Paul Wighton

Optimizing real time fMRI neurofeedback for therapeutic discovery and development

While reducing the burden of brain disorders remains a top priority of organizations like the World Health Organization and National Institutes of Health, the development of novel, safe and effective treatments for brain disorders has been slow. In this paper, we describe the state of the science for an emerging technology, real time functional magnetic resonance imaging (rtfMRI) neurofeedback, in clinical neurotherapeutics. We review the scientific potential of rtfMRI and outline research strategies to optimize the development and application of rtfMRI neurofeedback as a next generation therapeutic tool. We propose that rtfMRI can be used to address a broad range of clinical problems by improving our understanding of brain–behavior relationships in order to develop more specific and effective interventions for individuals with brain disorders. We focus on the use of rtfMRI neurofeedback as a clinical neurotherapeutic tool to drive plasticity in brain function, cognition, and behavior. Our overall goal is for rtfMRI to advance personalized assessment and intervention approaches to enhance resilience and reduce morbidity by correcting maladaptive patterns of brain function in those with brain disorders.

A Fully Automatic Random Walker Segmentation for Skin Lesions in a Supervised Setting

We present a method for automatically segmenting skin lesions by initializing the random walker algorithm with seed points whose properties, such as colour and texture, have been learnt via a training set. We leverage the speed and robustness of the random walker algorithm and augment it into a fully automatic method by using supervised statistical pattern recognition techniques. We validate our results by comparing the resulting segmentations to the manual segmentations of an expert over 120 cases, including 100 cases which are categorized as difficult (i.e.: low contrast, heavily occluded, etc.). We achieve an F-measure of 0.95 when segmenting easy cases, and an F-measure of 0.85 when segmenting difficult cases.

Dermascopic hair disocclusion using inpainting

Inpainting, a technique originally used to restore film and photographs, is used to disocclude hair from dermascopic images of skin lesions. The technique is compared to the conventional software DullRazor, which uses linear interpolation to perform disocclusion. Comparison was performed by simulating occluding hair on a dermascopic image, applying DullRazor and inpainting and calculating the error induced. Inpainting is found to perform approximately 33% better than DullRazors linear interpolation, and is more stable under heavy occlusion. The results are also compared to published results from two other alternatives: auto-regressive (AR) model signal extrapolation and band-limited (BL) signal interpolation.

Chromatic aberration correction: an enhancement to the calibration of low-cost digital dermoscopes.

Background/purpose: We present a method for calibrating low‐cost digital dermoscopes that corrects for color and inconsistent lighting and also corrects for chromatic aberration. Chromatic aberration is a form of radial distortion that often occurs in inexpensive digital dermoscopes and creates red and blue halo‐like effects on edges. Being radial in nature, distortions due to chromatic aberration are not constant across the image, but rather vary in both magnitude and direction. As a result, distortions are not only visually distracting but could also mislead automated characterization techniques.

Neurofeedback using functional spectroscopy

Neurofeedback based on real‐time measurement of the blood oxygenation level‐dependent (BOLD) signal has potential for treatment of neurological disorders and behavioral enhancement. Commonly used methods are based on functional magnetic resonance imaging (fMRI) sequences that sacrifice speed and accuracy for whole‐brain coverage, which is unnecessary in most applications. We present multivoxel functional spectroscopy (MVFS): a system for computing the BOLD signal from multiple volumes of interest (VOI) in real‐time that improves speed and accuracy of neurofeedback. MVFS consists of a FS pulse sequence, a BOLD reconstruction component, a neural activation estimator, and a stimulus system. The FS pulse sequence is a single‐voxel, magnetic resonance spectroscopy sequence without water suppression that has been extended to allow acquisition of a different VOI at each repetition and real‐time subject head motion compensation. The BOLD reconstruction component determines the T2* decay rate, which is directly related to BOLD signal strength. The neural activation estimator discounts nuisance signals and scales the activation relative to the amount of ROI noise. Finally, the neurofeedback system presents neural activation‐dependent stimuli to experimental subjects with an overall delay of less than 1 s. Here, we present the MVFS system, validation of certain components, examples of its usage in a practical application, and a direct comparison of FS and echo‐planar imaging BOLD measurements. We conclude that in the context of realtime BOLD imaging, MVFS can provide superior accuracy and temporal resolution compared with standard fMRI methods.

Pigment Network Detection and Analysis

We describe the importance of identifying pigment networks in lesions which may be melanomas, and survey methods for identifying pigment networks (PN) in dermoscopic images. We then give details of how machine learning can be used to classify images into three classes: PN Absent, Regular PN and Irregular PN.

Multi-level feature extraction for skin lesion segmentation in dermoscopic images

This paper presents a novel approach in computer aided skin lesion segmentation of dermoscopic images. We apply spatial and color features in order to model the lesion growth pattern. The decomposition is done by repeatedly clustering pixels into dark and light sub-clusters. A novel tree structure based representation of the lesion growth pattern is constructed by matching every pixel sub-cluster with a node in the tree structure. This model provides a powerful framework to extract features and to train models for lesion segmentation. The model employed allows features to be extracted at multiple layers of the tree structure, enabling a more descriptive feature set. Additionally, there is no need for preprocessing such as color calibration or artifact disocclusion. Preliminary features (mean over RGB color channels) are extracted for every pixel over four layers of the growth pattern model and are used in association with radial distance as a spatial feature to segment the lesion. The resulting per pixel feature vectors of length 13 are used in a supervised learning model for estimating parameters and segmenting the lesion. A dataset containing 116 challenging images from dermoscopic atlases is used to validate the method via a 10-fold cross validation procedure. Results of segmentation are compared with six other skin lesion segmentation methods. Our method outperforms ve other methods and performs competitively with another method. We achieve a per-pixel sensitivity/specicity of 0.890 and 0.901 respectively.