Can I convert DICOM images to standard formats like PNG?

Absolutely. The skill includes a dedicated conversion workflow using Pillow and NumPy to transform medical pixel data into standard image formats.

Can this skill handle compressed DICOM files?

Yes, it provides guidance on installing and using additional handlers for JPEG, JPEG 2000, and RLE compression formats within the pydicom ecosystem.

How does this skill help with data privacy?

It provides specific scripts and code patterns to remove or replace sensitive patient identifiable information (PHI) within DICOM tags, facilitating HIPAA-compliant research.

Does it support batch processing of medical image series?

Yes, it includes workflows for reading entire directories of DICOM files and reconstructing them into 3D NumPy volumes for analysis.

Pydicom Medical Imaging

Name: Pydicom Medical Imaging
Author: ricable

byricable

•

Ciencia de Datos y ML

Reads, writes, and manipulates DICOM medical imaging data and metadata for healthcare and research applications.

Acerca de

The Pydicom skill for Claude Code enables developers to work seamlessly with Digital Imaging and Communications in Medicine (DICOM) files, the global standard for medical imaging. It provides robust implementation patterns for extracting pixel data from CT, MRI, and X-ray scans, managing complex metadata tags, and ensuring data privacy through automated anonymization. Ideal for radiology workflows, PACS integration, and healthcare software development, this skill simplifies the handling of multi-frame images, compressed datasets, and 3D volume reconstruction within an AI-assisted development environment.

Características Principales

1 GitHub stars
Read and write DICOM files across various modalities (CT, MRI, Ultrasound)
Navigate and modify nested DICOM sequences and structured reports
Anonymize Protected Health Information (PHI) for clinical research compliance
Extract and manipulate pixel data with NumPy and Matplotlib integration
Handle compressed transfer syntaxes including JPEG 2000 and RLE

Casos de Uso

Building medical imaging analysis pipelines for machine learning models
Anonymizing large patient datasets for secure data sharing and research
Converting DICOM files to web-compatible formats like PNG, JPEG, or TIFF

Acerca de

Características Principales

1 GitHub stars
Read and write DICOM files across various modalities (CT, MRI, Ultrasound)
Navigate and modify nested DICOM sequences and structured reports
Anonymize Protected Health Information (PHI) for clinical research compliance
Extract and manipulate pixel data with NumPy and Matplotlib integration
Handle compressed transfer syntaxes including JPEG 2000 and RLE

Casos de Uso

Building medical imaging analysis pipelines for machine learning models
Anonymizing large patient datasets for secure data sharing and research
Converting DICOM files to web-compatible formats like PNG, JPEG, or TIFF