一键在 Manus 中运行任何 Skill

medsam2-3d-segmentation

星标31

分支8

更新时间2026年6月18日 19:20

Operate MedSAM2 for promptable segmentation of 3D medical images and medical videos, including CT lesion propagation, MRI volumes, RECIST-guided prompts, efficient CPU-oriented variants, training, and 3D Slicer integration. Use when generating or validating volumetric masks from sparse prompts or propagating masks through image slices or video frames.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

mdbabumiamssm

mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

MedSAM2 3D Segmentation

Use MedSAM2 to accelerate annotation and research segmentation. Every generated mask requires anatomical and task-specific quality review before quantitative or clinical use.

Workflow

Define the target anatomy or lesion, modality, acquisition protocol, prompt source, and downstream measurement.
De-identify inputs and preserve voxel spacing, orientation, affine, frame order, and original series identifiers in a controlled manifest.
Convert DICOM or vendor formats with a validated pipeline. Do not treat array index order as physical orientation.
Choose the prompt strategy:
- point or box prompt for interactive segmentation;
- RECIST marker or middle-slice box for lesion propagation;
- initial mask for video propagation.
Run a pilot and inspect propagation across the full volume or video, not only the prompted slice or frame.
Post-process only with prespecified operations such as component filtering or hole filling, and compare masks before and after each operation.
Evaluate Dice, surface Dice, Hausdorff distance, lesion-wise detection, volume error, and inter-reader variability as appropriate.
Stratify performance by scanner, site, contrast phase, slice thickness, anatomy, lesion size, and prompt quality.
Export masks with the original geometry and retain prompt provenance for audit.

Guardrails

Do not use unreviewed masks for diagnosis, radiation planning, surgery, or response assessment.
Detect missing slices, inconsistent orientation, anisotropic spacing, motion, and corrupted frames.
Review small lesions and volume boundaries slice by slice.
Do not evaluate only on datasets used for model development.
Verify checkpoint, dataset, SAM2, and downstream plugin licenses separately.
Require qualified clinical annotation and local validation for real-world deployment.

Output Contract

Return input geometry and provenance, prompt type, checkpoint, preprocessing, segmentation metrics, per-case failures, subgroup analysis, post-processing, exported-mask format, and review status.

Read references/operations.md for installation, inference commands, training patterns, and canonical sources.

同仓库更多 Skills

同仓库

monai-medical-imaging

mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-

Build reproducible healthcare imaging pipelines with Project MONAI for DICOM, NIfTI, pathology, and multidimensional imaging tasks including preprocessing, augmentation, training, sliding-window inference, evaluation, model bundles, labeling, and deployment. Use when implementing medical image classification, segmentation, registration, detection, generative, or foundation-model workflows in PyTorch.

2026-06-1831

txgemma-therapeutics

mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-

Operate Google TxGemma prediction and chat models for therapeutic property prediction across small molecules, proteins, nucleic acids, diseases, targets, and cell lines. Use when formatting Therapeutics Data Commons tasks, choosing TxGemma model size or variant, running local or Model Garden inference, fine-tuning on private therapeutic data, or evaluating TxGemma in drug-discovery workflows.

2026-06-1831

opencrispr-gene-editors

mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-

Evaluate and operate released Profluent OpenCRISPR gene-editing systems, especially OpenCRISPR-1, for controlled research workflows using its published Cas9-like protein, compatible guide RNA designs, protocols, licensing, specificity testing, and experimental validation. Use when comparing OpenCRISPR-1 with SpCas9, planning nonclinical editing studies, or assessing use in nuclease, nickase, deactivated, base, prime, or epigenome-editing contexts.

2026-06-1831

transcriptformer-cell-embeddings

mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-

Operate CZI TranscriptFormer cross-species generative single-cell models to produce cell embeddings, contextual gene embeddings, likelihoods, zero-shot classifiers, disease-state representations, and regulatory analyses from raw-count AnnData files. Use when selecting TF-Sapiens, TF-Exemplar, or TF-Metazoa, processing in- or out-of-distribution species, or scaling embedding extraction across GPUs.

2026-06-1831

protenix-structure-prediction

mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-

Operate ByteDance Protenix-v2 for open biomolecular structure prediction of proteins, antibodies, nucleic acids, ligands, and complexes using JSON inputs, MSA and template features, constraints, and inference-time sampling. Use when running Protenix locally or through its server, comparing AlphaFold3-style open models, or building reproducible co-folding evaluations.

2026-06-1831

medgemma-health-ai

mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills-

Build and evaluate medical text and vision applications with Google MedGemma, including MedGemma 1.5 workflows for CT, MRI, whole-slide pathology, longitudinal chest X-rays, lab reports, and EHR text. Use when prototyping, fine-tuning, deploying, or validating MedGemma-based health AI under clinical data and safety controls.

2026-06-1831

name	medsam2-3d-segmentation
description	Operate MedSAM2 for promptable segmentation of 3D medical images and medical videos, including CT lesion propagation, MRI volumes, RECIST-guided prompts, efficient CPU-oriented variants, training, and 3D Slicer integration. Use when generating or validating volumetric masks from sparse prompts or propagating masks through image slices or video frames.

MedSAM2 3D Segmentation

Use MedSAM2 to accelerate annotation and research segmentation. Every generated mask requires anatomical and task-specific quality review before quantitative or clinical use.

Workflow

Define the target anatomy or lesion, modality, acquisition protocol, prompt source, and downstream measurement.
De-identify inputs and preserve voxel spacing, orientation, affine, frame order, and original series identifiers in a controlled manifest.
Convert DICOM or vendor formats with a validated pipeline. Do not treat array index order as physical orientation.
Choose the prompt strategy:
- point or box prompt for interactive segmentation;
- RECIST marker or middle-slice box for lesion propagation;
- initial mask for video propagation.
Run a pilot and inspect propagation across the full volume or video, not only the prompted slice or frame.
Post-process only with prespecified operations such as component filtering or hole filling, and compare masks before and after each operation.
Evaluate Dice, surface Dice, Hausdorff distance, lesion-wise detection, volume error, and inter-reader variability as appropriate.
Stratify performance by scanner, site, contrast phase, slice thickness, anatomy, lesion size, and prompt quality.
Export masks with the original geometry and retain prompt provenance for audit.

Guardrails

Do not use unreviewed masks for diagnosis, radiation planning, surgery, or response assessment.
Detect missing slices, inconsistent orientation, anisotropic spacing, motion, and corrupted frames.
Review small lesions and volume boundaries slice by slice.
Do not evaluate only on datasets used for model development.
Verify checkpoint, dataset, SAM2, and downstream plugin licenses separately.
Require qualified clinical annotation and local validation for real-world deployment.

Output Contract

Return input geometry and provenance, prompt type, checkpoint, preprocessing, segmentation metrics, per-case failures, subgroup analysis, post-processing, exported-mask format, and review status.

Read references/operations.md for installation, inference commands, training patterns, and canonical sources.