Utilizing Artificial Intelligence for Head and Neck Cancer Outcomes Prediction From Imaging.

Artificial intelligence (AI)-based models have become a growing area of interest in predictive medicine and have the potential to aid physician decision-making to improve patient outcomes. Imaging and radiomics play an increasingly important role in these models. This review summarizes recent developments in the field of radiomics for AI in head and neck cancer. Prediction models for oncologic outcomes, treatment toxicity, and pathological findings have all been created. Exploratory studies are promising; however, validation studies that demonstrate consistency, reproducibility, and prognostic impact remain uncommon. Prospective clinical trials with standardized procedures are required for clinical translation.

Predicting the need for a replan in oropharyngeal cancer: A radiomic, clinical, and dosimetric model.

BACKGROUND: Patients with oropharyngeal cancer (OPC) treated with chemoradiation can experience weight loss and tumor shrinkage, altering the prescribed treatment. Treatment replanning ensures patients do not receive excessive doses to normal tissue. However, it is a time- and resource-intensive process, as it takes 1 to 2 weeks to acquire a new treatment plan, and during this time, overtreatment of normal tissues could lead to increased toxicities. Currently, there are limited prognostic factors to determine which patients will require a replan. There remains an unmet need for predictive models to assist in identifying patients who could benefit from the knowledge of a replan prior to treatment. PURPOSE: We aimed to develop and evaluate a CT-based radiomic model, integrating clinical and dosimetric information, to predict the need for a replan prior to treatment. METHODS: A dataset of patients (n = 315) with OPC treated with chemoradiation was used for this study. The dataset was split into independent training (n = 220) and testing (n = 95) datasets. Tumor volumes and organs at risk (OARs) were contoured on planning CT images. PyRadiomics was used to compute radiomic image features (n = 1218) on the original and filtered images from each of the primary tumor, nodal volumes, and ipsilateral and contralateral parotid glands. Nine clinical features and nine dose features extracted from the OARs were collected and those significantly (p < 0.05) associated with the need for a replan in the training dataset were used in a baseline model. Random forest feature selection was applied to select the optimal radiomic features to predict replanning. Logistic regression, Naïve Bayes, support vector machine, and random forest classifiers were built using the non-correlated selected radiomic, clinical, and dose features on the training dataset and performance was assessed in the testing dataset. The area under the curve (AUC) was used to assess the prognostic value. RESULTS: A total of 78 patients (25%) required a replan. Smoking status, nodal stage, base of tongue subsite, and larynx mean dose were found to be significantly associated with the need for a replan in the training dataset and incorporated into the baseline model, as well as into the combined models. Five predictive radiomic features were selected (one nodal volume, one primary tumor, two ipsilateral and one contralateral parotid gland). The baseline model comprised of clinical and dose features alone achieved an AUC of 0.66 [95% CI: 0.51-0.79] in the testing dataset. The random forest classifier was the top-performing radiomics model and achieved an AUC of 0.82 [0.75-0.89] in the training dataset and an AUC of 0.78 [0.68-0.87] in the testing dataset, which significantly outperformed the baseline model (p = 0.023, testing dataset). CONCLUSIONS: This is the first study to use radiomics from the primary tumor, nodal volumes, and parotid glands for the prediction of replanning for patients with OPC. Radiomic features augmented clinical and dose features for predicting the need for a replan in our testing dataset. Once validated, this model has the potential to assist physicians in identifying patients that may benefit from a replan, allowing for better resource allocation and reduced toxicities.

External validation of a CT-based radiomics signature in oropharyngeal cancer: Assessing sources of variation.

BACKGROUND AND PURPOSE: Radiomics is a high-throughput approach that allows for quantitative analysis of imaging data for prognostic applications. Medical images are used in oropharyngeal cancer (OPC) diagnosis and treatment planning and these images may contain prognostic information allowing for treatment personalization. However, the lack of validated models has been a barrier to the translation of radiomic research to the clinic. We hypothesize that a previously developed radiomics model for risk stratification in OPC can be validated in a local dataset. MATERIALS AND METHODS: The radiomics signature predicting overall survival incorporates features derived from the primary gross tumor volume of OPC patients treated with radiation +/- chemotherapy at a single institution (n = 343). Model fit, calibration, discrimination, and utility were evaluated. The signature was compared with a clinical model using overall stage and a model incorporating both radiomics and clinical data. A model detecting dental artifacts on computed tomography images was also validated. RESULTS: The radiomics signature had a Concordance index (C-index) of 0.66 comparable to the clinical model's C-index of 0.65. The combined model significantly outperformed (C-index of 0.69, p = 0.024) the clinical model, suggesting that radiomics provides added value. The dental artifact model demonstrated strong ability in detecting dental artifacts with an area under the curve of 0.87. CONCLUSION: This work demonstrates model performance comparable to previous validation work and provides a framework for future independent and multi-center validation efforts. With sufficient validation, radiomic models have the potential to improve traditional systems of risk stratification, treatment personalization and patient outcomes.

Sarcopenia in head and neck cancer: A scoping review.

OBJECTIVES: In those undergoing treatment for head and neck cancer (HNC), sarcopenia is a strong prognostic factor for outcomes and mortality. This review identified working definitions and methods used to objectively assess sarcopenia in HNC. METHOD: The scoping review was performed in accordance with Arksey and O'Malley's five-stage methodology and the Joanna Briggs Institute guidelines. INFORMATION SOURCES: Eligible studies were identified using MEDLINE, Embase, Scopus, Cochrane Library, and CINAHL databases. STUDY SELECTION: Inclusion criteria represented studies of adult HNC patients in which sarcopenia was listed as an outcome, full-text articles written in English, and empirical research studies with a quantitative design. DATA EXTRACTION: Eligible studies were assessed using a proprietary data extraction form. General information, article details and characteristics, and details related to the concept of the scoping review were extracted in an iterative process. RESULTS: Seventy-six studies published internationally from 2016 to 2021 on sarcopenia in HNC were included. The majority were retrospective (n = 56; 74%) and the prevalence of sarcopenia ranged from 3.8% to 78.7%. Approximately two-thirds of studies used computed tomography (CT) to assess sarcopenia. Skeletal muscle index (SMI) at the third lumbar vertebra (L3) (n = 53; 70%) was the most prevalent metric used to identify sarcopenia, followed by SMI at the third cervical vertebra (C3) (n = 4; 5%). CONCLUSIONS: Currently, the most effective strategy to assess sarcopenia in HNC depends on several factors, including access to resources, patient and treatment characteristics, and the prognostic significance of outcomes used to represent sarcopenia. Skeletal muscle mass (SMM) measured at C3 may represent a practical, precise, and cost-effective biomarker for the detection of sarcopenia. However, combining SMM measurements at C3 with other sarcopenic parameters-including muscle strength and physical performance-may provide a more accurate risk profile for sarcopenia assessment and allow for a greater understanding of this condition in HNC.

Impact of radiofrequency ablation (RFA) on bone quality in a murine model of bone metastases.

Thermal therapies such as radiofrequency ablation (RFA) are gaining widespread clinical adoption in the local treatment of skeletal metastases. RFA has been shown to successfully destroy tumor cells, yet the impact of RFA on the quality of the surrounding bone has not been well characterized. RFA treatment was performed on femora of rats with bone metastases (osteolytic and osteoblastic) and healthy age matched rats. Histopathology, second harmonic generation imaging and backscatter electron imaging were used to characterize changes in the structure, organic and mineral components of the bone after RFA. RFA treatment was shown to be effective in targeting tumor cells and promoting subsequent new bone formation without impacting the surrounding bone negatively. Mineralization profiles of metastatic models were significantly improved post-RFA treatment with respect to mineral content and homogeneity, suggesting a positive impact of RFA treatment on the quality of cancer involved bone. Evaluating the impact of RFA on bone quality is important in directing the growth of this minimally invasive therapeutic approach with respect to fracture risk assessment, patient selection, and multimodal treatment planning.

Modern treatment outcomes for early T-stage oropharyngeal cancer treated with intensity-modulated radiation therapy at a tertiary care institution.

BACKGROUND: Transoral surgery (TOS), particularly transoral robotic surgery (TORS) has become the preferred modality in the United States for the treatment of early stage oropharyngeal cancer, largely due to assumptions of fewer toxicities and improved quality of life compared to primary radiotherapy (RT). However, these assumptions are based on retrospective analysis, a subset of which utilize primary RT groups not limited to T1-2 stage tumors for which transoral robotic surgery is FDA approved. Thus, there is potential for underestimating survival and overestimating toxicity, including treatment related mortality, in primary RT. METHODS: Consecutive cases of early T-stage (T1-T2) oropharyngeal cancer presenting to the London Health Sciences Centre between 2014 and 2018 treated with RT or chemoradiation (CRT) were reviewed. Patient demographics, treatment details, survival outcomes and toxicity were collected. Toxicities were retrospectively graded using the Common Terminology Criteria for Adverse Events criteria. RESULTS: A total of 198 patients were identified, of which 82% were male and 73% were HPV-positive. Sixty-eight percent of patients experienced a grade 2 toxicity, 48% a grade 3 and 4% a grade 4. The most frequent toxicities were dysphagia, neutropenia and ototoxicity. The rates of gastrostomy tube dependence at 1 and 2 years were 2.5% and 1% respectively. There were no grade 5 (fatal) toxicities. HPV-positive patients experienced improved 5-year overall survival (86% vs 64%, p = 0.0026). CONCLUSIONS: Primary RT or CRT provides outstanding survival for early T-stage disease, with low rates of severe toxicity and feeding tube dependence. This study provides a reference for comparison for patients treated with primary transoral surgery.

Preliminary Investigation of Focused Ultrasound-Facilitated Drug Delivery for the Treatment of Leptomeningeal Metastases.

Leptomeningeal metastases (LM) are a serious complication of cancer in the central nervous system (CNS) and are diagnosed in approximately 5% of patients with solid tumors. Effective treatment using systemically administered therapeutics is hindered by the barriers of the CNS. Ultrasound can mediate delivery of drugs through these barriers. The goal of this study was to test the feasibility of using ultrasound-mediated drug delivery to improve the treatment of LM. LM was induced in the spinal cord of athymic rats by injecting HER2-expressing breast cancer cells into the subarachnoid space of the thoracic spine. Animals were divided into three groups: no treatment (n = 5), trastuzumab only (n = 6) or trastuzumab + focused ultrasound + microbubbles (FUS + MBs) (n = 7). Animals in groups 2 and 3 were treated weekly with intravenous trastuzumab +/- FUS + MBs for three weeks. Suppression in tumor growth was qualitatively observed by MRI in the group receiving ultrasound, and was confirmed by a significant difference in the tumor volume measured from the histology data (25 ± 17 mm3 vs 8 ± 5 mm3, p = 0.04 in the trastuzumab-only vs trastuzumab + FUS + MBs). This pilot study demonstrates the potential of ultrasound-mediated drug delivery as a novel treatment for LM. Future studies will extend this work to larger cohorts and the investigation of LM arising from other cancers.