Radiomics in Head and Neck Cancer Outcome Predictions

Abstract

Head and neck cancer has great regional anatomical complexity, as it can develop in different structures, exhibiting diverse tumour manifestations and high intratumoural heterogeneity, which is highly related to resistance to treatment, progression, the appearance of metastases, and tumour recurrences. Radiomics has the potential to address these obstacles by extracting quantitative, measurable, and extractable features from the region of interest in medical images. Medical imaging is a common source of information in clinical practice, presenting a potential alternative to biopsy, as it allows the extraction of a large number of features that, although not visible to the naked eye, may be relevant for tumour characterisation. Taking advantage of machine learning techniques, the set of features extracted when associated with biological parameters can be used for diagnosis, prognosis, and predictive accuracy valuable for clinical decision-making. Therefore, the main goal of this contribution was to determine to what extent the features extracted from Computed Tomography (CT) are related to cancer prognosis, namely Locoregional Recurrences (LRs), the development of Distant Metastases (DMs), and Overall Survival (OS). Through the set of tumour characteristics, predictive models were developed using machine learning techniques. The tumour was described by radiomic features, extracted from images, and by the clinical data of the patient. The performance of the models demonstrated that the most successful algorithm was XGBoost, and the inclusion of the patients’ clinical data was an asset for cancer prognosis. Under these conditions, models were created that can reliably predict the LR, DM, and OS status, with the area under the ROC curve (AUC) values equal to 0.74, 0.84, and 0.91, respectively. In summary, the promising results obtained show the potential of radiomics, once the considered cancer prognosis can, in fact, be expressed through CT scans.

Head and neck cancer treatment outcome prediction: a comparison between machine learning with conventional radiomics features and deep learning radiomics

“…For HNSCC, radiomics has been used for prediction of treatment outcomes including locoregional control (LRC), distant metastases (DM), disease-free survival (DFS), progression-free survival (PFS), and overall survival (OS) (15)(16)(17)(18)(19)(20)(21)(22), as well as nodal failure (23,24), HPV status (10), and xerostomia (25). Radiomics features from multimodality images can improve radiomics model performance relative to single-modality features in some but not all cases (19,26).…”

Value of clinical features combined with multimodal ultrasound in predicting lymph node metastasis in cervical central area of papillary thyroid carcinoma

“…Radiomics is less affected by the operator's professional knowledge. Through innovative machine learning technology, medical imaging data is transformed into features related to biological parameters, which are applied to predict the accuracy of diagnosis and prognosis 19 . Previous studies have proved the feasibility of evaluating the risk of lateral cervical lymph node metastasis (LNM) in PTC patients based on gray‐scale ultrasound imaging analysis 20 .…”

A novel loss function to reproduce texture features for deep learning‐based MRI‐to‐CT synthesis

“…For instance, there was a dependency between the predictive accuracy and texture features of gross tumor volume for head and neck patients. 21 There were four major processing tasks included: (a) image acquisition, (b) ROI segmentation, (c) radiomics feature extraction, and (d) statistical modeling. 22 If the established model would be put into practice, the robustness tends to be challenged.…”

“…The radiomics studies are based on analyzing the texture features of specific ROIs. For instance, there was a dependency between the predictive accuracy and texture features of gross tumor volume for head and neck patients 21 . There were four major processing tasks included: (a) image acquisition, (b) ROI segmentation, (c) radiomics feature extraction, and (d) statistical modeling 22 .…”