| Titre : | Pediatric Bone Age Assessment from Hand X-ray using Deep Learning Approach |
| Auteurs : | Achouak Zerari, Auteur ; Laïd Kahloul, Directeur de thèse |
| Type de document : | Monographie imprimée |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2022 |
| Format : | 1 vol. (40p.) / couv. ill. en coul / 30 cm |
| Langues: | Anglais |
| Mots-clés: | Bone age assessment, Deep learning, Preprocessing, Machine learning, Preprocessing, Image Processing, Convolutional Neural Networks |
| Résumé : |
Bone age assessments are methods that doctors use in pediatric medicine. They are used to assess the growth of children by analyzing X-ray images. This work focuses on the development of a deep learning model to estimate bone age from X-ray images. Such a model would avoid the fallacies of subjective methods and raise the accuracy of the assessment. In our work, the model is based on convolutional neural networks (CNN) and is composed of two steps: a preprocessing step generating image masks, and a prediction step that uses these masks to generate the assessment. The model is trained and tested using a public Radiological Society of North America(RSNA) bone age dataset1. Finally, experimental results demonstrate the effectiveness of the proposed approach compared to similar works in the literature. |
| Sommaire : |
Acknowledgements i Abstract iii Résumé iv List of Figures vii List of Tables viii 1 General Introduction 1 1.1 Introduction .. 1 1.2 Organisation of the dissertation 2 2 Technical Background 4 2.1 Introduction 4 2.2 Health Care definition 4 2.2.1 Health Care types 4 2.2.2 Artificial intelligence and healthcare 5 2.3 Machine learning 7 2.4 Deep Learning 9 2.4.1 The differences between the Machine Learning and the Deep Learning10 2.4.2 Artificial neural networks 10 2.5 Convolution Neural Network 15 2.5.1 CNN definition 16 2.5.2 CNN Architecture . 16 2.5.3 CNN layers configuration 19 2.5.4 Some CNN architectures 20 2.6 Bone age assessment . 21 2.6.1 Bone Age Assessment Methods 22 2.7 Related work 23 2.8 Conclusion 24 3 Design and implementation of a deep learning architecture for Bone Age Assessment 25 3.1 Introduction 25 3.2 The proposed approach 25 3.3 Data set description 26 3.4 Preprocessing phase26 3.4.1 Image masking using U-net architecture 27 3.4.2 Edges enhancement . 29 3.5 CNN-based regression model. 30 3.6 Conclusion 31 4 Frameworks, tools and libraries 32 4.1 Introduction 32 4.2 Frameworks, tools and libraries 32 4.3 Conclusion 35 5 Results 36 5.1 Introduction . 36 5.2 Obtained results and discussion . . . 36 5.2.1 Results of test phase 37 5.3 Conclusion . 38 6 Conclusion and Perspectives 39 6.1 Conclusion and Perspectives 39 References 40 |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/723 | Mémoire master | bibliothèque sciences exactes | Consultable |
