http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Kazuki Hashimotoa,Junhyun Park,Seongmin Ha,Hyo-Il Jung,Tohru Kamiya 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Currently, cancer is the leading cause of death in the world, and in 2020, about 10 million people died from cancer. Since cancer progresses by repeating metastasis, early detection and early treatment are required. There are various treatments for diagnosing cancer, but it is difficult to determine the presence or absence of metastasis. Therefore, as a new biomarker, analysis of CTCs (Circulating Tumor Cells) in blood including HL-60 and MCF-7 is drawing attention. However, since the proportion of CTCs in the blood is very small, there is concern that the burden on doctors will increase. Therefore, in order to detect CTC in blood, we propose a method that automatically detects CTCs from fluorescence microscope images and enables quantitative analysis by computer. First, rough extraction of cell candidate regions is performed by morphological filtering, and the watershed method using hue images is applied to the connected cells to set the ROI (region of interest). In this paper, the proposed method was applied to a total of 16 images, 8 for HL-60 and 8 for MCF-7, and CTCs detection experiment was performed. As a result, the number of detections was 882 (TPR = 98.4%) for HL-60 and 275 (TPR = 99.2%) for MCF-7.
Classification of Circulating Tumor Cells in Fluorescence Microscopy Images Based on SqueezeNet
Kazuki NAKAMICHI,Huimin LU,Hyoungseop KIM,Kazue YONEDA,Fumihiro TANAKA 제어로봇시스템학회 2019 제어로봇시스템학회 국제학술대회 논문집 Vol.2019 No.10
Circulating Tumor Cells (CTC) is expected as a useful biomarker test that can evaluate cancer metastasis. CTC exists in the blood of cancer patients and is considered to be an incentive of cancer metastasis. Pathologists analyze the blood to find these metastasis cancers from three colors of fluorescence microscopy images, but the manual analysis is time-consuming. In this paper, we develop an automatic CTC classification method in fluorescence microscopy images to reduce the burden of pathologists. In the proposed method, we detect cell regions by the bacterial foraging-based edge detection (BFED) algorithm and classify CTC by SqueezeNet, which is the kind of convolutional neural network (CNN). We apply the proposed method to 5040 microscopy images (6 samples) and evaluate the effectiveness. The experimental results demonstrate that the proposed method has a true positive rate is 89.86% and a false positive rate is 3.27%.
Extraction of GGO candidate regions from the LIDC database using deep learning
Kazuki HIRAYAMA,Joo Kooi TAN,Hyoungseop KIM 제어로봇시스템학회 2016 제어로봇시스템학회 국제학술대회 논문집 Vol.2016 No.10
In recent years, development of the computer-aided diagnosis (CAD) systems for the purpose of reducing the false positive on visual screening and improving accuracy of lesion detection has been advanced. Lung cancer is the leading cause of cancer death in the world. Among them, GGO (Ground Glass Opacity) that exhibited early in the before cancer lesion and carcinoma in situ shows a pale concentration, have been concerned about the possibility of undetected on the screening. In this paper, we propose an automatic extraction method of GGO candidate regions from the chest CT image. Our proposed image processing algorithms is consist of four main steps; 1) segmentation of volume of interest from the chest CT image and removing the blood vessel regions, bronchus regions based on 3D line filter, 2) first detection of GGO regions based on density and gradient which is selected the initial GGO candidate regions, 3) identification of the final GGO candidate regions based on DCNN (Deep Convolutional Neural Network) algorithms. Finally, we calculates the statistical features for reducing the false-positive (FP) shadow by the rule-based method, performs identification of the final GGO candidate regions by SVM (Support Vector Machine). Our proposed method performed on to the 31 cases of the LIDC (Lung Image Database Consortium) database, and final identification performance of TP: 93.02[%], FP: 128.52[/case] are obtained respectively.
Kazuki Akamatsu,Ryo Nagumo,Shin-ichi Nakao 한국막학회 2020 멤브레인 Vol.30 No.4
This short review focuses on fouling by proteins and macromolecules in microfiltration/ultrafiltration. First, an experimental system that enables investigation of how the extent of the adsorption of proteins and macromolecules on membrane surfaces contributes to a decrease in filtrate flux in microfiltration/ultrafiltration is described. Using this system, a causal relationship - not a correlation - indicating that adsorption results in a decrease in filtrate flux could be clearly demonstrated in some cases. Second, a hydration structure at the membrane surface that can suppress adsorption is discussed, inspired by biomaterial research. In their hydrated states, polymers with low-fouling properties have water molecules with a particular structure. Finally, some successful examples of the development of low-fouling membranes via surface modification using low-fouling polymers are discussed.
Kazuki Hirao 대한정신약물학회 2014 CLINICAL PSYCHOPHARMACOLOGY AND NEUROSCIENCE Vol.12 No.3
Objective: The relationship between paranoia symptoms and underlying prefrontal cortex mechanisms among healthy subjectswas analyzed using near-infrared spectroscopy. Methods: Seventy-eight healthy subjects were assessed for paranoia symptoms using the Japanese version of the ParanoiaChecklist. Changes in hemoglobin concentrations were assessed using 2-channel near-infrared spectroscopy on the surfaceof the prefrontal cortex while subjects performed a verbal fluency test. Results: Changes in the concentration of oxygenated hemoglobin in the prefrontal cortex during a verbal fluency test did notcorrelate with the Japanese version of the Paranoia Checklist. Conclusion: Our findings show that the symptoms of paranoia do not negatively affect the prefrontal cortex function amonghealthy subjects.
Minimum Duration for Presenting Tactile Stimuli to Perceive Stimulus Locations on the Palm
( Kazuki Sakai ),( Kentaro Kotani ),( Satoshi Suzuki ),( Takafumi Asao ) 한국감성과학회 2014 춘계학술대회 Vol.2014 No.-
The duration for presenting tactile stimuli to generate certain images are important for developing tactile displays with effective information processing since such duration affects human short term memory, which determine accurate and effective perception for tactile information. In this study the experiment was conducted to obtain the duration required for generating spatial images from tactile stimuli. A total of five subjects participated in the experiment, where they performed two-point discrimination task with tactile stimuli ranging from 100ms to 300ms of stimulus duration. As a result, less than 200ms of duration lowered the performance of two-point differential threshold when two consecutive stimuli were given without inter-stimulus intervals. These results implied that less than 200ms of duration was not enough for identifying spatial information associated with tactile stimuli. The quantitative data obtained in this study give some insight for developing a mental model for identifying tactile spatial information.
Extraction of GGO Regions from Chest CT Images Using Deep Learning
Kazuki HIRAYAMA,Noriaki MIYAKE,Huimin LU,Joo Kooi TAN,Hyoungseop KIM,Rie TACHIBANA,Yasushi HIRANO,Shoji KIDO 제어로봇시스템학회 2017 제어로봇시스템학회 국제학술대회 논문집 Vol.2017 No.10
Lung cancer is the leading cause of death which accounts for the number of deaths in cancer in the world. Early detection and early treatment are regarded as an important. Especially, the ground glass opacity (GGO) is a shadow called pre-cancerous lesion, but it is a shadow which is difficult to detect by a radiologist because of haze and complicated shape. Therefore, in recent years, a computer aided diagnosis (CAD) system has been developed for the purpose of improving the detection accuracy for early detection and reducing the burden to radiologists. In this paper, we extract the GGO using Deep Convolutional Neural Network (DCNN) based on emphasized images. Before detect a GGO region, we apply preprocessing such as isotropic voxel to the original images, and extraction of the lung area. Next, we remove the vessel and bronchial region by 3D line filter based on Hessian matrix, and extract the initial candidate regions using density gradient, volume and sphericity. Subsequently, we segment the candidate regions, extraction of features, and reducing false positive shadows. Finally we create emphasize images and identify with DCNN using those images. As a result of applying the proposed method to 31 cases on Lung Image Database Consortium (LIDC), we obtained a true positive rate (TP) of 86.05 [%] and false positive number (FP) of 4.81 [/case].