Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 61 for “"Medical Datasets"”.
-
A Framework for Knowledge Discovery from Sparse, High-Dimensional Medical Datasets
Made available in DSpace on 2010-01-06T16:40:06Z (GMT). No. of bitstreams: 8 license.txt: 4075 bytes, checksum: 75c9f88c8c3d53847b2b8300486ad025 (MD5) Ramachandran_Chandrasekar.tex: 116907 bytes, checksum: 6ff74ee0854d0b449656849027c384a9 (MD5) 1_Ramachandran_Chandrasekar.tex: 116907 bytes, …
-
From scarcity to abundance : augmenting ultrasound medical datasets with advanced deep learning techniques
… of large quantity of training data. In the medical domain, however, large-scale data collection and annotation are often limited by the high cost and time demands, particularly due to the workload of clinical professionals. Furthermore, maintaining model robustness across varying imaging …
-
A comparative analysis of large language models on medical datasets : performance evaluation and fine-tuning strategies
… benchmarks and fine-tuning with specialized datasets. This study addresses this gap by investigating the role of KD in enhancing LLM performance within the medical domain, where accuracy and contextual understanding are crucial. A dual-track approach is adopted: (1) distilling knowledge from …
-
Training Strategy for Limited Labeled Data by Learning from Confusion
… domains partly due to large labeled image datasets and increased computing power. However, a persistent problem of training supervised deep learning image classifiers is the limited availability of domain-specific annotated image datasets. This problem is particularly important in areas …
-
Image Classification Using Transfer Learning and Convolution Neural Networks
… Technology domain. This paper aims to classify medical images by leveraging the advantages of Transfer Learning over Conventional methods. Three types of approaches are used namely, pre-trained CNN as a Feature Extractor, Feature Extractor with Image Augmentation, and Fine-tuning with Image …
-
OFSET_mine:an integrated framework for cardiovascular diseases risk prediction based on retinal vascular function
… on RVA data that is also applicable to other medical datasets with similar characteristics. The three identified essential characteristics are 1) imbalanced dataset,2) high dimensionality and 3) overlapping feature ranges with the possibility of acquiring new samples. The thesis proposes …
-
Visualization of large medical volume data
Visualization of large medical datasets is important in the field of computer aided surgery. It is a challenging problem that requires a solution integrating image processing and computer graphics. This thesis investigated various methods of 4-D medical image compression including clustering-based …
-
Automated feature selection for survival analysis with deep learning
… for competing risks. However, in real-world medical settings with many features and insufficient data, deep learning models can suffer from severe performance deficits.</p> <p>In this dissertation, we propose robust changes to DeepHit’s architecture and training procedure to counter this …
-
Restoring Consistency in Ontological Multidimensional Data Models via Weighted Repairs
… and demonstrate improved performance using medical datasets, making it realizable in practice.
-
Multiple GAN Augmentation for Acute Myocardial Infarction Classification
… tasks with large labeled training data. However, medical images are hard to collected and therefore, most medical datasets are small. In this thesis, generating diverse and reliable images by Generative Adversarial Networks (GANs) are proposed as a new augmentation method, which can introduce …
-
Revisiting Benchmarks for Privacy-Preserving Image Classification
… ML benchmarks to measure progress. Popular datasets like CIFAR-10, while extensively used in non-private settings, may not accurately capture the complexities of privacy-sensitive areas like medical data. Additionally, pre-training on publicly available datasets may not yield the same …
-
Improving Image Classification Through Generative Data Augmentation
… to use this technology to revolutionize how medical diagnostic imaging is performed. The ability to accurately classify the information contained within a medical image is of critical importance for clinical implementation. Successful application of machine learning classification algorithms …
-
Analysis of Discrete Shapes Using Lie Groups
… solving a computationally expensive problem. Two medical datasets were analyzed: 2D contours of femoral head-neck cross-sections and 3D surfaces of proximal femurs. The Lie-group method outperformed the established principal-component analysis by capturing higher variability with fewer components. …
-
USING GENERATIVE MODELS TO CREATE SYNTHETIC MEDICAL IMAGING DATA TO BOOST MODEL PERFORMANCE ON SPARSE DEMOGRAPHIC GROUPS
… introduced new methods for generating synthetic medical imaging data. These models can produce highly realistic images, particularly for underrepresented demographic groups, thereby enhancing the diversity of existing medical datasets without incur- ring significant data collection costs. This …
-
A Study of Random Partitions vs. Patient-Based Partitions in Breast Cancer Tumor Detection using Convolutional Neural Networks
… of each other, which is often not the case for medical datasets, where multiple images are taken of each patient. This work focuses on convolutional neural network binary classifiers using the BreakHis dataset. Previous works are reviewed. Classifiers from previous literature are tested with …
-
Deep learning for precision medicine
… Learning (ML) is gaining attention in the medical domain, since ML algorithms can make use of all the available information to predict the most likely future events that will occur to each individual patient. Physicians can include these predictions in their decision processes which can …
-
Integrating Expertise: Domain-Driven AI Approaches for Cardiovascular Disease
… caused by hidden data acquisition artifacts in medical datasets. Second, we propose domain-knowledge AI models that embed cardiovascular expertise into the models. For ventricular arrhythmia risk prediction, we incorporate QRS peak features that were identified through domain expertise and …
-
Overcoming catastrophic forgetting in heterogeneous federated learning
… learning (FL) has gained prominence in the medical domain for enabling collaborative machine learning across decentralized datasets while preserving patient privacy. However, key challenges such as catastrophic forgetting and local overfitting hinder the effectiveness of FL models in …
-
Spiking Neural Networks for Low-Power Medical Applications
… whether AI can serve as a diagnostic aid in the medical domain. However, the primary weakness of traditional machine learning for many applications is energy efficiency, and this may hamper its ability to be effectively utilized in medicine for portable or edge systems. In order to be more …
-
Medical image analysis and visualization using geometric deformable model
Medical image analysis and visualization has become increasingly important in computer aided medicine. Throughout the history of medicine, advances in imaging have led to great progress in medical interventions. The thesis proposes, develops and evaluates methods for automated analysis, …
Page 1 of 4