Communication Dans Un Congrès Année : 2024

Explainability in Deep Learning Segmentation Models for Breast Cancer by Analogy with Texture Analysis

Résumé

Despite their predictive capabilities and rapid advancement, the black-box nature of Artificial Intelligence (AI) models, particularly in healthcare, has sparked debate regarding their trustworthiness and accountability. In response, the field of Explainable AI (XAI) has emerged, aiming to create transparent AI technologies. We present a novel approach to enhance AI interpretability by leveraging texture analysis, with a focus on cancer datasets. By focusing on specific texture features and their correlations with a prediction outcome extracted from medical images, our proposed methodology aims to elucidate the underlying mechanics of AI, improve AI trustworthiness, and facilitate human understanding. The code is available at https://github.com/xrai-lib/xai-texture.

Fichier principal
Vignette du fichier
MIDL2024_Short_Paper_XAI_Team_Camera_Ready.pdf (179.09 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04562334 , version 1 (29-04-2024)
hal-04562334 , version 2 (29-05-2024)

Licence

Identifiants

  • HAL Id : hal-04562334 , version 2

Citer

Md. Masum Billah, Pragati Manandhar, Sarosh Krishan, Alejandro Cedillo, Hergys Rexha, et al.. Explainability in Deep Learning Segmentation Models for Breast Cancer by Analogy with Texture Analysis. Medical Imaging with Deep Learning (MIDL 2024), Jul 2024, Paris, France. ⟨hal-04562334v2⟩
405 Consultations
502 Téléchargements

Partager

  • More