Search

ObjectivesEarly melanoma detection decreases morbidity and mortality. Early detection classically involves dermoscopy to identify suspicious lesions for which biopsy is indicated. Biopsy and histological examination then diagnose benign nevi, atypical nevi, or cancerous growths. With current methods, a considerable number of unnecessary biopsies are performed as only 11% of all biopsied, suspicious lesions are actually melanomas. Thus, there is a need for more advanced noninvasive diagnostics to guide the decision of whether or not to biopsy. Artificial intelligence can generate screening algorithms that transform a set of imaging biomarkers into a risk score that can be used to classify a lesion as a melanoma or a nevus by comparing the score to a classification threshold. Melanoma imaging biomarkers have been shown to be spectrally dependent in Red, Green, Blue (RGB) color channels, and hyperspectral imaging may further enhance diagnostic power. The purpose of this study was to use the same melanoma imaging biomarkers previously described, but over a wider range of wavelengths to determine if, in combination with machine learning algorithms, this could result in enhanced melanoma detection.MethodsWe used the melanoma advanced imaging dermatoscope (mAID) to image pigmented lesions assessed by dermatologists as requiring a biopsy. The mAID is a 21-wavelength imaging device in the 350-950 nm range. We then generated imaging biomarkers from these hyperspectral dermoscopy images, and, with the help of artificial intelligence algorithms, generated a melanoma Q-score for each lesion (0 = nevus, 1 = melanoma). The Q-score was then compared to the histopathologic diagnosis.ResultsThe overall sensitivity and specificity of hyperspectral dermoscopy in detecting melanoma when evaluated in a set of lesions selected by dermatologists as requiring biopsy was 100% and 36%, respectively.ConclusionWith widespread application, and if validated in larger clinical trials, this non-invasive methodology could decrease unnecessary biopsies and potentially increase life-saving early detection events. Lasers Surg. Med. 51:214-222, 2019. © 2019 The Authors. Lasers in Surgery and Medicine Published by Wiley Periodicals, Inc.

Significance: Hyperspectral cameras capture spectral information at each pixel in an image. Acquired spectra can be analyzed to estimate quantities of absorbing and scattering components, but the use of traditional fitting algorithms over megapixel images can be computationally intensive. Deep learning algorithms can be trained to rapidly analyze spectral data and can potentially process hyperspectral camera data in real time. Aim: A hyperspectral camera was used to capture 1216 × 1936 pixel wide-field reflectance images of in vivo human tissue at 205 wavelength bands from 420 to 830 nm. Approach: The optical properties of oxyhemoglobin, deoxyhemoglobin, melanin, and scattering were used with multi-layer Monte Carlo models to generate simulated diffuse reflectance spectra for 24,000 random combinations of physiologically relevant tissue components. These spectra were then used to train an artificial neural network (ANN) to predict tissue component concentrations from an input reflectance spectrum. Results: The ANN achieved low root mean square errors in a test set of 6000 independent simulated diffuse reflectance spectra while calculating concentration values more than 4000× faster than a conventional iterative least squares approach. Conclusions: In vivo finger occlusion and gingival abrasion studies demonstrate the ability of this approach to rapidly generate high-resolution images of tissue component concentrations from a hyperspectral dataset acquired from human subjects. [ABSTRACT FROM AUTHOR]

Background and objectiveSuccessful laser treatment of port wine stain (PWS) birthmarks requires knowledge of lesion geometry. Laser parameters, such as pulse duration, wavelength, and radiant exposure, and other treatment parameters, such as cryogen spurt duration, need to be optimized according to epidermal melanin content and lesion depth. We designed, constructed, and clinically tested a photoacoustic probe for PWS depth determination.Study design/materials and methodsEnergy from a frequency-doubled, Nd:YAG laser (lambda=532 nm, tau(p)=4 nanoseconds) was coupled into two 1,500 mum optical fibers fitted into an acrylic handpiece containing a piezoelectric acoustic detector. Laser light induced photoacoustic waves in tissue phantoms and a patient's PWS. The photoacoustic propagation time was used to calculate the depth of the embedded absorbers and PWS lesion.ResultsCalculated chromophore depths in tissue phantoms were within 10% of the actual depths of the phantoms. PWS depths were calculated as the sum of the epidermal thickness, determined by optical coherence tomography (OCT), and the epidermal-to-PWS thickness, determined photoacoustically. PWS depths were all in the range of 310-570 microm. The experimentally determined PWS depths were within 20% of those measured by optical Doppler tomography (ODT).ConclusionsPWS lesion depth can be determined by a photoacoustic method that utilizes acoustic propagation time.

The application of pulsed photothermal radiometry (PPTR) diagnostics to characterize port wine stain (PWS) lesions is discussed. Influence of epidermal absorbance and PWS depth on the PPTR signal is analyzed using an in-vitro model of PWS skin consisting of multilayered collagen films. An instrument is constructed and used for patient and animal model PPTR measurements. When an infrared fiber is incorporated, the instrumentation facilitates convenient skin-site accessibility. Modulation of the PPTR signal and homodyne detection substantially improve the system signal-to-noise ratio over previous methods. Given the measured PPTR signal, an algorithm computes the initial temperature distribution in the PWS skin immediately after the laser pulse. The use and limitations of the algorithm are presented and discussed.

The application of pulsed photothermal radiometry (PPTR) diagnostics to characterize port wine stain (PWS) lesions is discussed. A PPTR signal of a PWS in response to pulsed laser exposure is shown to consist of an initial `T-jump' due to epidermal melanin absorption and a `delayed thermal wave' resulting from laser generated heat in subsurface blood vessels diffusing to the skin surface. A prototype PPTR instrument incorporating an infrared fiber is constructed which facilitates convenient skin-site accessibility. Laser heating of the infrared collection optics results in an artifactual signal which overestimates the initial `T-jump.' Magnitude of the error is measured and a method to eliminate it is suggested.

A method for quantitative characterization of port wine slain (PWS) is presented. Pulsed photothermal radiometry (PPTR) uses a non-invasive infrared radiometry system to measure changes in surface temperature induced by pulsed radiation. When a pulsed laser is used to irradiate a PWS, an initial temperature jump (T-jump) is seen due to the heating of the epidermis as a result of melanin absorption. Subsequently, heat generated in the subsurface blood vessels due to hemoglobin absorption is detected by PPTR as a delayed thermal wave as the heat diffuses toward the skin surface. The time delay and magnitude of the delayed PPTR signal indicate the depth and thickness of the PWS. In this report, we present an initial clinical study of PPTR measurements on PWS patients. Computer simulations of various classes of PWS illustrate how the PPTR signal depends on the concentration of epidermal melanin, and depth and thickness of the PWS. The goal of this research is to provide a means of characterizing PWS before initialing therapy, guiding laser dosimetry, and advising the palient as to the time course and efficacy of the planned protocol.

The precise removal of stratum corneum from cadaveric swine skin by a mid-infrared erbium:yttrium scandium gallium garnet laser (lambda = 2.79 microns; 250 microseconds pulse width) was assessed by electrical resistance measurements and documented by histology. The effects of stratum corneum removal by laser ablation and by adhesive tape-stripping on the in vitro penetration of 3H-hydrocortisone and 125I-gamma-interferon were determined. Excised swine skin was irradiated with laser (1 J/cm2; 31 mJ/pulse; 1 Hz; 2 mm spot diameter). For skin penetration studies, laser pulses were delivered to discrete 2-mm areas to ablate up to 12.6% of the total 3-cm2 stratum corneum diffusional area. Franz in vitro skin penetration chambers were used to measure the cumulative 48-h penetration of 3H-hydrocortisone and 125I-gamma-interferon in laser-treated and tape-stripped skin. Electrical resistance measurements and histologic studies demonstrated that 10-14 laser pulses at the above energy density were required to abolish skin resistance and selectively ablate stratum corneum without damage to adjacent dermal structures. Laser ablation of 12.6% of the surface area of stratum corneum produced a 2.8 and 2.1-times increase in permeability constant (kp) for 3H-hydrocortisone and 125I-gamma-interferon, respectively. These studies demonstrate that a pulsed mid-infrared laser can reliably and precisely remove the stratum corneum, facilitating penetration of large molecules such as 125I-gamma-interferon that cannot penetrate intact skin. This new technique may be useful for basic and clinical investigation of skin barrier properties.