RESUMEN
OBJECTIVE: Little information is available about deep learning methods used in ultrasound images of salivary gland tumors. We aimed to compare the accuracy of the ultrasound-trained model to computed tomography or magnetic resonance imaging trained model. MATERIALS AND METHODS: Six hundred and thirty-eight patients were included in this retrospective study. There were 558 benign and 80 malignant salivary gland tumors. A total of 500 images (250 benign and 250 malignant) were acquired in the training and validation set, then 62 images (31 benign and 31 malignant) in the test set. Both machine learning and deep learning were used in our model. RESULTS: The test accuracy, sensitivity, and specificity of our final model were 93.5%, 100%, and 87%, respectively. There were no over fitting in our model as the validation accuracy was similar with the test accuracy. CONCLUSIONS: The sensitivity and specificity were comparable with current MRI and CT images using artificial intelligence.
Asunto(s)
Inteligencia Artificial , Neoplasias de las Glándulas Salivales , Humanos , Estudios Retrospectivos , Redes Neurales de la Computación , Ultrasonografía/métodos , Neoplasias de las Glándulas Salivales/diagnóstico por imagenRESUMEN
The nutritional status in cancer patients is related to cancer survival and surgical outcome. The objective of this study was to examine the relationship between preoperative prognostic nutritional index (PNI) and post-operative clinical outcomes in head and neck cancer (HNC) patients. A total of 1282 head and neck cancer patients receiving surgical resection in Changhua Christian Hospital between 1 January 2010 and 30 August 2021 were recruited in the final analysis after undergoing propensity score matching analysis. The logistic regression model was used to assess the association of the PNI group with overall and various complications. The patients in the high PNI group had a significant lower incidence of overall complications, medical complications, and pulmonary complications; but not significant surgical complications. The high PNI group had lower mortality risk. The results in this study revealed that PNI score was a significant independent predictor of postoperative complications in HNC patients undergoing surgical resection. We recommend preoperative testing and evaluation of HNC patients to identify low PNI and high-risk groups for postoperative surveillance.