Radiomics in Nasopharyngeal Carcinoma

Abstract

Nasopharyngeal carcinoma (NPC) is one of the most common head and neck malignancies, and the primary treatment methods are radiotherapy and chemotherapy. Radiotherapy alone, concurrent chemoradiotherapy, and induction chemotherapy combined with concurrent chemoradiotherapy can be used according to different grades. Treatment options and prognoses vary greatly depending on the grade of disease in the patients. Accurate grading and risk assessment are required. Recently, radiomics has combined a large amount of invisible high-dimensional information extracted from computed tomography, magnetic resonance imaging, or positron emission tomography with powerful computing capabilities of machine-learning algorithms, providing the possibility to achieve an accurate diagnosis and individualized treatment for cancer patients. As an effective tumor biomarker of NPC, the radiomic signature has been widely used in grading, differential diagnosis, prediction of prognosis, evaluation of treatment response, and early identification of therapeutic complications. The process of radiomic research includes image segmentation, feature extraction, feature selection, model establishment, and evaluation. Many open-source or commercial tools can be used to achieve these procedures. The development of machine-learning algorithms provides more possibilities for radiomics research. This review aimed to summarize the application of radiomics in NPC and introduce the basic process of radiomics research.

Review of functional magnetic resonance imaging in the assessment of nasopharyngeal carcinoma treatment response

“…Instead, by making use of predefined mathematical formulae or intermediate layers from deeplearning, high-dimensional radiomics features can be extracted. With the use of machine learning and deep learning (artificial intelligence), 71 model building with clinical data for local recurrence, 72 distant metastasis, 73 prognosis, 72,[74][75][76] and toxicity prediction 77,78…”

“…Instead, by making use of predefined mathematical formulae or intermediate layers from deep‐learning, high‐dimensional radiomics features can be extracted. With the use of machine learning and deep learning (artificial intelligence), 71 model building with clinical data for local recurrence, 72 distant metastasis, 73 prognosis, 72,74–76 and toxicity prediction 77,78 become implementable. Researchers carried out studies on the risk of local recurrence and prognosis prediction in NPC patients with radiomics features extracted from Computed Tomography (CT) images 79,80 .…”

Radiomics for Discrimination between Early-Stage Nasopharyngeal Carcinoma and Benign Hyperplasia with Stable Feature Selection on MRI

“…Radiomics involves high-throughput analyses of radiology features for the characterization of tissues, which offers the possibility of sparing invasive procedures and accelerating the workflow in many clinical aspects, including cancer management for NPC [ 10 , 11 ]. Radiomics analysis generally relies on handcrafted features that have better transparency compared to CNNs and is therefore a natural candidate with respect to our interest in discrimination of the two considered abnormalities.…”

“…Therefore, we are interested in searching for a comprehensive analytical method that can discriminate between NPC and BH, such that we could eventually develop a transparent system that can be widely applied in future NPC screening programs. Radiomics involves high-throughput analyses of radiology features for the characterization of tissues, which offers the possibility of sparing invasive procedures and accelerating the workflow in many clinical aspects, including cancer management for NPC [10,11]. Radiomics analysis generally relies on handcrafted features that have better transparency compared to CNNs and is therefore a natural candidate with respect to our interest in discrimination of the two considered abnormalities.…”

Application of radiomics in the differential diagnosis in ameloblastomas and dentigerous cysts. Part 2

“…In the past few years, radiomics has been used for diagnosis Nasopharyngeal carcinoma [3]; prediction of treatment response in non-small-cell lung cancer [4]; for preoperative prediction of microvascular invasion in hepatocellular carcinoma [5]; for the Non-Invasive Assessment of Coronary Inflammation [6]; in precision diagnosis, prognostication and treatment planning of head and neck squamous cell carcinomas [7]. Textural analysis of images in the studies was aimed at identifying prognostic biomarkers of disease imaging.…”