Abstract
Tumor histology is an important predictor of therapeutic response and outcomes in lung cancer. Tissue sampling for pathologist review is the most reliable method for histology classification, however, recent advances in deep learning for medical image analysis allude to the utility of radiologic data in further describing disease characteristics and for risk stratification. In this study, we propose a radiomics approach to predicting non-small cell lung cancer (NSCLC) tumor histology from non-invasive standard-of-care computed tomography (CT) data. We trained and validated convolutional neural networks (CNNs) on a dataset comprising 311 early-stage NSCLC patients receiving surgical treatment at Massachusetts General Hospital (MGH), with a focus on the two most common histological types: adenocarcinoma (ADC) and Squamous Cell Carcinoma (SCC). The CNNs were able to predict tumor histology with an AUC of 0.71(p = 0.018). We also found that using machine learning classifiers such as k-nearest neighbors (kNN) and support vector machine (SVM) on CNN-derived quantitative radiomics features yielded comparable discriminative performance, with AUC of up to 0.71 (p = 0.017). Our best performing CNN functioned as a robust probabilistic classifier in heterogeneous test sets, with qualitatively interpretable visual explanations to its predictions. Deep learning based radiomics can identify histological phenotypes in lung cancer. It has the potential to augment existing approaches and serve as a corrective aid for diagnosticians.
Highlights
Radiomics has emerged as a tool for quantifying solid tumor phenotype through the extraction of quantitative radiographic features[15]
While radiomics has primarily relied on the explicit extraction of hand-crafted imaging features[17,19], more recent studies have shifted towards deep learning—convolutional neural networks (CNNs) —where representative features are learned automatically from d ata[20,21,22,23,24,25,26]
Building on data collected through the comprehensive Boston Lung Cancer Survival (BLCS) cohort, we created deep learning models that can act as non-invasive pathological biomarkers for non-small cell lung cancer (NSCLC)
Summary
Radiomics has emerged as a tool for quantifying solid tumor phenotype through the extraction of quantitative radiographic features[15]. While radiomics has primarily relied on the explicit extraction of hand-crafted imaging features[17,19], more recent studies have shifted towards deep learning—convolutional neural networks (CNNs) —where representative features are learned automatically from d ata[20,21,22,23,24,25,26]. This has fostered the construction of advanced multi-parametric algorithms for cognitive decision-making in many clinical settings[14]. This preliminary work demonstrates the potential for deep learning based radiomics to enhance the human-based decision tree for NSCLC histology classification
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
