RaDialog is an image-text-to-text model hosted on Hugging Face for generating radiology reports from medical images. It is provided as a Transformers-compatible model under the name ChantalPellegrini/RaDialog-interactive-radiology-report-generation and carries the tags medical, radiology report generation, and medical chatbot.
The model is built for the specific task of producing textual radiology reports. Its listed capabilities include image-text-to-text processing and text generation. It is associated with the arxiv preprint 2311.18681 and is tagged with mimic-cxr and llava, indicating its training and architectural lineage.
It is delivered as an open-source model on the Hugging Face platform. Users load it through the Transformers library using either a high-level pipeline for image-text-to-text or by directly instantiating AutoProcessor and AutoModelForCausalLM. The model card provides code examples for both approaches and supports deployment via standard Hugging Face inference methods.
The model is released under the Apache-2.0 license. No pricing information is stated because it is offered as a freely downloadable open-source artifact.
RaDialog Interactive Radiology Report Generation sits in PulseGate's Foundation models & chat category. It focuses on generating accurate and interactive radiology reports from medical images without manual dictation. RaDialog Interactive Radiology Report Generation is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web, the command line, and API.
Behind RaDialog Interactive Radiology Report Generation is ChantalPellegrini, and the product first shipped in 2024. The project is developed in the open on GitHub with 26 stars. Among its 3 catalogued features are Medical Image Analysis, Radiology Report Generation, and Interactive Chat.
Latest indexed changes and source events
ChantalPellegrini/RaDialog-interactive-radiology-report-generation verified by the PulseGate indexer
Other apps tracked under the same category.
