Dermatological Images Research Articles

Sharpening Dermatological Color Images in the Wavelet Domain

Tele-dermatology is becoming an important tool for early skin cancer detection in public health, but low-cost cameras tend to cause image blurring, which affect diagnosis quality. Obtaining cost-effective images with diagnosis quality is a current challenge, and this paper proposes a novel method for enhancing the local contrast of dermatological images in the wavelet domain. The distribution of squared gradient magnitudes computed through an undecimated wavelet transform is modeled as a combination of chi-squared and gamma distributions, and a posteriori probabilities are used to discriminate coefficients related to edges from those related to noise or homogeneous regions at each scale of the wavelet decomposition. Consistency across scales is used to preserve coefficients likely to be edge related in consecutive levels of the wavelet decomposition, and local directional smoothing is used to reduce residual noise. Then, a nonlinear enhancement function is applied to wavelet coefficients, so that low-contrast edge-related wavelet coefficients are increased. Our experimental results indicate that the proposed approach can effectively sharpen image details, without amplifying background noise. Preliminary validation by specialists indicate that the proposed sharpening algorithm improves the visual quality of dermatological images.

Health Sciences Online: Eight+ Revolutions and Ten+ Brief Analyses

Health Sciences Online: Eight+ Revolutions and Ten+ Brief Analyses

Digital Image Compression in Dermatology: Format Comparison

Digital image compression (reduction of the amount of numeric data needed to represent a picture) is widely used in electronic storage and transmission devices. Few studies have compared the suitability of the different compression algorithms for dermatologic images. We aimed at comparing the performance of four popular compression formats, Tagged Image File (TIF), Portable Network Graphics (PNG), Joint Photographic Expert Group (JPEG), and JPEG2000 on clinical and videomicroscopic dermatologic images. Nineteen (19) clinical and 15 videomicroscopic digital images were compressed using JPEG and JPEG2000 at various compression factors and TIF and PNG. TIF and PNG are "lossless" formats (i.e., without alteration of the image), JPEG is "lossy" (the compressed image has a lower quality than the original), JPEG2000 has a lossless and a lossy mode. The quality of the compressed images was assessed subjectively (by three expert reviewers) and quantitatively (by measuring, point by point, the color differences from the original). Lossless JPEG2000 (49% compression) outperformed the other lossless algorithms, PNG and TIF (42% and 31% compression, respectively). Lossy JPEG2000 compression was slightly less efficient than JPEG, but preserved image quality much better, particularly at higher compression factors. For its good quality and compression ratio, JPEG2000 appears to be a good choice for clinical/videomicroscopic dermatologic image compression. Additionally, its diffusion and other features, such as the possibility of embedding metadata in the image file and to encode various parts of an image at different compression levels, make it perfectly suitable for the current needs of dermatology and teledermatology.

Lead magnesium niobate‐lead titanate single crystal thick films on silicon substrate for high‐frequency micromachined ultrasonic transducers

Some new clinical applications requiring ultrasonic frequencies higher than 30 MHz are emerging, such as ophthalmological and dermatological imaging and intravascular imaging with probes mounted on catheter tips. High frequency ultrasonic transducer (HFUT) has thus been a growing research area in recent years. Most of the HFUTs reported are using piezoelectric PZT ceramic thin plates, ZnO films or PVDF films as the transducer materials. The PMN‐PT ((1‐x)Pb(Mg1/3Nb2/3)O3‐xPbTiO3) single crystal, although possessing the highest piezoelectric coefficients, has seldom been used for this purpose because it is difficult to lap down the brittle single crystals to thin plates and handle them in conventional way of transducer fabrication. In this work, a novel high‐frequency ultrasonic transducer structure is realized by using PMN‐PT‐on‐silicon technology and silicon micromachining. A hybrid processing method involving wafer bonding, mechanical lapping and wet chemical thinning is successfully developed. PMN‐PT thick films with thickness ranging from several to tens of microns have been demonstrated and they have properties comparable to those of PMN‐PT bulk samples. A prototype high frequency ultrasonic transducer is being fabricated and characterized. Acknowledgement Financial support from the Innovation and Technology Fund (K‐ZP21) is acknowledged.

A web-based melanoma image diagnosis support system using topic map and AJAX technologies

The design and implementation of a web-based diagnostic support tool for melanoma dermatological images and related diagnostic data is presented. The proposed system is semantic web-based and is driven by exploiting the combination of AJAX framework and topic map technology. A novel client/server architecture was developed that enables several clients to interact online with the topic map-based system. Users have the ability to access the system anywhere and anytime via a simple Internet browser. Additionally, an ABCD application has been developed for automated calculation of ABCD parameters and consequently embedded in the proposed TM-based system.

Dermatological image search engines on the Internet: do they work?

Atlases on CD-ROM first substituted the use of paediatric dermatology atlases printed on paper. This permitted a faster search and a practical comparison of differential diagnoses. The third step in the evolution of clinical atlases was the onset of the online atlas. Many doctors now use the Internet image search engines to obtain clinical images directly. The aim of this study was to test the reliability of the image search engines compared to the online atlases. We tested seven Internet image search engines with three paediatric dermatology diseases. In general, the service offered by the search engines is good, and continues to be free of charge. The coincidence between what we searched for and what we found was generally excellent, and contained no advertisements. Most Internet search engines provided similar results but some were more user friendly than others. It is not necessary to repeat the same research with Picsearch, Lycos and MSN, as the response would be the same; there is a possibility that they might share software. Image search engines are a useful, free and precise method to obtain paediatric dermatology images for teaching purposes. There is still the matter of copyright to be resolved. What are the legal uses of these 'free' images? How do we define 'teaching purposes'? New watermark methods and encrypted electronic signatures might solve these problems and answer these questions.

Consistent Cutaneous Imaging With Commercial Digital Cameras

To demonstrate how to improve the reproducibility and accuracy of digital images of the skin taken with commercially available digital cameras by transforming them to a standard color space, sRGB. Our computer algorithm transforms digital images to the standard sRGB color space. It is based on a card with a number of color squares with known colorimetric properties that is included in the image, thereby removing any ambiguity about the color information in the image. Reproducibility and accuracy of the method were assessed by comparing images of color squares with known colorimetric properties taken with different digital cameras at different exposures and zoom settings. Although calibrated images exhibit markedly improved precision and accuracy compared with noncalibrated images, all variability of the imaging process cannot be eliminated. With a little care and effort, a calibrated color chart, and computer software, it is possible to greatly improve the quality of clinical imaging in dermatology and possibly other fields of medicine.

Collecting highly reproducible images to support dermatological medical diagnosis

In this article, an integrated imaging system for acquisition of accurate standardized images is proposed. The system also aims at making highly reproducible images over time, so images taken at different times can be compared. The system is made up of an integrating intensity sphere illumination together with a high resolution 3CCD color camera. The well-defined and diffuse illumination of the optically closed scene enhances the true color and avoids effects from specular reflections, shading and shadows. Two experiments are conducted to show the precision of the system and the suitability of the collected images to track dermatological diseases. Results indicate that the developed equipment is an excellent tool for getting high quality digital images. Furthermore, the images collected with the equipment turn out to be a good source to characterize dermatological images.

Practical color calibration for dermoscopy, applied to a digital epiluminescence microscope

The assessment of colors is essential for melanoma (MM) diagnosis, both for pattern analysis on dermoscopic images, and when using semiquantitative methods. Our aim was to provide a simple, precise characterization and reproducible calibration of the color response for dermoscopic instruments. Three processes were used to correct the non-uniform illumination pattern of the instrument, to easily estimate the camera gamma settings and to describe the color space conversion matrices required to produce standard images, in any color space. A specific color space was also developed to optimize the representation of dermatoscopic colors. The calibration technique was tested both on synthetic reference surfaces and on real images by comparing the difference between the images colors obtained with two different equipments. The differences between the images acquired by means of the two instruments, calculated on the reference patterns after calibration, were up to 10 times lower then before, while comparison of histograms referring to real images provided an improvement of about seven times on average. A complete workflow for dermatologic image calibration, which allows the user to continue using his own software and algorithms, but with a much higher informative content, is presented. The technique is simple and may improve cooperation between different research centers, in teleconsulting contexts or for result comparisons.

Dermoscopy of Sebaceous Hyperplasia

T HE LESIONS ARE FROM THE FOREHEAD OF A 67-year-old woman (Figure 1), the left cheek of a 57-year-old man (Figure 2), and the right cheek of a 49-year-old man (Figure 3) (size bar, 3 mm). All 3 lesions reveal a similar pattern. Aggregated white or yellow nodules can be identified at the center of the lesion. These yellowish nodules correspond to hyperplastic sebaceous glands. Sometimes the ostium of the gland is visible as a small crater. The yellowish nodules are surrounded by groups of orderly winding, scarcely branching vessels. The vessels may extend toward the center but they never cross it. They are not arborizing. Their pattern can be described clearly by the term “crown vessels” and this vascular pattern is specific for hyperplastic sebaceous glands. Editor’s Note: The skINsight section is a forum for the presentation of dermatologic images. The current effort is to foster the recognition of patterns in dermatologic disease processes that may enhance both diagnostic and research capabilities. The initial focus is on dermoscopic images. Theoretically, these patterns reflect the interaction of specific gene defects with local environmental factors. The exercise here is to group lesions with similar dermoscopic patterns—not pathologic criteria. The ultimate benign or malignant behavior is not the focus of this section.

Hyperkeratotic Rim of Gram-Negative Toe Web Infections

T HE LESIONS SHOWN ARE FROM THE PLANTAR surface of a foot of a 41-year-old white man (Figure1) and a foot of a 48-year-old white man (Figure 2). Each photograph represents a case of gram-negative toe web infection that was resistant to several courses of antibiotics, antifungal agents, and immunosuppressants, alone or in combination. With continued disease, development of a hyperkeratotic rim was noted in these 2 cases as well as in other cases seen at our institution. This hyperkeratotic rim pattern seems to be characteristic of toe web infections that are resistant to standard medical intervention. In our experience, surgical debridement of the hyperkeratotic rim and surface exudate with a standard curette with the patient under local anesthesia leads to rapid improvement (Figure 3) with routine wound care and without further medical therapy. The hyperkeratotic rim pattern may be the result of epidermal undermining of the polymicrobial infection and may serve both as a protected environment for the infecting agents and as a barrier to wound healing, blocking lateral epidermal migration. Editor’s Note: The skINsight section is a forum for the presentation of dermatologic images. The current effort is to foster the recognition of patterns in dermatologic disease processes that may enhance both diagnostic and research capabilities. The initial focus is on dermoscopic images. Theoretically, these patterns reflect the interaction of specific gene defects with local environmental factors. The exercise here is to group lesions with similar dermoscopic patterns—not pathologic criteria. The ultimate benign or malignant behavior is not the focus of this section.

An Integrated Computer Supported Acquisition, Handling, and Characterization System for Pigmented Skin Lesions in Dermatological Images

This paper describes an integrated prototype computer-based system for the characterization of skin digital images. The first stage includes an image acquisition arrangement designed for capturing skin images, under reproducible conditions. The system processes the captured images and performs unsupervised image segmentation and image registration utilizing an efficient algorithm based on the log-polar transform of the images' Fourier spectrum. Border- and color-based features, extracted from the digital images of skin lesions, were used to construct a classification module for the recognition of malignant melanoma versus dysplastic nevus. Different methods, drawn from the fields of artificial intelligence (neural networks) and statistical modeling (discriminant analysis), were used in order to find the best classification rules and to compare the results of different approaches to the problem.

Images in dermatology

Images in dermatology

Dermoscopy of Disseminated Superficial Actinic Porokeratosis

T HE LESIONS ARE FROM THE RIGHT ARM OF A 53-year-old man (Figure 1), the left leg of a 57-year-old woman (Figure 2), and the left arm of a 48-year-old man (Figure 3) (size bar, 3 mm) affected with a disseminated superficial actinic porokeratosis. All 3 lesions reveal a similar pattern. A “white track” structure can be identified at the periphery of the lesion with a brownish pigmentation in the inner side and with “double white track” in some parts of the lesion. This structure is characteristic of porokeratosis. The images in Figures 1 and 2 reveal red dots, globules, and lines in the center of the lesion; however, the lesion in Figure 3 shows a white homogeneous area. The single or double “white track” structure at the margin corresponds to the cornoid lamella, and the red dots, globules, and lines are enlarged capillary vessels that can be observed because the epithelium is atrophic. The white homogeneous area in the center of the third lesion corresponds to acanthotic epithelium, which can be rarely observed in these lesions. Editor’s Note: The skINsight section is a forum for the presentation of dermatologic images. The current effort is to foster the recognition of patterns in dermatologic disease processes that may enhance both diagnostic and research capabilities. The initial focus is on dermoscopic images. Theoretically, these patterns reflect the interaction of specific gene defects with local environmental factors. The exercise here is to group lesions with similar dermoscopic patterns—not pathologic criteria. The ultimate benign or malignant behavior is not the focus of this section.

New hybrid stochastic-deterministic technique for fast registration of dermatological images

Digital image processing in the medical field has become very popular in recent years owing to the significant advantages it offers over conventional techniques of visual or analogue image analysis. One of the most significant aspects in medical image processing has been that of image registration, which deals with the task of registering two images taken under different conditions. Image registration is considered an important issue in the field of dermatology, as pictures of a lesion taken in different periods need to be compared and quantitatively analysed. A hybrid image registration scheme was developed and evaluated for dermatological applications. The method splits the parameter estimation problem into two, with a combination of deterministic and iterative estimation techniques. The scaling and rotation parameters are estimated using a cross-correlation of image invariant image descriptors algorithm, whereas the two translation parameters are estimated with a non-parametric similarity criterion and a hill-climbing optimisation scheme. The efficacy of the method has been validated for the registration and comparison of malignant melanoma images. Determination of rotation and scaling parameters was performed using the log-polar transformation technique, which proved to be very accurate, even when high rotation and scaling values were imposed. Deviations for the rotation parameter estimations were less than 0.5%, whereas, for the scaling factor, differences were on average less than 2.5%, with a maximum difference estimated to be 4.5%. Translation parameter estimation was performed using integer similarity measures namely the stochastic sign change, the deterministic sign change (DSC) and the window value range, the performance of which has been assessed and, in all cases, was found to be highly effective. A novel hill-climbing optimisation algorithm has been proposed and, in combination with the DSC similarity criterion, was evaluated and proved to successfully estimate translation parameters. Thus the proposed hybrid registration technique can successfully estimate problem parameters in a time-efficient manner.

Real-time spatial compound ultrasound imaging of skin.

The aim of our study was to evaluate the potential of real-time spatial compound imaging (RTSCI) in dermatology. An ATL 5000 SonoCT equipped with compact linear 15-7 MHz and linear 12-5 MHz transducers was obtained for skin visualization in a group of dermatological patients with various skin diseases. Thirty-four people participated: 21 patients with various skin diseases and 13 persons with normal skin. The mean age was 43.4 years. For many diseases, RTSCI gave useful information about the lesional structure, thickness and relationship with surrounding structures. RTSCI allows objective, accurate, noninvasive and easy measurements of several parameters of skin morphology. It is useful in clinical trials, for evaluation of the effects of therapy, for preoperative evaluation of dermatological lesions, and enables visualization of subclinical and deep lesions, giving physicians the possibility of starting treatment before disease intensity increases. However, even such highly advanced ultrasound cannot completely substitute the clinical dermatological approach and the occasional need for histological diagnosis. This new method may, however, become an important adjunct method for the study of skin lesions.

Performances of high numerical aperture water and oil immersion objective in deep-tissue, multi-photon microscopic imaging of excised human skin.

Multi-photon fluorescence microscopy (MPFM) is a powerful technique for imaging scattering, biological specimens in depth. In addition to the sectioning effect generated by the point-like excitation volume, the near-infrared wavelengths used for multi-photon excitation allow deeper penetration into optically turbid specimens. In physiological specimens, the optical properties such as the scattering coefficients and refractive indices are often heterogeneous. In these specimens, it is not clear which type of immersion objective can provide optimized images in-depth. In particular, in-depth dermatological imaging applications using MPFM requires such optimization to obtain qualitative and quantitative information from the skin specimens. In this work, we address this issue by comparing the performances of two common types of high numerical aperture (NA) objectives: water-immersion and oil-immersion. A high-quality water-immersion objective (Zeiss, 40 x C-Apochromat, NA 1.2) and a comparable oil-immersion objective (Zeiss, 40 x Fluar, NA 1.25) were used for in-depth imaging of autofuorescent excised human skin and sulforhodamine B treated human skin specimens. Our results show that in the epidermal layers, the two types of immersion objectives perform comparably. However, in the dermis, multi-photon imaging using the oil immersion objective results in stronger fluorescence detection. These observations are most likely due to the degraded point-spread-function (PSF) caused by refractive index mismatch between the epidermis and the dermis.

IL-39 Reproducible clinical dermatological imaging with commercially available digital cameras

IL-39 Reproducible clinical dermatological imaging with commercially available digital cameras

Digital imaging in clinical dermatology across the UK in the year 2001.

Colour photography is an important tool in the daily practice of dermatologists. Digital photography promises quicker acquisition and handling of clinical images. Despite increasing availability and falling costs, dermatologists have been slow in adopting this new technique. To establish to what degree digital photography has found its way into routine practice in dermatology departments in the UK during the year 2001, we conducted a postal survey of all dermatology departments in the UK about usage of digital cameras. A total of 65.4% of the questionnaires were returned. The responses indicated that 71% of departments in teaching hospitals vs. 56% of departments in district general hospitals (DGH) had access to a digital camera. Reasons for not having a digital camera were satisfaction with conventional photography and lack of resources. In 48% of the departments of teaching hospitals or DGH with access to a digital camera, less than 10% of all photos were taken digitally. However, 24% of departments in DGH and 22% in teaching hospitals took more than 80% of their clinical photos digitally, indicating that in many departments digital photography is still in an early phase and only occasionally used, whilst in others a change from conventional photography towards digital photography as the mainly used technique has already taken place. Overall, the main drawbacks of digital photography were poorer resolution in comparison with conventional photography, problems with storage and filing images and time required for downloading and storing images.

Automated Segmentation and Registration of Dermatological Images

During the last years, there has been a significant increase in the level of interest in image morphology, full-color image processing, image data compression, image recognition and knowledge based analysis systems for medical images. The present paper describes the implementation and tests the efficiency of algorithms dealing with the issues of segmentation and registration of digital images containing skin lesions. Those steps are considered of great importance in computer based characterization systems as they are responsible for the isolation of pathological findings and the matching of sequential images during follow-up studies in medical imaging. Mathematics Subject Classifications (2000): 68U10, 92C55. Up until now, medical professionals have based the diagnosis of skin lesions on visual assessment of pathological skin and the evaluation of macroscopic features. This fact shows the high dependency of the correct diagnosis on the observer's experience and on his or her visual acuity. Moreover, the human vision lacks ac- curacy, reproducibility and quantification in gathering information from an image. The quantification of tissue lesion features has been proven to be of essential impor- tance in clinical practice, because several tissue lesions can be identified based on measurable features extracted from an image. In addition the use of digital image features may help in an objective follow up study of skin lesion progression and test the efficacy of therapeutic procedures (6, 7, 15, 13, 11). The present paper describes the implementation and evaluates the efficiency of algorithms dealing with the issue of segmentation and registration of digital images containing skin lesions. The segmentation procedure concerns the isolation of pathological skin lesions from the surrounding healthy skin, while registration involves the matching of sequential images displaying the same skin lesion, acquired in different time periods, e.g., during follow-up studies. The paper in a first stage (Sections 2 and 3) deals with the segmentation problem while in the second stage (Sections 4, 5, 6 and 7) proposes a deterministic algorithm