Titre :

Automatic Bone Metastasis Classification: An in-depth Comparison of CNN and Transformer Architectures

Auteur(s) :

Afnouch, Marwa [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Gaddour, Olfa [Auteur]
Université de Sfax - University of Sfax
Bougourzi, Fares [Auteur]
Laboratoire Images, Signaux et Systèmes Intelligents [LISSI]
Hentati, Yosr [Auteur]
Université de Sfax - University of Sfax
Tahleb Ahmed, Abdelmalik [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Abid, Mohamed [Auteur]
Université de Sfax - University of Sfax

Titre de la manifestation scientifique :

2023 International Conference on Innovations in Intelligent Systems and Applications (INISTA)

Ville :

Hammamet

Pays :

Tunisie

Date de début de la manifestation scientifique :

2023-09-20

Éditeur :

IEEE

Discipline(s) HAL :

Physique [physics]
Sciences de l'ingénieur [physics]

Résumé en anglais : [en]

Automatic classification of bone metastases is a major challenge and is receiving increasing attention from the research community. One of the major challenges is the accurate classification of medical images, especially ...
Lire la suite >Automatic classification of bone metastases is a major challenge and is receiving increasing attention from the research community. One of the major challenges is the accurate classification of medical images, especially the distinction between benign and malignant images, which can greatly help physicians in decision-making. Recently, several deep-learning techniques have been proposed for medical image classification. Their performance, however, is influenced by both the dataset and the imaging modality. In this work, we investigate the performance of several state-of-the-art CNN architectures, namely InceptionV3, EfficientNet, ResNext50, and DenseNet161, as well as Transformer architectures, namely ViT and DeiT. We trained and tested these algorithms on a large dataset consisting of CT-scan images. The Transformer algorithms were found to be superior to CNN algorithms in detecting bone metastases. In particular, ViT Tiny achieved the best performance in terms of accuracy and F1-score as compared to other architectures.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL