IDT: an incremental deep tree framework for biological image classification - Archive ouverte HAL
Article Dans Une Revue Artificial Intelligence in Medicine Année : 2022

IDT: an incremental deep tree framework for biological image classification

Résumé

Nowadays, breast and cervical cancers are respectively the first and fourth most common causes of cancer death in females. It is believed that, automated systems based on artificial intelligence would allow the early diagnostic which increases significantly the chances of proper treatment and survival. Although Convolutional Neural Networks (CNNs) have achieved human-level performance in object classification tasks, the regular growing of the amount of medical data and the continuous increase of the number of classes make them difficult to learn new tasks without being re-trained from scratch. Nevertheless, fine tuning and transfer learning in deep models are techniques that lead to the well-known catastrophic forgetting problem. In this paper, an Incremental Deep Tree (IDT) framework for biological image classification is proposed to address the catastrophic forgetting of CNNs allowing them to learn new classes while maintaining acceptable accuracies on the previously learnt ones. To evaluate the performance of our approach, the IDT framework is compared against with three popular in-cremental methods, namely iCaRL, LwF and SupportNet. The experimental results on MNIST dataset achieved 87 % of accuracy and the obtained values on the BreakHis, the LBC and the SIPaKMeD datasets are promising with 92 %, 98 % and 93 % respectively.
Fichier principal
Vignette du fichier
MOUSSER_Wafa_Artificial Intelligence In Medicine_2022.pdf (9.59 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03895733 , version 1 (03-12-2024)

Identifiants

Citer

Wafa Mousser, Salima Ouadfel, Abdelmalik Taleb-Ahmed, Ilham Kitouni. IDT: an incremental deep tree framework for biological image classification. Artificial Intelligence in Medicine, 2022, 134, pp.102392. ⟨10.1016/j.artmed.2022.102392⟩. ⟨hal-03895733⟩
20 Consultations
0 Téléchargements

Altmetric

Partager

More