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

By Kun-Hsing Yu, Ce Zhang, Gerald J. Berry, Russ B. Altman, Christopher R'e, Daniel L. Rubin, Michael Snyder. Nature Communications, 2016

909 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Oncology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/94087ad5ed11555c260a42f2f9ca9da183c6f87e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Oncology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Innovative approaches for cancer treatment: current perspectives and new challenges (2019, background): “Radiomics and pathomics are two promising and innovative fields based on accumulating quantitative image features from radiology and pathology screenings as therapeutic and prognostic indicators of disease outcome [12, 13, 230].”
Machine Learning Methods for Histopathological Image Analysis (2017, background): “Other researches include prognosis predictions from histopathological image of cancer [37], prediction of somatic mutation [13], and discovery of new gene variants related to autoimmune thyroiditis based on image QTL [38].”
Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks (2020, methodology): “Following the recent framework [14], we extracted 10 dense image patches from ROIs and calculated hand-crafted features using CellProfiler [54] which serves as a state-of-the-art medical image feature extracting and quantitative analysis tool.”
Clinical Trials for Artificial Intelligence in Cancer Diagnosis: A Cross-Sectional Study of Registered Trials in ClinicalTrials.gov (2020, methodology): “(22) reported that the automatic analysis method of AI could perform pathological image analysis to predict the prognosis of patients with lung cancer.”
Introduction to artificial intelligence in medicine (2019, background): “In a study using 2186 stained histopathology whole-slide images of lung adenocarcinoma and squamous cell carcinoma, Yu et al. demonstrated the accuracy of AI for pathological diagnosis [35].”
Integrative omics for health and disease (2018, methodology): “Finally, integration of imaging information with omics information is expected to be valuable in cancer diagnosis and prognosis 66,67 .”
Methods for Segmentation and Classification of Digital Microscopy Tissue Images (2018, methodology): “(Yu et al. 2016) extracted a range of quantitative image features from tissue regions and used an array of classical machine techniques to classify each WSI.”
A Two-pronged Progress in Structured Dense Matrix Vector Multiplication (2018, methodology): “In fact, our investigation into structured matrix-vector multiplication problems started with some applied work on Zernike polynomials, and our results applied to fast Zernike transforms have been used in improved cancer imaging [58].”
Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine (2020, background): “radiology (71) (early diagnosis, enhance visualization of pathologies and predicting emergency situations (64,73,71)), oncology (diagnosis of breast (75), skin (76), lung cancer (77)), cardiology (interpreting electrocardiogram readings, echocardiography with 3D cardiac imaging, cardiac CT angiograp”
High-performance medicine: the convergence of human and artificial intelligence (2019, background): “Marked heterogeneity and inconsistency among pathologists’ interpretations of slides has been amply documented, exemplified by a lack of agreement in diagnosis of common types of lung cancer ( Κ = 0.41–0.46) 40 .”