| Titre : | Breast Cancer Classification from Mammography Images using Deep Learning. |
| Auteurs : | Mohammed Esseddik Braken, Auteur ; Brahim. Khaldi, Directeur de thèse |
| Type de document : | texte manuscrit |
| Editeur : | Université mustapha stambouli de Mascara:Faculté des sciences exactes, 2022 |
| ISBN/ISSN/EAN : | SE02236T |
| Format : | 59P. / couv. ill. / 29cm. |
| Accompagnement : | disque optique numérique (CD-ROM) |
| Langues: | Anglais |
| Résumé : |
Early detection of Microcalcifications (MCs) is an effective indicator in breast cancer diagnosis. The detection of MCs in mammogram is still suboptimal because of the complexity of malignant behaviours. The aim of this work to improve early and accurate detection of breast cancer with MCs and aiding radiologists in distinguishing suspicious MCs. CNN shown powerful classification in image data.To deal with this challenge, this work assessed the performance of deep learning based on big dataset. Present a convolutional neural network (CNN) classifier model with automatic feature learning used to assess accuracy. To train CNN using total of dataset 13128 mammograms images, training data used 10504 images where testing data 2626 images. Results show training (99.98%) and testing (99.92%) accuracies. So the model had very high accuracy for classifying the breast Microcalcifications either benign or malignant, both accuracies high (specially testing) that indicates the model is free from any overfitting. This may have clinical value for early detection and treatment of breast cancer. Keywords : DL, CADe, CADx, CNN, MCs, ANN. |
Exemplaires (1)
| Code-barres | Cote | Support | Localisation | Section | Disponibilité |
|---|---|---|---|---|---|
| SE02236T | INF835 | Livre audio | Bibliothèque des Sciences Exactes | 7-Mémoires Master | Consultation sur place Exclu du prêt |
Aucun avis, veuillez vous identifier pour ajouter le vôtre !
Accueil
