Add Algorithm

Integration with CARPL

Follow the steps to integrate any algorithm with CARPL

Log in to CARPL with your registered email id and go to Algorithms section present on the left panel of the window
Click on ADD ALGORITHM on the right top corner of the window
Fill the details
- Name: Name of the algorithm
- Description: Description of the algorithm
- Choose Modality: Modality of input data to the algorithm
- Choose Body Part: Body part for which the algorithm is designed for
- Check mark ‘Inferencing Available’ if the algorithm is ready for inferencing
API Details: A dictionary with API details to upload dataset and receive results
Algorithm Configuration: A dictionary with algorithm’s inferencing details
Click on submit

API details is a dictionary with the following keys:

Endpoint: API endpoint URL
Type: Type of Request- POST
Headers: Additional information to connect client and server. For e.g.- Bearer token for authorization

Endpoint: API URL to retrieve results with studyIUID
Type: type of request- GET
Headers: Additional information to connect client and server. For e.g.- Bearer token for authorization

Endpoint: API URL to fetch ROI json
Type: type of request- GET
Headers: Additional information to connect client and server. For e.g.- Bearer token for authorization

An example API Details dictionary is shown below

Algorithm Configuration is a dictionary with the following keys

UploadType: format of the files to be uploaded (DICOM/TAR.GZ)

EnforceSeriesDescription: dictionary to enforce Series description condition on the uploaded file. Following keys are used:

Status: true/false. If true, series description condition will be enforced
Keywords: list of keywords of series description to enforce. For eg- T1,T2(for MRI)

PostProcessing: true/false. If the algorithm is not manually integrated, put this value to false

AlgorithmOutputs: dictionary containing output type(s)

ProcessingTime: Time(in seconds) after which the next processing request should be sent

MaxRetries: Max number of times a case should be rerun on the algorithm before giving it a FAIL status

An example is shown below

The output of the algorithm is expected to be in json format with list of dictionaries.

Each dictionary corresponds to only one finding and should contain the following

Type: (string) “rectangle” or “freehand”. Whether the ROI points in the “points” key are for rectangle or freehand.
Points: (list of list). If “type” is rectangle, then it should be a list of [x,y] points representing left top point and right bottom points. If “type” is freehand, then it should be a list of all [x,y] points.
StudyInstanceUID: (string) StudyInstanceUID of the case
SeriesInstanceUID: (string) SeriesInstanceUID of the case
SOPInstanceUID: (string) SOPInstanceUID of the case
Finding_name : (string) finding corresponding to the ROI

Page updated

Report abuse