LAB LOGA page on LabLog, a review site (not the lab's official page)
Koizumi Lab
Machine-translated · View original
A lab that digitizes medical skills using ultrasound and robots.
AboutAbout the lab
Digitizing medical skills and building them into robots
The Koizumi Lab applies IT such as AI and robotics to medicine, and researches robots for diagnosis and treatment using ultrasound.
The lab proceeds with development based on the concept of "medical skill digitization," in which medical skills are organized by function and built into robot mechanisms and programs.
The lab is building systems that use high-intensity focused ultrasound to diagnose and treat affected areas without cutting the body.
Lab visits are accepted at any time.
Key terms
- High-intensity focused ultrasound
- Technology that concentrates ultrasound to focus energy on a small region inside the body without damaging the surrounding tissue. It is also called HIFU.
- Medical skill digitization
- The concept of extracting diagnostic and treatment skills as functions, organizing them, and building them as functions into mechanisms, control, and image processing.
- Body motion compensation
- A method that examines the movement of an affected area that moves with breathing and heartbeat, and makes the system make the same movement so that it follows the area.
NewsLab news
A master's student received the 27th Encouragement Award of the Japan Society of Ultrasonics in Medicine
A paper by Assistant Professor Peiji Chen et al. was published in Neurocomputing
A paper by Assistant Professor Peiji Chen et al. was published in IEEE Robotics and Automation Letters
ResearchResearch themes
This lab applies IT and robotics to medicine, and studies how to build specialized diagnostic and treatment skills into medical devices that are easy for general healthcare workers to use. Specifically, it builds high-intensity focused ultrasound systems that diagnose and treat affected areas without cutting the body, based on the concept of turning medical skills into technology and digitizing them (medical skill digitization).
*Illustrative imageUltrasound treatment that follows a moving target
The system tracks and monitors, with high accuracy, affected areas that move with breathing and heartbeat, and delivers ultrasound precisely to them. Using body motion compensation that follows this movement, the lab proposes a mechanism that treats cancer and stones with a low burden on the patient, without cutting the skin.
*Illustrative imageMedical skill digitization: turning skills into functions
The lab extracts diagnostic and treatment skills as functions, breaks them down and reconstructs them, and analyzes them quantitatively. It then builds them as functions into mechanism, control, and image-processing algorithms, and uses them to develop medical support systems.
*Illustrative imageTracking and fragmenting stones
The lab proposes a method that automatically detects stones in ultrasound images and tracks them accurately even amid the noise caused by focused ultrasound irradiation. In tracking and fragmentation experiments using model stones and excised animal kidneys, it achieved a tracking accuracy of 2.5 mm.
*Illustrative imageTracking kidney cancer from images
Unlike stones, cancer has no landmark such as high brightness in ultrasound images. The lab therefore uses information on the kidney's contour and texture (pattern). In the contour-based method, a 3D kidney model that includes the shape of the tumor is overlaid on the ultrasound image to identify the tumor's position indirectly.
MembersFaculty
The Koizumi Lab consists of faculty, visiting professors, visiting associate professors, and visiting researchers, industry-academia collaboration coordinators, academic support staff, master's and undergraduate students, and international students.As of 2026
- ProfessorNorihiko Koizumi
- Assistant ProfessorPeiji Chen
- Assistant ProfessorJiayi Zhou
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Koizumi Lab
Nakamura LabSchool of Informatics and Engineering, Class II (Fusion)Artificial intelligence / Intelligent robotics / Human-robot…Noda LabSchool of Informatics and Engineering, Class II (Fusion)Intelligent robots
Matsumoto LabSchool of Informatics and Engineering, Class II (Fusion)Perceptual information processing / human-machine symbiotic …
Nomura LabSchool of Informatics and Engineering, Class II (Fusion)Acoustic electronics / ultrasonics / nonlinear acoustics / s…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Medical ultrasound examination” Christopher Hubenthal, U.S. Air Force / Public domain (cropped)
- Ultrasound treatment that follows a moving target: “Ultrasound-guided high-intensity focused ultrasound system” Vivian Wai-Yan Ng, Vincent Yuk-Tong Cheung / CC BY 4.0 (cropped)
- Medical skill digitization: turning skills into functions: “WBAMC first in DoD to use robot for surgery 160426-A-EK666-506” Marcy Sanchez / Public domain (cropped)
- Tracking and fragmenting stones: “Kidney Stone Image 4172-PH” US gov / Public domain (cropped)
- Tracking kidney cancer from images: “Ultrasound of left kidney lower pole with stone” Cerevisae / CC BY-SA 4.0 (cropped)
- Related lab (Nakamura Lab): “Robot based on AI on the move in the conference hall” Shani Evenstein / CC BY-SA 4.0 (cropped)
- Related lab (Matsumoto Lab): “2008 Robot Taiwan CSIST Intelligent Hazard Removing Robot” Rico Shen / CC BY-SA 3.0 (cropped)
- Related lab (Nomura Lab): “40kHz ultrasonic transducer” DMGualtieri / CC BY-SA 4.0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.