Clinical, Conventional CT and Radiomic Feature-Based Machine Learning Models for Predicting ALK Rearrangement Status in Lung Adenocarcinoma Patients

Abstract

Objectives: To predict the anaplastic lymphoma kinase (ALK) mutations in lung adenocarcinoma patients non-invasively with machine learning models that combine clinical, conventional CT and radiomic features. Methods: This retrospective study included 335 lung adenocarcinoma patients who were randomly divided into a primary cohort (268 patients; 90 ALK-rearranged; and 178 ALK wild-type) and a test cohort (67 patients; 22 ALK-rearranged; and 45 ALK wild-type). One thousand two hundred and eighteen quantitative radiomic features were extracted from the semi-automatically delineated volume of interest (VOI) of the entire tumor using both the original and the pre-processed non-enhanced CT images. Twelve conventional CT features and seven clinical features were also collected. Normalized features were selected using a sequential of the F-test-based method, the density-based spatial clustering of applications with noise (DBSCAN) method, and the recursive feature elimination (RFE) method. Selected features were then used to build three predictive models (radiomic, radiological, and integrated models) for the ALK-rearranged phenotype by a soft voting classifier. Models were evaluated in the test cohort using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity, and the performances of three models were compared using the DeLong test. Results: Our results showed that the addition of clinical information and conventional CT features significantly enhanced the validation performance of the radiomic model in the primary cohort (AUC = 0.83-0.88, P = 0.01), but not in the test cohort (AUC = 0.80-0.88, P = 0.29). The majority of radiomic features associated with ALK mutations reflected information around and within the high-intensity voxels of lesions. The presence of the cavity and left lower lobe location were new imaging phenotypic patterns Song et al. Radiomic-Based Model for ALK Mutations in association with ALK-rearranged tumors. Current smoking was strongly correlated with non-ALK-mutated lung adenocarcinoma. Conclusions: Our study demonstrates that radiomics-derived machine learning models can potentially serve as a non-invasive tool to identify ALK mutation of lung adenocarcinoma.

A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma

“…In order to non-invasively identify patients with ALK mutations, this study intends to develop a predictive radiomic model based on PET/CT images. Recently, several machine learning models based on CT images and clinical features have been developed to predict ALK rearrangement in lung adenocarcinoma (24,39). The aim of the current study is to construct a machine learning model that can be used to non-invasively and automatically detect ALK mutation based on PET/CT images from tumor lesions of lung adenocarcinoma patients and clinical characteristics of these patients.…”

“…Recently, Song et al. developed a machine learning model based on CT radiomic features to predict ALK rearrangement status for lung adenocarcinoma patients ( 24 ).…”

“…Arbour et al showed that ALK rearranged NSCLC primary tumor CT imaging features are different from those of EGFR mutated or wide type NSCLC (3). Recently, Song et al developed a machine learning model based on CT radiomic features to predict ALK rearrangement status for lung adenocarcinoma patients (24).…”

Structural and functional radiomics for lung cancer

“…With the development of personalized treatment for lung cancer, the identification of therapeutically actionable mutations ((e.g., Epidermal growth factor receptor (EGFR), anaplastic lymphoma kinase (ALK), programmed cell death 1 ligand, (PD-L1), and v-Raf murine sarcoma viral oncogene homolog B1 (BRAF)) has been a significant premises for an optimal treatment strategy. Thanks to the existence of noninvasive, simple, and low cost of radiomics compared to gene detection, which has demonstrated strong predictive efficacy for the mutation type and can used as an alternative method [79][80][81][82]. In addition to predicting the status of gene mutations, some studies aimed to directly predict the treatment response, such as Immunotherapy, chemotherapy, and radiotherapy [83][84][85][86].…”

CT Radiomics and Morphologic Characteristics for Predicting PD-L1 Expression on Tumour Cells and Tumour Infiltrating Lymphocytes in Gastric Cancer

“…To our limited knowledge, no study has been conducted to predict PD-L1 and PD-L1-TILs expressions in GC based on CT radiomics. Moreover, there is a substantial interest in the use of machine learning algorithms for selecting optimal radiomic features from medical images and applying them to tumour evaluation, as well as in the improvement of diagnostic e cacy [20,21].…”