LAB LOGA page on LabLog, a review site (not the lab's official page)
Artificial Intelligence in Diagnostic Radiology Lab
Machine-translated · View original
The lab is a joint research chair that works to bring AI-based systems supporting diagnosis from medical images into clinical practice.
AboutAbout the lab
Bringing clinically usable AI to the front lines of diagnostic imaging.
The Joint Research Chair of Artificial Intelligence in Diagnostic Radiology researches the use of artificial intelligence in computer-aided diagnosis (CAD), which supports physicians' diagnosis based on medical images.
Together with companies, the lab tackles the challenges involved in developing AI-based CAD: preparing training data, developing high-accuracy systems, and incorporating them into the clinical workflow.
The lab also develops AI technologies that handle the problem of limited case numbers, as well as explainable AI, aiming for practical use of next-generation AI-CAD.
Key terms
- Computer-aided diagnosis (CAD)
- A system in which a computer supports a physician's diagnostic imaging. CAD that uses AI is called AI-CAD.
- Deep learning
- One AI technique, strong at image recognition. Expectations for its use in medicine are especially high.
- Joint research chair
- A university chair that tackles problems jointly with companies.
ResearchResearch themes
The lab aims for practical clinical use of AI-CAD, which uses deep-learning AI to support physicians' diagnostic imaging. Together with companies, it addresses three challenges: the shortage of training data, the development of high-accuracy CAD, and its integration into the clinical workflow.
*Illustrative imageBuilding large-scale image datasets for AI
The shortage of training data for AI is the first problem that urgently needs to be solved. The lab builds a large-scale database of imaging cases in which physicians have marked the locations of lesions.
*Illustrative imageHigh-accuracy CAD usable in real clinical practice
CAD for breast cancer and colorectal cancer screening is moving toward practical use, but development of the high-accuracy CAD needed in actual diagnostic imaging has not progressed. The lab addresses this challenge.
*Illustrative imageIntroducing CAD into the clinical workflow
Even CAD that has been successfully developed is often not incorporated into the clinical workflow. The lab tackles this problem together with companies as well.
*Illustrative imageAI for limited cases and explainable AI
The lab develops AI that handles the problem of limited case numbers (X-shot learning AI) and explainable AI (Explainable AI) technologies, aiming for practical use of next-generation AI-CAD.
MembersFaculty
- Project ProfessorMasatoshi Hori
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 Artificial Intelligence in Diagnostic Radiology Lab
Musculoskeletal Medical-Engineering Therapeutics LabGraduate School of Medicine, Department of MedicineDevelopment of artificial joints and computer-assisted surge…
Transformative Medical Information System Development LabGraduate School of Medicine, Department of MedicineInformation, human resource development, innovation / Develo…
Medical Data Science LabGraduate School of Medicine, Department of MedicineBuilding new evidence by integrating real-world data and cli…
Metabolism and Vascular Medicine LabGraduate School of Medicine, Department of MedicineLifestyle-related diseases and atherosclerosis: from basic 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: “CT Naeotom Alpha Pilsen 2022 (cropped)” Tomáš Vendiš / CC BY-SA 4.0 (cropped)
- Building large-scale image datasets for AI: “CT Brain Scan” Goleisureintl / CC BY 4.0 (cropped)
- High-accuracy CAD usable in real clinical practice: “Magnification view mammography” Cerevisae / CC BY-SA 4.0 (cropped)
- Introducing CAD into the clinical workflow: “Radiologist in San Diego CA 2010” w:User:Zackstarr / CC BY-SA 3.0 (cropped)
- AI for limited cases and explainable AI: “L’IA explicable & application exploitant la data comportementales pour profilage psychologique” Yanou Ramon, R.A. Farrokhnia, Sandra C. Matz & David Martens / CC BY 4.0 (cropped)
- Related lab (Musculoskeletal Medical-Engineering Therapeutics Lab): “Orthopedic surgery in Afghanistan 141103-N-JY715-999” Lt.Cmdr. Jesse Ehrenfeld / Public domain (cropped)
- Related lab (Transformative Medical Information System Development Lab): “E-learning process model” Khanb / CC BY-SA 3.0 (cropped)
- Related lab (Medical Data Science Lab): “Medical Data Collection and Screening - ATK Grassroots Development Programme - Kolkata” Biswarup Ganguly / CC BY 3.0 (cropped)
- Related lab (Metabolism and Vascular Medicine Lab): “Histopathology of coronary artery atherosclerosis, original” Mikael Häggström, M.D. Author info - Reusing images- Conflicts of interest: None Mikael Häggström, M.D.Consent note: Consent from the patient or patient's relatives is regarded as redundant, because of absence of identifiable features (List of HIPAA identifiers) in the media and case information (See also HIPAA case reports guidance). / CC0 (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.