BKC-Net: Bi-Knowledge Contrastive Learning for renal tumor diagnosis on 3D CT images - Université de Rennes Accéder directement au contenu
Article Dans Une Revue Knowledge-Based Systems Année : 2022

BKC-Net: Bi-Knowledge Contrastive Learning for renal tumor diagnosis on 3D CT images

Résumé

Renal tumor diagnosis on abdominal enhanced CT volumes is one of the most significant tasks in kidney disease diagnosis. It helps clinicians decide whether to perform the surgery (subtype classification), perform radical operations or minimally invasive treatment (grade classification). However, inherent challenges greatly limit the performance of the model: 1) Tumor appearance differences caused by non-tumor factors. 2) Small inter-class differences and large intra-class variations. In this paper, we propose a novel diagnosis framework for renal tumors, Bi-knowledge Contrastive Network (BKC-Net), which has two innovations: (1) Focus-perceive learning segments the tumors while perceiving the surrounding healthy tissues, thus adjusting the model's representation of tumor appearance, helping the BKC-Net represent the inherent features of tumors. (2) Bi-knowledge contrastive learning introduces prior radiomics features, makes the prior radiomics knowledge and latent deep knowledge complementary to each other from the intra-case level, and forces the high cohesion and low coupling embedding feature space from the inter-case levels, helping to discover subtle but essential differences among classes. Experiments demonstrate that our BKC-Net has the best performance in renal tumor diagnosis. Results reveal that our framework has great potential for renal tumor diagnosis in clinical use. Source codes will be released at https://github.com/DD0922/BKC-Net-pytorch. © 2022 Elsevier B.V.
Fichier non déposé

Dates et versions

hal-03779269 , version 1 (16-09-2022)

Identifiants

Citer

J. Kong, Y. He, X Zhu, P. Shao, Y. Xu, et al.. BKC-Net: Bi-Knowledge Contrastive Learning for renal tumor diagnosis on 3D CT images. Knowledge-Based Systems, 2022, 252, pp.109369. ⟨10.1016/j.knosys.2022.109369⟩. ⟨hal-03779269⟩
29 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More