Innovations and Developments in Dermatologic Non-invasive Optical Imaging and Potential Clinical Applications

Tkaczyk, Eric R.

doi:10.2340/00015555-2717

Cited by 30 publications

(28 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, if combined with images from noninvasive devices for melanoma diagnosis, which may overcome the problems presented by a thick skin, the accuracy of CNN can be markedly improved. Several non-invasive devices such as confocal and photon microscopy are being introduced to provide convenient ways to diagnose melanoma early [28]. However, they require much effort and time for a physician to gain expertise.…”

Section: Discussionmentioning

confidence: 99%

Acral melanoma detection using a convolutional neural network for dermoscopy images

Yang

Kim

et al. 2018

PLoS ONE

View full text Add to dashboard Cite

Background/PurposeAcral melanoma is the most common type of melanoma in Asians, and usually results in a poor prognosis due to late diagnosis. We applied a convolutional neural network to dermoscopy images of acral melanoma and benign nevi on the hands and feet and evaluated its usefulness for the early diagnosis of these conditions.MethodsA total of 724 dermoscopy images comprising acral melanoma (350 images from 81 patients) and benign nevi (374 images from 194 patients), and confirmed by histopathological examination, were analyzed in this study. To perform the 2-fold cross validation, we split them into two mutually exclusive subsets: half of the total image dataset was selected for training and the rest for testing, and we calculated the accuracy of diagnosis comparing it with the dermatologist’s and non-expert’s evaluation.ResultsThe accuracy (percentage of true positive and true negative from all images) of the convolutional neural network was 83.51% and 80.23%, which was higher than the non-expert’s evaluation (67.84%, 62.71%) and close to that of the expert (81.08%, 81.64%). Moreover, the convolutional neural network showed area-under-the-curve values like 0.8, 0.84 and Youden’s index like 0.6795, 0.6073, which were similar score with the expert.ConclusionAlthough further data analysis is necessary to improve their accuracy, convolutional neural networks would be helpful to detect acral melanoma from dermoscopy images of the hands and feet.

show abstract

Section: Discussionmentioning

confidence: 99%

Acral melanoma detection using a convolutional neural network for dermoscopy images

Yang

Kim

et al. 2018

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Several other non-invasive optical diagnostic tools and innovative technologies that are already available or are still being developed, such as Raman spectroscopy and multiphoton microscopy, have potential clinical applications in skin cancer diagnosis. These are described in another paper in this supplement (see Tkaczyk,62).…”

Section: High-frequency Ultrasoundmentioning

confidence: 95%

Dermoscopy, Confocal Microscopy and other Non-invasive Tools for the Diagnosis of Non-Melanoma Skin Cancers and Other Skin Conditions

Malvehy

Pellacani²

2017

Acta Derm Venerol

View full text Add to dashboard Cite

Non-melanoma skin cancer (NMSC), including basal cell and squamous cell carcinomas, is the most common form of neoplasm. The incidence of NMSC is increasing worldwide. The cure rate is high with early detection and appropriate treatment. Visual examination is the first screening tool used by clinicians, but it is sometimes not sufficient to discriminate benign from malignant lesions. Skin biopsy with histopathology is the gold standard for differential diagnosis; however, this procedure is invasive and occasionally painful. Repeated tissue sampling is not possible in patients with several suspicious lesions and various clinical presentations that are challenging to identify. There are several medical imaging tools for non-invasive in-depth skin examination that can be used to guide clinical diagnosis: dermoscopy, confocal microscopy, cross-polarized light and fluorescence photography, optical coherence tomography and high-frequency ultrasound. These tools are discussed along with their clinical applications. These techniques provide valuable morphological information for better identification, confident diagnosis and treatment monitoring of NMSC.

show abstract

“…Non-invasive in vivo imaging has been an integral part of the armamentarium in dermatology for decades [1,2]. In addition to traditional dermoscopy and ultrasound (US), optical imaging methods such as Raman spectroscopy, confocal microscopy, and optical coherence tomography have demonstrated utility in the diagnosis of skin diseases [3][4][5]. Photoacoustic imaging (PAI) or optoacoustic imaging is a relatively new imaging method that provides excellent optical contrast with the spatial resolution of US [6,7].…”

Section: Introductionmentioning

confidence: 99%

Photoacoustic Imaging of Tattoo Inks: Phantom and Clinical Evaluation

et al. 2020

View full text Add to dashboard Cite

Photoacoustic imaging (PAI) is a novel hybrid imaging modality that provides excellent optical contrast with the spatial resolution of ultrasound in vivo. The method is widely being investigated in the clinical setting for diagnostic applications in dermatology. In this report, we illustrate the utility of PAI as a non-invasive tool for imaging tattoos. Ten different samples of commercially available tattoo inks were examined for their optoacoustic properties in vitro. In vivo PAI of an intradermal tattoo on the wrist was performed in a healthy human volunteer. Black/gray, green, violet, and blue colored pigments provided higher levels of PA signal compared to white, orange, red, and yellow pigments in vitro. PAI provided excellent contrast and enabled accurate delineation of the extent of the tattoo in the dermis. Our results reveal the photoacoustic properties of tattoo inks and demonstrate the potential clinical utility of PAI for intradermal imaging of tattoos. PAI may be useful as a clinical adjunct for objective preoperative evaluation of tattoos and potentially to guide/monitor laser-based tattoo removal procedures.

show abstract

Innovations and Developments in Dermatologic Non-invasive Optical Imaging and Potential Clinical Applications

Cited by 30 publications

References 31 publications

Acral melanoma detection using a convolutional neural network for dermoscopy images

Acral melanoma detection using a convolutional neural network for dermoscopy images

Dermoscopy, Confocal Microscopy and other Non-invasive Tools for the Diagnosis of Non-Melanoma Skin Cancers and Other Skin Conditions

Photoacoustic Imaging of Tattoo Inks: Phantom and Clinical Evaluation

Contact Info

Product

Resources

About