Margarida Silveira

Comparison of Segmentation Methods for Melanoma Diagnosis in Dermoscopy Images

In this paper, we propose and evaluate six methods for the segmentation of skin lesions in dermoscopic images. This set includes some state of the art techniques which have been successfully used in many medical imaging problems (gradient vector flow (GVF) and the level set method of Chan et al.[(C-LS)]. It also includes a set of methods developed by the authors which were tailored to this particular application (adaptive thresholding (AT), adaptive snake (AS), EM level set (EM-LS), and fuzzy-based split-and-merge algorithm (FBSM)]. The segmentation methods were applied to 100 dermoscopic images and evaluated with four different metrics, using the segmentation result obtained by an experienced dermatologist as the ground truth. The best results were obtained by the AS and EM-LS methods, which are semi-supervised methods. The best fully automatic method was FBSM, with results only slightly worse than AS and EM-LS.

Crater Detection by a Boosting Approach

An approach to automatically detect impact craters on planetary surfaces is presented in this letter. It is built up from a boosting algorithm proposed by Viola and Jones (2004) whose simplicity combined with an original learning strategy leads to a fast and robust process with consistent results. The approach is validated with image data sets from Mars surface captured by the Mars Orbiter Camera onboard Mars Global Surveyor probe.

Separation Between Water and Land in SAR Images Using Region-Based Level Sets

This letter presents a method for the separation between land and water in synthetic aperture radar (SAR) amplitude images. The proposed technique uses region-based level sets and adopts a mixture of lognormal densities as the probabilistic model for the pixel intensities in both water and land classes. The expectation-maximization algorithm is used to estimate the probability density functions for each class. Experimental results with real SAR images of riverbeds, flood extent areas, and shorelines demonstrate the good performance of the proposed algorithm compared with state-of-the-art approaches.

Automatic segmentation of the lungs using robust level sets

This paper presents a method for the automatic segmentation of the lungs in X-ray computed tomography (CT) images. The proposed technique is based on the use of a robust geometric active contour that is initialized around the lungs, automatically splits in two, and performs outlier rejection during the curve evolution. The technique starts by grey-level thresholding of the images followed by edge detection. Then the edge connected points are organized into strokes and classified as valid or invalid. A confidence degree (weight) is assigned to each stroke and updated during the evolution process with the valid strokes receiving a high confidence degree and the confidence degrees of the outlier strokes tending to zero. These weights depend on the distance between the stroke points and the curve and also on the stroke size. Initialization of the curve is fully automatic. Experimental results show the effectiveness of the proposed technique.

Decoding visual brain states from fMRI using an ensemble of classifiers

Decoding perceptual or cognitive states based on brain activity measured using functional magnetic resonance imaging (fMRI) can be achieved using machine learning algorithms to train classifiers of specific stimuli. However, the high dimensionality and intrinsically low signal to noise ratio (SNR) of fMRI data poses great challenges to such techniques. The problem is aggravated in the case of multiple subject experiments because of the high inter-subject variability in brain function. To address these difficulties, the majority of current approaches uses a single classifier. Since, in many cases, different stimuli activate different brain areas, it makes sense to use a set of classifiers each specialized in a different stimulus. Therefore, we propose in this paper using an ensemble of classifiers for decoding fMRI data. Each classifier in the ensemble has a favorite class or stimulus and uses an optimized feature set for that particular stimulus. The output for each individual stimulus is therefore obtained from the corresponding classifier and the final classification is achieved by simply selecting the best score. The method was applied to three empirical fMRI datasets from multiple subjects performing visual tasks with four classes of stimuli. Ensembles of GNB and k-NN base classifiers were tested. The ensemble of classifiers systematically outperformed a single classifier for the two most challenging datasets. In the remaining dataset, a ceiling effect was observed which probably precluded a clear distinction between the two classification approaches. Our results may be explained by the fact that different visual stimuli elicit specific patterns of brain activation and indicate that an ensemble of classifiers provides an advantageous alternative to commonly used single classifiers, particularly when decoding stimuli associated with specific brain areas.

Comparison of Segmentation Methods for Automatic Diagnosis of Dermoscopy Images

Dermoscopy is a non-invasive diagnostic technique for the in vivo observation of pigmented skin lesions used in dermatology. There is currently a great interest in the prospects of automatic image analysis methods for dermoscopy, both to provide quantitative information about a lesion, which can be of relevance for the clinician, and as a stand alone early warning tool. The effective implementation of such a tool could lead to a reduction in the number of cases selected for exeresis, with obvious benefits both to the patients and to the health care system. The standard approach in automatic dermoscopic image analysis has usually three stages: (i) image segmentation, (ii) feature extraction and feature selection, (iii) lesion classification. This paper presents a comparison of segmentation methods applied to 50 dermoscopic image analysis, along with a clinical evaluation of each segmentation result performed by an experienced dermatologist.

Predicting conversion from MCI to AD with FDG-PET brain images at different prodromal stages

Early diagnosis of Alzheimer disease (AD), while still at the stage known as mild cognitive impairment (MCI), is important for the development of new treatments. However, brain degeneration in MCI evolves with time and differs from patient to patient, making early diagnosis a very challenging task. Despite these difficulties, many machine learning techniques have already been used for the diagnosis of MCI and for predicting MCI to AD conversion, but the MCI group used in previous works is usually very heterogeneous containing subjects at different stages. The goal of this paper is to investigate how the disease stage impacts on the ability of machine learning methodologies to predict conversion. After identifying the converters and estimating the time of conversion (TC) (using neuropsychological test scores), we devised 5 subgroups of MCI converters (MCI-C) based on their temporal distance to the conversion instant (0, 6, 12, 18 and 24 months before conversion). Next, we used the FDG-PET images of these subgroups and trained classifiers to distinguish between the MCI-C at different stages and stable non-converters (MCI-NC). Our results show that MCI to AD conversion can be predicted as early as 24 months prior to conversion and that the discriminative power of the machine learning methods decreases with the increasing temporal distance to the TC, as expected. These findings were consistent for all the tested classifiers. Our results also show that this decrease arises from a reduction in the information contained in the regions used for classification and by a decrease in the stability of the automatic selection procedure.

Boosting Alzheimer Disease Diagnosis Using PET Images

Alzheimers disease (AD) is one of the most frequent type of dementia. Currently there is no cure for AD and early diagnosis is crucial to the development of treatments that can delay the disease progression. Brain imaging can be a biomarker for Alzheimers disease. This has been shown in several works with MR Images, but in the case of functional imaging such as PET, further investigation is still needed to determine their ability to diagnose AD, especially at the early stage of Mild Cognitive Impairment (MCI). In this paper we study the use of PET images of the ADNI database for the diagnosis of AD and MCI. We adopt a Boosting classification method, a technique based on a mixture of simple classifiers, which performs feature selection concurrently with the segmentation thus is well suited to high dimensional problems. The Boosting classifier achieved an accuracy of 90.97% in the detection of AD and 79.63% in the detection of MCI.

Automatic segmentation of the lungs using multiple active contours and outlier model.

This paper presents a method for the automatic segmentation of the lungs in X-ray computed tomography (CT) images. The proposed technique is based on the use of multiple active contour models (ACMs) for the simultaneous segmentation of both lungs and outlier detection. The technique starts by grey-level thresholding of the images followed by edge detection. Then the edge points are organized in strokes and a set of weights summing to one is assigned to each stroke. These weights represent the soft assignment of the stroke to each of the ACMs and depend on the distance between the stroke points and the ACM units, on gradient direction information and also on the stroke size. Both the weights and the ACMs energy minimization are computed using the generalized expectation-maximization (EM) algorithm. Initialization of the ACMs is fully automatic. Experimental results show the effectiveness of the proposed technique

An algorithm for the detection of multiple concentric circles

This paper presents a method for the detection of multiple concentric circles which is based on the Hough Transform (HT). In order to reduce time and memory space the concentric circle detection with the HT is separated in two stages, one for the center detection and another for the radius determina-tion. A new HT algorithm is proposed for the center detection stage which is simple, fast and robust. The proposed method selects groups of three points in each of the concentric circles to solve the circle equation and vote for the cen-ter. Geometrical constraints are imposed of the sets of three points to guarantee that they in fact belong to different concentric circles. In the radius detection stage the concentric circles are validated. The proposed algorithm was com-pared with several other HT circle detection techniques. Experimental results show the superiority and effectiveness of the proposed technique.