The main factor that affects the prognosis of patients with head and neck cancer (HNC) is regional lymph node metastases. For this reason, the accurate evaluation of neck metastases is required for neck management. This study investigates the sentinel lymph node identification and the accuracy of the histopathology of the sentinel lymph node in patients with HNC. Eleven patients with histologically proven oral squamous cell carcinoma accessible to radiocolloid injection were enrolled in this study. Using both lymphoscintigraphy and a handheld gamma probe, the sentinel lymph node could be identified in all 11 patients. Subsequently, the sentinel lymph nodes and the neck dissection specimen were examined for lymph node involvement due to tumor. The histopathology of sentinel lymph nodes was consistent with the pathological N classification in all 11 patients. Furthermore, the histopathology of sentinel lymph nodes was superior to physical examination, computed tomography (CT), magnetic resonance imaging (MRI) and positron emission tomography (PET) scan. The results of this study indicate that sentinel lymph node identification is technically feasible and predicts cervical metastases in patients with oral cavity cancer. This may be a useful diagnostic technique for identifying lymph node disease in staging lymph node dissection.
This paper describes a novel quasi-Newton (QN) based accelerated technique for training of neural networks. Recently, Nesterov's accelerated gradient method has been utilized for the acceleration of the gradient-based training. In this paper the acceleration of the QN training algorithm is realized by the quadratic approximation of the error function incorporating the momentum term as Nesterov's method. It is shown that the proposed algorithm has a similar convergence property with the QN method. Neural network trainings for the function approximation and the microwave circuit modeling problems are presented to demonstrate the proposed algorithm. The method proposed here drastically improves the convergence speed of the conventional QN algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.