Search results

The purpose of this paper is to describe innovative machine vision methods that have been employed for the capture and analysis of 3D skin textures; and the resulting potential for assisting with identification of suspicious lesions in the detection of skin cancer.

A machine vision approach has been employed for analysis of 3D skin textures. This involves an innovative application of photometric stereo for the capture of the textures, and a range of methods for analysing and quantifying them, including statistical methods and neural networks.

3D skin texture has been identified as a useful indicator of skin cancer. It can be used to improve realism of virtual skin reconstructions in tele‐dermatology. 3D texture features can also be combined with 2D features to obtain a more robust classifier for improving diagnostic accuracy, thereby assisting with the long‐term goal of implementing computer‐aided diagnostics for skin cancer.

The device developed for capturing 3D skin textures is known as the “Skin Analyser”, and as far as the authors know it is unique in the world in being able to recover 3D textures from pigmented lesions in vivo. There currently exist numerous methods for analysing lesions, including manual inspection (using established heuristics commonly known as ABCD rules), dermoscopy and SIAoscopy. The ability to capture and analyse 3D lesion textures complements these existing techniques and forms a valuable additional indicator for assisting with the early detection of dangerous skin cancers such as melanoma.

The study aims to cope with the problems confronted in the skin lesion datasets with less training data toward the classification of melanoma. The vital, challenging issue is the insufficiency of training data that occurred while classifying the lesions as melanoma and non-melanoma.

In this work, a transfer learning (TL) framework Transfer Constituent Support Vector Machine (TrCSVM) is designed for melanoma classification based on feature-based domain adaptation (FBDA) leveraging the support vector machine (SVM) and Transfer AdaBoost (TrAdaBoost). The working of the framework is twofold: at first, SVM is utilized for domain adaptation for learning much transferrable representation between source and target domain. In the first phase, for homogeneous domain adaptation, it augments features by transforming the data from source and target (different but related) domains in a shared-subspace. In the second phase, for heterogeneous domain adaptation, it leverages knowledge by augmenting features from source to target (different and not related) domains to a shared-subspace. Second, TrAdaBoost is utilized to adjust the weights of wrongly classified data in the newly generated source and target datasets.

The experimental results empirically prove the superiority of TrCSVM than the state-of-the-art TL methods on less-sized datasets with an accuracy of 98.82%.

Experiments are conducted on six skin lesion datasets and performance is compared based on accuracy, precision, sensitivity, and specificity. The effectiveness of TrCSVM is evaluated on ten other datasets towards testing its generalizing behavior. Its performance is also compared with two existing TL frameworks (TrResampling, TrAdaBoost) for the classification of melanoma.

The mortality rate due to skin cancers has been increasing over the past decades. Early detection and treatment of skin cancers can save lives. However, due to visual resemblance of normal skin and lesion and blurred lesion borders, skin cancer diagnosis has become a challenging task even for skilled dermatologists. Hence, the purpose of this study is to present an image-based automatic approach for multiclass skin lesion classification and compare the performance of various models.

In this paper, the authors have presented a multiclass skin lesion classification approach based on transfer learning of deep convolutional neural network. The following pre-trained models have been used: VGG16, VGG19, ResNet50, ResNet101, ResNet152, Xception, MobileNet and compared their performances on skin cancer classification.

The experiments have been performed on HAM10000 dataset, which contains 10,015 dermoscopic images of seven skin lesion classes. The categorical accuracy of 83.69%, Top2 accuracy of 91.48% and Top3 accuracy of 96.19% has been obtained.

Early detection and treatment of skin cancer can save millions of lives. This work demonstrates that the transfer learning can be an effective way to classify skin cancer images, providing adequate performance with less computational complexity.

The purpose of this paper is to develop an automatic control system for mechanical ventilation therapy based on the open lung concept (OLC) using artificial intelligence. In addition, mean arterial blood pressure (MAP) is stabilized by means of a decoupling controller with automated noradrenaline (NA) dosage to ensure adequate systemic perfusion during ventilation therapy for patients with acute respiratory distress syndrome (ARDS).

The aim is to develop an automatic control system for mechanical ventilation therapy based on the OLC using artificial intelligence. In addition, MAP is stabilized by means of a decoupling controller with automated NA dosage to ensure adequate systemic perfusion during ventilation therapy for patients with ARDS.

This innovative closed-loop mechanical ventilation system leads to a significant improvement in oxygenation, regulates end-tidal carbon dioxide for appropriate gas exchange and stabilizes MAP to guarantee proper systemic perfusion during the ventilation therapy.

Currently, this automatic ventilation system based on the OLC can only be applied in animal trials; for clinical use, such a system generally requires a mechanical ventilator and sensors with medical approval for humans.

For implementation of a closed-loop ventilation system, reliable signals from the sensors are a prerequisite for successful application.

The experiment with porcine dynamics demonstrates the feasibility and usefulness of this automatic closed-loop ventilation therapy, with hemodynamic control for severe ARDS. Moreover, this pilot study validated a new algorithm for implementation of the OLC, whereby all control objectives are fulfilled during the ventilation therapy with adequate hemodynamic control of patients with ARDS.

Pressure ulcer is a clinical pathology of localized damage to the skin and underlying tissue caused by pressure, shear, and friction. Diagnosis, treatment and care of pressure ulcers involve high costs for sanitary systems. Accurate wound evaluation is a critical task to optimize the efficacy of treatments and health‐care. Clinicians evaluate the pressure ulcers by visual inspection of the damaged tissues, which is an imprecise manner of assessing the wound state. Current computer vision approaches do not offer a global solution to this particular problem. The purpose of this paper is to use a hybrid learning approach based on neural and Bayesian networks to design a computational system to automatic tissue identification in wound images.

A mean shift procedure and a region‐growing strategy are implemented for effective region segmentation. Color and texture features are extracted from these segmented regions. A set of k multi‐layer perceptrons is trained with inputs consisting of color and texture patterns, and outputs consisting of categorical tissue classes determined by clinical experts. This training procedure is driven by a k‐fold cross‐validation method. Finally, a Bayesian committee machine is formed by training a Bayesian network to combine the classifications of the k neural networks (NNs).

The authors outcomes show high efficiency rates from a two‐stage cascade approach to tissue identification. Giving a non‐homogeneous distribution of pattern classes, this hybrid approach has shown an additional advantage of increasing the classification efficiency when classifying patterns with relative low frequencies.

The methodology and results presented in this paper could have important implications to the field of clinical pressure ulcer evaluation and diagnosis.

The novelty associated with this work is the use of a hybrid approach consisting of NNs and Bayesian classifiers which are combined to increase the performance of a pattern recognition task applied to the real clinical problem of tissue detection under non‐controlled illumination conditions.

The purpose of this paper is to present a numerical analysis of the laser surgery of port wine stain (PWS) with cryogen spray cooling to compare the treatment effect between pulse dye laser and Nd:YAG laser, explain the incomplete clear of the lesion and optimize the laser parameter.

The complex structure of skin and PWS is simplified to a multi-layer skin model that consists of top epidermal layer and underneath dermis layer embedded with discrete blood vessels. The cooling effect of cryogen spray before laser firing is quantified by a general correlation obtained recently from the experimental data. The light distribution is modeled by the Monte Carlo method. The heat transfer in skin tissue is calculated by Pennes bioheat transfer model. The thermal damage of blood vessel is quantified by the Arrhenius damage integral.

For the vessel size studied (10-120 µm), pulse duration is recommended shorter than 6 ms. Large and deeply buried vessels, which may survive from 595 nm laser irradiation, can be coagulated by 1,064 nm laser due to its deep light penetration depth in skin. Furthermore, a desired uniform heating within the large vessel lumen can be achieved by 1,064 nm laser whereas 595 nm laser produce non-uniform heating.

The possible reason for the poor responding and incomplete clearance lesions is clarified. Laser wavelength and pulse duration are suggested to improve the clinical results.

The purpose of this paper is to propose a generic framework based on the colour and the texture features for colour‐textured image segmentation. The framework can be applied to any real‐world applications for appropriate interpretation.

The framework derives the contributions of colour and texture in image segmentation. Local binary pattern and an unsupervised k‐means clustering are used to cluster pixels in the chrominance plane. An unsupervised segmentation method is adopted. A quantitative estimation of colour and texture performance in segmentation is presented. The proposed method is tested using different mosaic and natural images and other image database used in computer vision. The framework is applied to three different applications namely, Irish script on screen images, skin cancer images and sediment profile imagery to demonstrate the robustness of the framework.

The inclusion of colour and texture as distributions of regions provided a good discrimination of the colour and the texture. The results indicate that the incorporation of colour information enhanced the texture analysis techniques and the methodology proved effective and efficient.

The novelty lies in the development of a generic framework using both colour and texture features for image segmentation and the different applications from various fields.

The main objective of this paper is to investigate the response of human skin to an intense temperature drop at the surface. In addition, this paper aims to evaluate the efficiency of finite difference and finite volume methods in solving the highly nonlinear form of Pennes’ bioheat equation.

One-dimensional linear and nonlinear forms of Pennes’ bioheat equation with uniform grids were used to study the behavior of human skin. The specific heat capacity, thermal conductivity and blood perfusion rate were assumed to be linear functions of temperature. The nonlinear form of the bioheat equation was solved using the Newton linearization method for the finite difference method and the Picard linearization method for the finite volume method. The algorithms were validated by comparing the results from both methods.

The study demonstrated the capacity of both finite difference and finite volume methods to solve the one-dimensional and highly nonlinear form of the bioheat equation. The investigation of human skin’s thermal behavior indicated that thermal conductivity and blood perfusion rate are the most effective properties in mitigating a surface temperature drop, while specific heat capacity has a lesser impact and can be considered constant.

This paper modeled the transient heat distribution within human skin in a one-dimensional manner, using temperate-dependent physical properties. The nonlinear equation was solved with two numerical methods to ensure the validity of the results, despite the complexity of the formulation. The findings of this study can help in understanding the behavior of human skin under extreme temperature conditions, which can be beneficial in various fields, including medical and engineering.

This paper aims to understand the laser–tissue interaction mechanism during ophthalmic laser surgeries through numerical analysis. The influence of laser parameters and the multipulse technique were investigated.

The ocular fundus was simplified as a multilayered homogenous medium model. Afterward, the multilayer Monte Carlo method was used to simulate the propagation and energy deposition of laser light, and a local thermal non-equilibrium two-temperature model was established to simulate the temperature variation of chromophores and surrounding tissue with different laser wavelength.

Through the model, the selective heating of chromophore (melanin and blood vessels) was clearly illustrated: 1) neglecting the laser energy absorbance by blood in the traditional model will cause significant errors in temperature calculation; 2) the non-thermal equilibrium heat transfer model was needed to obtain an accurate description of the thermal process when the dimensionless pulse width (tp*) is <10⁵. For 532 nm Argon laser, the optimize tp* is around 10⁵ and the appropriate energy density is 5 J/cm²; 3) multipulse technique makes the energy more concentrated within the melanin, thereby reducing the thermal damage in surrounding tissue, with most appropriate pulse number and duty cycle is 10 and 1/10.

Taking the blood absorption into account, the different temperature variations of melanin/vessels and surrounding tissue caused by the selective photo-thermolysis were simulated successfully. By understanding the mechanism of laser therapy, laser parameters and multipulse technique are suggested to improve the clinical results.

The prayer against the Poultry (Hygiene) Regulations which we briefly mentioned in the editorial of our last issue, was lodged as a result of activity by the Environmental Health Officers' Association. Incidentally it is the first occasion as far as we can recall that a prayer has been lodged against any of the rash of food regulations of recent years, and reflects the strong feelings of the public health inspectorate.