No abstract

Since the onset of the coronavirus disease 2019 (COVID-19) pandemic, researchers and clinicians in the radiation oncology sector have been paying attention to the supply of radiation therapy (RT) and the safeguard of patients with regard to their infectious status. Based on the experience of 2 RT departments in Apulia (Brindisi and Barletta), Italy, we argue that the Italian guidelines currently in place are far from adequate to ensure staff and patient safety and should be strengthened with urgency.On March 11, 2020, the staff of the RT department at A. Perrino Hospital in Brindisi was informed that 3 patients coming from the medical oncology ward were found to be COVID-19 positive. One of them had received RT treatment the previous month, on February 18, and it unclear whether, at that time, the patient was already COVID-19 positive. Moreover, some health care workers (HCWs) from our staff had met with the other 2 patients daily from March 2 to 6 without personal protective equipment (PPE). It should be noted that surgical masks for HCWs in this department have been available only since March 9 1 ; in another RT department (Ospedale Mons. Dimiccoli in Barletta), PPE has been available since March 10 (surgical masks and Filtering Face Piece Sources of support: This work had no specific funding.

Background and purposeAlthough the latest breakthroughs in radiotherapy (RT) techniques have led to a decrease in adverse event rates, these techniques are still associated with substantial toxicity, including xerostomia. Imaging biomarkers could be useful to predict the toxicity risk related to each individual patient. Our preliminary work aims to develop a radiomic-based support tool exploiting pre-treatment CT images to predict late xerostomia risk in 3 months after RT in patients with oropharyngeal cancer (OPC).Materials and methodsWe performed a multicenter data collection. We enrolled 61 patients referred to three care centers in Apulia, Italy, out of which 22 patients experienced at least mild xerostomia 3 months after the end of the RT cycle. Pre-treatment CT images, clinical and dose features, and alcohol-smoking habits were collected. We proposed a transfer learning approach to extract quantitative imaging features from CT images by means of a pre-trained convolutional neural network (CNN) architecture. An optimal feature subset was then identified to train an SVM classifier. To evaluate the robustness of the proposed model with respect to different manual contouring practices on CTs, we repeated the same image analysis pipeline on “fake” parotid contours.ResultsThe best performances were achieved by the model exploiting the radiomic features alone. On the independent test, the model reached median AUC, accuracy, sensitivity, and specificity values of 81.17, 83.33, 71.43, and 90.91%, respectively. The model was robust with respect to diverse manual parotid contouring procedures.ConclusionRadiomic analysis could help to develop a valid support tool for clinicians in planning radiotherapy treatment, by providing a risk score of the toxicity development for each individual patient, thus improving the quality of life of the same patient, without compromising patient care.

No abstract

No abstract