IMedicalVLM<T>

Interfaces · AiDotNet.VisionLanguage.Interfaces

Interface for medical domain vision-language models specializing in biomedical image understanding.

Implements: IGenerativeVisionLanguageModel<T>

Known implementations: DragonflyMed<T>, LLaVAMed<T>, MedFlamingo<T>, PathVLM<T>, RadFM<T>

How It Works

Medical VLMs are trained on biomedical image-text pairs for tasks such as radiology report generation, medical visual question answering, pathology analysis, and clinical decision support.

Properties

Property Summary
string LanguageModelName { get; } Gets the name of the language model backbone.
string MedicalDomain { get; } Gets the medical domain this model specializes in (e.g., “Radiology”, “Pathology”, “General”).

Methods

Method Summary
Tensor<T> AnswerMedicalQuestion(Tensor<T> image, string question) Answers a medical question about a biomedical image.