TG-Net: Using text prompts for improved skin lesion segmentation.

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.

[Skin lesion classification with multi-level fusion of Swin-T and ConvNeXt].

Skin cancer is a significant public health issue, and computer-aided diagnosis technology can effectively alleviate this burden. Accurate identification of skin lesion types is crucial when employing computer-aided diagnosis. This study proposes a multi-level attention cascaded fusion model based on Swin-T and ConvNeXt. It employed hierarchical Swin-T and ConvNeXt to extract global and local features, respectively, and introduced residual channel attention and spatial attention modules for further feature extraction. Multi-level attention mechanisms were utilized to process multi-scale global and local features. To address the problem of shallow features being lost due to their distance from the classifier, a hierarchical inverted residual fusion module was proposed to dynamically adjust the extracted feature information. Balanced sampling strategies and focal loss were employed to tackle the issue of imbalanced categories of skin lesions. Experimental testing on the ISIC2018 and ISIC2019 datasets yielded accuracy, precision, recall, and F1-Score of 96.01%, 93.67%, 92.65%, and 93.11%, respectively, and 92.79%, 91.52%, 88.90%, and 90.15%, respectively. Compared to Swin-T, the proposed method achieved an accuracy improvement of 3.60% and 1.66%, and compared to ConvNeXt, it achieved an accuracy improvement of 2.87% and 3.45%. The experiments demonstrate that the proposed method accurately classifies skin lesion images, providing a new solution for skin cancer diagnosis.

The efficacy and safety of autologous epidermal cell suspensions for re-epithelialization of skin lesions: A systematic review and meta-analysis of randomized trials.

BACKGROUND: Successful usage of autologous skin cell suspension (ASCS) has been demonstrated in some clinical trials. However, its efficacy and safety have not been verified. This latest systematic review and meta-analysis aim to examine the effects of autologous epidermal cell suspensions in re-epithelialization of skin lesions. METHODS: Relevant articles were retrieved from PubMed, Embase, Cochrane Database, Web of Science, International Clinical Trials Registry Platform, China National Knowledge Infrastructureris, VIP Database for Chinese Technical Periodicals and Wanfang database. The primary output measure was the healing time, and the secondary outputs were effective rate, size of donor site for treatment, size of study treatment area, operation time, pain scores, repigmentation, complications, scar scale scores and satisfaction scores. Data were pooled and expressed as relative risk (RR), mean difference (MD) and standardized mean difference (SMD) with a 95% confidence interval (CI). RESULTS: Thirty-one studies were included in this systematic review and meta-analysis, with 914 patients who received autologous epidermal cell suspensions (treatment group) and 883 patients who received standard care or placebo (control group). The pooled data from all included studies demonstrated that the treatment group has significantly reduced healing time (SMD = -0.86; 95% CI: -1.59-0.14; p = 0.02, I2 = 95%), size of donar site for treatment (MD = -115.41; 95% CI: -128.74-102.09; p<0.001, I2 = 89%), operation time (MD = 25.35; 95% CI: 23.42-27.29; p<0.001, I2 = 100%), pain scores (SMD = -1.88; 95% CI: -2.86-0.90; p = 0.0002, I2 = 89%) and complications (RR = 0.59; 95% CI: 0.36-0.96; p = 0.03, I2 = 66%), as well as significantly increased effective rate (RR = 1.20; 95% CI: 1.01-1.42; p = 0.04, I2 = 77%). There were no significant differences in the size of study treatment area, repigmentation, scar scale scores and satisfaction scores between the two groups. CONCLUSION: Our meta-analysis showed that autologous epidermal cell suspensions is beneficial for re-epithelialization of skin lesions as they significantly reduce the healing time, size of donar site for treatment, operation time, pain scores and complications, as well as increased effective rate. However, this intervention has minimal impact on size of treatment area, repigmentation, scar scale scores and satisfaction scores.

Formulation and Characterization of Nanoemulsion Incorporating Chamomilla recutita L. Extract Stabilized with Hyaluronic Acid.

Skin lesions are an important health concern, exposing the body to infection risks. Utilizing natural products containing chamomile (Chamomilla recutita L.) holds promise for curative purposes. Additionally, hyaluronic acid (HA), an active ingredient known for its tissue regeneration capacity, can expedite healing. In this study, we prepared and characterized an extract of C. recutita and integrated it into a nanoemulsion system stabilized with HA, aiming at harnessing its healing potential. We assessed the impact of alcoholic strength on flavonoid extraction and chemically characterized the extract using UHPLC/MS while quantifying its antioxidant and antimicrobial capacity. We developed a nanoemulsion loaded with C. recutita extract and evaluated the effect of HA stabilization on pH, droplet size, polydispersity index (PDI), zeta potential, and viscosity. Results indicated that 70% hydroalcoholic extraction yielded a higher flavonoid content. The extract exhibited antioxidant capacity in vitro, a desirable trait for skin regeneration, and demonstrated efficacy against key microbial strains (Staphylococcus aureus, Streptococcus pyogenes, Escherichia coli, and Pseudomonas aeruginosa) associated with skin colonization and infections. Flavonoids spireoside and apiin emerged as the most abundant bioactives. The addition of HA led to increased viscosity while maintaining a suitable pH for topical application. Zeta potential, droplet size, and PDI met acceptable criteria. Moreover, incorporating C. recutita extract into the nanoemulsion enhanced its antimicrobial effect. Hence, the nanoemulsion system loaded with C. recutita and HA stabilization exhibits favorable characteristics for topical application, showing promise in aiding the healing processes.

Dermoscopy Differential Diagnosis Explorer (D3X) Ontology to Aggregate and Link Dermoscopic Patterns to Differential Diagnoses: Development and Usability Study.

BACKGROUND: Dermoscopy is a growing field that uses microscopy to allow dermatologists and primary care physicians to identify skin lesions. For a given skin lesion, a wide variety of differential diagnoses exist, which may be challenging for inexperienced users to name and understand. OBJECTIVE: In this study, we describe the creation of the dermoscopy differential diagnosis explorer (D3X), an ontology linking dermoscopic patterns to differential diagnoses. METHODS: Existing ontologies that were incorporated into D3X include the elements of visuals ontology and dermoscopy elements of visuals ontology, which connect visual features to dermoscopic patterns. A list of differential diagnoses for each pattern was generated from the literature and in consultation with domain experts. Open-source images were incorporated from DermNet, Dermoscopedia, and open-access research papers. RESULTS: D3X was encoded in the OWL 2 web ontology language and includes 3041 logical axioms, 1519 classes, 103 object properties, and 20 data properties. We compared D3X with publicly available ontologies in the dermatology domain using a semiotic theory-driven metric to measure the innate qualities of D3X with others. The results indicate that D3X is adequately comparable with other ontologies of the dermatology domain. CONCLUSIONS: The D3X ontology is a resource that can link and integrate dermoscopic differential diagnoses and supplementary information with existing ontology-based resources. Future directions include developing a web application based on D3X for dermoscopy education and clinical practice.

A novel multi-task learning network for skin lesion classification based on multi-modal clues and label-level fusion.

In this paper, we propose a multi-task learning (MTL) network based on the label-level fusion of metadata and hand-crafted features by unsupervised clustering to generate new clustering labels as an optimization goal. We propose a MTL module (MTLM) that incorporates an attention mechanism to enable the model to learn more integrated, variable information. We propose a dynamic strategy to adjust the loss weights of different tasks, and trade off the contributions of multiple branches. Instead of feature-level fusion, we propose label-level fusion and combine the results of our proposed MTLM with the results of the image classification network to achieve better lesion prediction on multiple dermatological datasets. We verify the effectiveness of the proposed model by quantitative and qualitative measures. The MTL network using multi-modal clues and label-level fusion can yield the significant performance improvement for skin lesion classification.

Cutaneous Cryptococcosis Manifested as a Large Cystic Mass: A Rare Manifestation of Cryptococcus Infection.

Cryptococcus infection is an invasive fungal infection common in immunocompromised hosts, especially in organ transplant recipients and in patients with HIV. Its presentation varies from localized skin lesions to systemic disseminated infection involving the lungs and the central nervous system (CNS). We present the case of a 50-year-old woman with diabetes mellitus type 2 (DM-2), end-stage renal disease (ESRD) status post deceased donor kidney transplantation seven and a half years ago who presented with a low-grade fever, cough, nausea, vomiting, and a large cystic mass on the right foot. A CT scan of the chest showed a 14 mm cavitary lesion in the middle lobe of the right lung. Serum and cerebrospinal fluid cryptococcal antigens were detected. MRI of the right foot showed a large multilocular lobulated septated cystic mass. Histopathology showed cryptococcus; the diagnosis was made as disseminated cryptococcus infection. She was treated with antifungal therapy successfully. A large cutaneous cystic mass is a rare cutaneous presentation of cryptococcus infection; clinicians should keep it in the differential diagnosis, especially in transplant recipient patients.

Enhancing skin lesion segmentation with a fusion of convolutional neural networks and transformer models.

Accurate segmentation is crucial in diagnosing and analyzing skin lesions. However, automatic segmentation of skin lesions is extremely challenging because of their variable sizes, uneven color distributions, irregular shapes, hair occlusions, and blurred boundaries. Owing to the limited range of convolutional networks receptive fields, shallow convolution cannot extract the global features of images and thus has limited segmentation performance. Because medical image datasets are small in scale, the use of excessively deep networks could cause overfitting and increase computational complexity. Although transformer networks can focus on extracting global information, they cannot extract sufficient local information and accurately segment detailed lesion features. In this study, we designed a dual-branch encoder that combines a convolution neural network (CNN) and a transformer. The CNN branch of the encoder comprises four layers, which learn the local features of images through layer-wise downsampling. The transformer branch also comprises four layers, enabling the learning of global image information through attention mechanisms. The feature fusion module in the network integrates local features and global information, emphasizes important channel features through the channel attention mechanism, and filters irrelevant feature expressions. The information exchange between the decoder and encoder is finally achieved through skip connections to supplement the information lost during the sampling process, thereby enhancing segmentation accuracy. The data used in this paper are from four public datasets, including images of melanoma, basal cell tumor, fibroma, and benign nevus. Because of the limited size of the image data, we enhanced them using methods such as random horizontal flipping, random vertical flipping, random brightness enhancement, random contrast enhancement, and rotation. The segmentation accuracy is evaluated through intersection over union and duration, integrity, commitment, and effort indicators, reaching 87.7 % and 93.21 %, 82.05 % and 89.19 %, 86.81 % and 92.72 %, and 92.79 % and 96.21 %, respectively, on the ISIC 2016, ISIC 2017, ISIC 2018, and PH2 datasets, respectively (code: https://github.com/hyjane/CCT-Net).

Multi-scale feature fusion and class weight loss for skin lesion classification.

Skin cancer is one of the common types of cancer. It spreads quickly and is not easy to detect in the early stages, posing a major threat to human health. In recent years, deep learning methods have attracted widespread attention for skin cancer detection in dermoscopic images. However, training a practical classifier becomes highly challenging due to inter-class similarity and intra-class variation in skin lesion images. To address these problems, we propose a multi-scale fusion structure that combines shallow and deep features for more accurate classification. Simultaneously, we implement three approaches to the problem of class imbalance: class weighting, label smoothing, and resampling. In addition, the HAM10000_RE dataset strips out hair features to demonstrate the role of hair features in the classification process. We demonstrate that the region of interest is the most critical classification feature for the HAM10000_SE dataset, which segments lesion regions. We evaluated the effectiveness of our model using the HAM10000 and ISIC2019 dataset. The results showed that this method performed well in dermoscopic classification tasks, with ACC and AUC of 94.0% and 99.3%, on the HAM10000 dataset and ACC of 89.8% for the ISIC2019 dataset. The overall performance of our model is excellent in comparison to state-of-the-art models.

Uncommon Scurvy Manifestation: Solitary Skin Lesion in an Alcoholic Case.

Scurvy, characterized by vitamin C deficiency, typically manifests with various symptoms, most commonly skin lesions. However, the presentation of a solitary skin lesion is considered atypical. An elderly patient with a history of heavy alcohol consumption presented with a small skin lesion that developed rapidly into a solitary open wound without any preceding trauma. Laboratory analysis revealed severe vitamin C deficiency (<5 µmol/L). The patient showed significant improvement following high-dose vitamin C replacement therapy. This case underscores the potential for scurvy to present with a solitary lower body wound devoid of typical symptoms. It highlights the importance of prompt consideration of vitamin C replacement therapy, particularly in high-risk groups such as alcoholics, by healthcare providers.

Improved Treatment Outcome Following the Use of a Wound Dressings in Cutaneous Leishmaniasis Lesions.

Leishmaniasis, caused by Leishmania parasites, is a neglected tropical disease and Cutaneous Leishmaniasis (CL) is the most common form. Despite the associated toxicity and adverse effects, Meglumine antimoniate (MA) remains the first-choice treatment for CL in Brazil, pressing the need for the development of better alternatives. Bacterial NanoCellulose (BNC), a biocompatible nanomaterial, has unique properties regarding wound healing. In a previous study, we showed that use of topical BNC + systemic MA significantly increased the cure rate of CL patients, compared to treatment with MA alone. Herein, we performed a study comparing the combination of a wound dressing (BNC or placebo) plus systemic MA versus systemic MA alone, in CL caused by Leishmania braziliensis. We show that patients treated with the combination treatment (BNC or placebo) + MA showed improved cure rates and decreased need for rescue treatment, although differences compared to controls (systemic MA alone) were not significant. However, the overall time-to-cure was significantly lower in groups treated with the combination treatment (BNC+ systemic MA or placebo + systemic MA) in comparison to controls (MA alone), indicating that the use of a wound dressing improves CL treatment outcome. Assessment of the immune response in peripheral blood showed an overall downmodulation in the inflammatory landscape and a significant decrease in the production of IL-1a (p < 0.05) in patients treated with topical BNC + systemic MA. Our results show that the application of wound dressings to CL lesions can improve chemotherapy outcome in CL caused by L. braziliensis.

Evaluation of High-Dimensional Data Classification for Skin Malignancy Detection Using DL-Based Techniques.

Skin cancer can be detected through visual screening and skin analysis based on the biopsy and pathological state of the human body. The survival rate of cancer patients is low, and millions of people are diagnosed annually. By determining the different comparative analyses, the skin malignancy classification is evaluated. Using the Isomap with the vision transformer, we analyze the high-dimensional images with dimensionality reduction. Skin cancer can present with severe cases and life-threatening symptoms. Overall performance evaluation and classification tend to improve the accuracy of the high-dimensional skin lesion dataset when completed. In deep learning methodologies, the distinct phases of skin malignancy classification are determined by its accuracy, specificity, F1 recall, and sensitivity while implementing the classification methodology. A nonlinear dimensionality reduction technique called Isomap preserves the data's underlying nonlinear relationships intact. This is essential for the categorization of skin malignancies, as the features that separate malignant from benign skin lesions may not be linearly separable. Isomap decreases the data's complexity while maintaining its essential characteristics, making it simpler to analyze and explain the findings. High-dimensional datasets for skin lesions have been evaluated and classified more effectively when evaluated and classified using Isomap with the vision transformer.

Masked autoencoders with generalizable self-distillation for skin lesion segmentation.

In the field of skin lesion image segmentation, accurate identification and partitioning of diseased regions is of vital importance for in-depth analysis of skin cancer. Self-supervised learning, i.e., MAE, has emerged as a potent force in the medical imaging domain, which autonomously learns and extracts latent features from unlabeled data, thereby yielding pre-trained models that greatly assist downstream tasks. To encourage pre-trained models to more comprehensively learn the global structural and local detail information inherent in dermoscopy images, we introduce a Teacher-Student architecture, named TEDMAE, by incorporating a self-distillation mechanism, it learns holistic image feature information to improve the generalizable global knowledge learning of the student MAE model. To make the image features learned by the model suitable for unknown test images, two optimization strategies are, Exterior Conversion Augmentation (EC) utilizes random convolutional kernels and linear interpolation to effectively transform the input image into one with the same shape but altered intensities and textures, while Dynamic Feature Generation (DF) employs a nonlinear attention mechanism for feature merging, enhancing the expressive power of the features, are proposed to enhance the generalizability of global features learned by the teacher model, thereby improving the overall generalization capability of the pre-trained models. Experimental results from the three public skin disease datasets, ISIC2019, ISIC2017, and PH 2 indicate that our proposed TEDMAE method outperforms several similar approaches. Specifically, TEDMAE demonstrated optimal segmentation and generalization performance on the ISIC2017 and PH 2 datasets, with Dice scores reaching 82.1% and 91.2%, respectively. The best Jaccard values were 72.6% and 84.5%, while the optimal HD95% values were 13.0% and 8.9%, respectively.

SUTrans-NET: a hybrid transformer approach to skin lesion segmentation.

Melanoma is a malignant skin tumor that threatens human life and health. Early detection is essential for effective treatment. However, the low contrast between melanoma lesions and normal skin and the irregularity in size and shape make skin lesions difficult to detect with the naked eye in the early stages, making the task of skin lesion segmentation challenging. Traditional encoder-decoder built with U-shaped networks using convolutional neural network (CNN) networks have limitations in establishing long-term dependencies and global contextual connections, while the Transformer architecture is limited in its application to small medical datasets. To address these issues, we propose a new skin lesion segmentation network, SUTrans-NET, which combines CNN and Transformer in a parallel fashion to form a dual encoder, where both CNN and Transformer branches perform dynamic interactive fusion of image information in each layer. At the same time, we introduce our designed multi-grouping module SpatialGroupAttention (SGA) to complement the spatial and texture information of the Transformer branch, and utilize the Focus idea of YOLOV5 to construct the Patch Embedding module in the Transformer to prevent the loss of pixel accuracy. In addition, we design a decoder with full-scale information fusion capability to fully fuse shallow and deep features at different stages of the encoder. The effectiveness of our method is demonstrated on the ISIC 2016, ISIC 2017, ISIC 2018 and PH2 datasets and its advantages over existing methods are verified.

Construction of a pathological model of skin lesions in acute herpes zoster virus infection and its molecular mechanism.

Varicella-zoster virus (VZV), a common pathogen with humans as the sole host, causes primary infection and undergoes a latent period in sensory ganglia. The recurrence of VZV is often accompanied by severe neuralgia in skin tissue, which has a serious impact on the life of patients. During the acute infection of VZV, there are few related studies on the pathophysiological mechanism of skin tissue. In this study, transcriptome sequencing data from the acute response period within 2 days of VZV antigen stimulation of the skin were used to explore a model of the trajectory of skin tissue changes during VZV infection. It was found that early VZV antigen stimulation caused activation of mainly natural immune-related signaling pathways, while in the late phase activation of mainly active immune-related signaling pathways. JAK-STAT, NFκB, and TNFα signaling pathways are gradually activated with the progression of infection, while Hypoxia is progressively inhibited. In addition, we found that dendritic cell-mediated immune responses play a dominant role in the lesion damage caused by VZV antigen stimulation of the skin. This study provides a theoretical basis for the study of the molecular mechanisms of skin lesions during acute VZV infection.

Health Effects of Patagial Wing Tags in Red Kites (Milvus milvus) in the UK.

Patagial wing tags are commonly used for identification of Red Kites (Milvus milvus) for postrelease monitoring, as they are easy to apply, affordable, permanent, and are apparently safe. The Red Kite was successfully reintroduced in the UK in the second half of the 20th century and postrelease health surveillance has been achieved through radio and satellite tracking, monitoring nest sites, and pathologic investigation of Red Kites found dead. This study reports on pathologic findings associated with the use of patagial wing tags in three of 142 (2.1%) wing-tagged Red Kites examined postmortem since the beginning of the reintroduction project in 1989. In these three Red Kites the presence of the patagial wing tags was associated with inflammatory lesions. Further surveys of the potential short- and longer-term negative effects of patagial wing tags on Red Kites and other birds are advocated; the future use of patagial wing tags in raptors should be carefully monitored.

MDKLoss: Medicine domain knowledge loss for skin lesion recognition.

Methods based on deep learning have shown good advantages in skin lesion recognition. However, the diversity of lesion shapes and the influence of noise disturbances such as hair, bubbles, and markers leads to large intra-class differences and small inter-class similarities, which existing methods have not yet effectively resolved. In addition, most existing methods enhance the performance of skin lesion recognition by improving deep learning models without considering the guidance of medical knowledge of skin lesions. In this paper, we innovatively construct feature associations between different lesions using medical knowledge, and design a medical domain knowledge loss function (MDKLoss) based on these associations. By expanding the gap between samples of various lesion categories, MDKLoss enhances the capacity of deep learning models to differentiate between different lesions and consequently boosts classification performance. Extensive experiments on ISIC2018 and ISIC2019 datasets show that the proposed method achieves a maximum of 91.6% and 87.6% accuracy. Furthermore, compared with existing state-of-the-art loss functions, the proposed method demonstrates its effectiveness, universality, and superiority.

Improving Skin Lesion Segmentation with Self-Training.

Skin lesion segmentation plays a key role in the diagnosis of skin cancer; it can be a component in both traditional algorithms and end-to-end approaches. The quality of segmentation directly impacts the accuracy of classification; however, attaining optimal segmentation necessitates a substantial amount of labeled data. Semi-supervised learning allows for employing unlabeled data to enhance the results of the machine learning model. In the case of medical image segmentation, acquiring detailed annotation is time-consuming and costly and requires skilled individuals so the utilization of unlabeled data allows for a significant mitigation of manual segmentation efforts. This study proposes a novel approach to semi-supervised skin lesion segmentation using self-training with a Noisy Student. This approach allows for utilizing large amounts of available unlabeled images. It consists of four steps-first, training the teacher model on labeled data only, then generating pseudo-labels with the teacher model, training the student model on both labeled and pseudo-labeled data, and lastly, training the student* model on pseudo-labels generated with the student model. In this work, we implemented DeepLabV3 architecture as both teacher and student models. As a final result, we achieved a mIoU of 88.0% on the ISIC 2018 dataset and a mIoU of 87.54% on the PH2 dataset. The evaluation of the proposed approach shows that Noisy Student training improves the segmentation performance of neural networks in a skin lesion segmentation task while using only small amounts of labeled data.