Search

Glioma is one of the most important central nervous system tumors, ranked 15th in the most common cancer for men and women. Magnetic Resonance Imaging (MRI) represents a common tool for medical experts to the diagnosis of glioma. A set of multi-sequences from an MRI is selected according to the severity of the pathology. Our proposed approach aims moreto create a computer-aided system that is capable of helping morethe expert diagnose the brain gliomas. moreWe propose a supervised learning regime based on a convolutional neural network based framework and transfer learning techniques. Our research morefocuses on the performance of different pre-trained deep learning models with respect to different MRI sequences. We highlight the best combinations of such model-MRI sequence couple for our specific task of classifying healthy brain against brain with glioma. moreWe also propose to visually analyze the extracted deep features for studying the existing relation of the MRI sequences and models. This interpretability analysis gives some hints for medical expert to understand the diagnosis made by the models. Our study is based on the well-known BraTS datasets including multi-sequence images and expert diagnosis.

Non-invasive assessment of kidney function and structure remains of clinical importance in the diagnosis and prognosis of chronic kidney disease. This work aims to evaluate the role of textures extracted from functional magnetic resonance imaging in renal dysfunction detection by differentiating healthy and chronic kidney disease patients. Textural descriptors are extracted from apparent diffusion coefficient, blood oxygenation level dependent images and T2 maps. Synthetic resampling technique is performed to account for imbalanced classes and increase the variety of sample domain. Principal component analysis projection is applied to eliminate irrelevant features and compact the dataset. The performance of linear discriminant analysis, logistic regression and Naive Bayes classifiers in terms of discriminating healthy and affected kidney is evaluated. The results of this preliminary study support the fact that chronic kidney disease affects texture parameters significantly. Textures-based predictive models have shown promise in accurate and safe renal function evaluation (accuracy, sensitivity and AUC up to 98%, 98% and 1 respectively).

This study focuses specifically on content-based image retrieval. The objective being to characterize the images according to their content, in the form of an index, a score which will be used for the manipulation of the images.We propose two visual perception quantification methods, one for colorfulness and one for depth. In terms of quantifying an impression, it was necessary to set up objective and rigorous criteria reflecting a sometimes subjective concept.Based on saturation, lightness and color disparity, we propose a framework that assigns to image an index between 0 and 100 to convey the impression that the image is very colorful or not. While in the case of depth, the estimate of a depth map will serve as a starting point. We estimate that the impression of depth is linked to the spread of the elements that make up the image from the farthest to the closest.

Assessment of renal function and structure accurately remains essential in the diagnosis and prognosis of Chronic Kidney Disease (CKD). Advanced imaging, including Magnetic Resonance Imaging (MRI), Ultrasound Elastography (UE), Computed Tomography (CT) and scintigraphy (PET, SPECT) offers the opportunity to non-invasively retrieve structural, functional and molecular information that could detect changes in renal tissue properties and functionality. Currently, the ability of artificial intelligence to turn conventional medical imaging into a full-automated diagnostic tool is widely investigated. In addition to the qualitative analysis performed on renal medical imaging, texture analysis was integrated with machine learning techniques as a quantification of renal tissue heterogeneity, providing a promising complementary tool in renal function decline prediction. Interestingly, deep learning holds the ability to be a novel approach of renal function diagnosis. This paper proposes a survey that covers both qualitative and quantitative analysis applied to novel medical imaging techniques to monitor the decline of renal function. First, we summarize the use of different medical imaging modalities to monitor CKD and then, we show the ability of Artificial Intelligence (AI) to guide renal function evaluation from segmentation to disease prediction, discussing how texture analysis and machine learning techniques have emerged in recent clinical researches in order to improve renal dysfunction monitoring and prediction. The paper gives a summary about the role of AI in renal segmentation.

Accurate assessment of renal microstructure and function remains a key point for the prediction and diagnosis of chronic kidney disease (CKD). Applications of novel medical imaging techniques offer a non-invasive and safer tool for analyzing CKD as it allows health care providers to identify morphological, functional and molecular information that detects changes in renal tissue properties and functionalities. Recently, the ability of artificial intelligence to address information retrieval and other critical issues in big medical data analytics has led to a great interest in CKD diagnosis. Besides qualitative analysis of renal medical imaging, texture analysis combined with machine learning has emerged as a promising technique to quantify renal tissue heterogeneity, thus providing a complementary tool for renal function decline prediction. Most importantly, deep learning holds the potential to be a novel approach for renal dysfunction monitoring. This paper proposes a survey focusing on the most recent approaches for using texture analysis and machine learning techniques that can be integrated in clinical research in order to improve renal dysfunction diagnosis and prognosis.

Gliomas are the most common central nervous system tumors. They represent 1.3% of cancers and are the 15th most common cancer for men and women. For the diagnosis of such pathology, doctors commonly use Magnetic Resonance Imaging (MRI) with different sequences. In this work, we propose a global framework using convolutional neural networks to create an intelligent assistant system for neurologists to diagnose the brain gliomas. Within this framework, we study the performance of different neural networks on four MRI modalities. This work allows us to highlight the most specific MRI sequences so that the presence of gliomas in brain tissue can be classified. We also visually analyze extracted features from the different modalities and networks with an aim to improve the interpretability and analysis of the performance obtained. We apply our study on the MRI sequences that are obtained from BraTS datasets.

The prevention of cardiovascular diseases starts by a thorough examination of the coronary artery vessels for atherosclerotic plaques existence. By combining deep learning convolutional Neural Network (CNN) architectures and the biological knowledge, we introduce a novel method for the automatic extraction of coronary artery centerlines in Computed Tomography Angiography (CTA) data. The proposed method is based on a 3D convolutional neural network used as a local vessel centerline detector to extract the main and side branches of the coronary artery tree. Coupled with a preprocessing vessel enhancing step, the model takes advantage of the analytical analysis of the former as well as the feature extraction ability of the CNN. In addition, automatic aorta and heart region detections are also performed to delineate the origin and the extent of the coronary tree and phase out the false predictions. We investigate the use of Coronary Stenosis’ Detection and Quantification (2012) Database to enrich the training process while ensuring the homogeneity of the scans. Our work offers a fully automatic, CNN based, pipeline for coronary artery centerline detection while circumventing the scarcity of the medical data in hand. Its validation against the ground truth annotation from the Rotterdam Coronary Artery Algorithm Evaluation Framework yields a retrieval ratio of 95% and 93%.