Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

ROENTGEN: case-based reasoning and radiation therapy planning.

J Berger1

  • 1Artificial Intelligence Laboratory, Univesity of Chicago, IL 60637.

Proceedings. Symposium on Computer Applications in Medical Care
|January 1, 1992
PubMed
Summary

ROENTGEN, an artificial intelligence design assistant, aids radiation therapy planning by learning from user experience and direct instruction. It addresses knowledge acquisition challenges in AI for medical applications.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Co-expression of mutated and normal adrenoleukodystrophy protein reduces protein function: implications for gene therapy of X-linked adrenoleukodystrophy.

Human molecular genetics·2000
Same author

Srf(-/-) ES cells display non-cell-autonomous impairment in mesodermal differentiation.

The EMBO journal·2000
Same author

A randomized comparison of balloon angioplasty versus rotational atherectomy in complex coronary lesions (COBRA study).

European heart journal·2000
Same author

Treatment of aortocoronary vein graft lesions with membrane-covered stents: A multicenter surveillance trial.

Circulation·2000
Same author

The law of unintended consequences in action: increase in incidence of hypokalemia with improved adequacy of dialysis.

Advances in peritoneal dialysis. Conference on Peritoneal Dialysis·2000
Same author

Schistosoma mansoni: adhesion of mannan-binding lectin to surface glycoproteins of cercariae and adult worms.

Experimental parasitology·2000

Area of Science:

  • Medical Physics
  • Artificial Intelligence
  • Radiation Therapy

Background:

  • Radiation therapy planning requires complex decision-making.
  • Existing AI systems may lack domain-specific knowledge.
  • Case-based reasoning (CBR) offers a potential solution for AI learning.

Purpose of the Study:

  • To present the knowledge acquisition and design techniques of ROENTGEN, an AI assistant for radiation therapy planning.
  • To explore how CBR can be enhanced with direct user instruction.
  • To address representational challenges in AI for complex domains.

Main Methods:

  • Utilizing case-based reasoning (CBR) for AI learning.
  • Implementing direct user instruction for knowledge acquisition.
  • Developing techniques for indexing, failure definition, explanation, and repair within the AI system.

Related Experiment Videos

Main Results:

  • ROENTGEN learns from both past problem-solving experiences and explicit user input.
  • The system addresses the need for an internal physics model through user guidance.
  • Techniques for knowledge acquisition and design in ROENTGEN are detailed.

Conclusions:

  • ROENTGEN effectively integrates CBR with user instruction for radiation therapy planning.
  • The AI system demonstrates a viable approach to knowledge acquisition in specialized domains.
  • This work highlights the importance of user interaction in developing AI for medical applications.