Gifu University of Medical Science

About: Gifu University of Medical Science is a education organization based out in Gifu City, Japan. It is known for research contribution in the topics: Imaging phantom & Motion sickness. The organization has 89 authors who have published 202 publications receiving 1350 citations.

Artificial Intelligence for Medical Imaging and Hygiene

Abstract: Artificial Intelligence (AI) is commonly defined as machine intelligence that is programmed to think like humans and emulate their behavior or simply the technology of developing AI. People receive great benefits from services based on AI technology without even realizing it. One of the technologies that underlie AI is machine learning, and deep learning is a new type of machine learning. Mathematical models of deep learning usually employ a neural network model that imitates the human brain neural network, and a deep neural network has some middle layers to solve the highly difficult issues. A Convolutional Neural Network (CNN), which is a type of deep learning network, can analyze an image directly. In the field of medical imaging and diagnosis, deep learning is already being used to solve numerous difficult issues. Systems have been developed using CNNs and have achieved practical medical application. This chapter focuses in detail on the relationship between deep learning, medical imaging, and hygiene. In particular, it contains an explanation and technical summary of machine learning, the application of deep learning in medical imaging, and the association of the Coronavirus disease 2019 (COVID-19) infection with hygiene and deep learning.

[Construction and Analysis of a Digital Mammography Database: Analysis of Breast Compression Pressures at Four Facilities].

Abstract: We analyzed the compression pressures in 2772 mammography images of 807 patients acquired by digital mammography equipment at four facilities. The analysis included the average compression pressure at all facilities, difference in compression pressure at each facility, differences between the pressures used by radiological technologists in the same facility, and difference attributed to the breast structure. We also analyzed the effects of the compression pressure on the breast thickness and mean glandular dose (MGD) at each facility. The median values of the compression pressure and breast thickness for the 2772 images at all facilities were 86.5 N and 43 mm, respectively. The compression pressures differed among the institutions. The maximum difference in the median pressures among the four facilities was 38.6 N, while the difference in the breast thickness was 6 mm. The radiological technologists working at the same facility used almost the same compression pressure. However, differences between the compression pressures used by different radiological technologists were observed. The compression pressure in a dense breast was smaller than that in a non-dense breast. The difference in the compression pressure affected the breast thickness and MGD. The results of this analysis could be utilized for an optimal imaging in future digital mammography.

Extracting and Mathematical Identifying Form of Stationary Noise in X-ray Images

Abstract: Image noise may prevent proper diagnostic X-ray imaging. This study is aimed at developing new noise rejection methods using a mathematical model that describes the form of X-ray image noise. Stationary noise is one type of noise found in X-ray images. Stationary noise is nonstochastic and appears independent of the radiographic factors. In this paper, we verify methods for identifying stationary noise using a polynomial regression model, and extracting such noise from X-ray images obtained from a CR system. The results of this study demonstrate that stationary noise can be extracted with high precision using a particular low-pass filter frequency. We found that a regression model for greater than second-degree polynomials can be applied for roughly identifying stationary noise. However, the fitting accuracy of the regression curve is not significantly improved in terms of the amount of multiplication required when increasing the degree of the polynomial regression model. Ke yw ords: X-ray Image, Nonstochastic Noise, Stationary Noise, Polynomial Regression Model and CR System

Effects of graded load of artificial gravity on vestibule-spinal and vestibulo-ocular functions

Abstract: To clarify the trajectory of the hypothalamo-spinal pathway involved with thermal sweating (TS), I made a qualitative study of 38 patients with lateral medullary syndrome, 37 infarctions and one probable inflammation. Five patients showed “normal” thermal sweating and 33 an “abnormal” thermal sweating; ipsilateral hypohidrosis was present chiefly in the upper body. Relative hypohidrosis in the side of the body opposite to the side of the brain lesionwas seen in 4 cases. Contralateral facial sweating before heating was seen in 4 cases. Quantitative data (mg/cm/min) from 13 subjects in the “abnormal” thermal sweating group were compared to those in age-matched control subjects with “normal” thermal sweating. Sweat volume (SV) at the forehead on the side contralateral to the lesion in the patient group was significantly larger than on the ipsilateral side (p=0.0007) and also larger than in the control group (p=0.0442). In contrast, sweat volume at the ipsilateral forearm in the patient group was significantly lesser than on the contralateral side (p=0.0012), and also lesser than in the control group. Sweat volume at the ipsilateral side of the forehead, at the contralateral forearm, and at both legs showed no significant difference between patients and control subjects. The results indicated that the hypothalamo-spinal pathway does not evenly innervate the entire body, but has some regional predominance. The hypohidrosis at the ipsilateral forearm suggests that the hypothalamo-spinal pathway may exert a facilitatory influence on sweating of the upper body. The absence of any apparent reduction of thermal sweating at the legs suggests that there might be crossing fibers in the hypothalamo-spinal pathway involved in the thermal sweating of the lower body; another possibility is that there are cross-communicating fibers in more peripheral parts of the pathway, as suggested on morphological grounds by Cowley & Yeager (1964) and Webber (1956). Furthermore, excessive sweating at the forehead on the side contralateral to the lesion may be due mainly to a damage to the inhibitory pathway, and the pathway may be related predominantly to sweating of the upper body, particularly of the face and neck. (The Autonomic Nervous System, 47: 479–484, 2010)