2430
View Abstract / View Presentation
Multi-sequence and multi-regional background segmentation on multi-centric DSC and DCE MRI using deep learning
Henitsoa RASOANANDRIANINA1, Anais BERNARD1, Guillaume GAUTIER1, Julien ROUYER1, Yves HAXAIRE2, Christophe AVARE3, and Lucile BRUN1
1Department of Research & Innovation, Olea Medical, La Ciotat, France, 2Clinical Program Department, Olea Medical, La Ciotat, France, 3Avicenna.ai, La Ciotat, France
A 2D U-net model exhibits very good performances (median Dice: 0.979, median inference duration: 0.15s per 3D volume) in background segmentation and removal on both DSC MRI data from the brain and DCE MRI data from brain, breast, abdomen, and pelvis regions.  

Figure 2: Illustrations of background segmentation results for the development database.

The columns display segmented slices per modality and anatomical region, whereas the rows correspond to the 3 different visual quality ratings (Perfect, Acceptable, Not acceptable). Dice, Jaccard and AMI values for the 3D volume are reported under each slice. Only two DSC brain volumes segmentations were found not acceptable.Their segmentations are displayed with transparency to show the underlying tissue.

Figure 1: Background segmentation performances in the development database.

Top: Quantitative results with values of Dice coefficient (Dice), Jaccard similarity index (Jaccard), and adjusted mutual information (AMI). Dice and Jaccard values range between [0-1], 1 means the two segmentations are identical. AMI values are <=1, 1 means the two clusters are identical.

Bottom: Qualitative (visual) evaluation of obtained segmentations with 3-stage rating: perfect, acceptable (i.e. without tissue voxels removed) and not acceptable (i.e. with tissue voxels removed) results.