Current Affiliation Organization 【 display / non-display 】

Current Affiliation Organization 【 display / non-display 】

External Career 【 display / non-display 】

External Career 【 display / non-display 】

display all >>

Affiliated academic organizations 【 display / non-display 】

Affiliated academic organizations 【 display / non-display 】

Research Interests 【 display / non-display 】

Research Interests 【 display / non-display 】

display all >>

Research Areas 【 display / non-display 】

Research Areas 【 display / non-display 】

Published Papers 【 display / non-display 】

Published Papers 【 display / non-display 】

• Integrating text and medical images for segmentation using interpretable graph neural network

  Chai, SR; Jain, RK; Mo, SC; Liu, JQ; Teng, SY; Tateyama, T; Lin, LF; Chen, YW

  BIOMEDICAL SIGNAL PROCESSING AND CONTROL ( Biomedical Signal Processing and Control )  115   2026.04 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  • Access this article

    DOI

• Classification of liver lesions based on temporal changes in hepatobiliary phase contrast on magnetic resonance imaging: a preliminary study

  Takatsu, Y; Nakamura, M; Tateyama, T; Miyati, T; Kobayashi, S

  RADIOLOGICAL PHYSICS AND TECHNOLOGY ( Radiological Physics and Technology )  18 ( 4 ) 1267 - 1282   2025.12 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  • Access this article

    DOI
  • Search related information
    PubMed

• Fundamental Concepts of Self-Attention in Generative AI

  LIU Jiaqing, TATEYAMA Tomoko, CHEN Yen-Wei

  Medical Imaging Technology ( The Japanese Society of Medical Imaging Technology )  43 ( 2 ) 35 - 39   2025.03 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  　View Summary

  <p>With the rapid development of generative AI, the Transformer architecture―centered on Self-Attention―has emerged as a fundamental technology across various fields, including natural language processing and image generation. This paper provides a step-by-step explanation of the mathematical foundations of Self-Attention, focusing on the roles of Query, Key, and Value, the computation and normalization of similarity scores using the Softmax function, and the generation of output vectors through weighted averaging. In addition, the architectural design and theoretical principles of Attention mechanisms within Transformers are reviewed to clarify the central role of Self-Attention in generative AI. Through the use of equations and illustrative figures, this work aims to support intuitive understanding and to contribute to the foundational knowledge required for future applications in the field of medical image analysis and visualization.</p>

  • Access this article

    DOI
  • Search related information
    CiNii Research

• 乳房ダイナミック造影三次元MRIにおいてk空間充填法に基づいた時間信号曲線のシミュレーション(Simulation of time-intensity curve based on k-space filling in breast dynamic contrast-enhanced three-dimensional magnetic resonance imaging)

  Takatsu Yasuo, Ueyama Tsuyoshi, Iwasaki Takahiro, Tateyama Tomoko, Miyati Tosiaki

  Radiological Physics and Technology ( (公社)日本放射線技術学会 )  17 ( 2 ) 536 - 552   2024.06 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  　View Summary

  典型的な悪性乳房腫瘍の乳房ダイナミック造影MRIにおいて、時間信号曲線(TIC)にpartial Fourier(PF)法を取込んだ三次元k空間軌跡が及ぼす影響について、デジタルファントムで検討した。腫瘍画像はCancer Imaging Archive Open Data for Breast Cancerから得た後、高時間分解能での1分間撮像を分析した。また、k空間軌跡の設定はLinear(逐次的)、Low-High(中心的)、PF(62.5%;Z方向、Y方向および両方向)とLow-High Radialとして評価した。その結果、k空間の中心であるk0のタイミングとTICの形状はk空間軌跡の選択とPF法実装による影響を受け、Low-High Radial使用時には小規模のTIC勾配が得られた。これらの結果から、特にradial法のようにk空間充填法でTIC勾配が生成される場合には、腫瘍悪性度の評価で誤った解釈を生じ得ることが懸念された。

• Simulation of time-intensity curve based on k-space filling in breast dynamic contrast-enhanced three-dimensional magnetic resonance imaging.

  Yasuo Takatsu, Tsuyoshi Ueyama, Takahiro Iwasaki, Tomoko Tateyama, Tosiaki Miyati

  Radiological physics and technology   17 ( 2 ) 536 - 552   2024.06 [ Peer Review Accepted ]

  Type of publication: Research paper (scientific journal)

  　View Summary

  This study elucidated the effects of a three-dimensional k-space trajectory incorporating the partial Fourier (PF) technique on a time-intensity curve (TIC) in a dynamic contrast-enhanced magnetic resonance imaging of a typical malignant breast tumor using a digital phantom. Images were obtained from the Cancer Imaging Archive Open Data for Breast Cancer, and 1-min scans with high temporal resolution were analyzed. The order of the k-space trajectory was set as Linear (sequential), Low-High (centric), PF (62.5%; Z-, Y-, and both directions), and Low-High Radial. k0 (center of the k-space) timing and TIC shape were affected by the chosen k-space trajectory and implementation of the PF technique. A small TIC gradient was obtained using a Low-High Radial order. If the k-space filling method (particularly the radial method) produces a gentle TIC gradient, misinterpretation could arise during the assessment of tumor malignancy status.

  • Access this article

    DOI
  • Search related information
    PubMed

display all >>

Other Papers 【 display / non-display 】

Other Papers 【 display / non-display 】

• うつ病検出のための多感情視聴覚特徴を用いた均一および多様な制約を持つ内的および相互感情間相互変換器ベース融合モデル

  TENG Shiyu, LIU Jiaqing, HUANG Yue, CHAI Shurong, TATEYAMA Tomoko, HUANG Xinyin, LIN Lanfen, CHEN Yen-Wei

  IEICE Transactions on Information and Systems (Web)   E107.D ( 3 )   2024

   

  J-GLOBAL

• Feature Recognition and Organ Segmentation from Medical Images Based on Machine Learning

  健山智子

  日本放射線技術学会総会学術大会予稿集   79th   2023

   

  J-GLOBAL

• ホロレンズを用いたCOVID-19のコンピュータ支援診断システム(Computer-aided Diagnosis System of COVID-19 with Hololens)

  Lyu Liang, Chai Shurong, Liu Jiaqing, Huang Huimin, Wang Fang, Tateyama Tomoko, Lin Lanfen, Chen Yenwei

  電子情報通信学会技術研究報告(MEとバイオサイバネティックス) ( (一社)電子情報通信学会 )  122 ( 291 ) 7 - 10   2022.11

   

• PointNet++に基づく遺伝子関連研究に向けた3次元顔面形態認識

  岡田一真, 寺田卓馬, LIU Jiaqing, 健山智子, 木村亮介, CHEN Yen-Wei

  映像情報メディア学会技術報告   46 ( 39(ME2022 86-97/SIP2022 5-16) )   2022

   

  J-GLOBAL

• Examination of high accuracy of mango grade classification by image analysis and composition of fruit imaging environment

  城間康, 健山智子, 平良英三, 長山格

  電気学会研究会資料   ( IIS-21-001-004.006 ) 13 - 14   2021.02

   

  J-GLOBAL

display all >>

Grant-in-Aid for Scientific Research 【 display / non-display 】

Grant-in-Aid for Scientific Research 【 display / non-display 】

• Elucidation of the Paper Road by data science. -Based on Quantitative, Qualitative research and AI Multidimensional analysis-

  Grant-in-Aid for Scientific Research(A)

  Project Year: 2022.04  -  2027.03 

  Direct: 32,300,000 (YEN)  Overheads: 41,990,000 (YEN)  Total: 9,690,000 (YEN)

• Grant-in-Aid for Scientific Research(C)

  Project Year: 2020  -  2025.03 

  Direct: 3,200,000 (YEN)  Overheads: 4,160,000 (YEN)  Total: 960,000 (YEN)

• Gesture model and database construct for intaractive visualization of medical images in surgery

  Grant-in-Aid for Scientific Research(C)

  Project Year: 2018.04  -  2021.03 

  Investigator(s): Tateyama Tomoko 

  Direct: 3,400,000 (YEN)  Overheads: 4,420,000 (YEN)  Total: 1,020,000 (YEN)

  　View Summary

  In this study, we developed the touch-less interactive system for visualization medical images based on gesture recognition using RGB-D sensors in an simulated surgery environment. The gestures constructed in this study consisted of 25 different gesture types, which were observed from the front and from the upper 45-degree frontal direction, and which were simultaneously acquired in terms of color and depth information. Then, the dataset was published as the MaHG-RGBD database. In addition, for more efficient and accurate gesture analysis, we adopted deep learning to perform more detailed feature analysis and recognition.

Social Activity 【 display / non-display 】

Social Activity 【 display / non-display 】

• 2020.09

  　

  　

• 2020.04