A multi-task learning approach for compartmental model parameter estimation in DCE-CT sequences

Blandine Romain (1, 2, 3) , Veronique Letort (3) , Olivier Lucidarme (4) , Laurence Rouet (2) , Florence d'Alché-Buc (1, 5)

1 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes
2 Medisys - MedisysResearch Lab
3 MAS - Mathématiques Appliquées aux Systèmes - EA 4037
4 CHU Pitié-Salpêtrière [AP-HP]
5 TAO - Machine Learning and Optimisation

Today's follow-up of patients presenting abdominal tumors is generally performed through acquisition of dynamic sequences of contrast-enhanced CT. Estimating parameters of appropriate models of contrast intake diffusion through tissues should help characterizing the tumor physiology, but is impeded by the high level of noise inherent to the acquisition conditions. To improve the quality of estimation, we consider parameter estimation in voxels as a multi-task learning problem (one task per voxel) that takes advantage from the similarity between two tasks. We introduce a temporal similarity between tasks based on a robust distance between observed contrast-intake profiles of intensity. Using synthetic images, we compare multi-task learning using this temporal similarity, a spatial similarity and a single-task learning. The similarities based on temporal profiles are shown to bring significant improvements compared to the spatial one. Results on real CT sequences also confirm the relevance of the approach.

Domaines: Informatique [cs]

Blandine Romain, Veronique Letort, Olivier Lucidarme, Laurence Rouet, Florence d'Alché-Buc. A multi-task learning approach for compartmental model parameter estimation in DCE-CT sequences. 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2013), Sep 2013, Nagoya, Japan. pp.271-278, ⟨10.1007/978-3-642-40763-5_34⟩. ⟨hal-00832184⟩