In this article, a synchronization control method is studied for coupled neural networks (CNNs) with constant time delay using sampled-data information. A distributed control protocol relying on the sampled-data information of neighboring nodes is proposed. Lyapunov functional is constructed to analyze the synchronization of CNNs with constant time delay.
View Article and Find Full Text PDFIntroduction: Radiation-induced lung injury (RILI) is one of the most clinically-challenging toxicities and dose-limiting factors during and/or after thoracic radiation therapy for oesophageal squamous cell carcinoma (ESCC). With limited effective protective drugs against RILI, the main strategy to reduce the injury is strict adherence to dose-volume restrictions of normal lungs. RILI can manifest as acute radiation pneumonitis with cellular injury, cytokine release and cytokine recruitment to inflammatory infiltrate, and subsequent chronic radiation pulmonary fibrosis.
View Article and Find Full Text PDFBackground: Limited evidence supports the omission of routine bone marrow (BM) examination (biopsy and aspiration) in patients with nasal-type extranodal NK/T-cell lymphoma (ENKTCL). This study was aimed at assessing whether BM examination provides valuable information for positron emission tomography/computed tomography (PET/CT)-based staging in this patient population.
Patients And Methods: Patients newly diagnosed with ENKTCL who underwent initial staging with both PET/CT and BM examination between 2013 and 2020 were retrospectively identified in two Chinese institutions.
Background: Regional lymph node (LN) metastasis is a significant factor influencing the treatment choice of esophageal squamous cell carcinoma (ESCC). The performance PET/CT as an imaging evaluation method for regional LNs in ESCC, is unsatisfactory due to the lack of logical criterion. We explored how a modified criterion improved the diagnostic value of F-FDG PET/CT in regional LN metastasis.
View Article and Find Full Text PDFIEEE Trans Neural Netw Learn Syst
July 2023
Deep reinforcement learning (DRL) is a machine learning method based on rewards, which can be extended to solve some complex and realistic decision-making problems. Autonomous driving needs to deal with a variety of complex and changeable traffic scenarios, so the application of DRL in autonomous driving presents a broad application prospect. In this article, an end-to-end autonomous driving policy learning method based on DRL is proposed.
View Article and Find Full Text PDFCentral nervous system (CNS) involvement is a rare manifestation of multiple myeloma (MM) and the optimal management strategies have yet to be determined. The aim of the present study was to describe the case of a 47-year-old male patient with immunoglobulin D-λ MM who presented with multiple extramedullary infiltrations at diagnosis. This patient achieved stringent complete response after 9 cycles of treatment with bortezomib, lenalidomide and dexamethasone, and then received lenalidomide as maintenance therapy.
View Article and Find Full Text PDFObjective: To explore the preoperative diagnostic value of ¹⁸F-fluorodexyglucose positron emission tomography combined with contrast enhanced computed tomography (¹⁸F-FDG PET-ceCT) in patients with colorectal cancer liver metastasis.
Methods: Clinical and imaging data of 58 patients with suspicious colorectal cancer liver metastasis between April 2010 and March 2013 were retrospectively evaluated. All the patients underwent ¹⁸F-FDG PET-ceCT.