Lung Nodule Classification Using Biomarkers, Volumetric Radiomics, and 3D CNNs

Abstract

We present a hybrid algorithm to estimate lung nodule malignancy that combines imaging biomarkers from Radiologist’s annotation with image classification of CT scans. Our algorithm employs a 3D Convolutional Neural Network (CNN) as well as a Random Forest in order to combine CT imagery with biomarker annotation and volumetric radiomic features. We analyze and compare the performance of the algorithm using only imagery, only biomarkers, combined imagery + biomarkers, combined imagery + volumetric radiomic features, and finally the combination of imagery + biomarkers + volumetric features in order to classify the suspicion level of nodule malignancy. The National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) IDRI dataset is used to train and evaluate the classification task. We show that the incorporation of semi-supervised learning by means of K-Nearest-Neighbors (KNN) can increase the available training sample size of the LIDC-IDRI, thereby further improving the accuracy of malignancy estimation of most of the models tested although there is no significant improvement with the use of KNN semi-supervised learning if image classification with CNNs and volumetric features is combined with descriptive biomarkers. Unexpectedly, we also show that a model using image biomarkers alone is more accurate than one that combines biomarkers with volumetric radiomics, 3D CNNs, and semi-supervised learning. We discuss the possibility that this result may be influenced by cognitive bias in LIDC-IDRI because malignancy estimates were recorded by the same radiologist panel as biomarkers, as well as future work to incorporate pathology information over a subset of study participants.

3D multi‐resolution attention capsule network for diagnosing multi‐pathological types of pulmonary nodules

“…The difference between 3D MRA‐CapsNet‐DL_B and the best SVM fusion model is only 0.73%. Compared with some binary classification methods in literatures, 39–42 although our results are partially suboptimal, our performed four‐classification task is more difficult than the binary classification tasks. In addition, the constructed aided diagnosis model does not need to design and extract traditional manual features, nor does it use additional supplementary information such as serum biomarkers, and it can achieve good and stable performance in the classification of multiple pathological types of pulmonary nodules by only using CT image information.…”

“…In order to more comprehensively verify the classification performance of the constructed 3D MRA‐CapsNet‐DL aided diagnosis model, we compared the 3D MRA‐CapsNet‐DL model with six multi‐modal fusion models 16,17,39–42 . The comparison results are shown in Table 6.…”

“…In order to more comprehensively verify the classification performance of the constructed 3D MRA-CapsNet-DL aided diagnosis model, we compared the 3D MRA-CapsNet-DL model with six multi-modal fusion models. 16,17,[39][40][41][42] The comparison results are shown in Table 6. Compared with the two models constructed in literature, 16 the aided diagnosis models based on 3D MRA-CapsNet-DL do not use serum biomarker information and has a larger number of classifications, but still achieves higher and more stable AUC scores.…”

Radiomics in Lung Diseases Imaging: State-of-the-Art for Clinicians

“…Early works on convolutional neural networks (CNNs) compared to computer-aided detection/diagnosis (CAD) demonstrated a superiority of the radiomic approach in nodule classification, with a decrease in false positives, possibly reducing the need of several follow-ups [ 19 , 20 , 21 ]. Mehta et al combined biomarkers, volumetric radiomics, and 3D CNNs to reach an algorithm classifying lung nodules [ 22 ]. Concerning histological subtyping, numerous studies have demonstrated the correlation between radiomic features and histology.…”

Evaluating Histological Subtypes Classification of Primary Lung Cancers on Unenhanced Computed Tomography Based on Random Forest Model

“…Lung cancer is the leading cause of cancer-related death in many countries, and the accurate histopathological diagnosis is of great importance in subsequent treatment [11,12]. In previous studies, the RF model was mostly applied to detecting lung cancer, the classifcation of benign and malignant pulmonary nodules, and the analysis of lung cancer prognosis [13][14][15][16]. However, for therapeutic purposes, primary lung cancers fall into three major subtypes: lung adenocarcinoma (ADC), lung squamous cell carcinoma (SCC), and small cell lung cancer (SCLC), and distinguishing among subtypes is still particularly challenging.…”