The potential of x-ray virtual histology in the diagnosis of skin tumors.

BACKGROUND: Histopathological analysis represents the gold standard in clinical practice for diagnosing skin neoplasms. While the current diagnostic workflow has specialized in producing robust and accurate results, interpreting tissue architecture and malignant cellular morphology correctly remains one of the greatest challenges for pathologists. This paper aims to explore the prospect of applying x-ray virtual histology to human skin tumor excisions and correlating it with the histological validation. MATERIALS AND METHODS: Seven skin biopsies containing intriguing melanoma types and pigmented skin lesions were scanned using x-ray Computed micro-Tomography (µCT) and then sectioned for conventional histology assessment. RESULTS: The tissue microarchitecture reconstructed by µCT offers detailed insights into diagnosing the malignancy or benignity of the skin lesions. Three-dimensional reconstruction via x-ray virtual histology reveals infiltrative patterns in basal cell carcinoma and evaluated invasiveness in melanoma. The technology enables the identification of pagetoid distributions of neoplastic cells and the assessment of melanoma depth in three dimensions. CONCLUSION: Although the proposed approach is not intended to replace conventional histology, the non-destructive nature of the sample and the clarity provided by virtual inspection demonstrate the promising impact of µCT as a valid support method prior to conventional histological sectioning. Indeed, µCT images can suggest the optimal sectioning position before using a microtome, as is commonly performed in histological practice. Moreover, the three-dimensional nature of the proposed approach paves the way for a more accurate assessment of significant prognostic factors in melanoma, such as Breslow thickness, by considering the whole micro-volume rather than a two-dimensional observation.

Diffuse reflectance spectroscopy and RGB-imaging: a comparative study of non-invasive haemoglobin assessment.

Non-invasive assessment of haemoglobin (Hb) level in blood is a hot spot in the point-of-care biomedical diagnostics. Several optical methods are suggested as a solution, some of them being approved for clinical use. Still, there is no consensus on the accuracy of optical techniques, the quality of Hb assessment on different tissue sites, and on the ability of combined use of several optical techniques to improve the quality of Hb level prediction. In this work we examined the capabilities of two optical techniques-diffuse reflectance spectroscopy and RGB-imaging of the skin and fingernails areas-in detecting low blood Hb level. The test sample consisted of 240 adult volunteers with 70 volunteers exhibiting Hb level lower than 120 g/L. We show that using simple descriptors of the diffuse reflectance spectrum of the forearm skin and fingernails is applicable for predicting low blood Hb concentration (ROC-AUC = 0.84 ± 0.08), while RGB-imaging shows similar performance when applied to the fingernail areas (ROC-AUC = 0.83 ± 0.07), which can be considered perspective for clinical use and screening properties. We also report that while the joint use of predictions from two optical methods slightly improves the accuracy of non-invasive Hb level assessment (ROC-AUC = 0.86 ± 0.07), the effect is not as high as one might expect from combining predictions of truly independent modalities, indicating the limit of the accuracy one can expect with multimodal optical approach. We review this case and propose possible solutions towards more sensitive non-invasive optical determination of hemoglobin.

A Modified Deep Semantic Segmentation Model for Analysis of Whole Slide Skin Images.

Automated segmentation of biomedical image has been recognized as an important step in computer-aided diagnosis systems for detection of abnormalities. Despite its importance, the segmentation process remains an open challenge due to variations in color, texture, shape diversity and boundaries. Semantic segmentation often requires deeper neural networks to achieve higher accuracy, making the segmentation model more complex and slower. Due to the need to process a large number of biomedical images, more efficient and cheaper image processing techniques for accurate segmentation are needed. In this article, we present a modified deep semantic segmentation model that utilizes the backbone of EfficientNet-B3 along with UNet for reliable segmentation. We trained our model on Non-melanoma skin cancer segmentation for histopathology dataset to divide the image in 12 different classes for segmentation. Our method outperforms the existing literature with an increase in average class accuracy from 79 to 83%. Our approach also shows an increase in overall accuracy from 85 to 94%.

Dataset of human skin and fingernails images for non-invasive haemoglobin level assessment.

Anaemia, a decrease in total concentration of haemoglobin (Hb) in blood, affects substantial percentage of the population worldwide. Currently, the gold standard for determining the Hb level is the invasive analysis of venous blood. Yet, more and more research groups demonstrate the possibility of non-invasive Hb assessment using white light imaging of tissue sites where Hb is the main chromophore, in particular, fingernails. Despite the promising declarations, non-invasive Hb assessment via RGB-imaging is still poorly used in practice. The main reason is the difficulty in establishing the true accuracy of the methods presented in different works since they are tested on private datasets collected under different experimental conditions. Here we present an open dataset containing RGB images of skin and fingernails for patients with a known level of Hb, thus providing a single benchmark for researchers and engineers in the field, aimed at fostering translation of non-invasive imaging methods to the bedside.

Clinical Efficacy and Safety of Low-Energy Extracorporeal Shock Wave Therapy for Various Conditions of Deep Dermal and Subdermal Fibrosis.

BACKGROUND: Extracorporeal shock wave therapy (ESWT) enhances extracellular matrix remodeling and tissue regeneration by promoting growth factor release, regulating blood and lymphatic flows, and reducing fat and fibrotic tissues. Focused shock wave therapy (F-SWT), radial shock wave therapy (R-SWT), and combined F-SWT and R-SWT have been used to deliver different patterns of shock energy depending on the characteristics of the target lesions. METHODS: We investigated the efficacy and safety of ESWT in patients with dermal and subdermal fibrosis. Fifty-two patients treated with F-SWT and/or R-SWT for dermal and subdermal fibrosis caused due to various reasons were retrospectively analyzed by reviewing their medical records, clinical images, and ultrasound study images. RESULTS: The mean number of pulses administered for F-SWT on the cheek, temple, and chin were 2600.0 ± 1040.8 shocks/session and for R-SWT were 5080.0 ± 2234.6 pulses/session, and the number of treatment sessions were 8.0 ± 4.4. In patients who were treated with ESWT on the abdomen, the mean number of pulses for F-SWT were 2600.0 ± 2408.3 shocks/session and for R-SWT were 8400.0 ± 894.4 pulses/session, and the number of treatment sessions were 3.2 ± 1.6. Most patients were satisfied with the results. Pain during ESWT was well tolerated and post-ESWT edema was more common in R-SWT than in F-SWT. CONCLUSION: Our data demonstrated that ESWT effectively and safely improved the clinical appearance and functional movement of patients with dermal and subdermal fibrosis caused due to various reasons.

Artificial Intelligence Smartphone Application for Detection of Simulated Skin Changes: An In Vivo Pilot Study.

BACKGROUND: The development of artificial intelligence (AI) is rapidly expanding, showing promise in the dermatological field. Skin checks are a resource-heavy challenge that could potentially benefit from AI-tool assistance, particularly if provided in widely available AI solutions. A novel smartphone application(app)-based AI system, "SCAI," was developed and trained to recognize spots in paired images of skin, pursuing identification of new skin lesions. This pilot study aimed to investigate the feasibility of the SCAI-app to identify simulated skin changes in vivo. MATERIALS AND METHODS: The study was conducted in a controlled setting with healthy volunteers and standardized, simulated skin changes (test spots), consisting of customized 3-mm adhesive spots in three colors (black, brown, and red). Each volunteer had a total of eight test spots adhered to four areas on back and legs. The SCAI-app collected smartphone- and template-guided standardized images before and after test spot application, using its backend AI algorithms to identify changes between the paired images. RESULTS: Twenty-four volunteers were included, amounting to a total of 192 test spots. Overall, the detection algorithms identified test spots with a sensitivity of 92.0% (CI: 88.1-95.9) and a specificity of 95.5% (CI: 95.0-96.0). The SCAI-app's positive predictive value was 38.0% (CI: 31.0-44.9), while the negative predictive value was 99.7% (CI: 99.0-100). CONCLUSION: This pilot study showed that SCAI-app could detect simulated skin changes in a controlled in vivo setting. The app's feasibility in a clinical setting with real-life skin lesions remains to be investigated, where the challenge with false positives in particular needs to be addressed.

Skin Tone Analysis Through Skin Tone Map Generation With Optical Approach and Deep Learning.

BACKGROUND: Skin tone assessment is critical in both cosmetic and medical fields, yet traditional methods like the individual typology angle (ITA) have limitations, such as sensitivity to illuminants and insensitivity to skin redness. METHODS: This study introduces an automated image-based method for skin tone mapping by applying optical approaches and deep learning. The method generates skin tone maps by leveraging the illuminant spectrum, segments the skin region from face images, and identifies the corresponding skin tone on the map. The method was evaluated by generating skin tone maps under three standard illuminants (D45, D65, and D85) and comparing the results with those obtained using ITA on skin tone simulation images. RESULTS: The results showed that skin tone maps generated under the same lighting conditions as the image acquisition (D65) provided the highest accuracy, with a color difference of around 6, which is more than twice as small as those observed under other illuminants. The mapping positions also demonstrated a clear correlation with pigment levels. Compared to ITA, the proposed approach was particularly effective in distinguishing skin tones related to redness. CONCLUSION: Despite the need to measure the illuminant spectrum and for further physiological validation, the proposed approach shows potential for enhancing skin tone assessment. Its ability to mitigate the effects of illuminants and distinguish between the two dominant pigments offers promising applications in both cosmetic and medical diagnostics.

Skin, Soft Tissue, and Musculoskeletal Ultrasound.

Point-of-care ultrasound may be used to assist in the diagnosis of skin, soft tissue, and musculoskeletal concerns in the emergency department. Frequently, linear or curvilinear probes are used to perform these studies and ultrasound may be used to assist in common emergency department procedures related to these conditions.

Dual optical elastography detects TGF - ß -induced alterations in the biomechanical properties of skin scaffolds.

Significance: The skin's mechanical properties are tightly regulated. Various pathologies can affect skin stiffness, and understanding these changes is a focus in tissue engineering. Ex vivo skin scaffolds are a robust platform for evaluating the effects of various genetic and molecular interactions on the skin. Transforming growth factor-beta ( TGF - ß ) is a critical signaling molecule in the skin that can regulate the amount of collagen and elastin in the skin and, consequently, its mechanical properties. Aim: This study investigates the biomechanical properties of bio-engineered skin scaffolds, focusing on the influence of TGF - ß , a signaling molecule with diverse cellular functions. Approach: The TGF - ß receptor I inhibitor, galunisertib, was employed to assess the mechanical changes resulting from dysregulation of TGF - ß . Skin scaffold samples, grouped into three categories (control, TGF - ß -treated, and TGF - ß + galunisertib-treated), were prepared in two distinct culture media-one with aprotinin (AP) and another without. Two optical elastography techniques, namely wave-based optical coherence elastography (OCE) and Brillouin microscopy, were utilized to quantify the biomechanical properties of the tissues. Results: Results showed significantly higher wave speed (with AP, p < 0.001 ; without AP, p < 0.001 ) and Brillouin frequency shift (with AP, p < 0.001 ; without AP, p = 0.01 ) in TGF - ß -treated group compared with the control group. The difference in wave speed between the control and TGF - ß + galunisertib with ( p = 0.10 ) and without AP ( p = 0.36 ) was not significant. Moreover, the TGF - ß + galunisertib-treated group exhibited lower wave speed without and with AP and reduced Brillouin frequency shift than the TGF - ß -treated group without AP, further strengthening the potential role of TGF - ß in regulating the mechanical properties of the samples. Conclusions: These findings offer valuable insights into TGF - ß -induced biomechanical alterations in bio-engineered skin scaffolds, highlighting the potential of OCE and Brillouin microscopy in the development of targeted therapies in conditions involving abnormal tissue remodeling and fibrosis.

Electrical Impedance Tomography-Based Electronic Skin for Multi-Touch Tactile Sensing Using Hydrogel Material and FISTA Algorithm.

Flexible electronic skin (e-skin) can enable robots to have sensory forms similar to human skin, enhancing their ability to obtain more information from touch. The non-invasive nature of electrical impedance tomography (EIT) technology allows electrodes to be arranged only at the edges of the skin, ensuring the stretchability and elasticity of the skin's interior. However, the image quality reconstructed by EIT technology has deteriorated in multi-touch identification, where it is challenging to clearly reflect the number of touchpoints and accurately size the touch areas. This paper proposed an EIT-based flexible tactile sensor that employs self-made hydrogel material as the primary sensing medium. The sensor's structure, fabrication process, and tactile imaging principle were elaborated. To improve the quality of image reconstruction, the fast iterative shrinkage-thresholding algorithm (FISTA) was embedded into the EIDORS toolkit. The performances of the e-skin in aspects of assessing the touching area, quantitative force sensing and multi-touch identification were examined. Results showed that the mean intersection over union (MIoU) of the reconstructed images was improved up to 0.84, and the tactile position can be accurately imaged in the case of the number of the touchpoints up to seven (larger than two to four touchpoints in existing studies), proving that the combination of the proposed sensor and imaging algorithm has high sensitivity and accuracy in multi-touch tactile sensing. The presented e-skin shows potential promise for the application in complex human-robot interaction (HRI) environments, such as prosthetics and wearable devices.

A Preliminary Study Using High-Frequency Ultrasound to Evaluate Vulvar Skin With Lichenoid Vulvar Dermatoses.

BACKGROUND: Lichenoid vulvar dermatoses (LVD) are inflammatory diseases primarily affecting the vulva and anus. This study aims to evaluate the skin changes in patients with LVD using high-frequency ultrasound. METHODS: Forty-five patients with LVD, who attended Henan Provincial People's Hospital from November 2021 to March 2024, were selected. According to the pathological conclusions, patients were divided into two groups: the vulvar lichen sclerosus (VLS) group (n = 24) and the vulvar lichen simplex chronicus (VLSC) group (n = 21). Thirty age- and BMI-matched healthy women were selected as the control group. We assessed the epidermal thickness, subepidermal low echogenic band (SLEB) thickness, dermal thickness, and vascular index (VI) among the three groups. Receiver operating characteristic curve (ROC) analysis was performed to determine the diagnostic efficacy of these ultrasound parameters for LVD. Binary logistic regression was used to investigate risk factors influencing LVD pathology in VLS patients. RESULTS: Epidermal thickness, SLEB thickness, dermal thickness, and VI were increased in the VLS and VLSC groups compared to the control group (p < 0.05). There were no statistically significant differences in ultrasound parameters between the VLS and VLSC groups (p > 0.05). The ROC curves showed that the area under the curve (AUC) value for the dermis (AUC = 0.882) was the largest for VLS, and VI (AUC = 0.917), it was the largest for VLSC. Binary logistic regression indicated that having an allergic disease was a risk factor for VLS between VLS and VLSC groups (OR = 6.797, p = 0.028). CONCLUSION: High-frequency ultrasound can detect thickening of the skin and increasing VI in patients with LVD, which can be helpful in the evaluation and management of LVD.

A novel Skin lesion prediction and classification technique: ViT-GradCAM.

BACKGROUND: Skin cancer is one of the highly occurring diseases in human life. Early detection and treatment are the prime and necessary points to reduce the malignancy of infections. Deep learning techniques are supplementary tools to assist clinical experts in detecting and localizing skin lesions. Vision transformers (ViT) based on image segmentation classification using multiple classes provide fairly accurate detection and are gaining more popularity due to legitimate multiclass prediction capabilities. MATERIALS AND METHODS: In this research, we propose a new ViT Gradient-Weighted Class Activation Mapping (GradCAM) based architecture named ViT-GradCAM for detecting and classifying skin lesions by spreading ratio on the lesion's surface area. The proposed system is trained and validated using a HAM 10000 dataset by studying seven skin lesions. The database comprises 10 015 dermatoscopic images of varied sizes. The data preprocessing and data augmentation techniques are applied to overcome the class imbalance issues and improve the model's performance. RESULT: The proposed algorithm is based on ViT models that classify the dermatoscopic images into seven classes with an accuracy of 97.28%, precision of 98.51, recall of 95.2%, and an F1 score of 94.6, respectively. The proposed ViT-GradCAM obtains better and more accurate detection and classification than other state-of-the-art deep learning-based skin lesion detection models. The architecture of ViT-GradCAM is extensively visualized to highlight the actual pixels in essential regions associated with skin-specific pathologies. CONCLUSION: This research proposes an alternate solution to overcome the challenges of detecting and classifying skin lesions using ViTs and GradCAM, which play a significant role in detecting and classifying skin lesions accurately rather than relying solely on deep learning models.

Use of Optical Coherence Tomography to Assess Properties of Cutaneous Defects Following Radiofrequency Microneedling and Laser Treatment.

OBJECTIVES: To characterize the properties of cutaneous defects created by energy-based devices using optical coherence tomography. MATERIALS AND METHODS: Radiofrequency (RF) microneedling and non-ablative fractional laser (NAFL) treatment were performed in vivo with various parameters. Following treatment, optical coherence tomography (OCT) was used to image and measure cutaneous defects at multiple time points over a 24 h period. RESULTS: Channel-like cutaneous defects were visible with OCT following bipolar RF microneedling and NAFL treatment. Using a double pulse technique with RF microneedling yielded a greater number of defects visible with OCT, as well as defects that were deeper and more durable over time. Following treatment with 1927 nm thulium fiber laser, the average diameter of the defects was greater when the energy level was 20 mJ as compared to 10 mJ (0.33 mm vs. 0.27 mm, p < 0.01). CONCLUSIONS: Cutaneous defects were observed following both RF microneedling and NAFL treatment. Properties of the cutaneous defects varied based on device, treatment setting, and technique, which may be useful in guiding further study of device-assisted drug delivery.

Advanced US of the Skin, Nerves, and Muscles of the Neck: Pearls and Pitfalls with Use of High-Frequency Transducers.

High-frequency US provides excellent visualization of superficial structures and lesions, is a preferred diagnostic modality for anatomic characterization of neck abnormalities, and has a central role in clinical decision making. Recent technological advancements have led to the development of transducers that surpass 20 MHz, elevating high-frequency US to a highly valuable diagnostic tool with broader clinical use and enabling greater spatial resolution in the assessment of skin and superficial nerves and muscles. The authors focus on evolving applications of high-frequency US in neck imaging, emphasizing practical insights and strategies in skin and neuromuscular applications. ©RSNA, 2024 Supplemental material and the slide presentation from the RSNA Annual Meeting are available for this article.

Biodistribution of iron oxide tattoo pigment: An experimental murine study.

Tattoo pigment is expected to migrate beyond the skin to regional lymph nodes and the liver. Modern tattoo ink commonly contains metals that may pose a clinical problem during MRI examinations. This study aimed to investigate the biodistribution of iron oxide pigment to internal organs in mice. Moreover, when exposed to a static magnetic field, we studied whether any reactions followed in the tattooed skin. Twenty-seven hairless C3.Cg-Hrhr/TifBomTac mice were included; 20 were tattooed with iron oxide ink in a rectangular 3 cm2 pattern; seven were controls. Ten of the tattooed mice were exposed to a 3 T MRI scanner's static magnetic field. Following euthanasia, evaluations of dissected organs involved MRI T2*-mapping, light microscopy (LM) and metal analysis. T2*-mapping measures the relaxation times of hydrogen nuclei in water and fat, which may be affected by neighbouring ferrimagnetic particles, thus enabling the detection of iron oxide particles in organs. Elemental analysis detected a significant level of metals in the tattooed skin compared to controls, but no skin reactions occurred when exposed to a 3 T static magnetic field. No disparity was observed in the liver samples with metal analysis. T2* mapping found no significant difference between the two groups. Only minute clusters of pigment particles were observed in the liver by LM. Our results demonstrate a minimal systemic distribution of the iron oxide pigments to the liver, whereas the kidney and brain were unaffected. The static magnetic field did not trigger skin reactions in magnetic tattoos but may induce image artefacts during MRI.

Training artificial neural networks using self-organizing migrating algorithm for skin segmentation.

This study presents an application of the self-organizing migrating algorithm (SOMA) to train artificial neural networks for skin segmentation tasks. We compare the performance of SOMA with popular gradient-based optimization methods such as ADAM and SGDM, as well as with another evolutionary algorithm, differential evolution (DE). Experiments are conducted on the skin dataset, which consists of 245,057 samples with skin and non-skin labels. The results show that the neural network trained by SOMA achieves the highest accuracy (93.18%), outperforming ADAM (84.87%), SGDM (84.79%), and DE (91.32%). The visual evaluation also reveals the SOMA-trained neural network's accurate and reliable segmentation capabilities in most cases. These findings highlight the potential of incorporating evolutionary optimization algorithms like SOMA into the training process of artificial neural networks, significantly improving performance in image segmentation tasks.

Mechanism of Zuogui pill enhancing ovarian function and skin elastic repair in premature aging rats based on artificial intelligence medical image analysis.

BACKGROUND: AI medical image analysis shows potential applications in research on premature aging and skin. The purpose of this study was to explore the mechanism of the Zuogui pill based on artificial intelligence medical image analysis on ovarian function enhancement and skin elasticity repair in rats with premature aging. MATERIALS AND METHODS: The premature aging rat model was established by using an experimental animal model. Then Zuogui pills were injected into the rats with premature aging, and the images were detected by an optical microscope. Then, through the analysis of artificial intelligence medical images, the image data is analyzed to evaluate the indicators of ovarian function. RESULTS: Through optical microscope image detection, we observed that the Zuogui pill played an active role in repairing ovarian tissue structure and increasing the number of follicles in mice, and Zuogui pill also significantly increased the level of progesterone in the blood of mice. CONCLUSION: Most of the ZGP-induced outcomes are significantly dose-dependent.

Association between skin autofluorescence and coronary calcification in the general population.

OBJECTIVE: To address the relationship between tissue accumulation of advanced glycation end-products, assessed by skin autofluorescence (SAF), and subclinical atherosclerosis quantified with coronary artery calcium score (CACS) in the general Dutch population. METHODS: A total of 3,839 participants of the LifeLines Cohort Study without diabetes or cardiovascular disease were included in this cross-sectional evaluation. They underwent SAF measurement and cardiac computed tomography to measure CACS. Associations between SAF and CACS was assessed using regression models. Participants at elevated risk for cardiovascular disease were selected by either CACS≥100, or SAF value in the top 15%; overlap and cardiovascular risk profile of these participants were compared. RESULTS: In univariate analysis, every 1 arbitrary unit (AU) increase in SAF resulted in an odds ratio of 2.91 (95% confidence interval 2.44-3.48, p<0.001) for coronary calcification. After adjustment for cardiovascular risk factors, there was still 20% higher odds of coronary calcification with 1 AU increase in SAF, but significance was lost. In total, 1025 (27%) participants either had high SAF and/or high CACS, of these 441 (12%) had only high SAF, 450 (12%) had only high CACS and 134 (3%) participants had high SAF and high CACS. CONCLUSION: In a population-based Dutch cohort, SAF was associated with the degree of coronary calcification. This association was largely explained by classical cardiovascular risk factors. Limited overlap was found in subgroups with high SAF or high CACS, indicating that SAF and CACS may have complementary role in identifying individuals at elevated cardiovascular risk.