PAI is provided with a demonstration case called MRI Tumor Detection, which is also used for this documentation. It is based on the MICCAI Brain Tumor Segmentation (BraTS) Challenge: . BraTS utilizes multi-institutional pre-operative MRI scans and focuses on the segmentation of intrinsically heterogeneous (in appearance, shape, and histology) brain glioma tumors.
Training and testing of the MRI Tumor Detection model in PAI was performed using the data from the 2020 BraTS Challenge containing 369 samples. Each sample consists of four MR images (native T1, post-Gd-contrast T1-weighted, T2 FLAIR, T2-weighted) and one image containing three reference segments as label numbers.
The MRI Tumor Detection architecture is a modified version of the convolutional neural network U-Net:
Output is a label image with three segments (label 1: non-enhancing tumor; label 2: peritumoral edema; label 4: Gd-enhancing tumor).
Bakas, Spyridon & Reyes Jan. (2019). Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge.