High-frequency ultrasound in clinical dermatology: a review

Levy, J. M.; Barrett, Devon; Harris, Nile; Jeong, Jiwoong; Yang, Xiaofeng; Chen, Shuo

doi:10.1186/s13089-021-00222-w

Cited by 71 publications

(111 citation statements)

References 95 publications

(161 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Being non-invasive, convenient and safe, it is widely used in multiple organ examinations, prenatal screening, or guided biopsies. Its fast development, resulting in high-frequency ultrasound (HFUS, between 20 and 30 MHz) and ultra high-frequency ultrasound (UHFUS, >30 MHz), has opened up new opportunities for medical applications [ 2 ]. It is gaining popularity in dermatology, dermatological oncology, ophthalmology, cosmetology, and aesthetic medicine.…”

Section: Introductionmentioning

confidence: 99%

“…US at frequencies below 100 MHz is now commonly used in medical practice [ 3 ], and the >100 MHz probes are constantly being designed [ 4 ]. Improving spatial resolution of acquired images, the higher frequency of the US probe enables clear visualization of superficial structures such as the fat layer, the muscle layer, blood vessels, hair follicles, and skin appendages [ 2 , 5 , 6 , 7 ]. HFUS is used for healthy skin analysis, where skin thickness is inversely proportional to age, and due to increased collagen production connected with aging, echogenicity tends to increase too [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

“…Improving spatial resolution of acquired images, the higher frequency of the US probe enables clear visualization of superficial structures such as the fat layer, the muscle layer, blood vessels, hair follicles, and skin appendages [ 2 , 5 , 6 , 7 ]. HFUS is used for healthy skin analysis, where skin thickness is inversely proportional to age, and due to increased collagen production connected with aging, echogenicity tends to increase too [ 2 ]. It can be used to estimate the hair follicle growth phase, identify their inflammation and early signs of adnexal pathologies [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

“…HFUS is used for healthy skin analysis, where skin thickness is inversely proportional to age, and due to increased collagen production connected with aging, echogenicity tends to increase too [ 2 ]. It can be used to estimate the hair follicle growth phase, identify their inflammation and early signs of adnexal pathologies [ 2 ]. HFUS is a reliable method with outstanding intrahand interreproducibility for measuring melanoma depth in vivo and may enable single-step surgical excision [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

“…HFUS is a reliable method with outstanding intrahand interreproducibility for measuring melanoma depth in vivo and may enable single-step surgical excision [ 8 ]. The use of ultrasound helps in therapeutic decisions and surgical planning for non-melanoma and melanoma skin cancers and detecting early neoplasms [ 2 ]. Kleinerman et al [ 9 ] demonstrate its potential for differentiation between melanoma, benign nevi, and seborrheic keratoses, along with the monitoring of inflammatory conditions and photo damage.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning-Based High-Frequency Ultrasound Skin Image Classification with Multicriteria Model Evaluation

Czajkowska

Badura

Korzekwa

et al. 2021

Sensors

View full text Add to dashboard Cite

This study presents the first application of convolutional neural networks to high-frequency ultrasound skin image classification. This type of imaging opens up new opportunities in dermatology, showing inflammatory diseases such as atopic dermatitis, psoriasis, or skin lesions. We collected a database of 631 images with healthy skin and different skin pathologies to train and assess all stages of the methodology. The proposed framework starts with the segmentation of the epidermal layer using a DeepLab v3+ model with a pre-trained Xception backbone. We employ transfer learning to train the segmentation model for two purposes: to extract the region of interest for classification and to prepare the skin layer map for classification confidence estimation. For classification, we train five models in different input data modes and data augmentation setups. We also introduce a classification confidence level to evaluate the deep model’s reliability. The measure combines our skin layer map with the heatmap produced by the Grad-CAM technique designed to indicate image regions used by the deep model to make a classification decision. Moreover, we propose a multicriteria model evaluation measure to select the optimal model in terms of classification accuracy, confidence, and test dataset size. The experiments described in the paper show that the DenseNet-201 model fed with the extracted region of interest produces the most reliable and accurate results.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning-Based High-Frequency Ultrasound Skin Image Classification with Multicriteria Model Evaluation

Czajkowska

Badura

Korzekwa

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

Superb microvascular imaging: Steering the wheel toward a better sonographic depiction of dermal vascularization—A work in progress

Torres

D'Ippólito

2022

J of Clinical Ultrasound

View full text Add to dashboard Cite

Static and dynamic high‐resolution ultrasound analysis of tissue distribution of poly‐L‐lactic acid particles during subdermal application in two different presentations

Cunha

Sigrist

2022

Skin Health and Disease

View full text Add to dashboard Cite

Background All the changes the skin goes through, peaking at flaccidity, occur in the dermis and hypodermis, leading to loss of support and a lower capacity to totally accommodate displacements or any loss of subjacent volume, bringing about the onset of furrows and sagging. Improvements in facial sagging may be obtained with the administrations of substances like poly‐L‐lactic acid (PLLA), which triggers a tissue response through a controlled inflammatory reaction. Objectives Compare the tissue distribution of the particles of PLLA of both products available in Brazil (Sculptra® and Rennova Elleva®) during and immediately after their subdermal administrations, with 22G cannulas, through high‐resolution ultrasound imaging. Methods A total of four patients aged between 18 and 64 years had the inner part of the upper arms divided into eight quadrants and treated with 16 ml of each product, reconstituted to correspond to 9.5 mg/ml. The sites where PLLA was injected were analyzed through the high‐resolution ultrasound during (dynamic imaging) and immediately after the procedures (static imaging). Results During Sculptra® injection, high‐resolution ultrasound revealed that its distribution did not follow the trajectory of the cannula homogeneously. It was characterized by a more hyperechogenic central portion and an anechogenic peripheral portion, forming discrete posterior acoustic shadowing at times. Regarding Rennova ELLEVA® injection, the high‐resolution ultrasound analysis showed a homogeneous distribution of the product across the subcutaneous tissue following the trajectory of the cannula without formation of significant interface with the surrounding tissue, maintaining the sonographic aspect of thinly granulated hyperechogenic deposits, with strong posterior acoustic shadowing during and immediately after its administration. Conclusion Static and dynamic high‐resolution ultrasound imaging show a more homogenous distribution of PLLA particles with the use of Rennova ELLEVA® when compared with Sculptra®, which may induce the formation of capsules and a subsequent more dispersed fibroplasia, with larger area of action and a possible better therapeutic result. The interest of this article lies in its originality, highlighting the differences in the tissue distribution of two different brands of PLLA particles, which can impact the clinical response to the two products ‐ which we are researching and seems to interfere with the increase in dermal thickness.

show abstract

High-frequency ultrasound in clinical dermatology: a review

Cited by 71 publications

References 95 publications

Deep Learning-Based High-Frequency Ultrasound Skin Image Classification with Multicriteria Model Evaluation

Deep Learning-Based High-Frequency Ultrasound Skin Image Classification with Multicriteria Model Evaluation

Superb microvascular imaging: Steering the wheel toward a better sonographic depiction of dermal vascularization—A work in progress

Static and dynamic high‐resolution ultrasound analysis of tissue distribution of poly‐L‐lactic acid particles during subdermal application in two different presentations

Contact Info

Product

Resources

About