Ecancermedicalscience is the peer-reviewed open access cancer journal founded by the European Institute of Oncology in Milan. We consider articles on all aspects of research relating to cancer, including molecular biology, genetics, pathophysiology, epide

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.

Oral squamous cell carcinoma (OSCC) is the most common cancer of the oral cavity and constitutes 95% of all cancers of this area. Men are affected twice as commonly as women, primarily if they are over 50 years of age. Forty percent of the lesions are localized in the tongue and 30% in the floor of the oral cavity. OSCC often affects upper and lower gingiva, buccal mucous membrane, the retromolar triangle and the palate. The prognosis is poor and the five-year survival rate ranges from 20% (OSCC in the floor of the mouth) to 60% (OSCC in the alveolar part of the mandible). Treatment is difficult, because of the localization and the invasiveness of the available methods. The diagnosis is made based on a histopathological examination of a biopsy sample. The low detection rate of early oral SCC is a considerable clinical issue. Although the oral cavity can be easily examined, in the majority of cases oral SCC is diagnosed in its late stages. It is difficult to diagnose metastases in local lymph nodes and distant organs, which is important for planning the scope of resection and further treatment, graft implantation, and differentiation between reactive and metastatic lymph nodes as well as between disease recurrence and scars or adverse reactions after surgery or radiation therapy. Imaging studies are performed as part of the routine work-up in oral SCC. However, it is difficult to interpret the results at the early stages of the disease. The following imaging methods are used – dental radiographs, panoramic radiographs, magnetic resonance imaging with diffusion-weighted and dynamic sequences, perfusion computed tomography, cone beam computed tomography, single-photon emission computed tomography, hybrid methods (PET/CT, PET/MRI, SPECT/CT) and ultrasound. Some important clinical problems can be resolved with the use of novel modalities such as MRI with ADC sequences and PET. The aim of this article is to describe oral squamous cell carcinoma as it appears in different imaging methods considering both their advantages and limitations.

Most studies indicate that the mechanical removal of the bacterial biofilm from the implant surface is the central goal of peri-implantitis therapy. However, controversial results in the treatment of peri-implantitis have led to the consideration of additional strategies that include surgical approaches and chemical adjuvants. Local/topical antibiotics, such as minocycline, azithromycin, tetracycline, amoxicillin, doxycycline, and metronidazole, may improve the efficacy of the definitive treatment of the disease, but the lack of conclusive findings prevents their use in clinical practice. This systematic review aimed to evaluate the effect of local/topical antibiotics for peri-implantitis treatment. Randomised controlled studies (RCT) on patients with peri-implantitis and comparing the efficacy of local/topical antibiotics vs. placebo or mechanical debridement were included. A systematic search strategy was carried out using three registered databases (PubMed, Web of Science, and Scopus). RoB2 was used to assess risk of bias. Five RCTs were identified (n = 250 patients and 333 implants). Contrast results emerged among the included studies, and a high heterogeneity level was observed. Risk of bias revealed some concerns for three studies out of five, while one study was judged at high risk. Only one study analysed the limitations of its findings. Overall, local antibiotic use can be considered a valid approach in the treatment of peri-implantitis. Therefore, future long-term clinical trials with standardised protocols and antibiotics with similar biological activity profiles should be tested to achieve a valid and definitive conclusion.

Background and Purpose: 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). Materials and Methods: 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. Results: 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). Discussion and Conclusion: 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.