Lasso logistic regression to derive workflow-specific algorithm performance requirements as demonstrated for head and neck cancer deformable image registration in adaptive radiation therapy

Identification of genetic mechanisms underlying lipid metabolism-mediated tumor immunity in head and neck squamous cell carcinoma

OBJECTIVE

To identify the genetic mechanisms underlying lipid metabolism-mediated tumor immunity in head and neck squamous carcinoma (HNSC).

MATERIALS AND METHODS

RNA sequencing data and clinical characteristics of HNSC patients were procured from The Cancer Genome Atlas (TCGA) database. Lipid metabolism-related genes were collected from KEGG and MSigDB databases. Immune cells and immune-related genes were obtained from the TISIDB database. The differentially expressed genes (DEGs) in HNSC were identified and weighted correlation network analysis (WGCNA) was performed to identify the significant gene modules. Lasso regression analysis was performed to identify hub genes. The differential gene expression pattern, diagnostic values, relationships with clinical features, prognostic values, relationships with tumor mutation burden (TMB), and signaling pathways involved, were each investigated.

RESULTS

One thousand six hundred sixty-eight DEGs were identified as dysregulated between HNSC tumor samples and healthy control head and neck samples. WGCNA analysis and Lasso regression analysis identified 8 hub genes, including 3 immune-related genes (PLA2G2D, TNFAIP8L2 and CYP27A1) and 5 lipid metabolism-related genes (FOXP3, IL21R, ITGAL, TRAF1 and WIPF1). Except CYP27A1, the other hub genes were upregulated in HNSC as compared with healthy control samples, and a low expression of these hub genes indicated a higher risk of death in HNSC. Except PLA2G2D, all other hub genes were significantly and negatively related with TMB in HNSC. The hub genes were implicated in several immune-related signaling pathways including T cell receptor signaling, Th17 cell differentiation, and natural killer (NK) cell mediated cytotoxicity.

CONCLUSION

Three immune genes (PLA2G2D, TNFAIP8L2, and CYP27A1) and immune-related pathways (T cell receptor signaling, Th17 cell differentiation, and natural killer (NK) cell mediated cytotoxicity) were predicted to play significant roles in the lipid metabolism-mediated tumor immunity in HNSC.

Recent Applications of Artificial Intelligence in Radiotherapy: Where We Are and Beyond

In recent decades, artificial intelligence (AI) tools have been applied in many medical fields, opening the possibility of finding novel solutions for managing very complex and multifactorial problems, such as those commonly encountered in radiotherapy (RT). We conducted a PubMed and Scopus search to identify the AI application field in RT limited to the last four years. In total, 1824 original papers were identified, and 921 were analyzed by considering the phase of the RT workflow according to the applied AI approaches. AI permits the processing of large quantities of information, data, and images stored in RT oncology information systems, a process that is not manageable for individuals or groups. AI allows the iterative application of complex tasks in large datasets (e.g., delineating normal tissues or finding optimal planning solutions) and might support the entire community working in the various sectors of RT, as summarized in this overview. AI-based tools are now on the roadmap for RT and have been applied to the entire workflow, mainly for segmentation, the generation of synthetic images, and outcome prediction. Several concerns were raised, including the need for harmonization while overcoming ethical, legal, and skill barriers.

Alert system for monitoring changes in patient anatomy during radiation therapy of head and neck cancer

The purpose of this study is to validate a previously developed algorithm for alerting clinicians when to consider re-CT simulation due to changes in the patient's anatomy during radiation therapy of head and neck cancer. Cone beam computed tomography (CBCT) data were collected prospectively for 77 patients. Each CBCT was mathematically compared to a reference CBCT using the gamma index. We defined the match quality parameter (MQP) as an indicator of CBCT image similarity, where a negative MQP value indicates a poorer CBCT match than the match between the first two CBCT acquired during treatment. If three consecutive MQP values were below a chosen threshold, an "alert" is triggered to indicate action required, for example, possible re-CT simulation. The timing of image review requests made by the radiation therapists and any re-CT/re-plan decisions were documented for each patient's treatment course. The MQP for each patient (including any re-plans) was calculated in a manner that was blinded from the clinical process. The MQP as a function of fraction number was compared to actual clinical decisions in the treatment progress to evaluate alert system performance. There was a total of 93 plans (including re-plans) with 34 positives (action required) and 59 negatives (no action required). The sensitivity of the alert system was 0.76 and the false positive rate was 0.37. Only 1 case out of the 34 positive cases would have been missed by both the alert system and our clinical process. Despite the false negatives and false positives, analysis of the timing of alert triggers showed that the alert system could have resulted in seven fewer clinical misses. The alert system has the potential to be a valuable tool to complement human judgment and to provide a quality assurance safeguard to help improve the delivery of radiation treatment of head and neck cancer.

Determining Clinical Patient Selection Guidelines for Head and Neck Adaptive Radiation Therapy Using Random Forest Modelling and a Novel Simplification Heuristic

Purpose

To determine which head and neck adaptive radiotherapy (ART) correction objectives are feasible and to derive efficient ART patient selection guidelines.

Methods

We considered various head and neck ART objectives including independent consideration of dose-sparing of the brainstem/spinal cord, parotid glands, and pharyngeal constrictor, as well as prediction of patient weight loss. Two-hundred head and neck cancer patients were used for model development and an additional 50 for model validation. Patient chart data, pre-treatment images, treatment plans, on-unit patient measurements, and combinations thereof were assessed as potential predictors of each objective. A stepwise approach identified combinations of predictors maximizing the Youden index of random forest (RF) models. A heuristic translated RF results into simple patient selection guidelines which were further refined to balance predictive capability and practical resource costs. Generalizability of the RF models and simplified guidelines to new data was tested using the validation set.

Results

Top performing RF models used various categories of predictors, however, final simplified patient selection guidelines only required pre-treatment information for ART predictions, indicating the potential for significant ART process streamlining. The simplified guidelines for each objective predicted which patients would experience increases in dose to: brainstem/spinal cord with sensitivity = 1.0, specificity = 0.66; parotid glands with sensitivity = 0.82, specificity = 0.70; and pharyngeal constrictor with sensitivity = 0.84, specificity = 0.68. Weight loss could be predicted with sensitivity = 0.60 and specificity = 0.55. Furthermore, depending on the ART objective, 28%-58% of patients required replan assessment, less than for previous studies, indicating a step towards more effective patient selection.

Conclusions

The above ART objectives appear to be practically achievable, with patients selected for ART according to simple clinical patient selection guidelines. Explicit ART guidelines are rare in the literature, and our guidelines may aid in balancing the potential clinical gains of ART with high associated resource costs, formalizing ART trials, and ensuring the reproducibility of clinical successes.