matlab-read-medical-data

Name: matlab-read-medical-data
Author: matlab

815stars105forks

How to install matlab-read-medical-data?

matlab/matlab-agentic-toolkit/matlab-read-medical-data

$npx -y skills add matlab/matlab-agentic-toolkit --skill matlab-read-medical-data

Installs into the current project.

Summary

Read, write, and manipulate medical imaging data (DICOM, NIfTI, NRRD) in MATLAB. Covers Image Processing Toolbox functions (dicomreadVolume, niftiread, dicomContours, dicomanon) and Medical Imaging Toolbox enhanced APIs (medicalVolume, medicalImage, medicalref3d, extractSlice, up

Files · 1

View on GitHub

SKILL.md

1	# Read and Write Medical Data
2
3	Read, write, and manipulate medical imaging data in MATLAB. This skill covers both Image Processing Toolbox (IPT) functions and Medical Imaging Toolbox (MIT) enhanced APIs.
4
5	## When to Use
6
7	- Reading or writing DICOM, NIfTI, or NRRD files
8	- Listing DICOM series with `dicomCollection`
9	- Extracting spatial referencing or coordinate transforms
10	- Changing volume orientation or extracting oriented slices
11	- Working with DICOM RT structures (contours, masks, modify/write)
12	- Anonymizing DICOM data
13
14	## When NOT to Use
15
16	- Displaying or visualizing volumes (use `matlab-display-volume` skill)
17	- Displaying 2-D medical images with annotations (use `matlab-display-image` skill)
18	- Reading non-medical image formats (PNG, TIFF, JPEG) — use `imread`
19
20	## Toolbox Detection — CRITICAL FIRST STEP
21
22	Always check which toolboxes are available before choosing an approach. If Medical Imaging Toolbox is installed, prefer its APIs. If only Image Processing Toolbox is available, use IPT patterns.
23
24	## Task → Function Quick Reference
25
26	\| Task \| IPT only \| With Medical Imaging Toolbox (preferred) \|
27	\|------\|----------\|------------------------------------------\|
28	\| Read single DICOM file \| `dicomread` + `dicominfo` \| `medicalImage` \|
29	\| Read DICOM folder \| `dicomreadVolume` \| `medicalVolume` \|
30	\| Read NIfTI \| `niftiread` + `niftiinfo` \| `medicalVolume` \|
31	\| Read NRRD \| — (requires MIT) \| `medicalVolume` or `nrrdread` + `nrrdinfo` \|
32	\| List DICOM series \| `dicomCollection` \| `dicomCollection` \|
33	\| Spatial referencing \| `imref3d` \| `medicalref3d` \|
34	\| Extract oriented slice \| Manual indexing \| `extractSlice` \|
35	\| Change orientation \| Manual `permute` \| `updateOrientation` \|
36	\| Read DICOM RT structure \| `dicomContours(dicominfo(file))` \| Same \|
37	\| Anonymize DICOM \| `dicomanon` + `dicomuid` \| Same \|
38	\| Visualize volume \| `volumeViewer` \| `medicalVolumeViewer` or `volshow(medVol)` \|
39
40	## Top 4 Patterns
41
42	### 1. Read DICOM folder
43
44	Call `medicalVolume` or `dicomreadVolume` directly on the DICOM folder path. Do NOT call `dicomCollection` first — it is unnecessary when reading a single-series folder.
45
46	```matlab
47	% WITH Medical Imaging Toolbox (preferred):
48	medVol = medicalVolume("path/to/dicom/folder");
49	V = medVol.Voxels; % Auto-rescaled (e.g., HU for CT)
50	spacing = medVol.VoxelSpacing; % [dx dy dz] in mm
51	orientation = medVol.Orientation; % "transverse", "coronal", "sagittal"
52	modality = medVol.Modality; % "CT", "MR"
53
54	% Access spatial referencing via VolumeGeometry (medicalref3d object)
55	geom = medVol.VolumeGeometry;
56	geom.VolumeSize; % [rows cols slices]
57	geom.PatientCoordinateSystem; % "LPS+" or "RAS+"
58	geom.Position; % [slices×3] slice positions in patient coords
59	geom.VoxelDistances; % {[slices×3] [slices×3] [slices×3]} per-axis distances
60	geom.PixelSpacing; % [slices×2] in-plane pixel spacing per slice
61	geom.IsAffine; % true if uniform spacing (affine transform)
62	geom.IsAxesAligned; % true if volume axes align with patient axes
63	geom.IsMixed; % true if slices have varying pixel spacing
64
65	% IPT only:
66	[V, spatial, dim] = dicomreadVolume("path/to/dicom/folder");
67	V = squeeze(V); % Remove singleton 4th dimension
68	```
69
70	### 2. Read NIfTI file
71
72	```matlab
73	% WITH Medical Imaging Toolbox (preferred):
74	medVol = medicalVolume("path/to/file.nii.gz");
75
76	% IPT only:
77	V = niftiread("path/to/file.nii.gz");
78	info = niftiinfo("path/to/file.nii.gz");
79	voxelSize = info.PixelDimensions(1:3);
80	```
81
82	### 3. List DICOM series and read one
83
84	Use `dicomCollection` only when:
85	- The user says the folder contains multiple series or volumes
86	- `medicalVolume` or `dicomreadVolume` fails with an error (e.g., "not a DICOM file" or "multiple volumes detected")
87	- You need to identify what series exist before deciding which one to read
88
89	`dicomCollection` scans the directory, excludes non-DICOM files, and returns a table where each row is one series. It does not read pixel data.
90
91	```matlab
92	collection = dicomCollection("path/to/directory");
93	disp(collection); % Table with Modality, SeriesDescription, Rows, Columns, Frames
94
95	% WITH Medical Imaging Toolbox:
96	medVol = medicalVolume(collection, "s1");
97
98	% IPT only:
99	[V, spatial] = dicomreadVolume(collec

People who liked this also viewed

6 picks

Type

matlab-read-medical-data

815stars105forks

View on GitHub

How to install matlab-read-medical-data?

matlab/matlab-agentic-toolkit/matlab-read-medical-data

$npx -y skills add matlab/matlab-agentic-toolkit --skill matlab-read-medical-data

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Read and Write Medical Data
2
3	Read, write, and manipulate medical imaging data in MATLAB. This skill covers both Image Processing Toolbox (IPT) functions and Medical Imaging Toolbox (MIT) enhanced APIs.
4
5	## When to Use
6
7	- Reading or writing DICOM, NIfTI, or NRRD files
8	- Listing DICOM series with `dicomCollection`
9	- Extracting spatial referencing or coordinate transforms
10	- Changing volume orientation or extracting oriented slices
11	- Working with DICOM RT structures (contours, masks, modify/write)
12	- Anonymizing DICOM data
13
14	## When NOT to Use
15
16	- Displaying or visualizing volumes (use `matlab-display-volume` skill)
17	- Displaying 2-D medical images with annotations (use `matlab-display-image` skill)
18	- Reading non-medical image formats (PNG, TIFF, JPEG) — use `imread`
19
20	## Toolbox Detection — CRITICAL FIRST STEP
21
22	Always check which toolboxes are available before choosing an approach. If Medical Imaging Toolbox is installed, prefer its APIs. If only Image Processing Toolbox is available, use IPT patterns.
23
24	## Task → Function Quick Reference
25
26	\| Task \| IPT only \| With Medical Imaging Toolbox (preferred) \|
27	\|------\|----------\|------------------------------------------\|
28	\| Read single DICOM file \| `dicomread` + `dicominfo` \| `medicalImage` \|
29	\| Read DICOM folder \| `dicomreadVolume` \| `medicalVolume` \|
30	\| Read NIfTI \| `niftiread` + `niftiinfo` \| `medicalVolume` \|
31	\| Read NRRD \| — (requires MIT) \| `medicalVolume` or `nrrdread` + `nrrdinfo` \|
32	\| List DICOM series \| `dicomCollection` \| `dicomCollection` \|
33	\| Spatial referencing \| `imref3d` \| `medicalref3d` \|
34	\| Extract oriented slice \| Manual indexing \| `extractSlice` \|
35	\| Change orientation \| Manual `permute` \| `updateOrientation` \|
36	\| Read DICOM RT structure \| `dicomContours(dicominfo(file))` \| Same \|
37	\| Anonymize DICOM \| `dicomanon` + `dicomuid` \| Same \|
38	\| Visualize volume \| `volumeViewer` \| `medicalVolumeViewer` or `volshow(medVol)` \|
39
40	## Top 4 Patterns
41
42	### 1. Read DICOM folder
43
44	Call `medicalVolume` or `dicomreadVolume` directly on the DICOM folder path. Do NOT call `dicomCollection` first — it is unnecessary when reading a single-series folder.
45
46	```matlab
47	% WITH Medical Imaging Toolbox (preferred):
48	medVol = medicalVolume("path/to/dicom/folder");
49	V = medVol.Voxels; % Auto-rescaled (e.g., HU for CT)
50	spacing = medVol.VoxelSpacing; % [dx dy dz] in mm
51	orientation = medVol.Orientation; % "transverse", "coronal", "sagittal"
52	modality = medVol.Modality; % "CT", "MR"
53
54	% Access spatial referencing via VolumeGeometry (medicalref3d object)
55	geom = medVol.VolumeGeometry;
56	geom.VolumeSize; % [rows cols slices]
57	geom.PatientCoordinateSystem; % "LPS+" or "RAS+"
58	geom.Position; % [slices×3] slice positions in patient coords
59	geom.VoxelDistances; % {[slices×3] [slices×3] [slices×3]} per-axis distances
60	geom.PixelSpacing; % [slices×2] in-plane pixel spacing per slice
61	geom.IsAffine; % true if uniform spacing (affine transform)
62	geom.IsAxesAligned; % true if volume axes align with patient axes
63	geom.IsMixed; % true if slices have varying pixel spacing
64
65	% IPT only:
66	[V, spatial, dim] = dicomreadVolume("path/to/dicom/folder");
67	V = squeeze(V); % Remove singleton 4th dimension
68	```
69
70	### 2. Read NIfTI file
71
72	```matlab
73	% WITH Medical Imaging Toolbox (preferred):
74	medVol = medicalVolume("path/to/file.nii.gz");
75
76	% IPT only:
77	V = niftiread("path/to/file.nii.gz");
78	info = niftiinfo("path/to/file.nii.gz");
79	voxelSize = info.PixelDimensions(1:3);
80	```
81
82	### 3. List DICOM series and read one
83
84	Use `dicomCollection` only when:
85	- The user says the folder contains multiple series or volumes
86	- `medicalVolume` or `dicomreadVolume` fails with an error (e.g., "not a DICOM file" or "multiple volumes detected")
87	- You need to identify what series exist before deciding which one to read
88
89	`dicomCollection` scans the directory, excludes non-DICOM files, and returns a table where each row is one series. It does not read pixel data.
90
91	```matlab
92	collection = dicomCollection("path/to/directory");
93	disp(collection); % Table with Modality, SeriesDescription, Rows, Columns, Frames
94
95	% WITH Medical Imaging Toolbox:
96	medVol = medicalVolume(collection, "s1");
97
98	% IPT only:
99	[V, spatial] = dicomreadVolume(collec

People who liked this also viewed

6 picks

Type