Teresa Mendonça

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.

PH 2 - A dermoscopic image database for research and benchmarking

The increasing incidence of melanoma has recently promoted the development of computer-aided diagnosis systems for the classification of dermoscopic images. Unfortunately, the performance of such systems cannot be compared since they are evaluated in different sets of images by their authors and there are no public databases available to perform a fair evaluation of multiple systems. In this paper, a dermoscopic image database, called PH2, is presented. The PH2 database includes the manual segmentation, the clinical diagnosis, and the identification of several dermoscopic structures, performed by expert dermatologists, in a set of 200 dermoscopic images. The PH2 database will be made freely available for research and benchmarking purposes.

Two Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Color Features

Melanoma is one of the deadliest forms of cancer; hence, great effort has been put into the development of diagnosis methods for this disease. This paper addresses two different systems for the detection of melanomas in dermoscopy images. The first system uses global methods to classify skin lesions, whereas the second system uses local features and the bag-of-features classifier. This paper aims at determining the best system for skin lesion classification. The other objective is to compare the role of color and texture features in lesion classification and determine which set of features is more discriminative. It is concluded that color features outperform texture features when used alone and that both methods achieve very good results, i.e., Sensitivity = 96% and Specificity = 80% for global methods against Sensitivity = 100% and Specificity = 75% for local methods. The classification results were obtained on a data set of 176 dermoscopy images from Hospital Pedro Hispano, Matosinhos.

PID control strategies for the automatic control of neuromuscular blockade

Abstract A digital PID controller incorporating several modifications to accommodate the characteristics of the neuromuscular blockade is described in this paper. The initial design was performed by the Ziegler-Nichols step response method. The controller gains are automatically adjusted to the specified target by a gain-scheduling technique. The control system was evaluated in 30 patients. Subsequent analysis of all the data collected during surgery indicates that the variability of the patient responses is much wider than that inferred from the literature. This observation clearly suggests the desirability of individual tuning of the controller parameters. A technique for an improved tuning of the PID controller parameters to the patient’s individual dynamics is presented.

Online nonlinear identification of the effect of drugs in anaesthesia using a minimal parameterization and BIS measurements

This paper addresses the problem of modeling and identification of the Depth of Anaesthesia (DoA). It presents a new MISO Wiener model for the pharmacokinetics and pharmacodynamics of propofol and remifentanil, when jointly administered to patients undergoing surgery. The models most commonly used to describe the effect of drugs in the human body are overparameterized Wiener models. In particular, in an anaesthesia environment, the high number of patient-dependent parameters coupled with the insufficient excitatory pattern of the input signals (drug dose profiles) and the presence of noise make robust identification strategies difficult to find. In fact, in such clinical application the user cannot freely choose the input signals to enable accurate parameter identification. A new MISO Wiener model with only four parameters is hence proposed to model the effect of the joint administration of the hypnotic propofol and the analgesic remifentanil. An Extended Kalman Filter (EKF) algorithm was used to perform the nonlinear online identification of the system parameters. The results show that both the new model and the identification strategy outperform the currently used tools to infer individual patient response. The proposed DoA identification scheme was evaluated in a real patient database, where the DoA is quantified by the Bispectral Index Scale (BIS) measurements. The results obtained so far indicate that the developed approach will be a powerful tool for modeling and identification of anaesthetic drug dynamics during surgical procedures.

Drug Delivery for Neuromuscular Blockade With Supervised Multimodel Adaptive Control

A major issue in drug delivery systems is the high level of uncertainty due to inter- and intrapatient variations in the dynamics of drug absorption and metabolism. This paper proposes an approach to tackle this problem based on supervised multimodel adaptive control (SMMAC). Although the specific case of neuromuscular-blockade-level control of patients subject to general anesthesia is considered, the overall procedure can be applied to the control of other physiological variables. Design guidelines to implement SMMAC are presented, together with clinical cases of patients undergoing general anesthesia, where atracurium is used as the blocking agent. The important role played by the selection of the observer polynomial in the supervisor is demonstrated.

Control of neuromuscular blockade in the presence of sensor faults

The problem of embedding sensor fault tolerance in feedback control of neuromuscular blockade is considered. For tackling interruptions of feedback measurements, a structure based upon Bayesian inference as well as a predictive filter is proposed. This algorithm is general and can be applied to different situations. Here, it is incorporated in an adaptive automatic system for feedback control of neuromuscular blockade using continuous infusion of muscle relaxants. A significant contribution consists in the experimental clinical testing of the algorithm in patients undergoing surgery.

The use of texture for image classification of black & white air photographs

The use of black & white (B&W) air photographs for the production of historic land cover maps can be done by image classification, using additional texture features. In this paper we evaluate the importance of a number of parameters in the image classification process based on texture, such as the window size, angle and distance used to produce the texture features, the number of features used, the image quantization level and its spatial resolution. The evaluation was performed using five photographs from the 1950s. The influence of the classification method, the number of classes searched for in the images and the post‐processing tasks were also investigated. The effect of each of these parameters for the classification accuracy was evaluated by cross‐validation. The selection of the best parameters was performed based on the validation results, and also on the computation load involved for each case and the end user requirements. The final classification results were good (average accuracy of 85.7%, k = 0.809) and the method has proven to be useful for the production of historic land cover maps from B&W air photographs.

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.

Hopfield neural networks for on-line parameter estimation

This paper addresses the problem of using Hopfield Neural Networks (HNNs) for on-line parameter estimation. As presented here, a HNN is a nonautonomous nonlinear dynamical system able to produce a time-evolving estimate of the actual parameterization. The stability analysis of the HNN is carried out under more general assumptions than those previously considered in the literature, yielding a weaker sufficient condition under which the estimation error asymptotically converges to zero. Furthermore, a robustness analysis is made, showing that, under the presence of perturbations, the estimation error converges to a bounded neighbourhood of zero, whose size decreases with the size of the perturbations. The results obtained are illustrated by means of two case studies, where the HNN is compared with two other methods.