Unsupervised machine learning of radiomic features for predicting treatment response and overall survival of early stage non-small cell lung cancer patients treated with stereotactic body radiation therapy

Abstract

Background and purpose: To predict treatment response and survival of NSCLC patients receiving stereotactic body radiation therapy (SBRT), we develop an unsupervised machine learning method for stratifying patients and extracting meta-features simultaneously based on imaging data. Material and methods: This study was performed based on an 18F-FDG-PET dataset of 100 consecutive patients who were treated with SBRT for early stage NSCLC. Each patient’s tumor was characterized by 722 radiomic features. An unsupervised two-way clustering method was used to identify groups of patients and radiomic features simultaneously. The groups of patients were compared in terms of survival and freedom from nodal failure. Meta-features were computed for building survival models to predict survival and free of nodal failure. Results: Differences were found between 2 groups of patients when the patients were clustered into 3 groups in terms of both survival (p = 0.003) and freedom from nodal failure (p = 0.038). Average concordance measures for predicting survival and nodal failure were 0.640 ± 0.029 and 0.664 ± 0.063 respectively, better than those obtained by prediction models built upon clinical variables (p < 0.04). Conclusions: The evaluation results demonstrate that our method allows us to stratify patients and predict survival and freedom from nodal failure with better performance than current alternative methods.

NCTN Assessment on Current Applications of Radiomics in Oncology

“…Radiomics features from CT, PET/CT, and cone beam CT have also shown predictive value for response to treatment. [16][17][18][19][20][21][22][23][24] Investigators analyzed the daily noncontrast CT scans, acquired during routine image-guided radiation therapy using in-room CT, from patients with head and neck, 25 lung, 26 and pancreatic cancers. 27 They reported that radiation can induce patient-specific changes in CT texture features and that these changes can be detected in the early phase of radiation therapy.…”

Machine Learning and Deep Neural Networks in Thoracic and Cardiovascular Imaging

“…This was achieved using an unsupervised clustering analysis method based on distinctive radiographic imaging features. 42 This field of image analysis, termed "radiomics," is geared at characterizing image features and correlating them with a tumor phenotype, with the intent of classifying and staging tumors noninvasively. Extracted features convert radiographic images into mineable data and can be utilized to build predictive and prognostic models.…”

Die Wichtigkeit des „Machine Learning“ und der Texturanalyse in der Onkologie anhand der Fusionsbildgebung

“…Dies führt im Endeffekt zu patientenindividuellen prognostischen Faktoren sowie patientenindividuellen prädiktiven Faktoren. Letztlich werden daraus eine Therapiestratifizierung sowie eine Therapiesequenzierung gefolgert und die Lebensqualität des Patienten maßgeblich beeinflusst [11].…”

“…Ein weiteres Einsatzgebiet für die Texturanalyse könnte zukünftig auch die Evaluation des Therapieansprechens sein, da bereits gezeigt werden konnte, dass die Texturanalyse der FDG-PET/CT Responder von Non-Respondern schon während des Therapiestarts unterscheiden konnte [3]. Es besteht bereits eine unbeaufsichtigte Clustermethode im Rahmen des "Machine Learning", um das Therapieansprechen und das allgemeine Überleben von bestrahlten NSCLC-Patienten zu überprüfen, die das Überleben und die nodale Rezidivfreiheit besser vorhersagen konnte als gängige Alternativmethoden [11].…”