This paper studies a novel recurrent neural network (RNN) with hyperbolic secant (sech) in the gate for a specific medical application task of Parkinson’s disease (PD) detection. In detail, it focuses on the fact that patients with PD have motor speech disorders, by converting the voice data into black-and-white images of a recurrence plot (RP) at specific time intervals and constructing the detection model that combines RNN and convolutional neural network (CNN); the study evaluates the performance of the RNN with sech gate compared with long short-term memory (LSTM) and gated recurrent unit (GRU) with conventional gates. As a result, the proposed model obtained similar results to LSTM and GRU (an average accuracy of about 70%) with less hyperparameters, resulting in faster learning. In addition, in the framework of the RNN with sech in gate, the accuracy obtained by using tanh as the output activation function is higher than using the relu function. The proposed method will see more improvement by increasing the data in the future. More analysis on the input sound type, the RP image size, and the deep learning structures will be included in our future work for further improving the performance of PD detection from voice.
Hypertrophic pulmonary osteoarthropathy( HPO) is a rare paraneoplastic manifestation of lung cancer that causes joint pain, joint swelling, and limited range of motion. Two surgical cases of lung cancer with HPO are presented. Case1:A 43-year-old female was referred to our department with a diagnosis of cStage ⅡB left hilar lung cancer. She had difficulty in walking due to arthralgia caused by HPO. Left pneumonectomy was performed and the arthralgia disappeared on the first postoperative day. The patient is being well after surgery without relapse of joint symptoms. Case2:The patient was a 65-year-old male with cStage ⅡA right lung cancer. The symptoms of HPO appeared after he was found to have lung cancer. After right upper lobectomy, the arthralgia disappeared on the first postoperative day. Currently, he is receiving adjuvant chemotherapy, without relapse of joint symptoms.
An improved photoelectric method for recording motile responses of individual leucophores was developed. Leucophores from scales of the medaka, Oryzias latipes, were used as a model. The intensity of light scattering from the peripheral dendritic zone (Sp) and that from the cell body (Sc) of each leucophore were separately transduced to the current changes, which were then converted to voltages, and appropriately amplified. Output voltages of both channels were represented as “Vp = A1 × Sp”, and “Vc = A2 × Sc”, where A1 and A2 were the overall amplification coefficients for these channels, respectively. When leucosomes dispersed from the cell body into the dendrites, the Vp increased and the Vc decreased, while the reverse changes occurred when the leucosomes aggregated. Using a simple electronic circuit, the remainder of the two outputs, namely, Vp − Vc, could easily be obtained and recorded. As alternative expressions of the response, the ratio of the outputs (Vp/Vc), its square root (), or could also be recorded using integrated circuits developed for such purposes (vp, vc: voltage biases applied to Vp and Vc). The relative merits of these types of analysis are discussed. Similar analysis should also be applicable to the motile activities of iridophores of the dendritic type, such as those of some gobiid fish.
