Search results for "020201 artificial intelligence & image processing"

Tackling the Problem of Data Imbalancing for Melanoma Classification

2016

Comunicació de congrés presentada a: 3rd International Conference on Bioimaging, BIOIMAGING 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016, Roma, Italy Malignant melanoma is the most dangerous type of skin cancer, yet melanoma is the most treatable kind of cancer when diagnosed at an early stage. In this regard, Computer-Aided Diagnosis systems based on machine learning have been developed to discern melanoma lesions from benign and dysplastic nevi in dermoscopic images. Similar to a large range of real world applications encountered in machine learning, melanoma classification faces the challenge of imbalanced data, where …

High Dynamic Range Spectral Imaging Pipeline For Multispectral Filter Array Cameras

2017

Spectral filter arrays imaging exhibits a strong similarity with color filter arrays. This permits us to embed this technology in practical vision systems with little adaptation of the existing solutions. In this communication, we define an imaging pipeline that permits high dynamic range (HDR)-spectral imaging, which is extended from color filter arrays. We propose an implementation of this pipeline on a prototype sensor and evaluate the quality of our implementation results on real data with objective metrics and visual examples. We demonstrate that we reduce noise, and, in particular we solve the problem of noise generated by the lack of energy balance. Data are provided to the community…

Towards EEG-Based Haptic Interaction within Virtual Environments

2019

International audience; Current virtual environments (VE) enable perceiving haptic stimuli to facilitate 3D user interaction, but lack brain-interfacial contents. Using electroencephalography (EEG), we undertook a feasibility study on exploring event-related potential (ERP) patterns of the user's brain responses during haptic interaction within a VE. The interaction was flying a virtual drone along a curved transmission line to detect defects under the stimuli (e.g., force increase and/or vibrotactile cues). We found that there were variations in the peak amplitudes and latencies (as ERP patterns) of the responses at about 200 ms post the onset of the stimuli. The largest negative peak occu…

Biological target volume segmentation for radiotherapy treatment planning

2016

Smartphone single-snapshot mapping of skin chromophores

2016

Suitability of smartphone for single-snapshot mapping of skin melanin, oxy-hemoglobin and deoxy-hemoglobin under 3-wavelengths illumination was demonstrated. Simultaneous 448-532-659 nm illumination was provided by a portable laser-based prototype.

Prostate Cancer Segmentation from Multiparametric MRI Based on Fuzzy Bayesian Model

2014

International audience

Modelling cardiac mechanics of left ventricular noncompaction

2020

Left ventricular noncompaction (LVNC) can be defined as a cardiomyopathy characterised by a pattern of prominent trabecular structure and deep intertrabecular recesses, that is thought to be caused by an arrest of normal endomyocardial morphogenesis. Using patient-specific computational modelling, we assessed the cardiac mechanics of five patients with LVNC and compared myocardial stress and pump performance to those of healthy controls. Findings shown that patients with LVNC have impaired left ventricular (LV) function, making it possible that the lack of fibre shortening of noncompacted layer can determine poor heart function. Pronounced end-systolic wall stress on left ventricular wall o…

Zonal Segmentation of Prostate T2W-MRI using Atrous Convolutional Neural Network

2019

The number of prostate cancer cases is steadily increasing especially with rising number of ageing population. It is reported that 5-year relative survival rate for man with stage 1 prostate cancer is almost 99% hence, early detection will significantly improve treatment planning and increase survival rate. Magnetic resonance imaging (MRI) technique is a common imaging modality for diagnosis of prostate cancer. MRI provide good visualization of soft tissue and enable better lesion detection and staging of prostate cancer. The main challenge of prostate whole gland segmentation is due to blurry boundary of central gland (CG) and peripheral zone (PZ) which lead to differential diagnosis. Sinc…

ON-LINE CONSTRUCTION OF A SMALL AUTOMATON FOR A FINITE SET OF WORDS

2012

In this paper we describe a "light" algorithm for the on-line construction of a small automaton recognising a finite set of words. The algorithm runs in linear time. We carried out good experimental results on real dictionaries, on biological sequences and on the sets of suffixes (resp. factors) of a set of words that shows how our automaton is near to the minimal one. For the suffixes of a text, we propose a modified construction that leads to an even smaller automaton. We moreover construct linear algorithms for the insertion and deletion of a word in a finite set, directly from the constructed automaton.

An EEMD Aided Comparison of Time Histories and Its Application in Vehicle Safety

2017

In the context of signal processing, the comparison of time histories is required for different purposes, especially for the model validation of vehicle safety. Most of the existing metrics focus on the mathematical value only. Therefore, they suffer the measuring errors, disturbance, and uncertainties and can hardly achieve a stable result with a clear physical interpretation. This paper proposes a novel scheme of time histories comparison to be used in vehicle safety analysis. More specifically, each signal for comparison is decomposed into a trend signal and several intrinsic mode functions (IMFs) by ensemble empirical mode decomposition. The trend signals reflect the general variation a…