Deep Learning Models for Medical Image Segmentation: Approaches and Applications / Houssem Dhia Eddine Arras

Public ISBD Titre : Deep Learning Models for Medical Image Segmentation: Approaches and Applications Type de document : document électronique Auteurs : Houssem Dhia Eddine Arras ; Dhia Eddine Lahrache, Auteur ; Hamdi ,Skander, Directeur de thèse Editeur : Setif:UFA Année de publication : 2025 Importance : 1 vol (64 f .) Format : 29 cm Langues : Anglais (eng) Catégories : Thèses & Mémoires:Informatique Mots-clés : Medical image segmentation Stroke Deep Learning U-Net UNet++ Attention U-Net MRI ATLAS 2.0 Convolutional Neural Networks Dice IoU Index. décimale : 004 Informatique Résumé : The increased availability of medical image data, particularly from modalities such as Magnetic Resonance Imaging (MRI), has opened up possibilities to develop smart systems to aid clinical diagnosis and treatment planning. However, the complexity and volume of such data render manual analysis cumbersome. This thesis addresses the problem of automatic stroke lesion segmentation in brain MRI images through deep learning techniques. A thorough experimental evaluation was conducted with three CNN architectures: U-Net, Attention U-Net, and UNet++. The networks were trained and evaluated on a sub-dataset of the ATLAS 2.0 dataset with annotated post-stroke MRI images. The performance of each model was evaluated by Dice coefficient and Intersection over Union (IoU) metrics. The result shows that the standard U-Net worked well for segmentation ( 74.76% ), and the Attention U-Net and UNet++ provided improvements in lesion boundary and location refinement. The findings show the effectiveness of CNN-based models in effectively segmenting stroke lesions from 2D medical images. This study adds value to the medical image analysis field by providing insight into the capabilities of deep learning models for stroke segmentation and acts as a baseline for further improvement using 3D architectures or transformer-based models. Note de contenu : Sommaire List of Tables.............................................................................................................................. IX 1 Introduction to Medical Image Segmentation Using Deep Learning ................................ 3 1.1 Introduction ..................................................................................................................... 3 1.2 Overview of Medical Image Segmentation in Healthcare .............................................. 3 1.2.1 Definition of medical image segmentation ......................................................... 3 1.2.2 Applications in disease diagnosis, treatment planning, and monitoring ............. 4 1.2.3 Importance of Medical Image segmentation in disease detection and analysis .. 4 1.3 Importance of Deep Learning in Improving Segmentation Accuracy ............................ 5 1.3.1 Traditional segmentation methods ...................................................................... 5 1.3.2 Deep learning revolution ..................................................................................... 6 1.3.3 Automation and precision: How DL models improve stroke segmentation ....... 7 1.4 Problem Statement and Research Motivation ................................................................. 7 1.4.1 Problem Statement .............................................................................................. 7 1.4.2 Research Motivation ........................................................................................... 8 1.5 Objectives of the Study ................................................................................................... 8 1.6 Conclusion ....................................................................................................................... 9 2 Deep Learning Fundamentals and Advances in Segmentation Models ........................... 10 2.1 Introduction ................................................................................................................... 10 2.2 Introduction to Deep Learning ...................................................................................... 11 2.2.1 Definition and history of deep learning ............................................................ 11 2.2.2 Difference between deep learning, machine learning, and artificial intelligence .. 11 2.3 Neural Networks and Architectures .............................................................................. 12 2.3.1 Basics of artificial neural networks (ANN) ...................................................... 12 2.3.2 Convolutional Neural Networks (CNN) and their role in image processing .... 14 2.3.2.1 Key Features of CNNs ........................................................................ 14 2.3.2.2 Applications in Image Processing ....................................................... 15 2.4 Training Deep Learning Models ................................................................................... 15 2.4.1 Data Preparation and Augmentation Techniques .............................................. 15 2.4.1.1 Preprocessing of Medical Images ....................................................... 16 2.4.1.2 Data Augmentation ............................................................................. 16 2.4.1.3 Common Data Augmentation Techniques........................................... 17 2.4.1.4 Handling Imbalanced Datasets ............................................................ 17 2.4.2 Loss Functions Used in Segmentation .............................................................. 18 2.4.2.1 Standard Losses in Segmentation ....................................................... 18 2.4.2.2 Segmentation-Specific Loss Functions ............................................... 18 2.4.2.3 Handling Class Imbalance and Small Lesions .................................... 19 2.4.3 Optimization Algorithms ................................................................................... 20 2.4.3.1 Common Optimization Algorithms ..................................................... 20 2.4.3.2 Hyperparameters and Training Behavior ............................................ 21 2.4.3.3 Learning Rate Schedulers ................................................................... 22 2.4.4 Regularization Techniques ................................................................................ 22 2.4.4.1 Common Regularization Techniques .................................................. 22 2.4.4.2 Additional Techniques ......................................................................... 24 2.5 Evaluation Metrics for Segmentation ............................................................................ 24 2.5.1 Dice Similarity Coefficient (DSC) .................................................................... 24 2.5.2 Intersection over Union (IoU) ........................................................................... 25 2.5.3 Sensitivity, Specificity, and Accuracy ............................................................... 27 2.6 Advances in Deep Learning for Segmentation .............................................................. 28 2.6.1 Introduction to Foundation Models ................................................................... 28 2.6.2 Transfer Learning and Pretrained Models ......................................................... 29 2.6.3 Attention Mechanisms in Segmentation Models............................................... 29 2.7 Model Architectures for Segmentation.......................................................................... 30 2.7.1 U-Net ................................................................................................................. 30 2.7.2 U-Net++ ............................................................................................................ 31 2.7.3 Attention U-Net ................................................................................................. 33 2.8 Conclusion ..................................................................................................................... 34 3 Background and Related Work on Stroke ......................................................................... 35 3.1 Introduction ................................................................................................................... 35 3.2 Stroke Overview ............................................................................................................ 35 3.2.1 Definition .......................................................................................................... 35 3.2.2 Types ................................................................................................................. 36 3.2.3 Symptoms .......................................................................................................... 37 3.2.4 Diagnostic ......................................................................................................... 37 3.2.5 Treatment .......................................................................................................... 38 3.3 Medical Imaging Techniques for Stroke ....................................................................... 39 3.3.1 Computed Tomography (CT) ............................................................................ 39 3.3.2 Magnetic Resonance Imaging (MRI) ............................................................... 40 3.4 Importance of Stroke Lesion Segmentation and Deep Learning’s Role ....................... 40 3.4.1 Significance of Stroke Lesion Segmentation in Research and Medicine ......... 40 3.4.2 Deep Learning for Stroke Lesion Segmentation ............................................... 41 3.5 Related Work ................................................................................................................. 42 3.6 Conclusion ..................................................................................................................... 45 4 Experiment And Results ...................................................................................................... 46 4.1 Introduction ................................................................................................................... 46 4.2 Data description ............................................................................................................. 46 4.2.1 Image Characteristics ........................................................................................ 47 4.2.2 Key Metadata Features ...................................................................................... 47 4.2.3 Data Samples ..................................................................................................... 48 4.3 Data Preprocessing ........................................................................................................ 49 4.3.1 Extraction of 2D Slices ..................................................................................... 49 4.3.2 Filtering Slices .................................................................................................. 49 4.3.3 Normalization of Images ................................................................................... 49 4.3.4 Resizing ............................................................................................................. 50 4.3.5 Data Augmentation............................................................................................ 50 4.4 Methodology and Results .............................................................................................. 50 4.4.1 Stroke UNet-Architecture ................................................................................. 51 4.4.1.1 Overall Structure ................................................................................. 52 4.4.1.2 Convolutional Block ........................................................................... 52 4.4.1.3 Contracting Path (Encoder) ................................................................. 52 4.4.1.4 Expanding Path (Decoder) .................................................................. 53 4.4.1.5 Output Layer ....................................................................................... 53 4.4.1.6 Results ................................................................................................. 53 4.4.2 Attention UNet-Architecture ............................................................................. 54 4.4.2.1 Overall Structure ................................................................................. 55 4.4.2.3 Attention Block Objectives ................................................................. 55 4.4.2.4 Results ................................................................................................. 56 4.4.3 UNet++ Architecture ......................................................................................... 57 4.4.3.1 Objectives ............................................................................................ 57 4.4.3.2 Results ................................................................................................. 58 4.4.4 Results Discussion ............................................................................................ 58 4.4.5 Model Prediction Capability ............................................................................. 60 4.5 Comparision With Related Works ................................................................................ 62 4.6 Conclusion .................................................................................................................... 62 Bibliography ................................................................................................................................ 64 Côte titre : MAI/0998 Deep Learning Models for Medical Image Segmentation: Approaches and Applications [document électronique] / Houssem Dhia Eddine Arras ; Dhia Eddine Lahrache, Auteur ; Hamdi ,Skander, Directeur de thèse . - [S.l.] : Setif:UFA, 2025 . - 1 vol (64 f .) ; 29 cm. Langues : Anglais (eng) Catégories : Thèses & Mémoires:Informatique Mots-clés : Medical image segmentation Stroke Deep Learning U-Net UNet++ Attention U-Net MRI ATLAS 2.0 Convolutional Neural Networks Dice IoU Index. décimale : 004 Informatique Résumé : The increased availability of medical image data, particularly from modalities such as Magnetic Resonance Imaging (MRI), has opened up possibilities to develop smart systems to aid clinical diagnosis and treatment planning. However, the complexity and volume of such data render manual analysis cumbersome. This thesis addresses the problem of automatic stroke lesion segmentation in brain MRI images through deep learning techniques. A thorough experimental evaluation was conducted with three CNN architectures: U-Net, Attention U-Net, and UNet++. The networks were trained and evaluated on a sub-dataset of the ATLAS 2.0 dataset with annotated post-stroke MRI images. The performance of each model was evaluated by Dice coefficient and Intersection over Union (IoU) metrics. The result shows that the standard U-Net worked well for segmentation ( 74.76% ), and the Attention U-Net and UNet++ provided improvements in lesion boundary and location refinement. The findings show the effectiveness of CNN-based models in effectively segmenting stroke lesions from 2D medical images. This study adds value to the medical image analysis field by providing insight into the capabilities of deep learning models for stroke segmentation and acts as a baseline for further improvement using 3D architectures or transformer-based models. Note de contenu : Sommaire List of Tables.............................................................................................................................. IX 1 Introduction to Medical Image Segmentation Using Deep Learning ................................ 3 1.1 Introduction ..................................................................................................................... 3 1.2 Overview of Medical Image Segmentation in Healthcare .............................................. 3 1.2.1 Definition of medical image segmentation ......................................................... 3 1.2.2 Applications in disease diagnosis, treatment planning, and monitoring ............. 4 1.2.3 Importance of Medical Image segmentation in disease detection and analysis .. 4 1.3 Importance of Deep Learning in Improving Segmentation Accuracy ............................ 5 1.3.1 Traditional segmentation methods ...................................................................... 5 1.3.2 Deep learning revolution ..................................................................................... 6 1.3.3 Automation and precision: How DL models improve stroke segmentation ....... 7 1.4 Problem Statement and Research Motivation ................................................................. 7 1.4.1 Problem Statement .............................................................................................. 7 1.4.2 Research Motivation ........................................................................................... 8 1.5 Objectives of the Study ................................................................................................... 8 1.6 Conclusion ....................................................................................................................... 9 2 Deep Learning Fundamentals and Advances in Segmentation Models ........................... 10 2.1 Introduction ................................................................................................................... 10 2.2 Introduction to Deep Learning ...................................................................................... 11 2.2.1 Definition and history of deep learning ............................................................ 11 2.2.2 Difference between deep learning, machine learning, and artificial intelligence .. 11 2.3 Neural Networks and Architectures .............................................................................. 12 2.3.1 Basics of artificial neural networks (ANN) ...................................................... 12 2.3.2 Convolutional Neural Networks (CNN) and their role in image processing .... 14 2.3.2.1 Key Features of CNNs ........................................................................ 14 2.3.2.2 Applications in Image Processing ....................................................... 15 2.4 Training Deep Learning Models ................................................................................... 15 2.4.1 Data Preparation and Augmentation Techniques .............................................. 15 2.4.1.1 Preprocessing of Medical Images ....................................................... 16 2.4.1.2 Data Augmentation ............................................................................. 16 2.4.1.3 Common Data Augmentation Techniques........................................... 17 2.4.1.4 Handling Imbalanced Datasets ............................................................ 17 2.4.2 Loss Functions Used in Segmentation .............................................................. 18 2.4.2.1 Standard Losses in Segmentation ....................................................... 18 2.4.2.2 Segmentation-Specific Loss Functions ............................................... 18 2.4.2.3 Handling Class Imbalance and Small Lesions .................................... 19 2.4.3 Optimization Algorithms ................................................................................... 20 2.4.3.1 Common Optimization Algorithms ..................................................... 20 2.4.3.2 Hyperparameters and Training Behavior ............................................ 21 2.4.3.3 Learning Rate Schedulers ................................................................... 22 2.4.4 Regularization Techniques ................................................................................ 22 2.4.4.1 Common Regularization Techniques .................................................. 22 2.4.4.2 Additional Techniques ......................................................................... 24 2.5 Evaluation Metrics for Segmentation ............................................................................ 24 2.5.1 Dice Similarity Coefficient (DSC) .................................................................... 24 2.5.2 Intersection over Union (IoU) ........................................................................... 25 2.5.3 Sensitivity, Specificity, and Accuracy ............................................................... 27 2.6 Advances in Deep Learning for Segmentation .............................................................. 28 2.6.1 Introduction to Foundation Models ................................................................... 28 2.6.2 Transfer Learning and Pretrained Models ......................................................... 29 2.6.3 Attention Mechanisms in Segmentation Models............................................... 29 2.7 Model Architectures for Segmentation.......................................................................... 30 2.7.1 U-Net ................................................................................................................. 30 2.7.2 U-Net++ ............................................................................................................ 31 2.7.3 Attention U-Net ................................................................................................. 33 2.8 Conclusion ..................................................................................................................... 34 3 Background and Related Work on Stroke ......................................................................... 35 3.1 Introduction ................................................................................................................... 35 3.2 Stroke Overview ............................................................................................................ 35 3.2.1 Definition .......................................................................................................... 35 3.2.2 Types ................................................................................................................. 36 3.2.3 Symptoms .......................................................................................................... 37 3.2.4 Diagnostic ......................................................................................................... 37 3.2.5 Treatment .......................................................................................................... 38 3.3 Medical Imaging Techniques for Stroke ....................................................................... 39 3.3.1 Computed Tomography (CT) ............................................................................ 39 3.3.2 Magnetic Resonance Imaging (MRI) ............................................................... 40 3.4 Importance of Stroke Lesion Segmentation and Deep Learning’s Role ....................... 40 3.4.1 Significance of Stroke Lesion Segmentation in Research and Medicine ......... 40 3.4.2 Deep Learning for Stroke Lesion Segmentation ............................................... 41 3.5 Related Work ................................................................................................................. 42 3.6 Conclusion ..................................................................................................................... 45 4 Experiment And Results ...................................................................................................... 46 4.1 Introduction ................................................................................................................... 46 4.2 Data description ............................................................................................................. 46 4.2.1 Image Characteristics ........................................................................................ 47 4.2.2 Key Metadata Features ...................................................................................... 47 4.2.3 Data Samples ..................................................................................................... 48 4.3 Data Preprocessing ........................................................................................................ 49 4.3.1 Extraction of 2D Slices ..................................................................................... 49 4.3.2 Filtering Slices .................................................................................................. 49 4.3.3 Normalization of Images ................................................................................... 49 4.3.4 Resizing ............................................................................................................. 50 4.3.5 Data Augmentation............................................................................................ 50 4.4 Methodology and Results .............................................................................................. 50 4.4.1 Stroke UNet-Architecture ................................................................................. 51 4.4.1.1 Overall Structure ................................................................................. 52 4.4.1.2 Convolutional Block ........................................................................... 52 4.4.1.3 Contracting Path (Encoder) ................................................................. 52 4.4.1.4 Expanding Path (Decoder) .................................................................. 53 4.4.1.5 Output Layer ....................................................................................... 53 4.4.1.6 Results ................................................................................................. 53 4.4.2 Attention UNet-Architecture ............................................................................. 54 4.4.2.1 Overall Structure ................................................................................. 55 4.4.2.3 Attention Block Objectives ................................................................. 55 4.4.2.4 Results ................................................................................................. 56 4.4.3 UNet++ Architecture ......................................................................................... 57 4.4.3.1 Objectives ............................................................................................ 57 4.4.3.2 Results ................................................................................................. 58 4.4.4 Results Discussion ............................................................................................ 58 4.4.5 Model Prediction Capability ............................................................................. 60 4.5 Comparision With Related Works ................................................................................ 62 4.6 Conclusion .................................................................................................................... 62 Bibliography ................................................................................................................................ 64 Côte titre : MAI/0998

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0998	MAI/0998	Mémoire	Bibliothèque des sciences	Anglais	Disponible Disponible

---

1 (1 - 1 / 1)