원클릭으로 Manus에서 모든 스킬 실행

monai-medical-imaging

스타31

포크8

업데이트2026년 6월 18일 19:20

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.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

mdbabumiamssm

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

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

MONAI Medical Imaging

Use MONAI as the domain framework around a clearly defined clinical imaging task, not as a substitute for data governance, study design, or external validation.

Workflow

Define the clinical question, modality, target, unit of analysis, annotation source, and intended deployment setting.
Build patient-level train, validation, and test splits before preprocessing. Separate sites, scanners, or time periods when testing generalization.
Preserve physical metadata: orientation, spacing, affine, DICOM identifiers, acquisition parameters, and label geometry.
Compose deterministic transforms before stochastic augmentation. Cache only transformations that are safe to reuse.
Choose the architecture, loss, sampling strategy, patch size, and class balancing from the target and memory constraints.
Train with fixed seeds, versioned configs, mixed-precision controls, checkpoint selection rules, and monitored failure states.
Use sliding-window or patch inference with explicit overlap and blending settings for large volumes.
Evaluate voxel or image metrics plus calibration, lesion-wise performance, surface metrics, subgroup behavior, and clinically meaningful errors.
Package the finalized pipeline as a versioned MONAI Bundle with preprocessing, network, post-processing, metadata, and tests.
Use MONAI Label for annotation workflows and MONAI Deploy components only after validating security, DICOM integration, and operational monitoring.

Guardrails

Prevent patient, study, patch, and temporal leakage.
Do not resample images and masks with incompatible interpolation.
Do not discard physical-space metadata after array conversion.
Report per-case failures and empty-mask behavior, not only aggregate Dice.
Pin MONAI, PyTorch, CUDA, bundle, and model-zoo versions.
Require local clinical, privacy, cybersecurity, and regulatory review before deployment.

Output Contract

Return the task definition, cohort and splits, transform graph, model and loss, training configuration, inference settings, metrics with uncertainty, failure analysis, bundle contents, and deployment readiness.

Read references/operations.md for installation, core patterns, bundle guidance, and canonical sources.

이 저장소의 다른 Skills

같은 저장소

medsam2-3d-segmentation

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

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.

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

monai-medical-imaging

description

MONAI Medical Imaging

Use MONAI as the domain framework around a clearly defined clinical imaging task, not as a substitute for data governance, study design, or external validation.

Workflow

Define the clinical question, modality, target, unit of analysis, annotation source, and intended deployment setting.
Build patient-level train, validation, and test splits before preprocessing. Separate sites, scanners, or time periods when testing generalization.
Preserve physical metadata: orientation, spacing, affine, DICOM identifiers, acquisition parameters, and label geometry.
Compose deterministic transforms before stochastic augmentation. Cache only transformations that are safe to reuse.
Choose the architecture, loss, sampling strategy, patch size, and class balancing from the target and memory constraints.
Train with fixed seeds, versioned configs, mixed-precision controls, checkpoint selection rules, and monitored failure states.
Use sliding-window or patch inference with explicit overlap and blending settings for large volumes.
Evaluate voxel or image metrics plus calibration, lesion-wise performance, surface metrics, subgroup behavior, and clinically meaningful errors.
Package the finalized pipeline as a versioned MONAI Bundle with preprocessing, network, post-processing, metadata, and tests.
Use MONAI Label for annotation workflows and MONAI Deploy components only after validating security, DICOM integration, and operational monitoring.

Guardrails

Prevent patient, study, patch, and temporal leakage.
Do not resample images and masks with incompatible interpolation.
Do not discard physical-space metadata after array conversion.
Report per-case failures and empty-mask behavior, not only aggregate Dice.
Pin MONAI, PyTorch, CUDA, bundle, and model-zoo versions.
Require local clinical, privacy, cybersecurity, and regulatory review before deployment.

Output Contract

Read references/operations.md for installation, core patterns, bundle guidance, and canonical sources.