API Reference#

MAISI NIM provides following API endpoints:

  • GET: /v1/health/live - Check if service is alive (might not be ready yet)

  • GET: /v1/health/ready - Check if service is ready and model is ready for inference

  • GET: /v1/license - Return the license for the NIM

  • GET: /v1/maisi/info - Fetch detailed information about the model such as version and labels

  • POST: /v1/maisi/run - Generate CT images with paired segmentation masks

Payload Options#

Parameter

Required

Type

Description

Options/Range

num_output_samples

Yes

Integer

Number of images to generate

Positive integer

body_region

Yes

List of Strings

Target body regions

[“head”, “chest”, “thorax”, “abdomen”, “pelvis”, “lower”]

anatomy_list

No

List of Strings

Specific anatomical structures

See Supported Anatomy section

output_size

No

List of 3 Integers

Image dimensions (x, y, z)

x, y: 256, 384, 512
z: 128, 256, 384, 512, 640, 768

spacing

No

List of 3 Floats

Voxel spacing

Each value: 0.5 to 5.0

controllable_anatomy_size

No

List of Tuples (String, Float) for organ name and size

Organ size control (max 10)

Organs: [“liver”, “gallbladder”, “stomach”, “pancreas”, “colon”, “lung tumor”, “bone lesion”, “hepatic tumor”, “colon cancer primaries”, “pancreatic tumor”]
Size: 0.0 to 1.0, or -1 (remove)

pre_signed_url

No

String

URL for result upload

-

local_working_dir

No

String

If specified, the generated images will be saved in the provided directory.

-

image_output_ext

No

String

Output file extension

Supported extensions: “.nrrd”, “.nii”, “.nii.gz”, “.dcm”. Default: “.nii.gz”

label_output_ext

No

String

Output file extension

Supported extensions: “.nrrd”, “.nii”, “.nii.gz”, “.dcm”. Default: “.nii.gz”

Supported Anatomy#

You can find all of the classes available in the model in the MAISI label_dict.json.