Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features

Lung cancer is the most prevalent cancer worldwide, and histopathological assessment is indispensable for its diagnosis. However, human evaluation of pathology slides cannot accurately predict patients’ prognoses. In this study, we obtain 2,186 haematoxylin and eosin stained histopathology whole-slide images of lung adenocarcinoma and squamous cell carcinoma patients from The Cancer Genome Atlas (TCGA), and 294 additional images from Stanford Tissue Microarray (TMA) Database. We extract 9,879 quantitative image features and use regularized machine-learning methods to select the top features and to distinguish shorter-term survivors from longer-term survivors with stage I adenocarcinoma (P<0.003) or squamous cell carcinoma (P=0.023) in the TCGA data set. We validate the survival prediction framework with the TMA cohort (P<0.036 for both tumour types). Our results suggest that automatically derived image features can predict the prognosis of lung cancer patients and thereby contribute to precision oncology. Our methods are extensible to histopathology images of other organs. Diagnosis of lung cancer through manual histopathology evaluation is insufficient to predict patient survival. Here, the authors use computerized image processing to identify diagnostically relevant image features and use these features to distinguish lung cancer patients with different prognoses.

• Publication year

  2016

• Venue

  Nature Communications

• Publication date

  2016-08-16

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1038/ncomms12474PMID 27527408PMCID 4990706
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Additional Information.

  2018cited by this paper
• Genomics and Personalized Medicine: What Everyone Needs to Know®

  2016cited by this paper
• Omics Profiling in Precision Oncology*

  2016cited by this paper
• Computational Pathology: Challenges and Promises for Tissue Analysis

  2015cited by this paper
• Subtype Classification of Lung Adenocarcinoma Predicts Benefit From Adjuvant Chemotherapy in Patients Undergoing Complete Resection.

  2015cited by this paper
• Proposal of a prognostically relevant grading scheme for pulmonary squamous cell carcinoma

  2015cited by this paper
• Tumor‐size‐based morphological features of metastatic lymph node tumors from primary lung adenocarcinoma

  2014cited by this paper
• Combined high‐grade neuroendocrine carcinoma of the lung: Clinicopathological and immunohistochemical study of 34 surgically resected cases

  2014cited by this paper
• Comprehensive Pathological Analyses in Lung Squamous Cell Carcinoma: Single Cell Invasion, Nuclear Diameter, and Tumor Budding Are Independent Prognostic Factors for Worse Outcomes

  2014cited by this paper
• Comprehensive molecular profiling of lung adenocarcinoma

  2014cited by this paper
• New pathologic classification of lung cancer: relevance for clinical practice and clinical trials.

  2013cited by this paper
• Validation of interobserver agreement in lung cancer assessment: hematoxylin-eosin diagnostic reproducibility for non-small cell lung cancer: the 2004 World Health Organization classification and therapeutically relevant subsets.

  2013cited by this paper
• Cancer statistics, 2013

  2013cited by this paper
• Personalized medicine for lung cancer: new challenges for pathology

  2012cited by this paper
• International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society International Multidisciplinary Classification of Lung Adenocarcinoma

  2012cited by this paper
• Reproducibility of histopathological subtypes and invasion in pulmonary adenocarcinoma. An international interobserver study

  2012cited by this paper
• Comprehensive genomic characterization of squamous cell lung cancers

  2012cited by this paper
• Training increases concordance in classifying pulmonary adenocarcinomas according to the novel IASLC/ATS/ERS classification

  2012cited by this paper
• The novel histologic International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society classification system of lung adenocarcinoma is a stage-independent predictor of survival.

  2012cited by this paper
• FoxQ1 Overexpression Influences Poor Prognosis in Non-Small Cell Lung Cancer, Associates with the Phenomenon of EMT

  2012cited by this paper
• Ancillary Testing in Lung Cancer Diagnosis

  2012cited by this paper
• Interobserver variability in the application of the novel IASLC/ATS/ERS classification for pulmonary adenocarcinomas

  2012cited by this paper
• Regularization Paths for Cox's Proportional Hazards Model via Coordinate Descent.

  2011cited by this paper
• Global cancer statistics

  2011cited by this paper
• Impact of proposed IASLC/ATS/ERS classification of lung adenocarcinoma: prognostic subgroups and implications for further revision of staging based on analysis of 514 stage I cases

  2011cited by this paper
• Computer aided diagnostic tools aim to empower rather than replace pathologists: Lessons learned from computational chess

  2011cited by this paper
• Systematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival

  2011influential reference
• Improved structure, function and compatibility for CellProfiler: modular high-throughput image analysis software

  2011cited by this paper
• International Association for the Study of Lung Cancer/American Thoracic Society/European Respiratory Society International Multidisciplinary Classification of Lung Adenocarcinoma

  2011cited by this paper
• ggplot2: Elegant Graphics for Data Analysis

  2010cited by this paper
• Pathologic diagnosis of advanced lung cancer based on small biopsies and cytology: a paradigm shift.

  2010cited by this paper
• Metadata matters: access to image data in the real world

  2010cited by this paper
• Detection of Follicles From IHC-Stained Slides of Follicular Lymphoma Using Iterative Watershed

  2010cited by this paper
• Subtyping of Undifferentiated Non-small Cell Carcinomas in Bronchial Biopsy Specimens

  2010cited by this paper
• Refining the Diagnosis and EGFR Status of Non-small Cell Lung Carcinoma in Biopsy and Cytologic Material, Using a Panel of Mucin Staining, TTF-1, Cytokeratin 5/6, and P63, and EGFR Mutation Analysis

  2010cited by this paper
• The differential efficacy of pemetrexed according to NSCLC histology: a review of two Phase III studies.

  2009cited by this paper
• Noninvasive Staging of Non-small Cell Lung Cancer: ACCP Evidenced-Based Clinical Practice Guidelines (2nd Edition)

  2009cited by this paper
• Histopathological Image Analysis Using Model-Based Intermediate Representations and Color Texture: Follicular Lymphoma Grading

  2009cited by this paper
• Computer-aided prognosis of neuroblastoma on whole-slide images: Classification of stromal development

  2009cited by this paper
• Molecular predictive and prognostic markers in non-small-cell lung cancer.

  2009cited by this paper
• BMC Bioinformatics BioMed Central Methodology article Conditional variable importance for random forests

  2008influential reference
• Lung cancer: diagnosis and management.

  2007cited by this paper
• Physiologic evaluation of the patient with lung cancer being considered for resectional surgery: ACCP evidenced-based clinical practice guidelines (2nd edition).

  2007cited by this paper
• Noninvasive staging of non-small cell lung cancer: ACCP evidenced-based clinical practice guidelines (2nd edition).

  2007cited by this paper
• The Stanford Tissue Microarray Database

  2007influential reference
• Classification and Regression by randomForest

  2007influential reference
• Paclitaxel-carboplatin alone or with bevacizumab for non-small-cell lung cancer.

  2006cited by this paper
• Diagnostic agreement in the histopathological evaluation of lung cancer tissue in a population-based case-control study.

  2006cited by this paper
• CellProfiler: image analysis software for identifying and quantifying cell phenotypes

  2006cited by this paper
• Computerized morphometry as an aid in determining the grade of dysplasia and progression to adenocarcinoma in Barrett's esophagus

  2006cited by this paper
• Two subclasses of lung squamous cell carcinoma with different gene expression profiles and prognosis identified by hierarchical clustering and non-negative matrix factorization

  2005cited by this paper
• : Diagnosis and Management

  2005cited by this paper
• Clinical impact and frequency of anatomic pathology errors in cancer diagnoses

  2005cited by this paper
• ROCR: visualizing classifier performance in R

  2005cited by this paper
• Gene-expression profiles predict survival of patients with lung adenocarcinoma

  2002cited by this paper
• Diagnoses

  2001cited by this paper
• Snoring, pregnancy-induced hypertension, and growth retardation of the fetus.

  2000cited by this paper
• Diagnosis of lung cancer: pathology of invasive and preinvasive neoplasia.

  2000cited by this paper
• Bayesian Network Classifiers

  1997cited by this paper
• A prognostic model of recurrence and death in stage I non-small cell lung cancer utilizing presentation, histopathology, and oncoprotein expression.

  1995influential reference
• Support-Vector Networks

  1995cited by this paper
• Cancer statistics

  1989cited by this paper
• Paradigm shift

  1989cited by this paper
• A Threshold Selection Method from Gray-Level Histograms

  1979cited by this paper
• The fine structure of large cell undifferentiated carcinoma of the lung. Evidence for its relation to squamous cell carcinomas and adenocarcinomas.

  1978cited by this paper

• Prototype-driven fusion of pathology and spatial transcriptomics for interpretable survival prediction

  2026cites this paper
• Integrating Omics and Pathological Imaging Data for Cancer Prognosis via a Deep Neural Network‐Based Cox Model

  2026cites this paper
• Impacts of artificial intelligence on healthcare business models and outcomes

  2026cites this paper
• PREPARE ALL: An Artificial Intelligence Tool for Predicting Relapse in Children With Acute Lymphoblastic Leukemia.

  2026cites this paper
• Artificial intelligence-based miRNA analysis for precision oncology: diagnostic and prognostic insights

  2026cites this paper
• A continuously coupled attention neural network for MSI status classification in whole slide images

  2026cites this paper
• Combined Use of Microwave Sensing Technologies and Artificial Intelligence for Biomedical Monitoring and Imaging

  2026cites this paper
• A pathomics-based pyroptosis signature predicts survival in clear cell renal cell carcinoma.

  2026cites this paper
• Lung Cancer in the New Era: Trends, Innovations, and Future Recommendations

  2026cites this paper
• Biological feature-based machine learning in histopathological images: a systematic review

  2026cites this paper
• Artificial Intelligence in Oncologic Thoracic Surgery: Clinical Decision Support and Emerging Applications

  2026influential citation
• Subtype classification of gastric spindle cell tumors in whole slide images

  2025cites this paper
• Integrating radiomics, pathomics, and biopsy-adapted immunoscore for predicting distant metastasis in locally advanced rectal cancer

  2025cites this paper
• AI-Based Models for Risk Prediction in MASLD: A Systematic Review.

  2025cites this paper
• Bio-interpretable ensemble learning model for invasive pulmonary adenocarcinoma grade using CT and histopathology images

  2025cites this paper
• Artificial intelligence in digital pathology diagnosis and analysis: technologies, challenges, and future prospects

  2025influential citation
• Artificial intelligence in cancer: applications, challenges, and future perspectives

  2025cites this paper
• Application of AI in medical imaging of lung cancer

  2025influential citation
• HSFSurv: A hybrid supervision framework at individual and feature levels for multimodal cancer survival analysis

  2025cites this paper
• Understanding and tackling the modality imbalance problem in multimodal survival prediction

  2025cites this paper
• Prospects and challenges of deep learning in gynecologic malignancies

  2025cites this paper
• A Novel Approach on Modularized MLP-Mixer for Automated Histopathological Classification of Lung and Colon Cancers

  2025cites this paper
• A High-Resolution Digital Pathological Image Staining Style Transfer Model Based on Gradient Guidance

  2025cites this paper
• Bayesian Modeling of Cancer Outcomes Using Genetic Variables Assisted by Pathological Imaging Data

  2025cites this paper
• Artificial intelligence for diagnosis and predictive biomarkers in Non-Small cell lung cancer Patients: New promises but also new hurdles for the pathologist.

  2025cites this paper
• Advancing personalised and precision medicine through artificial intelligence: Current insights and future directions

  2025cites this paper
• A depth-wise separable residual neural network for PCDH8 status prediction in thyroid cancer pathological images

  2025cites this paper
• Integrative molecular–radiopathomic characterization of AIRE-driven immune subtypes in bladder cancer

  2025cites this paper
• Quantifying Nuclear Structures of Digital Pathology Images Across Cancers Using Transport‐Based Morphometry

  2025cites this paper
• A deep learning framework to iDentify prOgnostically releVant cancEr Regions (DOVER) within whole slide histopathology images.

  2025cites this paper
• AI Prognostication in Nonsmall Cell Lung Cancer: A Systematic Review.

  2025cites this paper
• Machine learning-based histopathological features of histological slides and clinical characteristics as a novel prognostic indicator in diffuse large B-cell lymphoma.

  2025cites this paper
• Accurate prediction of disease-free and overall survival in non-small cell lung cancer using patient-level multimodal weakly supervised learning

  2025cites this paper
• Artificial Intelligence in Thoracic Surgery: Transforming Diagnostics, Treatment, and Patient Outcomes

  2025cites this paper
• Artificial intelligence entering the pathology arena in oncology: current applications and future perspectives.

  2025cites this paper
• Current and future applications of artificial intelligence in lung cancer and mesothelioma

  2025cites this paper
• Emerging Techniques of Translational Research in Immuno-Oncology: A Focus on Non-Small Cell Lung Cancer

  2025cites this paper
• Multi-platform integration of histopathological images and omics data predicts molecular features and prognosis of hepatocellular carcinoma

  2025cites this paper
• Deep learning-based identification of necrosis and microvascular proliferation in adult diffuse gliomas from whole-slide images

  2025cites this paper
• Deep learning enhances precision diagnosis and treatment of non-small cell lung cancer: future prospects

  2025cites this paper
• Deep Learning-Driven Multimodal Integration of miRNA and Radiomic for Lung Cancer Diagnosis

  2025cites this paper
• Towards Understanding and Harnessing the Transferability of Prognostic Knowledge in Computational Pathology

  2025cites this paper
• Decoding the human tongue of light chain amyloidosis in three dimensions (3D): three-dimensional pathological visualization drives early and precise screening of suspected cases

  2025cites this paper
• Terpenoids modulation of the IFI16-AIM2 interaction for enhanced immune response in lung squamous cell carcinoma and AIM2-dysregulated diseases

  2025cites this paper
• A multimodal whole-slide foundation model for pathology

  2025cites this paper
• Preoperative CT-based artificial intelligence-derived quantitative parameters and imaging features for predicting the invasiveness of histologically confirmed subcentimeter adenocarcinomatous nodules: a two-center study

  2025cites this paper
• TAD-Graph: Enhancing Whole Slide Image Analysis via Task-Aware Subgraph Disentanglement

  2025cites this paper
• AI-based methods for modelling whole-slide imaging data in cancer diagnosis and transcriptome profile prediction

  2025cites this paper
• Advanced hybrid deep learning model for enhanced evaluation of osteosarcoma histopathology images

  2025cites this paper
• Multi-omics models for predicting prognosis in non-small cell lung cancer patients following chemotherapy and radiotherapy: A multi-center study.

  2025cites this paper
• Facilitating Selection with Artificial Intelligence-Based Glypican-3 Expression Quantification in Patients with Solid Tumors

  2025cites this paper
• Azurin a potent anticancer and antimicrobial agent isolated from a novel Pseudomonas aeruginosa strain

  2025cites this paper
• A deep‐learning model for predicting tyrosine kinase inhibitor response from histology in gastrointestinal stromal tumor

  2025cites this paper
• Identifying invasiveness to aid lung adenocarcinoma diagnosis using deep learning and pathomics

  2025influential citation
• Public Awareness of and Attitudes Toward the Use of AI in Pathology Research and Practice: Mixed Methods Study

  2025cites this paper
• Spatiotemporal feature learning for actin dynamics

  2025cites this paper
• Multi-modal radiomics features to predict overall survival of locally advanced esophageal cancer after definitive chemoradiotherapy

  2025cites this paper
• Multimodal AI framework for lung cancer diagnosis: Integrating CNN and ANN models for imaging and clinical data analysis

  2025cites this paper
• Novel feature-based method for multi-modal biomedical image registration compared to intensity-based technique

  2025cites this paper
• Comprehensive analysis of malignant subtypes of lung adenocarcinoma based on multi-omics landscape and functional validation of prognostic biomarker BAIAP2L2

  2025cites this paper
• Contrastive learning enhances fairness in pathology artificial intelligence systems

  2025cites this paper
• MCLAM: a cost-effective deep learning model for predicting recurrence risk in HR+/HER2− breast cancer — a multi-center study in a Chinese cohort

  2025cites this paper
• The Application and Challenges of Histopathology Techniques in the Diagnosis, Treatment, and Prognostic Evaluation of Lung Cancer

  2025cites this paper
• Flexible Framework for Lung and Colon Cancer Automated Analysis Across Multiple Diagnosis Scenarios

  2025cites this paper
• PathOrchestra: a comprehensive foundation model for computational pathology with over 100 diverse clinical-grade tasks

  2025cites this paper
• Enhanced Multi-Scale Convolutional Neural Network with Attention Mechanism for Accurate and Efficient Automated Hematological Diagnostics from Blood Smear

  2025cites this paper
• Automated segmentation of intracranial carotid atherosclerosis in histological images: assessing the effect of staining

  2025cites this paper
• Multiscale transformers and multi-attention mechanism networks for pathological nuclei segmentation

  2025cites this paper
• Integration of histopathological image features and multi-dimensional omics data in predicting molecular features and survival in glioblastoma

  2025cites this paper
• Deep learning radiopathomics predicts targeted therapy sensitivity in EGFR-mutant lung adenocarcinoma

  2025cites this paper
• Integrating multimodal data and machine learning for entrepreneurship research

  2025cites this paper
• Advancements and future trends in machine learning for lung cancer: a comprehensive bibliometric analysis

  2025cites this paper
• Exploring AI tools and multi-omics for precision medicine in lung cancer therapy.

  2025cites this paper
• Multiscale-fusion models with genomic, topological and pathomic features to predict response to radiation therapy for non-small cell lung cancer patients.

  2025cites this paper
• Artificial intelligence in pediatric healthcare: current applications, potential, and implementation considerations

  2025cites this paper
• Advanced Cloud Framework for Lung Cancer Diagnosis and Severity Evaluation in Deep Learning

  2025cites this paper
• Machine learning for genomic profiling and drug discovery in personalised lung cancer therapeutics

  2025cites this paper
• Histology image analysis of 13 healthy tissues reveals molecular-histological correlations

  2025cites this paper
• AI Assisted Diagnosis in Pathological Diagnosis

  2025cites this paper
• Building digital histology models of transcriptional tumor programs with generative deep learning for pathology-based precision medicine

  2025cites this paper
• Cross-Cancer Knowledge Transfer in WSI-based Prognosis Prediction

  2025cites this paper
• RiskPath: Explainable deep learning for multistep biomedical prediction in longitudinal data

  2025cites this paper
• Transformer based on multi-scale local feature for colon cancer histopathological image classification

  2025cites this paper
• CISCA and CytoDArk0: A cell instance segmentation and classification method for histo(patho)logical image Analyses and a new, open, Nissl-stained dataset for brain cytoarchitecture studies

  2025cites this paper
• Applications and future prospects of artificial intelligence in the diagnosis and prognosis of lung cancer

  2025cites this paper
• EGFR Mutation Detection in Whole Slide Images of Non‐Small Cell Lung Cancers Using a Two‐Stage Deep Transfer Learning Approach

  2025cites this paper
• Denoising spatially resolved transcriptomics with consistency of heterogeneous spatial coordinates, transcription, and morphology

  2025cites this paper
• Pathology image-based predictive model for individual survival time of early-stage lung adenocarcinoma patients

  2025cites this paper
• Artificial intelligence in thoracic surgery: Perspectives and challenges

  2025cites this paper
• Understand how machine learning impact lung cancer research from 2010 to 2021: A bibliometric analysis

  2024cites this paper
• MIF: Multi-Shot Interactive Fusion Model for Cancer Survival Prediction Using Pathological Image and Genomic Data

  2024cites this paper
• AI-Enabled Lung Cancer Prognosis

  2024cites this paper
• Prediction of Tuberculosis From Lung Tissue Images of Diversity Outbred Mice Using Jump Knowledge Based Cell Graph Neural Network

  2024cites this paper
• Multi-Instance Multi-Task Learning for Joint Clinical Outcome and Genomic Profile Predictions From the Histopathological Images

  2024influential citation
• Inflammation-related molecular signatures involved in the anticancer activities of brigatinib as well as the prognosis of EML4-ALK lung adenocarcinoma patient

  2024cites this paper
• Computational pathology: A survey review and the way forward

  2024cites this paper
• Predicting Neuroblastoma Patient Risk Groups, Outcomes, and Treatment Response Using Machine Learning Methods: A Review

  2024influential citation
• Cyto R-CNN and CytoNuke Dataset: Towards reliable whole-cell segmentation in bright-field histological images

  2024cites this paper
• Future of Artificial Intelligence in Surgery: A Narrative Review

  2024cites this paper
• Heterogeneity of computational pathomic signature predicts drug resistance and intra-tumor heterogeneity of ovarian cancer

  2024cites this paper