = 573) and most comprehensive research data commons for pediatric osteosarcoma, a rare disease. This project demonstrates an effective framework for data integration and data commons development that can be readily applied to other projects sharing similar goals. CONCLUSION: The OSE offers an online exploration and analysis platform for integrated clinical, molecular profiling, and tissue imaging data of osteosarcoma. Its underlying data model, database, and web framework support continuous expansion onto new data modalities and sources. Osteosarcoma Explorer: a research data commons with clinical, genomic, protein, and image data. [ABSTRACT FROM AUTHOR]

Simple Summary: Oral cavity and pharyngeal cancer affects 560,000 people worldwide on a yearly basis. Despite advances in treatment, the survival rate remains poor, while prognoses typically improve with early diagnosis. The epithelium of the oral cavity often exhibits abnormal cellular growth, or dysplasia, that predisposes the patient to cancer depending on severity. Our study aims to address the current lack of rigorous quantitative methods for analyzing histopathological features relevant to clinical diagnosis, such as cellular morphology and epithelial layer number. We developed a deep learning approach that segments the oral epithelium and counts epithelial layer number within H&E-stained whole slide images. Our results demonstrate the feasibility of this automated approach for segmenting oral epithelium and counting its layer number. We also show its clinical relevance by comparing oral epithelium layer numbers between dysplasia of different severities. Head and neck squamous cell carcinoma (HNSCC), specifically in the oral cavity (oral squamous cell carcinoma, OSCC), is a common, complex cancer that significantly affects patients' quality of life. Early diagnosis typically improves prognoses yet relies on pathologist examination of histology images that exhibit high inter- and intra-observer variation. The advent of deep learning has automated this analysis, notably with object segmentation. However, techniques for automated oral dysplasia diagnosis have been limited to shape or cell stain information, without addressing the diagnostic potential in counting the number of cell layers in the oral epithelium. Our study attempts to address this gap by combining the existing U-Net and HD-Staining architectures for segmenting the oral epithelium and introducing a novel algorithm that we call Onion Peeling for counting the epithelium layer number. Experimental results show a close correlation between our algorithmic and expert manual layer counts, demonstrating the feasibility of automated layer counting. We also show the clinical relevance of oral epithelial layer number to grading oral dysplasia severity through survival analysis. Overall, our study shows that automated counting of oral epithelium layers can represent a potential addition to the digital pathology toolbox. Model generalizability and accuracy could be improved further with a larger training dataset. [ABSTRACT FROM AUTHOR]

Polyploidy, the duplication of the entire genome within a single cell, is a significant characteristic of cells in many tissues, including the liver. The quantification of hepatic ploidy typically relies on flow cytometry and immunofluorescence (IF) imaging, which are not widely available in clinical settings due to high financial and time costs. To improve accessibility for clinical samples, we developed a computational algorithm to quantify hepatic ploidy using hematoxylin-eosin (H&E) histopathology images, which are commonly obtained during routine clinical practice. Our algorithm uses a deep learning model to first segment and classify different types of cell nuclei in H&E images. It then determines cellular ploidy based on the relative distance between identified hepatocyte nuclei and determines nuclear ploidy using a fitted Gaussian mixture model. The algorithm can establish the total number of hepatocytes and their detailed ploidy information in a region of interest (ROI) on H&E images. This is the first successful attempt to automate ploidy analysis on H&E images. Our algorithm is expected to serve as an important tool for studying the role of polyploidy in human liver disease. [ABSTRACT FROM AUTHOR]

Molecular profiling technologies, such as genome sequencing and proteomics, have transformed biomedical research, but most such technologies require tissue dissociation, which leads to loss of tissue morphology and spatial information. Recent developments in spatial molecular profiling technologies have enabled the comprehensive molecular characterization of cells while keeping their spatial and morphological contexts intact. Molecular profiling data generate deep characterizations of the genetic, transcriptional and proteomic events of cells, while tissue images capture the spatial locations, organizations and interactions of the cells together with their morphology features. These data, together with cell and tissue imaging data, provide unprecedented opportunities to study tissue heterogeneity and cell spatial organization. This review aims to provide an overview of these recent developments in spatial molecular profiling technologies and the corresponding computational methods developed for analyzing such data. [ABSTRACT FROM AUTHOR]

Germ cell tumors (GCTs) are considered a rare disease but are the most common solid tumors in adolescents and young adults, accounting for 15% of all malignancies in this age group. The rarity of GCTs in some groups, particularly children, has impeded progress in treatment and biologic understanding. The most effective GCT research will result from the interrogation of data sets from historical and prospective trials across institutions. However, inconsistent use of terminology among groups, different sample-labeling rules, and lack of data standards have hampered researchers' efforts in data sharing and across-study validation. To overcome the low interoperability of data and facilitate future clinical trials, we worked with the Malignant Germ Cell International Consortium (MaGIC) and developed a GCT clinical data model as a uniform standard to curate and harmonize GCT data sets. This data model will also be the standard for prospective data collection in future trials. Using the GCT data model, we developed a GCT data commons with data sets from both MaGIC and public domains as an integrated research platform. The commons supports functions, such as data query, management, sharing, visualization, and analysis of the harmonized data, as well as patient cohort discovery. This GCT data commons will facilitate future collaborative research to advance the biologic understanding and treatment of GCTs. Moreover, the framework of the GCT data model and data commons will provide insights for other rare disease research communities into developing similar collaborative research platforms. [ABSTRACT FROM AUTHOR]

Background: With the expansion of non-small cell lung cancer (NSCLC) screening methods, the percentage of cases with early-stage NSCLC is anticipated to increase. Yet it remains unclear how the type and case volume of the health care facility at which treatment occurs may affect surgery selection and overall survival for cases with early-stage NSCLC.Methods: A total of 332,175 cases with the American Joint Committee on Cancer (AJCC) TNM stage I and stage II NSCLC who were reported to the National Cancer Data Base (NCDB) by 1302 facilities were studied. Facility type was characterized in the NCDB as community cancer program (CCP), comprehensive community cancer program (CCCP), academic/research program (ARP), or integrated network cancer program (INCP). Each facility type was dichotomized further into high-volume or low-volume groups based on the case volume. Multivariate Cox proportional hazard models, the logistic regression model, and propensity score matching were used to evaluate differences in survival and surgery selection among facilities according to type and volume.Results: Cases from ARPs were found to have the longest survival (median, 16.4 months) and highest surgery rate (74.8%), whereas those from CCPs had the shortest survival (median, 9.7 months) and the lowest surgery rate (60.8%). The difference persisted when adjusted by potential confounders. For cases treated at CCPs, CCCPs, and ARPs, high-volume facilities had better survival outcomes than low-volume facilities. In facilities with better survival outcomes, surgery was performed for a greater percentage of cases compared with facilities with worse outcomes.Conclusions: For cases with early-stage NSCLC, both facility type and case volume influence surgery selection and clinical outcome. Higher surgery rates are observed in facilities with better survival outcomes. [ABSTRACT FROM AUTHOR]

Oxygen‐sensitive MRI has been extensively used to investigate tumor oxygenation based on the response (R2* and/or R1) to a gas breathing challenge. Most studies have reported response to hyperoxic gas indicating potential biomarkers of hypoxia. Few studies have examined hypoxic gas breathing and we have now evaluated acute dynamic changes in rat breast tumors. Rats bearing syngeneic subcutaneous (n = 15) or orthotopic (n = 7) 13762NF breast tumors were exposed to a 16% O2 gas breathing challenge and monitored using blood oxygen level dependent (BOLD) R2* and tissue oxygen level dependent (TOLD) T1‐weighted measurements at 4.7 T. As a control, we used a traditional hyperoxic gas breathing challenge with 100% O2 on a subset of the subcutaneous tumor bearing rats (n = 6). Tumor subregions identified as responsive on the basis of R2* dynamics coincided with the viable tumor area as judged by subsequent H&E staining. As expected, R2* decreased and T1‐weighted signal increased in response to 100% O2 breathing challenge. Meanwhile, 16% O2 breathing elicited an increase in R2*, but divergent response (increase or decrease) in T1‐weighted signal. The T1‐weighted signal increase may signify a dominating BOLD effect triggered by 16% O2 in the relatively more hypoxic tumors, whereby the influence of increased paramagnetic deoxyhemoglobin outweighs decreased pO2. The results emphasize the importance of combined BOLD and TOLD measurements for the correct interpretation of tumor oxygenation properties. [ABSTRACT FROM AUTHOR]

Tyrosine kinase inhibitors (TKIs) targeting epidermal growth factor receptor (EGFR) are effective for many patients with lung cancer with EGFR mutations. However, not all patients are responsive to EGFR TKIs, including even those harboring EGFRsensitizing mutations. In this study, we quantified the cells and cellular interaction features of the tumor microenvironment (TME) using routine H&E-stained biopsy sections. These TME features were used to develop a prediction model for survival benefit from EGFR TKI therapy in patients with lung adenocarcinoma and EGFR-sensitizing mutations in the Lung Cancer Mutation Consortium 1 (LCMC1) and validated in an independent LCMC2 cohort. In the validation data set, EGFR TKI treatment prolonged survival in the predicted-to-benefit group but not in the predicted-not-to-benefit group. Among patients treated with EGFR TKIs, the predicted-to-benefit group had prolonged survival outcomes compared with the predicted not-to-benefit group. The EGFR TKI survival benefit positively correlated with tumor-tumor interaction image features and negatively correlated with tumor-stroma interaction. Moreover, the tumor-stroma interaction was associated with higher activation of the hepatocyte growth factor/MET-mediated PI3K/AKT signaling pathway and epithelial-mesenchymal transition process, supporting the hypothesis of fibroblast-involved resistance to EGFR TKI treatment. [ABSTRACT FROM AUTHOR]

Objective: Accurate diagnosis and prognosis are essential in lung cancer treatment selection and planning. With the rapid advance of medical imaging technology, whole slide imaging (WSI) in pathology is becoming a routine clinical procedure. An interplay of needs and challenges exists for computer-aided diagnosis based on accurate and efficient analysis of pathology images. Recently, artificial intelligence, especially deep learning, has shown great potential in pathology image analysis tasks such as tumor region identification, prognosis prediction, tumor microenvironment characterization, and metastasis detection. Materials and Methods: In this review, we aim to provide an overview of current and potential applications for AI methods in pathology image analysis, with an emphasis on lung cancer. Results: We outlined the current challenges and opportunities in lung cancer pathology image analysis, discussed the recent deep learning developments that could potentially impact digital pathology in lung cancer, and summarized the existing applications of deep learning algorithms in lung cancer diagnosis and prognosis. Discussion and Conclusion: With the advance of technology, digital pathology could have great potential impacts in lung cancer patient care. We point out some promising future directions for lung cancer pathology image analysis, including multi-task learning, transfer learning, and model interpretation. [ABSTRACT FROM AUTHOR]

Introduction: In our previous study, we constructed a Lung Cancer Explorer (LCE) database housing lung cancer-specific expression data and clinical data from over 6700 patients in 56 studies. Methods: Using this dataset of the largest collection of lung cancer gene expression along with our meta-analysis method, we systematically interrogated the association between gene expression and overall survival as well as the expression difference between tumor and normal (adjacent non-malignant tissue) samples in lung adenocarcinoma (ADC) and lung squamous cell carcinoma (SQCC). A case study for FAM83A and FAM83B was performed as a demonstration for hypothesis testing with our database. Results: We showed that the reproducibility of results across studies varied by histological subtype and analysis type. Genes and pathways unique or common to the two histological subtypes were identified and the results were integrated into LCE to facilitate user exploration. In our case study, we verified the findings from a previous study on FAM83A and FAM83B in non-small cell lung cancer. Conclusions: This study used gene expression data from a large cohort of patients to explore the molecular differences between lung ADC and SQCC. [ABSTRACT FROM AUTHOR]

The interaction between antigens and antibodies (B cell receptors, BCRs) is the key step underlying the function of the humoral immune system in various biological contexts. The capability to profile the landscape of antigen-binding affinity of a vast number of BCRs will provide a powerful tool to reveal novel insights at unprecedented levels and will yield powerful tools for translational development. However, current experimental approaches for profiling antibody-antigen interactions are costly and time-consuming, and can only achieve low-to-mid throughput. On the other hand, bioinformatics tools in the field of antibody informatics mostly focus on optimization of antibodies given known binding antigens, which is a very different research question and of limited scope. In this work, we developed an innovative Artificial Intelligence tool, Cmai, to address the prediction of the binding between antibodies and antigens that can be scaled to high-throughput sequencing data. Cmai achieved an AUROC of 0.91 in our validation cohort. We devised a biomarker metric based on the output from Cmai applied to high-throughput BCR sequencing data. We found that, during immune-related adverse events (irAEs) caused by immune-checkpoint inhibitor (ICI) treatment, the humoral immunity is preferentially responsive to intracellular antigens from the organs affected by the irAEs. In contrast, extracellular antigens on malignant tumor cells are inducing B cell infiltrations, and the infiltrating B cells have a greater tendency to co-localize with tumor cells expressing these antigens. We further found that the abundance of tumor antigen-targeting antibodies is predictive of ICI treatment response. Overall, Cmai and our biomarker approach filled in a gap that is not addressed by current antibody optimization works nor works such as AlphaFold3 that predict the structures of complexes of proteins that are known to bind.

Recent advances in foundation models have revolutionized model development in digital pathology, reducing dependence on extensive manual annotations required by traditional methods. The ability of foundation models to generalize well with few-shot learning addresses critical barriers in adapting models to diverse medical imaging tasks. This work presents the Granular Box Prompt Segment Anything Model (GB-SAM), an improved version of the Segment Anything Model (SAM) fine-tuned using granular box prompts with limited training data. The GB-SAM aims to reduce the dependency on expert pathologist annotators by enhancing the efficiency of the automated annotation process. Granular box prompts are small box regions derived from ground truth masks, conceived to replace the conventional approach of using a single large box covering the entire H&E-stained image patch. This method allows a localized and detailed analysis of gland morphology, enhancing the segmentation accuracy of individual glands and reducing the ambiguity that larger boxes might introduce in morphologically complex regions. We compared the performance of our GB-SAM model against U-Net trained on different sizes of the CRAG dataset. We evaluated the models across histopathological datasets, including CRAG, GlaS, and Camelyon16. GB-SAM consistently outperformed U-Net, with reduced training data, showing less segmentation performance degradation. Specifically, on the CRAG dataset, GB-SAM achieved a Dice coefficient of 0.885 compared to U-Net's 0.857 when trained on 25% of the data. Additionally, GB-SAM demonstrated segmentation stability on the CRAG testing dataset and superior generalization across unseen datasets, including challenging lymph node segmentation in Camelyon16, which achieved a Dice coefficient of 0.740 versus U-Net's 0.491. Furthermore, compared to SAM-Path and Med-SAM, GB-SAM showed competitive performance. GB-SAM achieved a Dice score of 0.900 on the CRAG dataset, while SAM-Path achieved 0.884. On the GlaS dataset, Med-SAM reported a Dice score of 0.956, whereas GB-SAM achieved 0.885 with significantly less training data. These results highlight GB-SAM's advanced segmentation capabilities and reduced dependency on large datasets, indicating its potential for practical deployment in digital pathology, particularly in settings with limited annotated datasets.

Over the past decade, many new cancer treatments have been developed and made available to patients. However, in most cases, these treatments only benefit a specific subgroup of patients, making the selection of treatment for a specific patient an essential but challenging task for oncologists. Although some biomarkers were found to associate with treatment response, manual assessment is time-consuming and subjective. With the rapid developments and expanded implementation of artificial intelligence (AI) in digital pathology, many biomarkers can be quantified automatically from histopathology images. This approach allows for a more efficient and objective assessment of biomarkers, aiding oncologists in formulating personalized treatment plans for cancer patients. This review presents an overview and summary of the recent studies on biomarker quantification and treatment response prediction using hematoxylin-eosin (H&E) stained pathology images. These studies have shown that an AI-based digital pathology approach can be practical and will become increasingly important in improving the selection of cancer treatments for patients., (Copyright © 2023 Elsevier Inc. All rights reserved.)

Background: Racial and ethnic minority groups in the United States experience a disproportionate burden of COVID-19 deaths., Objective: To evaluate whether outcome differences between Hispanic and non-Hispanic COVID-19 hospitalized patients exist and, if so, to identify the main malleable contributing factors., Design, Setting, Participants: Retrospective, cross-sectional, observational study of 6097 adult COVID-19 patients hospitalized within a single large healthcare system from March to November 2020., Exposures: Self-reported ethnicity and primary language., Main Outcomes and Measures: Clinical outcomes included intensive care unit (ICU) utilization and in-hospital death. We used age-adjusted odds ratios (OR) and multivariable analysis to evaluate the associations between ethnicity/language groups and outcomes., Results: 32.1% of patients were Hispanic, 38.6% of whom reported a non-English primary language. Hispanic patients were less likely to be insured, have a primary care provider, and have accessed the healthcare system prior to the COVID-19 admission. After adjusting for age, Hispanic inpatients experienced higher ICU utilization (non-English-speaking: OR, 1.75; 95% CI, 1.47-2.08; English-speaking: OR, 1.13; 95% CI, 0.95-1.33) and higher mortality (non-English-speaking: OR, 1.43; 95% CI, 1.10-1.86; English-speaking: OR, 1.53; 95% CI, 1.19-1.98) compared to non-Hispanic inpatients. There were no observed treatment disparities among ethnic groups. After adjusting for age, Hispanic inpatients had elevated disease severity at admission (non-English-speaking: OR, 2.27; 95% CI, 1.89-2.72; English-speaking: OR, 1.33; 95% CI, 1.10- 1.61). In multivariable analysis, the associations between ethnicity/language and clinical outcomes decreased after considering baseline disease severity (P < .001)., Conclusion: The associations between ethnicity and clinical outcomes can be explained by elevated disease severity at admission and limited access to healthcare for Hispanic patients, especially non-English-speaking Hispanics.

Background: Current treatment guidelines for stage IV non-small cell lung cancer (NSCLC) with brain metastases recommend brain treatments, including surgical resection and radiotherapy (RT), in addition to resection of the primary lung tumor. Here, we investigate the less-studied impact of treatment sequence on the overall survival. Methods: The National Cancer Database was queried for NSCLC patients with brain metastases who underwent surgical resection of the primary lung tumor ( n = 776). Kaplan-Meier survival curves with log-rank test and propensity score stratified Cox regression with Wald test were used to evaluate the associations between various treatment plans and overall survival (OS). Results: Compared to patients who did not receive any brain treatment (median OS = 6.05 months), significantly better survival was observed for those who received brain surgery plus RT (median OS = 26.25 months, p < 0.0001) and for those who received brain RT alone (median OS = 14.49 months, p < 0.001). Patients who received one upfront brain treatment (surgery or RT) before lung surgery were associated with better survival than those who received lung surgery first ( p < 0.05). The best survival outcome (median OS 27.1 months) was associated with the sequence of brain surgery plus postoperative brain RT followed by lung surgery. Conclusions: This study shows the value of performing upfront brain treatments followed by primary lung tumor resection for NSCLC patients with brain metastases, especially the procedure of brain surgery plus postoperative brain RT followed by lung surgery., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 He, Yin, Liu, Lu, Kernstine, Gerber, Xie and Yang.)

Background: Lung adenocarcinomas (ADCs) show heterogeneous morphological patterns that are classified into five subgroups: lepidic predominant, papillary predominant, acinar predominant, micropapillary predominant and solid predominant. The morphological classification of ADCs has been reported to be associated with patient prognosis and adjuvant chemotherapy response. However, the molecular mechanisms underlying the morphology differences among different subgroups remain largely unknown., Methods: Using the molecular profiling data from The Cancer Genome Atlas (TCGA) lung ADC (LUAD) cohort, we studied the molecular differences across invasive ADC morphological subgroups., Results: We showed that the expression of proteins and mRNAs, but not the gene mutations copy number alterations (CNA), were significantly associated with lung ADC morphological subgroups. In addition, expression of the FOXM1 gene (which is negatively associated with patient survival) likely plays an important role in the morphological differences among different subgroups. Moreover, we found that protein abundance of PD-L1 were associated with the malignancy of subgroups. These results were validated in an independent cohort., Conclusions: This study provides insights into the molecular differences among different lung ADC morphological subgroups, which could lead to potential subgroup-specific therapies., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/tlcr-19-321). JM serves as an unpaid editorial board member of Translational Lung Cancer Research. The other authors have no conflicts of interest to declare., (2020 Translational Lung Cancer Research. All rights reserved.)

The spatial organization of different types of cells in tumor tissues reveals important information about the tumor microenvironment (TME). To facilitate the study of cellular spatial organization and interactions, we developed Histology-based Digital-Staining, a deep learning-based computation model, to segment the nuclei of tumor, stroma, lymphocyte, macrophage, karyorrhexis, and red blood cells from standard hematoxylin and eosin-stained pathology images in lung adenocarcinoma. Using this tool, we identified and classified cell nuclei and extracted 48 cell spatial organization-related features that characterize the TME. Using these features, we developed a prognostic model from the National Lung Screening Trial dataset, and independently validated the model in The Cancer Genome Atlas lung adenocarcinoma dataset, in which the predicted high-risk group showed significantly worse survival than the low-risk group ( P = 0.001), with a HR of 2.23 (1.37-3.65) after adjusting for clinical variables. Furthermore, the image-derived TME features significantly correlated with the gene expression of biological pathways. For example, transcriptional activation of both the T-cell receptor and programmed cell death protein 1 pathways positively correlated with the density of detected lymphocytes in tumor tissues, while expression of the extracellular matrix organization pathway positively correlated with the density of stromal cells. In summary, we demonstrate that the spatial organization of different cell types is predictive of patient survival and associated with the gene expression of biological pathways. SIGNIFICANCE: These findings present a deep learning-based analysis tool to study the TME in pathology images and demonstrate that the cell spatial organization is predictive of patient survival and is associated with gene expression. See related commentary by Rodriguez-Antolin, p. 1912 ., (©2020 American Association for Cancer Research.)

Background: The spatial distributions of different types of cells could reveal a cancer cell's growth pattern, its relationships with the tumor microenvironment and the immune response of the body, all of which represent key "hallmarks of cancer". However, the process by which pathologists manually recognize and localize all the cells in pathology slides is extremely labor intensive and error prone., Methods: In this study, we developed an automated cell type classification pipeline, ConvPath, which includes nuclei segmentation, convolutional neural network-based tumor cell, stromal cell, and lymphocyte classification, and extraction of tumor microenvironment-related features for lung cancer pathology images. To facilitate users in leveraging this pipeline for their research, all source scripts for ConvPath software are available at https://qbrc.swmed.edu/projects/cnn/., Findings: The overall classification accuracy was 92.9% and 90.1% in training and independent testing datasets, respectively. By identifying cells and classifying cell types, this pipeline can convert a pathology image into a "spatial map" of tumor, stromal and lymphocyte cells. From this spatial map, we can extract features that characterize the tumor micro-environment. Based on these features, we developed an image feature-based prognostic model and validated the model in two independent cohorts. The predicted risk group serves as an independent prognostic factor, after adjusting for clinical variables that include age, gender, smoking status, and stage., Interpretation: The analysis pipeline developed in this study could convert the pathology image into a "spatial map" of tumor cells, stromal cells and lymphocytes. This could greatly facilitate and empower comprehensive analysis of the spatial organization of cells, as well as their roles in tumor progression and metastasis., (Copyright © 2019 The Authors. Published by Elsevier B.V. All rights reserved.)