Voxel-Wise Supervised Analysis of Tumors with Multimodal Engineered Features to Highlight Interpretable Biological Patterns - Inserm - Institut national de la santé et de la recherche médicale Accéder directement au contenu
Article Dans Une Revue Medical Physics Année : 2022

Voxel-Wise Supervised Analysis of Tumors with Multimodal Engineered Features to Highlight Interpretable Biological Patterns

Résumé

Background: Translation of predictive and prognostic image-based learning models to clinical applications are challenging due in part to their lack of interpretability. Some deep-learningbased methods provide information about the regions driving the model output. Yet, due to the high-level abstraction of deep features, these methods do not completely solve the interpretation challenge. In addition, low sample size cohorts can lead to instabilities and suboptimal convergence for models involving a large number of parameters such as convolutional neural networks. Purpose: Here, we propose a method for designing radiomic models that combines the interpretability of handcrafted radiomics with a sub-regional analysis. Materials and Methods: Our approach relies on voxel-wise engineered radiomic features with average global aggregation and logistic regression. The method is illustrated using a small dataset of 51 soft tissue sarcoma (STS) patients where the task is to predict the risk of lung metastasis occurrence during the follow-up period. Results: Using PET/CT and two MRI sequences separately to build two radiomic models, we show that our approach produces quantitative maps that highlight the signal that contributes to the decision within the tumor region of interest. In our STS example, the analysis of these maps identified two biological patterns that are consistent with STS grading systems and knowledge: necrosis development and glucose metabolism of the tumor. Conclusions: We demonstrate how that method makes it possible to spatially and quantitatively interpret radiomic models amenable to sub-regions identification and biological interpretation for patient stratification.

Domaines

Imagerie
Fichier principal
Vignette du fichier
Medical Physics - 2022 - Escobar.pdf (1.91 Mo) Télécharger le fichier
Origine : Publication financée par une institution

Dates et versions

inserm-03872918 , version 1 (26-11-2022)

Identifiants

Citer

Thibault Escobar, Sébastien Vauclin, Fanny Orlhac, Christophe Nioche, Pascal Pineau, et al.. Voxel-Wise Supervised Analysis of Tumors with Multimodal Engineered Features to Highlight Interpretable Biological Patterns. Medical Physics, 2022, 49 (6), pp.3816-3829. ⟨10.1002/mp.15603⟩. ⟨inserm-03872918⟩
22 Consultations
47 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More