HeroofAge

About
Summary
This algorithm is designed to perform PDAC lesion detection on contrast-enhanced CT(CECT) scans. The algorithm requires abdominal CECT image volume in Portal Venous phase and outputs: 1. A json file with the patient-level likelihood of lesion presence. 2.A .mha file containing the segmentation of detected lesions with each lesion volume represented by a probability value. This algorithm is based on nnUNet and utilizes pyradiomics for radiomics feature extraction.
Mechanism
Algorithm: The algorithm is based on two nnUNet model working at different resolutions. The first nnUNet extracts the ROI using the subsampled low resolution images. The LR ROI is then used to crop the original HR images. In addition, 4 voxel-based radiomics feature maps are generated by pyradiomics using the high resolution images and the LR ROI segmentation. The second nnUNet then performs PDAC detection using both the HR images and the matched radiomics feature maps.
Input:
- Datatype: Abdominal CECT volume in Portal Venous phase.
- File format: 4D DICOM or NIFTI image
- Target group: Patients older than 18 and younger than 99
Output:
- A json file containing the likelihood of patient having PDAC in percentage
- A mha file containing the segmentation of the detected PDAC lesion, with each lesion mask represented by the maximum voxel predicted probability within each mask
Interfaces
This algorithm implements all of the following input-output combinations:
Inputs | Outputs | |
---|---|---|
1 |
Validation and Performance
AUROC | AP | |
---|---|---|
Validation | 96.7% | 67.1% |
Test | 92.4% | 63.5% |
Challenge Performance
Date | Challenge | Phase | Rank |
---|---|---|---|
Oct. 28, 2024 | PANORAMA | Development Phase - Sanity Check | 1 |
Jan. 23, 2025 | PANORAMA | Development Phase - Tuning | 35 |
Feb. 25, 2025 | PANORAMA | Testing Phase | 2 |
Uses and Directions
This algorithm was developed for research purposes only.