检索结果-南通市图书馆

Journal of Biomedical Science and Engineering 2024年第1期17卷 1-12页

作者： Eri Matsuyama Masayuki Nishiki noriyuki takahashi Haruyuki Watanabe Faculty of Informatics University of Fukuchiyama Kyoto Japan Graduate School of Radiological Sciences International University of Health and Welfare Tochigi Japan School of Health Sciences Fukushima Medical University Fukushima Japan School of Radiological Technology Gunma Prefectural College of Health Sciences Gunma Japan

Cross entropy is a measure in machine learning and deep learning that assesses the difference between predicted and actual probability distributions. In this study, we propose cross entropy as a performance evaluation metric for image classifier models and apply it to the CT image classification of lung cancer. A convolutional neural network is employed as the deep neural network (DNN) image classifier, with the residual network (ResNet) 50 chosen as the DNN archi-tecture. The image data used comprise a lung CT image set. Two classification models are built from datasets with varying amounts of data, and lung cancer is categorized into four classes using 10-fold cross-validation. Furthermore, we employ t-distributed stochastic neighbor embedding to visually explain the data distribution after classification. Experimental results demonstrate that cross en-tropy is a highly useful metric for evaluating the reliability of image classifier models. It is noted that for a more comprehensive evaluation of model perfor-mance, combining with other evaluation metrics is considered essential. .

关键词： Cross Entropy Performance Metrics DNN Image Classifiers Lung Cancer Prediction Uncertainty

Explainable Analysis of Deep Learning Models for Coronavirus Disease (COVID-19) Classification with Chest X-Ray Images: Towards Practical Applications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Open Journal of Medical Imaging 2022年第3期12卷 83-102页

作者： Eri Matsuyama Haruyuki Watanabe noriyuki takahashi Faculty of Informatics University of Fukuchiyama Kyoto Japan School of Radiological Technology Gunma Prefectural College of Health Sciences Gunma Japan School of Hearth Sciences Fukushima Medical University Fukushima Japan

In recent years, with numerous developments of convolutional neural network (CNN) classification models for medical diagnosis, the issue of misrecognition/misclassification has become more and more important. Thus, research on misrecognition/misclassification has been progressing. This study focuses on the problem of misrecognition/misclassification of CNN classification models for coronavirus disease (COVID-19) using chest X-ray images. We construct two models for COVID-19 pneumonia classification by fine-tuning ResNet-50 architecture, i.e., a model retrained with full-sized original images and a model retrained with segmented images. The present study demonstrates the uncertainty (misrecognition/misclassification) of model performance caused by the discrepancy in the shapes of images at the phase of model construction and that of clinical applications. To achieve it, we apply three XAI methods to demonstrate and explain the uncertainty of classification results obtained from the two constructed models assuming for clinical applications. Experimental results indicate that the performance of classification models cannot be maintained when the type of constructed model and the geometric shape of input images are not matched, which may bring about misrecognition in clinical applications. We also notice that the effect of adversarial attack might be induced if the method of image segmentation is not performed properly. The results suggest that the best approach to obtaining a highly reliable prediction in the classification of COVID-19 pneumonia is to construct a model using full-sized original images as training data and use full-sized original images as the input when utilized in clinical applications.

关键词： Explainable AI CNN CXR Image COVID-19 Pneumonia

A Breast Density Classification System for Mammography Considering Reliability Issues in Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Open Journal of Medical Imaging 2023年第3期13卷 63-83页

作者： Eri Matsuyama Megumi Takehara noriyuki takahashi Haruyuki Watanabe Faculty of Informatics University of Fukuchiyama Kyoto Japan Breast Center Dokkyo Medical University Hospital Tochigi Japan School of Hearth Sciences Fukushima Medical University Fukushima Japan School of Radiological Technology Gunma Prefectural College of Health Sciences Gunma Japan

In a convolutional neural network (CNN) classification model for diagnosing medical images, transparency and interpretability of the model’s behavior are crucial in addition to high classification accuracy, and it is highly important to explicitly demonstrate them. In this study, we constructed an interpretable CNN-based model for breast density classification using spectral information from mammograms. We evaluated whether the model’s prediction scores provided reliable probability values using a reliability diagram and visualized the basis for the final prediction. In constructing the classification model, we modified ResNet50 and introduced algorithms for extracting and inputting image spectra, visualizing network behavior, and quantifying prediction ambiguity. From the experimental results, our proposed model demonstrated not only high classification accuracy but also higher reliability and interpretability compared to the conventional CNN models that use pixel information from images. Furthermore, our proposed model can detect misclassified data and indicate explicit basis for prediction. The results demonstrated the effectiveness and usefulness of our proposed model from the perspective of credibility and transparency.

关键词： Explainable AI t-SNE Entropy Wavelet Transform Mammogram

Laser-assisted direct roller imprinting of large-area microstructured optical surfaces

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第1期10卷 257-266页

作者： Keisuke Nagato Ken takahashi Yuki Yajima Masayuki Nakao Department of Mechanical Engineering Graduate School of EngineeringThe University of Tokyo7-3-1 HongoBunkyo-kuTokyo 113-8656Japan

In this study,a high-throughput fabrication method called laser-assisted direct roller imprinting(LADRI)was developed to lower the cost of nanoimprinting large-area polymer films and to address problems associated with nanoimprinting,namely,microstructural damage and precision in flatness of entire *** LADRI,the laser directly heats the microstructured surface of the roller mold,which heats and melts the surface of a polymethyl methacrylate(PMMA)film to replicate the microstructures on the mold *** this study,the effects of laser power density,scanning speed,size of the microstructures,and contact pressure on the replication speed were investigated *** replication speed increased as the power and scanning speed ***,because the film required heating until it filled the entire depth of the microstructure,an appropriate replication speed was *** result was supported by simulation of the temperature distribution inside the mold and the PMMA using transient heat conduction *** demonstrate the applications of LADRI,two different optical surfaces were replicated:an antireflection(AR)structure with conical structures sized several hundred nanometers and a lightextraction structure with a microlens array(MLA)comprising 10μm lenses,for display and illumination,*** replication degree of the MLA was governed by the contact *** flow simulation indicated that the heat conduction and flow speeds of the melted PMMA surface were comparable within several tens of *** addition,the reflectivity of the AR structure decreased from 4 to 0.5%,and the light intensity of the light-extraction structure increased by a factor of 1.47.

关键词： microstructure roller conduction

A Method of Using Information Entropy of an Image as an Effective Feature for Com-puter-Aided Diagnostic Applications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Biomedical Science and Engineering 2016年第6期9卷 315-322页

作者： Eri Matsuyama noriyuki takahashi Haruyuki Watanabe Du-Yih Tsai Department of Radiological Technology Faculty of Fukuoka Medical Technology Teikyo University Fukuoka Ja-pan Department of Radiology and Nuclear Medicine Research Institute for Brain and Vessels-Akita Akita Japan School of Radiological Technology Gunma Prefectural College of Health Sciences Gunma Japan Department of Electrical and Computer Engineering National Institute of Technology Gifu College Gifu Japan Department of Biomedical Engineering Hungkuang University Taiwan

Computer-aided detection and diagnosis (CAD) systems are increasingly being used as an aid by clinicians for detection and interpretation of diseases. In general, a CAD system employs a classifier to detect or distinguish between abnormal and normal tissues on images. In the phase of classification, a set of image features and/or texture features extracted from the images are commonly used. In this article, we investigated the characteristic of the output entropy of an image and demonstrated the usefulness of the output entropy acting as a texture feature in CAD systems. In order to validate the effectiveness and superiority of the output-entropy-based texture feature, two well-known texture features, i.e., mean and standard deviation were used for comparison. The database used in this study comprised 50 CT images obtained from 10 patients with pulmonary nodules, and 50 CT images obtained from 5 normal subjects. We used a support vector machine for classification. A leave-one-out method was employed for training and classification. Three combinations of texture features, i.e., mean and entropy, standard deviation and entropy, and standard deviation and mean were used as the inputs to the classifier. Three different regions of interest (ROI) sizes, i.e., 11 × 11, 9 × 9 and 7 × 7 pixels from the database were selected for computation of the feature values. Our experimental results show that the combination of entropy and standard deviation is significantly better than both the combination of mean and entropy and that of standard deviation and mean in the case of the ROI size of 11 × 11 pixels (p < 0.05). These results suggest that information entropy of an image can be used as an effective feature for CAD applications.

关键词： Information Entropy Image and Texture Feature Computer-Aided Diagnosis Support Vector Machine

Nondestructive and active interrogation system for special nuclear material:proof of principle and initial results

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第5期35卷 216-225页

作者： Mahmoud Bakr Kai Masuda Yoshiyuki takahashi Tsuyoshi Misawa Norio Yamakawa Tomas Scott Institute of Advanced Energy Kyoto UniversityGokashoUjiKyoto 611‑0011Japan School of Physics University of BristolBs81TL Tyndall AvenueBristolUK Physics Department Faculty of ScienceAssiut UniversityAssiut 71516Egypt Research Reactor Institute Kyoto University2 Asashiro‑NishiKumatoriOsaka 590‑0494Japan Pony Industry Co.Ltd. 2‑3‑6 Kitakyuhoji‑MachiChuo‑KuOsaka 541‑0057Japan Astral Neutronics LTD Unit H5HallenBristol BS107SBUK

Herein,we employ the threshold energy neutron analysis(TENA)technique to introduce the world's first active interrogation system to detect special nuclear materials(SNMs),including U-235 and *** system utilizes a DD neutron generator based on inertial electrostatic confinement(IEC)to interrogate suspicious *** detect secondary neutrons produced during fission reactions induced in SNMs,a tensioned metastable fluid detector(TMFD)is *** current status of the system's development is reported in this paper,accompanied by the results from experiments conducted to detect 10 g of highly enriched uranium(HEU).Notably,the experimental findings demonstrate a distinct difference in the count rates of measurements with and without *** difference in count rates surpasses two times the standard deviation,indicating a confidence level of more than 96% for identifying the presence of *** paper presents and extensively discusses the proof-of-principle experimental results,along with the system's planned trajectory.

关键词： Special nuclear materials Uranium detection Inertial electrostatic confinement fusion TENA HEU CTMFD

Fluorescence‑Based Calibration Model for In‑Situ Measurement of Micro‑scaled Lubricant Thickness Distribution at Indentation Interface

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Nanomanufacturing and Metrology 2024年第2期7卷 76-88页

作者： Motoya Yoshikawa Saeko Fujii Shotaro Kadoya Tatsuya Sugihara Masaki Michihata Satoru takahashi Department of Precision Engineering The University of TokyoHongo 7‑3‑1BunkyoTokyo 113‑8656Japan Department of Mechanical Engineering Osaka UniversityYamadaoka 2‑1SuitaOsaka 565‑0871Japan

This study proposes a model for the measurement of microscale liquid film thickness distribution using fluorescence *** interfacial conditions between the tool and the workpiece in mechanical machining are important for understanding these phenomena and *** this study,indentation tests with transparent tools were used to observe interfaces;however,it was challenging to obtain the signal from a thin fluorescent liquid film on smooth and steeply inclined ***,fluorescence-based measurement,such as laser-induced fluorescence,was *** measure the absolute thickness of the thin fluorescent film,calibration of the measurement system is ***,a theoretical model was proposed considering the multiple reflections of excitation light and fluorescence at the inclined surface between the indenter and *** measuring the profile of the surface topography of the indented workpiece and comparing the results with those measured by a surface profiler,the validity of the proposed calibration method and the performance of this measurement system were *** measured surface profiles,including scratches of 2–4μm,were in good agreement,demonstrating the validity of the proposed method.

关键词： Laser-induced fluorescence(LIF) Thickness distribution In-situ measurement Lubricant Mechanical machining

Corroborative Activities and Recognition Between Community Comprehensive Care Unit’s Nurses and Care Managers in Supporting Discharge of Elderly from Hospital - A Secondary Publication

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Clinical and Nursing Research 2024年第4期8卷 381-392页

作者： Yukie Sakamoto Shizuko Omote Rie Okamoto Yutaro takahashi Satomi Ikeuchi Division of Health Sciences Graduate School of Medical SciencesKanazawa UniversityKanazawa 920-0934Japan Kanazawa City Community Comprehensive Support Center Tobiume Kanazawa 920-0938Japan Faculty of Health Sciences Institute of MedicalPharmaceutical and Health SciencesKanazawa UniversityKanazawa 920-1192Japan

Objective: The purpose of this study was to clarify the collaborative activities and mutual recognition between community comprehensive care unit nurses (Ns) and care managers (CM) in supporting the discharge of the elderly from the hospital. Methods: A total of 300 nurses working in community comprehensive care wards and 360 care managers working in B City in A Prefecture were surveyed using an anonymous self-administered questionnaire. Results: The highest percentage of responses regarding necessary collaborative activities with multiple professions in supporting hospital discharge were the same for Ns and CMs. The items regarding practice with the highest percentages were “relationship as a team” for Ns, and “user-centered awareness” for CM. While these professionals were willing to share information about their patients’ lives after discharge, the percentage of those explaining their expertise was low. It is thought that collaborative activities focusing on these aspects would lead to more appropriate discharge support.

关键词： Discharge support Community comprehensive care ward Ward nurses Care managers Collaborative activities

Preoperative albumin-bilirubin score and liver resection percentage determine postoperative liver regeneration after partial hepatectomy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2024年第14期30卷 2006-2017页

作者： Kazuhiro takahashi Masahiko Gosho Yoshihiro Miyazaki Hiromitsu Nakahashi Osamu Shimomura Kinji Furuya Manami Doi Yohei Owada Koichi Ogawa Yusuke Ohara Yoshimasa Akashi Tsuyoshi Enomoto Shinji Hashimoto Tatsuya Oda Department of Gastrointestinal and Hepatobiliary-Pancreatic Surgery University of TsukubaTsukuba 3058-575IbarakiJapan Department of Biostatistics University of TsukubaTsukuba 3058-575IbarakiJapan

BACKGROUND The success of liver resection relies on the ability of the remnant liver to *** of the knowledge regarding the pathophysiological basis of liver regeneration comes from rodent studies,and data on humans are ***,there is limited knowledge about the preoperative factors that influence postoperative *** To quantify postoperative remnant liver volume by the latest volumetric software and investigate perioperative factors that affect posthepatectomy liver *** A total of 268 patients who received partial hepatectomy were *** were grouped into right hepatectomy/trisegmentectomy(RH/Tri),left hepa-tectomy(LH),segmentectomy(Seg),and subsegmentectomy/nonanatomical hepatectomy(Sub/Non)*** regeneration index(RI)and late rege-neration rate were defined as(postoperative liver volume)/[total functional liver volume(TFLV)]×100 and(RI at 6-months-RI at 3-months)/RI at 6-months,*** lower 25th percentile of RI and the higher 25th percentile of late regeneration rate in each group were defined as“low regeneration”and“delayed regeneration”.“Restoration to the original size”was defined as regeneration of the liver volume by more than 90%of the TFLV at 12 months *** The numbers of patients in the RH/Tri,LH,Seg,and Sub/Non groups were 41,53,99 and 75,*** RI plateaued at 3 months in the LH,Seg,and Sub/Non groups,whereas the RI increased until 12 months in the RH/Tri *** to our multivariate analysis,the preoperative albumin-bilirubin(ALBI)score was an independent factor for low regeneration at 3 months[odds ratio(OR)95%CI=2.80(1.17-6.69),P=0.02;per 1.0 up]and 12 months[OR=2.27(1.01-5.09),P=0.04;per 1.0 up].Multivariate analysis revealed that only liver resection percentage[OR=1.03(1.00-1.05),P=0.04]was associated with delayed ***,multivariate analysis demonstrated that the preoperative ALBI score[OR=2.63(1.00-1.05),P=0.02;per 1.

关键词： Liver regeneration Albumin-bilirubin score Liver resection percentage Partial hepatectomy Human Regeneration index

Preliminary Investigation of Copper(II) Ion Binding or Complex Coordination in Lysozeme Molecules

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Materials Science and Chemical Engineering 2024年第4期12卷 98-103页

作者： Kou takahashi Ryotaro Miyazaki Daisuke Nakane Temitayo O. Aiyelabola Takashiro Akitsu Department of Chemistry Faculty of Science Tokyo University of Science Tokyo Japan Department of Chemistry Faculty of Science Obafemi Awolowo University Ile-Ife Nigeria

Hydrophobic Val derivative Schiff base copper(II) complexes and dipeptide (AlaAla, GlyGly) derivative Schiff base copper(II) complexes were introduced into egg white lysozyme. X-ray crystal structure analysis revealed amino acid derivative Schiff base copper(II) complexes were obtained. Herein we discuss primarily on the binding mode of copper(II) of the complexes obtained with egg white lysozyme. The electron density of copper(II) ions was confirmed by X-ray crystal structure analysis. The Val derivative Schiff base copper(II) complex was weakly bound at Arg114 of egg white lysozyme. In other copper(II) complexes, binding of copper(II) ions with dissociated ligands to various residues was observed. The binding sites of copper(II) ions were compared with computational scientific predictions.

关键词： Copper Schiff Base Lysozyme Metal-Protein Binding Computational Methods