plug.directory
Add my server

NeuroSAM3

by mmrechco.huggingface.mmrech/neurosam3

  • Remote endpoint
  • 11 tools
  • APACHE-2.0
  • NeuroSAM3_agent_chat Agent Chat: send a natural-language request about the uploaded image. The agent (LLM via HF Inference Providers) plans tool calls — BiomedCLIP classification, SAM 3 / MedSAM segmentation, ROI measurement, report — and returns a synthesized answer plus overlay images. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_automatic_masks Automatic mask generation: a grid of point prompts through the SAM 3 tracker, NMS by IoU. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_clinical_pipeline Clinical Pipeline: classify -> segment -> measure -> report in one click. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_compare_ground_truth Ground truth: compare SAM 3 (or MedSAM box from GT bbox) with an expert mask -> Dice, IoU, HD95. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_compare_models Compare: SAM 3 text vs MedSAM (box from SAM 3) vs SAM 3 tracker (same box); pairwise Dice. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_edge_regions Classical Canny-based region proposal (no GPU) for quick boundary exploration. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_research_pipeline Research: batch segmentation with per-subject statistics and a ZIP export bundle. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_segment_interactive Point & Box: SAM 3 tracker (points/box) or MedSAM (box) interactive segmentation. points_text: 'x,y,label; x,y,label' in pixel coordinates (label 1 = foreground, 0 = background). If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_segment_text Segment: SAM 3 text-prompted segmentation with instance table, ROI metrics and exports. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_series_segment Series: segment every ordered slice of the selected series with one prompt; estimate volume. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
  • NeuroSAM3_system_diagnostics Run a GPU probe (torch/CUDA info, model devices, raw SAM 3 scores on a bundled FLAIR slice) and return the recent application log.

As the server's own listing gives them. We never call a tool.