RESUMEN

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.

Asunto(s)

RESUMEN

This study examined the thermal signature of pigmented lesions observed by digital infrared thermal imaging as a possible adjunct to physician diagnosis. Thermal images of pigmented lesions were compared to clinical examination by a plastic surgeon interested in skin diseases, dermatoscopy, and histopathology. A total of 35 patients with 55 pigmented skin lesions were considered. We found that all lesions emitting a dark signal on thermal imaging, compared to the nearby skin, were benign, while only one of all benign lesions (1.9%) had a bright "warm" signal. Benign lesions with papule/nodular morphology were dark in 87.5% of patients. All lesions diagnosed as malignant melanoma, both dermatoscopically and histologically, had plaque morphology; yet, only half demonstrated some signals on thermal imaging. Based on these results, we concluded that thermal imaging could be used as an adjunct to diagnosis when examining skin lesions. This study provided an introduction to using thermal imaging for spotting skin lesions.

Asunto(s)

RESUMEN

BACKGROUND: Cutaneous neurofibromas (cNFs) are a major cause of disfigurement in patients with Neurofibromatosis Type 1 (NF1). However, clinical trials investigating cNF treatments lack standardised outcome measures to objectively evaluate changes in cNF size and appearance. 3D imaging has been proposed as an objective standardised outcome measure however various systems exist with different features that affect useability in clinical settings. The aim of this study was to compare the accuracy, precision, feasibility, reliability and accessibility of three imaging systems. MATERIALS AND METHODS: We compared the Vectra-H1, LifeViz-Micro and Cherry-Imaging systems. A total of 58 cNFs from 13 participants with NF1 were selected for imaging and analysis. The primary endpoint was accuracy as measured by comparison of measurements between imaging systems. Secondary endpoints included reliability between two operators, precision as measured with the average coefficient of variation, feasibility as determined by time to capture and analyse an image and accessibility as determined by cost. RESULTS: There was no significant difference in accuracy between the three devices for length or surface area measurements (p > 0.05), and reliability and precision were similar. Volume measurements demonstrated the most variability compared to other measurements; LifeViz-Micro demonstrated the least measurement variability for surface area and image capture and analysis were fastest with LifeViz-Micro. LifeViz-Micro was better for imaging smaller number of cNFs (1-3), Vectra-H1 better for larger areas and Cherry for uneven surfaces. CONCLUSIONS: All systems demonstrated excellent reliability but possess distinct advantages and limitations. Surface area is the most consistent and reliable parameter for measuring cNF size in clinical trials.

Asunto(s)

Asunto(s)

RESUMEN

Automated segmentation algorithms for dermoscopic images serve as effective tools that assist dermatologists in clinical diagnosis. While existing deep learning-based skin lesion segmentation algorithms have achieved certain success, challenges remain in accurately delineating the boundaries of lesion regions in dermoscopic images with irregular shapes, blurry edges, and occlusions by artifacts. To address these issues, a multi-attention codec network with selective and dynamic fusion (MASDF-Net) is proposed for skin lesion segmentation in this study. In this network, we use the pyramid vision transformer as the encoder to model the long-range dependencies between features, and we innovatively designed three modules to further enhance the performance of the network. Specifically, the multi-attention fusion (MAF) module allows for attention to be focused on high-level features from various perspectives, thereby capturing more global contextual information. The selective information gathering (SIG) module improves the existing skip-connection structure by eliminating the redundant information in low-level features. The multi-scale cascade fusion (MSCF) module dynamically fuses features from different levels of the decoder part, further refining the segmentation boundaries. We conducted comprehensive experiments on the ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets. The experimental results demonstrate the superiority of our approach over existing state-of-the-art methods.

Asunto(s)

RESUMEN

Skin surface imaging has been used to examine skin lesions with a microscope for over a century and is commonly known as epiluminescence microscopy, dermatoscopy, or dermoscopy. Skin surface microscopy has been recommended to reduce the necessity of biopsy. This imaging technique could improve the clinical diagnostic performance of pigmented skin lesions. Different imaging techniques are employed in dermatology to find diseases. Segmentation and classification are the two main steps in the examination. The classification performance is influenced by the algorithm employed in the segmentation procedure. The most difficult aspect of segmentation is getting rid of the unwanted artifacts. Many deep-learning models are being created to segment skin lesions. In this paper, an analysis of common artifacts is proposed to investigate the segmentation performance of deep learning models with skin surface microscopic images. The most prevalent artifacts in skin images are hair and dark corners. These artifacts can be observed in the majority of dermoscopy images captured through various imaging techniques. While hair detection and removal methods are common, the introduction of dark corner detection and removal represents a novel approach to skin lesion segmentation. A comprehensive analysis of this segmentation performance is assessed using the surface density of artifacts. Assessment of the PH2, ISIC 2017, and ISIC 2018 datasets demonstrates significant enhancements, as reflected by Dice coefficients rising to 93.49 (86.81), 85.86 (79.91), and 75.38 (51.28) respectively, upon artifact removal. These results underscore the pivotal significance of artifact removal techniques in amplifying the efficacy of deep-learning models for skin lesion segmentation.

Asunto(s)

RESUMEN

This study aims to explore the efficacy of a hybrid deep learning and radiomics approach, supplemented with patient metadata, in the noninvasive dermoscopic imaging-based diagnosis of skin lesions. We analyzed dermoscopic images from the International Skin Imaging Collaboration (ISIC) dataset, spanning 2016-2020, encompassing a variety of skin lesions. Our approach integrates deep learning with a comprehensive radiomics analysis, utilizing a vast array of quantitative image features to precisely quantify skin lesion patterns. The dataset includes cases of three, four, and eight different skin lesion types. Our methodology was benchmarked against seven classification methods from the ISIC 2020 challenge and prior research using a binary decision framework. The proposed hybrid model demonstrated superior performance in distinguishing benign from malignant lesions, achieving area under the receiver operating characteristic curve (AUROC) scores of 99%, 95%, and 96%, and multiclass decoding AUROCs of 98.5%, 94.9%, and 96.4%, with sensitivities of 97.6%, 93.9%, and 96.0% and specificities of 98.4%, 96.7%, and 96.9% in the internal ISIC 2018 challenge, as well as in the external Jinan and Longhua datasets, respectively. Our findings suggest that the integration of radiomics and deep learning, utilizing dermoscopic images, effectively captures the heterogeneity and pattern expression of skin lesions.

Asunto(s)

RESUMEN

BACKGROUND: Melanoma is a serious risk to human health and early identification is vital for treatment success. Deep learning (DL) has the potential to detect cancer using imaging technologies and many studies provide evidence that DL algorithms can achieve high accuracy in melanoma diagnostics. OBJECTIVES: To critically assess different DL performances in diagnosing melanoma using dermatoscopic images and discuss the relationship between dermatologists and DL. METHODS: Ovid-Medline, Embase, IEEE Xplore, and the Cochrane Library were systematically searched from inception until 7th December 2021. Studies that reported diagnostic DL model performances in detecting melanoma using dermatoscopic images were included if they had specific outcomes and histopathologic confirmation. Binary diagnostic accuracy data and contingency tables were extracted to analyze outcomes of interest, which included sensitivity (SEN), specificity (SPE), and area under the curve (AUC). Subgroup analyses were performed according to human-machine comparison and cooperation. The study was registered in PROSPERO, CRD42022367824. RESULTS: 2309 records were initially retrieved, of which 37 studies met our inclusion criteria, and 27 provided sufficient data for meta-analytical synthesis. The pooled SEN was 82 % (range 77-86), SPE was 87 % (range 84-90), with an AUC of 0.92 (range 0.89-0.94). Human-machine comparison had pooled AUCs of 0.87 (0.84-0.90) and 0.83 (0.79-0.86) for DL and dermatologists, respectively. Pooled AUCs were 0.90 (0.87-0.93), 0.80 (0.76-0.83), and 0.88 (0.85-0.91) for DL, and junior and senior dermatologists, respectively. Analyses of human-machine cooperation were 0.88 (0.85-0.91) for DL, 0.76 (0.72-0.79) for unassisted, and 0.87 (0.84-0.90) for DL-assisted dermatologists. CONCLUSIONS: Evidence suggests that DL algorithms are as accurate as senior dermatologists in melanoma diagnostics. Therefore, DL could be used to support dermatologists in diagnostic decision-making. Although, further high-quality, large-scale multicenter studies are required to address the specific challenges associated with medical AI-based diagnostics.

Asunto(s)

RESUMEN

Acne scarring is a common sequela of acne vulgaris, which seriously affects facial esthetics. The treatment options for acne scars vary depending on the development stage, color, type, and location of scarring. The objective and precise assessment of acne scars is a prerequisite for treatment, and it is also an important means of monitoring the treatment effect. The traditional methods to evaluate the types and severity grade of acne scars are primarily based on subjective assessment by physicians, which lacks objectivity and accuracy. Novel noninvasive skin imaging techniques, such as skin surface imaging analysis systems, dermoscopy, reflectance confocal microscopy (RCM), high-frequency ultrasound (HFUS), optical coherence tomography (OCT), and multiphoton tomography (MPT), provide new tools for the rapid and objective assessment of acne scars. This article reviews the progress of skin imaging techniques in the diagnosis, classification, and efficacy evaluation of acne scars.

Asunto(s)

RESUMEN

BACKGROUND: In recent years, the increasing prevalence of skin cancers, particularly malignant melanoma, has become a major concern for public health. The development of accurate automated segmentation techniques for skin lesions holds immense potential in alleviating the burden on medical professionals. It is of substantial clinical importance for the early identification and intervention of skin cancer. Nevertheless, the irregular shape, uneven color, and noise interference of the skin lesions have presented significant challenges to the precise segmentation. Therefore, it is crucial to develop a high-precision and intelligent skin lesion segmentation framework for clinical treatment. METHODS: A precision-driven segmentation model for skin cancer images is proposed based on the Transformer U-Net, called BiADATU-Net, which integrates the deformable attention Transformer and bidirectional attention blocks into the U-Net. The encoder part utilizes deformable attention Transformer with dual attention block, allowing adaptive learning of global and local features. The decoder part incorporates specifically tailored scSE attention modules within skip connection layers to capture image-specific context information for strong feature fusion. Additionally, deformable convolution is aggregated into two different attention blocks to learn irregular lesion features for high-precision prediction. RESULTS: A series of experiments are conducted on four skin cancer image datasets (i.e., ISIC2016, ISIC2017, ISIC2018, and PH2). The findings show that our model exhibits satisfactory segmentation performance, all achieving an accuracy rate of over 96%. CONCLUSION: Our experiment results validate the proposed BiADATU-Net achieves competitive performance supremacy compared to some state-of-the-art methods. It is potential and valuable in the field of skin lesion segmentation.

Asunto(s)

RESUMEN

Background and Objectives: Amelanotic/hypomelanotic melanomas (AHMs) account for 2-8% of all cutaneous melanomas. Due to their clinical appearance and the lack of specific dermoscopic indicators, AHMs are challenging to diagnose, particularly in thinner cutaneous lesions. The aim of our study was to evaluate the clinicopathological and dermoscopic features of thin AHMs. Identifying the baseline clinical-pathological features and dermoscopic aspects of thin AHMs is crucial to better understand this entity. Materials and Methods: We divided the AHM cohort into two groups based on Breslow thickness: thin (≤1.00 mm) and thick (>1.00 mm). This stratification helped identify any significant clinicopathological differences between the groups. For dermoscopic analysis, we employed the "pattern analysis" approach, which involves a simultaneous and subjective assessment of different criteria. Results: Out of the 2.800 melanomas analyzed for Breslow thickness, 153 were identified as AHMs. Among these, 65 patients presented with thin AHMs and 88 with thick AHMs. Red hair color and phototype II were more prevalent in patients with thin AHMs. The trunk was the most common anatomic site for thin AHMs. Patients with thin AHMs showed a higher number of multiple melanomas. Dermoscopic analysis revealed no significant difference between thin AHMs and thick AHMs, except for a more frequent occurrence of residual reticulum in thin AHMs. Conclusions: Thin AHMs typically affect individuals with lower phototypes and red hair color. These aspects can be related to the higher presence of pheomelanin, which provides limited protection against sun damage. This also correlates with the fact that the trunk, a site commonly exposed to intermittent sun exposure, is the primary anatomical location for thin AHMs. Multiple primary melanomas are more common in patients with thin AHMs, likely due to an intrinsic predisposition as well as greater periodic dermatologic follow-ups in this class of patients. Apart from the presence of residual reticulum, no other significant dermoscopic differences were observed, complicating the differential diagnosis between thin and thick AHMs based on dermoscopy alone.

Asunto(s)

RESUMEN

BACKGROUND: The market requires ever-faster techniques, in particular for pre-rejuvenation condition. AIM: The purpose of this study was to assess if a fractional CO2 scanner modality (called moveo) results in a faster full-face rejuvenation treatment in comparison to the standard mode, currently existing in the scanner system. MATERIALS AND METHODS: A total of 12 female patients affected by fine lines participated in a split-face clinical investigation and underwent to two sessions with a fractional CO2 laser system equipped with an existing and a faster dedicated scanner units. Pain was assessed using VAS. Three-dimensional clinical photographs were captured before, immediately after, 3 days, 14 days after the first treatment and immediately after the second treatment and 1 months after the last one. The uniformity and aesthetic coverage of treatments were assessed using dermatoscopy. Global aesthetic improvement scale (GAIS) was used. The time taken to treat the two sides of the face and all possible side effects were monitored. RESULTS: Following only two treatment session with both scanner modes, the patient's skin texture improved significantly, with fine lines reduction. There is no statistically significant difference in perceived pain between patients. The GAIS score showed satisfactory results following both modalities. The time parameters indicated that with the faster scanner mode the full-face treatment time was reduced by 30% compared to the standard one. No adverse effects were observed. CONCLUSIONS: The moveo modality provide faster treatment and a better final dermal aesthetic outcome than the standard procedure while maintaining the same safety profile.

Asunto(s)

Asunto(s)

RESUMEN

Skin cancer stands as one of the foremost challenges in oncology, with its early detection being crucial for successful treatment outcomes. Traditional diagnostic methods depend on dermatologist expertise, creating a need for more reliable, automated tools. This study explores deep learning, particularly Convolutional Neural Networks (CNNs), to enhance the accuracy and efficiency of skin cancer diagnosis. Leveraging the HAM10000 dataset, a comprehensive collection of dermatoscopic images encompassing a diverse range of skin lesions, this study introduces a sophisticated CNN model tailored for the nuanced task of skin lesion classification. The model's architecture is intricately designed with multiple convolutional, pooling, and dense layers, aimed at capturing the complex visual features of skin lesions. To address the challenge of class imbalance within the dataset, an innovative data augmentation strategy is employed, ensuring a balanced representation of each lesion category during training. Furthermore, this study introduces a CNN model with optimized layer configuration and data augmentation, significantly boosting diagnostic precision in skin cancer detection. The model's learning process is optimized using the Adam optimizer, with parameters fine-tuned over 50 epochs and a batch size of 128 to enhance the model's ability to discern subtle patterns in the image data. A Model Checkpoint callback ensures the preservation of the best model iteration for future use. The proposed model demonstrates an accuracy of 97.78% with a notable precision of 97.9%, recall of 97.9%, and an F2 score of 97.8%, underscoring its potential as a robust tool in the early detection and classification of skin cancer, thereby supporting clinical decision-making and contributing to improved patient outcomes in dermatology.

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

BACKGROUND: Basosquamous carcinoma (BSC) is a rare and aggressive nonmelanoma skin cancer (NMSC) that exhibits features of both BCC and squamous cell carcinoma (SCC). The gold standard for diagnosis is histopathological examination. BSC is often challenging to diagnose and manage due to its mixed histological features and potential for aggressive behavior AIM: To identify specific features aiding clinicians in differentiating BSCs using non-invasive diagnostic techniques. METHODS: We conducted a retrospective descriptive, monocentric study of the epidemiological clinical, dermoscopic, and reflectance confocal microscopy (RCM) features of histopathologically proven BSCs diagnosed between 2010 and 2023. A total of 192 cases were selected. RESULTS: The study population consisted of 17 men (60.9%). Total 95.8% of patients at the time of diagnosis were ≥50 years. BSC occurred in the head and neck area in 124 cases (63.1%) of which 65 (33.9%) were in the H-zone. For 47.4% of patients, BSC presented as a macule with undefined clinical margins (43.3%). Dermoscopic images were available for 98 cases: the most common parameter was the presence of whitish structureless areas (59 [60.2%]), keratin masses (58 [59.2%]), superficial scales, and ulceration or blood crusts (49 [50%] both). Vessels pattern analysis revealed hairpin vessels (exclusively) and linear irregular vessels as the most frequent (55 [56.1%] both). RCM examination was performed in 21 cases which revealed specific SCC features such as solar elastosis (19 [90.5%]), atypical honeycomb pattern (17 [89%]), proliferation of atypical keratinocytes (16 [80%]) combined with BCC' ones as bright tumor islands (12 [57.8%]), and cleft-like dark spaces (11 [53.4%]). DISCUSSION: Our study reflects the largest cohort of BSCs from a single institution. We described an incidence rate of 4.7%, higher than reported in the Literature, with the involvement of patients ≥50years in almost 96% of cases and an overall male predominance. At clinical examination, BSC was described as a hyperkeratotic macule with undefined clinical margins with one or more dermoscopic SCC' features, whereas the presence of typical BCC aspects was observed in less than 10% of cases, differently from what was previously reported. At RCM analysis, BSCs presented with an atypical honeycomb pattern with proliferation of atypical keratinocytes, hyperkeratosis, and in nearly 55% of patients, bright tumor islands with cleft-like dark spaces. CONCLUSION: The distinctive dermoscopic patterns, along with the RCM features aid in the differentiation of BSCs from other NMSCs.

Asunto(s)

RESUMEN

Actinic keratosis (AK) classification relies on clinical characteristics limited to the skin's surface. Incorporating sub-surface evaluation may improve the link between clinical classification and the underlying pathology. We aimed to apply dynamic optical coherence tomography (D-OCT) to characterize microvessels in AK I-III and photodamaged (PD) skin, thereby exploring its utility in enhancing clinical and dermatoscopic AK evaluation. This explorative study assessed AK I-III and PD on face or scalp. AK were graded according to the Olsen scheme before assessment with dermatoscopy and D-OCT. On D-OCT, vessel shapes, -pattern and -direction were qualitatively evaluated at predefined depths, while density and diameter were quantified. D-OCT's ability to differentiate between AK grades was compared with dermatoscopy. Forty-seven patients with AK I-III (n = 207) and PD (n = 87) were included. Qualitative D-OCT evaluation revealed vascular differences between AK grades and PD, particularly at a depth of 300 µm. The arrangement of vessel shapes around follicles differentiated AK II from PD (OR = 4.75, p < 0.001). Vessel patterns varied among AK grades and PD, showing structured patterns in AK I and PD, non-specific in AK II (OR = 2.16,p = 0.03) and mottled in AK III (OR = 29.94, p < 0.001). Vessel direction changed in AK II-III, with central vessel accentuation and radiating vessels appearing most frequently in AK III. Quantified vessel density was higher in AK I-II than PD (p ≤ 0.025), whereas diameter remained constant. D-OCT combined with dermatoscopy enabled precise differentiation of AK III versus AK I (AUC = 0.908) and II (AUC = 0.833). The qualitative and quantitative evaluation of vessels on D-OCT consistently showed increased vascularization and vessel disorganization in AK lesions of higher grades.

Asunto(s)

Asunto(s)

RESUMEN

Automatic skin segmentation is an efficient method for the early diagnosis of skin cancer, which can minimize the missed detection rate and treat early skin cancer in time. However, significant variations in texture, size, shape, the position of lesions, and obscure boundaries in dermoscopy images make it extremely challenging to accurately locate and segment lesions. To address these challenges, we propose a novel framework named TG-Net, which exploits textual diagnostic information to guide the segmentation of dermoscopic images. Specifically, TG-Net adopts a dual-stream encoder-decoder architecture. The dual-stream encoder comprises Res2Net for extracting image features and our proposed text attention (TA) block for extracting textual features. Through hierarchical guidance, textual features are embedded into the process of image feature extraction. Additionally, we devise a multi-level fusion (MLF) module to merge higher-level features and generate a global feature map as guidance for subsequent steps. In the decoding stage of the network, local features and the global feature map are utilized in three multi-scale reverse attention modules (MSRA) to produce the final segmentation results. We conduct extensive experiments on three publicly accessible datasets, namely ISIC 2017, HAM10000, and PH2. Experimental results demonstrate that TG-Net outperforms state-of-the-art methods, validating the reliability of our method. Source code is available at https://github.com/ukeLin/TG-Net.

Asunto(s)