In order to limit radiotherapy (RT)-related side effects, effective toxicity prediction and assessment schemes are essential. In recent years, the growing interest toward artificial intelligence and ...machine learning (ML) within the science community has led to the implementation of innovative tools in RT. Several researchers have demonstrated the high performance of ML-based models in predicting toxicity, but the application of these approaches in clinics is still lagging, partly due to their low interpretability. Therefore, an overview of contemporary research is needed in order to familiarize practitioners with common methods and strategies. Here, we present a review of ML-based models for predicting and classifying RT-induced complications from both a methodological and a clinical standpoint, focusing on the type of features considered, the ML methods used, and the main results achieved. Our work overviews published research in multiple cancer sites, including brain, breast, esophagus, gynecological, head and neck, liver, lung, and prostate cancers. The aim is to define the current state of the art and main achievements within the field for both researchers and clinicians.
Paucity and low evidence-level data on proton therapy (PT) represent one of the main issues for the establishment of solid indications in the PT setting. Aim of the present registry, the POWER ...registry, is to provide a tool for systematic, prospective, harmonized, and multidimensional high-quality data collection to promote knowledge in the field of PT with a particular focus on the use of hypofractionation.
All patients with any type of oncologic disease (benign and malignant disease) eligible for PT at the European Institute of Oncology (IEO), Milan, Italy, will be included in the present registry. Three levels of data collection will be implemented: Level (1) clinical research (patients outcome and toxicity, quality of life, and cost/effectiveness analysis); Level (2) radiological and radiobiological research (radiomic and dosiomic analysis, as well as biological modeling); Level (3) biological and translational research (biological biomarkers and genomic data analysis). Endpoints and outcome measures of hypofractionation schedules will be evaluated in terms of either Treatment Efficacy (tumor response rate, time to progression/percentages of survivors/median survival, clinical, biological, and radiological biomarkers changes, identified as surrogate endpoints of cancer survival/response to treatment) and Toxicity. The study protocol has been approved by the IEO Ethical Committee (IEO 1885). Other than patients treated at IEO, additional PT facilities (equipped with Proteus®ONE or Proteus®PLUS technologies by IBA, Ion Beam Applications, Louvain-la-Neuve, Belgium) are planned to join the registry data collection. Moreover, the registry will be also fully integrated into international PT data collection networks.
Purpose
To critically review available literature on hypofractionated (≥ 3 Gy/fraction) proton therapy (PT) for breast cancer (BCa).
Methods
A systematic screening of the literature was performed in ...April 2021 in compliance with the preferred reporting items for systematic reviews and meta-analyses recommendations. All full-text publication written in English were considered eligible. Acute and late toxicities, oncological outcomes and dosimetric features were considered for the analysis.
Results
Twelve publications met the inclusion criteria; all studies but one focused on accelerated partial breast irradiation (APBI). Eleven works considered post-operative patients, one referred to ABPI as a curative-intent modality. The dosimetric profile of PT compared favorably with both photon-based 3D conformal and intensity-modulated techniques, while a more extended follow-up is warranted to fully assess both the long-term toxicities and the non-inferiority of oncological outcomes.
Conclusion
Our work shows that results on PT for BCa are currently only available for APBI applications, with dosimetric analyses demonstrating a clear advantage over both 3D conformal and intensity modulated X-rays techniques, especially when ≥ 2 treatment fields were used. However, further evidence is needed to define whether such theoretical benefit translates into clinical improvements, especially in the long-term.
To investigate the role of the altered activation of the immune system in the prognosis of patients affected by laryngeal squamous cell carcinoma (LSCC). We analyzed 56 patients with advanced LSCC ...divided into two groups according to their prognosis: the first group relapsed within 24 months after treatment, the second group had no evidence of disease at 2 years. The presence of stromal tumor infiltrating lymphocytes (TILs) at the tumor-host border was investigated. In 43 patients we evaluated the expression of 395 genes related to immune system activation through a next generation sequencing panel. Priority-LASSO models and clustering analyses were integrated with multivariate Cox proportional hazard modeling to identify independent genes associated with relapse and estimate hazard ratios in relation to gene expression and TILs. TILs and the expression of genes related with immune system activation (FCGR1A, IFNA17, FCRLA, NCR3, KREMEN1, CD14, CD3G, CD19, CD20 and CD79A) were significantly associated with prognostic factors or disease specific survival. In patients with lymph node metastases and advanced T stage (pT4), the expression of other genes was altered. Low TILs count was highly associated with relapse within 2 years (p < 0.001). Low TILs and altered expression of specific genes associated with tumor-immune systems interactions emerged as independent risk factors, associated to poor prognosis and relapse within 2 years in advanced LSCC. Evaluation of patients' immune profile could be useful for prognosis and future therapeutic approaches towards personalized therapy.
Objectives
To assess the independent prognostic value of standardized uptake value (SUV) and apparent diffusion coefficient (ADC), separately and combined, in order to evaluate if the combination of ...these two variables allows further prognostic stratification of patients with head and neck squamous cell carcinomas (HNSCC).
Methods
Pretreatment SUV and ADC were calculated in 57 patients with HNSCC. Mean follow-up was 21.3 months. Semiquantitative analysis of primary tumours was performed using SUV
maxT/B
, ADC
mean
, ADC
min
and ADC
max
. The prognostic value of SUV
maxT/B
, ADC
mean
, ADC
min
and ADC
max
in predicting disease-free survival (DFS) was evaluated with log-rank test and Cox regression models.
Results
Patients with SUV
maxT/B
≥5.75 had an overall worse prognosis (
p
= 0.003). After adjusting for lymph node status and diameter, SUV
maxT/B
and ADC
min
were both significant predictors of DFS with hazard ratio (HR) = 10.37 (95 % CI 1.22–87.95) and 3.26 (95 % CI 1.20–8.85) for SUV
maxT/B
≥5.75 and ADC
min
≥0.58 × 10
−3
mm
2
/s, respectively. When the analysis was restricted to subjects with SUV
maxT/B
≥5.75, high ADC
min
significantly predicted a worse prognosis, with adjusted HR = 3.11 (95 % CI 1.13–8.55).
Conclusions
The combination of SUV
maxT/B
and ADC
min
improves the prognostic role of the two separate parameters; patients with high SUV
maxT/B
and high ADC
min
are associated with a poor prognosis.
Key Points
•
High SUV
maxT/B
is a poor prognostic factor in HNSCC
•
High ADC
min
is a poor prognostic factor in HNSCC
•
In patients with high SUV
maxT/B
, high ADC
min
identified those with worse prognosis
Machine learning (ML) is emerging as a feasible approach to optimize patients' care path in Radiation Oncology. Applications include autosegmentation, treatment planning optimization, and prediction ...of oncological and toxicity outcomes. The purpose of this clinically oriented systematic review is to illustrate the potential and limitations of the most commonly used ML models in solving everyday clinical issues in head and neck cancer (HNC) radiotherapy (RT).
Electronic databases were screened up to May 2021. Studies dealing with ML and radiomics were considered eligible. The quality of the included studies was rated by an adapted version of the qualitative checklist originally developed by Luo et al. All statistical analyses were performed using R version 3.6.1.
Forty-eight studies (21 on autosegmentation, four on treatment planning, 12 on oncological outcome prediction, 10 on toxicity prediction, and one on determinants of postoperative RT) were included in the analysis. The most common imaging modality was computed tomography (CT) (40%) followed by magnetic resonance (MR) (10%). Quantitative image features were considered in nine studies (19%). No significant differences were identified in global and methodological scores when works were stratified per their task (i.e., autosegmentation).
The range of possible applications of ML in the field of HN Radiation Oncology is wide, albeit this area of research is relatively young. Overall, if not safe yet, ML is most probably a bet worth making.
COVID-19 is an infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), a recently discovered coronavirus, which in 2020 led to a global pandemic. Clinical ...manifestations of COVID-19 are very diverse and symptoms range from mild to severe. Correlated symptoms might also manifest in the oral cavity, which is a potential pathway for viral infection, and therefore might be a potential pathway for SARS-CoV-2. In recent research among patients with SARS-CoV-2 infection, taste and olfactory disorders, dry mouth, drones and inflammation of mouth, bitter taste in mouth, difficulty in swallowing and burning sensations have been reported. There have been cases of oral mucosal lesions in patients diagnosed with COVID-19 disease. Some correlations between periodontitis and severity of COVID-19 disease have also been observed. Oral mucosa, due to occurrence of ACE2 receptors, is highly susceptible to SARS-CoV-2 infection. The occurrence of changes on oral mucosa should increase the alertness of dental practitioners. However, knowledge in this area is still limited and in the field of oral manifestations of COVID-19 more research and patient observations are required.
Introduction
Reirradiation (reRT) of locally recurrent/second primary tumors of the head and neck region is a potentially curative treatment for patients not candidate to salvage surgery. Aim of the ...present study is to summarize available literature on both prognostic factors and indications to curative reRT in this clinical setting.
Materials and methods
A narrative review of the literature was performed on two topics: (1) patients’ selection according to prognostic factors and (2) dosimetric feasibility of reRT. Postoperative reRT and palliative intent treatments were out of the scope of this work.
Results
Patient-tumor and treatment-related prognostic factors were analyzed, together with dosimetric parameters concerning target volume and organs at risk. Based on available evidence, a stepwise approach has been proposed aiming to provide a useful tool to identify suitable candidates for curative reRT in clinical practice. This was then applied to two clinical cases, proposed at the end of this work.
Conclusion
A second course of RT in head and neck recurrence/second primary tumors is a personalized approach that can be offered to selected patients only in centers with expertise and dedicated equipment following a multidisciplinary team discussion.
PDF
