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.

An evaluation of the effectiveness of 'ULTRACOL 200' in enhancing nasolabial fold wrinkles through cutaneous repair.

BACKGROUND: Injectable filler, a nonsurgical beauty method, has gained popularity in rejuvenating sagging skin. In this study, polydioxanone (PDO) was utilized as the main component of the ULTRACOL200 filler that helps stimulate collagenesis and provide skin radiant effects. The study aimed to evaluate and compare the effectiveness of ULTRACOL200 with other commercialized products in visually improving dermatological problems. METHODS: Herein, 31 participants aged between 20 and 59 years were enrolled in the study. 1 mL of the testing product, as well as the quantity for the compared groups was injected into each participants face side individually. Subsequently, skin texture and sunken volume of skin were measured using ANTERA 3D CS imaging technology at three periods: before the application, 4 weeks after the initial application, and 4 weeks after the 2nd application of ULTRACOL200. RESULTS: The final results of skin texture and wrinkle volume evaluation consistently demonstrated significant enhancement. Consequently, subjective questionnaires were provided to the participants to evaluate the efficacy of the testing product, illustrating satisfactory responses after the twice applications. CONCLUSION: The investigation has contributed substantially to the comprehension of a PDO-based filler (ULTRACOL200) for skin enhancement and provided profound insight for future clinical trials.

An overview of current assessment techniques for evaluating cutaneous perfusion in reconstructive surgery.

This article provides a comprehensive analysis of modern techniques used in the assessment of cutaneous flaps in reconstructive surgery. It emphasizes the importance of preoperative planning and intra- and perioperative assessment of flap perfusion to ensure successful outcomes. Despite technological advancements, direct clinical assessment remains the gold standard. We categorized assessment techniques into non-invasive and invasive modalities, discussing their strengths and weaknesses. Non-invasive methods, such as acoustic Doppler sonography, near-infrared spectroscopy, hyperspectral imaging thermal imaging, and remote-photoplethysmography, offer accessibility and safety but may sacrifice specificity. Invasive techniques, including contrast-enhanced ultrasound, computed tomography angiography, near-infrared fluorescence angiography with indocyanine green, and implantable Doppler probe, provide high accuracy but introduce additional risks. We emphasize the need for a tailored decision-making process based on specific clinical scenarios, patient characteristics, procedural requirements, and surgeon expertise. It also discusses potential future advancements in flap assessment, including the integration of artificial intelligence and emerging technologies.

A novel SpaSA based hyper-parameter optimized FCEDN with adaptive CNN classification for skin cancer detection.

Skin cancer is the most prevalent kind of cancer in people. It is estimated that more than 1 million people get skin cancer every year in the world. The effectiveness of the disease's therapy is significantly impacted by early identification of this illness. Preprocessing is the initial detecting stage in enhancing the quality of skin images by removing undesired background noise and objects. This study aims is to compile preprocessing techniques for skin cancer imaging that are currently accessible. Researchers looking into automated skin cancer diagnosis might use this article as an excellent place to start. The fully convolutional encoder-decoder network and Sparrow search algorithm (FCEDN-SpaSA) are proposed in this study for the segmentation of dermoscopic images. The individual wolf method and the ensemble ghosting technique are integrated to generate a neighbour-based search strategy in SpaSA for stressing the correct balance between navigation and exploitation. The classification procedure is accomplished by using an adaptive CNN technique to discriminate between normal skin and malignant skin lesions suggestive of disease. Our method provides classification accuracies comparable to commonly used incremental learning techniques while using less energy, storage space, memory access, and training time (only network updates with new training samples, no network sharing). In a simulation, the segmentation performance of the proposed technique on the ISBI 2017, ISIC 2018, and PH2 datasets reached accuracies of 95.28%, 95.89%, 92.70%, and 98.78%, respectively, on the same dataset and assessed the classification performance. It is accurate 91.67% of the time. The efficiency of the suggested strategy is demonstrated through comparisons with cutting-edge methodologies.

Mapping cutaneous field carcinogenesis of nonmelanoma skin cancer using mesoscopic imaging of pro-inflammation cues.

Nonmelanoma skin cancers remain the most widely diagnosed types of cancers globally. Thus, for optimal patient management, it has become imperative that we focus our efforts on the detection and monitoring of cutaneous field carcinogenesis. The concept of field cancerization (or field carcinogenesis), introduced by Slaughter in 1953 in the context of oral cancer, suggests that invasive cancer may emerge from a molecularly and genetically altered field affecting a substantial area of underlying tissue including the skin. A carcinogenic field alteration, present in precancerous tissue over a relatively large area, is not easily detected by routine visualization. Conventional dermoscopy and microscopy imaging are often limited in assessing the entire carcinogenic landscape. Recent efforts have suggested the use of noninvasive mesoscopic (between microscopic and macroscopic) optical imaging methods that can detect chronic inflammatory features to identify pre-cancerous and cancerous angiogenic changes in tissue microenvironments. This concise review covers major types of mesoscopic optical imaging modalities capable of assessing pro-inflammatory cues by quantifying blood haemoglobin parameters and hemodynamics. Importantly, these imaging modalities demonstrate the ability to detect angiogenesis and inflammation associated with actinically damaged skin. Representative experimental preclinical and human clinical studies using these imaging methods provide biological and clinical relevance to cutaneous field carcinogenesis in altered tissue microenvironments in the apparently normal epidermis and dermis. Overall, mesoscopic optical imaging modalities assessing chronic inflammatory hyperemia can enhance the understanding of cutaneous field carcinogenesis, offer a window of intervention and monitoring for actinic keratoses and nonmelanoma skin cancers and maximise currently available treatment options.

A Protocol for the Automated Assessment of Cutaneous Pathology in a Mouse Model of Hemichannel Dysfunction.

In this chapter, we provide detailed instructions to perform quantitative reflectance imaging in a mouse model of a rare epidermal disorder caused by hyperactive connexin 26 hemichannels. Reflectance imaging is a versatile and powerful tool in dermatology, offering noninvasive, high-resolution insights into skin pathology, which is essential for both clinical practice and research. This approach offers several advantages and applications. Unlike traditional biopsy, reflectance imaging is noninvasive, allowing for real-time, in vivo examination of the skin. This is particularly valuable for monitoring chronic conditions or assessing the efficacy of treatments over time, enabling the detailed examination of skin morphology. This is crucial for identifying features of skin diseases such as cancers, inflammatory conditions, and infections. In therapeutic applications, reflectance imaging can be used to monitor the response of skin lesions to treatments. It can help in identifying the most representative area of a lesion for biopsy, thereby increasing the diagnostic accuracy. Reflectance imaging can also be used to diagnose and monitor inflammatory skin diseases, like psoriasis and eczema, by visualizing changes in skin structure and cellular infiltration. As the technology becomes more accessible, it has potential in telemedicine, allowing for remote diagnosis and monitoring of skin conditions. In academic settings, reflectance imaging can be a powerful research tool, enabling the study of skin pathology and the effects of novel treatments, including the development of monoclonal antibodies for therapeutic applications.

Parameter-based transfer learning for severity classification of atopic dermatitis using hyperspectral imaging.

BACKGROUND/PURPOSE: Because atopic dermatitis (AD) is a chronic inflammatory skin condition that causes structural changes, there is a growing need for noninvasive research methods to evaluate this condition. Hyperspectral imaging (HSI) captures skin structure features by exploiting light wavelength variations in penetration depth. In this study, parameter-based transfer learning was deployed to classify the severity of AD using HSI. Therefore, we aimed to obtain an optimal combination of classification results from the four models after constructing different source- and target-domain datasets. METHODS: We designated psoriasis, skin cancer, eczema, and AD datasets as the source datasets, and the set of images acquired via hyperspectral camera as the target dataset for wavelength-specific AD classification. We compared the severity classification performances of 96 combinations of sources, models, and targets. RESULTS: The highest classification performance of 83% was achieved when ResNet50 was trained on the augmented psoriasis dataset as the source, with the resulting parameters used to train the model on the target Near-infrared radiation (NIR) dataset. The second highest classification accuracy of 81% was achieved when ResNet50 was trained on the unaugmented psoriasis dataset as the source, with the resulting parameters used to train the model on the target R dataset. ResNet50 demonstrated potential as a generalized model for both the source and target data, also confirming that the psoriasis dataset is an effective training resource. CONCLUSION: The present study not only demonstrates the feasibility of the severity classification of AD based on hyperspectral images, but also showcases combinations and research scalability for domain exploration.

A model that predicts a real-time tumour surface using intra-treatment skin surface and end-of-expiration and end-of-inhalation planning CT images.

OBJECTIVES: To develop a mapping model between skin surface motion and internal tumour motion and deformation using end-of-exhalation (EOE) and end-of-inhalation (EOI) 3D CT images for tracking lung tumours during respiration. METHODS: Before treatment, skin and tumour surfaces were segmented and reconstructed from the EOE and the EOI 3D CT images. A non-rigid registration algorithm was used to register the EOE skin and tumour surfaces to the EOI, resulting in a displacement vector field that was then used to construct a mapping model. During treatment, the EOE skin surface was registered to the real-time, yielding a real-time skin surface displacement vector field. Using the mapping model generated, the input of a real-time skin surface can be used to calculate the real-time tumour surface. The proposed method was validated with and without simulated noise on 4D CT images from 15 patients at Léon Bérard Cancer Center and the 4D-lung dataset. RESULTS: The average centre position error, dice similarity coefficient (DSC), 95%-Hausdorff distance and mean distance to agreement of the tumour surfaces were 1.29 mm, 0.924, 2.76 mm, and 1.13 mm without simulated noise, respectively. With simulated noise, these values were 1.33 mm, 0.920, 2.79 mm, and 1.15 mm, respectively. CONCLUSIONS: A patient-specific model was proposed and validated that was constructed using only EOE and EOI 3D CT images and real-time skin surface images to predict internal tumour motion and deformation during respiratory motion. ADVANCES IN KNOWLEDGE: The proposed method achieves comparable accuracy to state-of-the-art methods with fewer pre-treatment planning CT images, which holds potential for application in precise image-guided radiation therapy.

HDS-Net: Achieving fine-grained skin lesion segmentation using hybrid encoding and dynamic sparse attention.

Skin cancer is one of the most common malignant tumors worldwide, and early detection is crucial for improving its cure rate. In the field of medical imaging, accurate segmentation of lesion areas within skin images is essential for precise diagnosis and effective treatment. Due to the capacity of deep learning models to conduct adaptive feature learning through end-to-end training, they have been widely applied in medical image segmentation tasks. However, challenges such as boundary ambiguity between normal skin and lesion areas, significant variations in the size and shape of lesion areas, and different types of lesions in different samples pose significant obstacles to skin lesion segmentation. Therefore, this study introduces a novel network model called HDS-Net (Hybrid Dynamic Sparse Network), aiming to address the challenges of boundary ambiguity and variations in lesion areas in skin image segmentation. Specifically, the proposed hybrid encoder can effectively extract local feature information and integrate it with global features. Additionally, a dynamic sparse attention mechanism is introduced, mitigating the impact of irrelevant redundancies on segmentation performance by precisely controlling the sparsity ratio. Experimental results on multiple public datasets demonstrate a significant improvement in Dice coefficients, reaching 0.914, 0.857, and 0.898, respectively.

Investigating the role of tumour-to-skin proximity in predicting nodal metastasis in breast cancer.

BACKGROUND: Understanding the factors influencing nodal status in breast cancer is vital for axillary staging, therapy, and patient survival. The nodal stage remains a crucial factor in prognostication indices. This study investigates the relationship between tumour-to-skin distance (in T1-T3 tumours where the skin is not clinically involved) and the risk of nodal metastasis. METHODS: We retrospectively reviewed data from 100 patients who underwent neoadjuvant chemotherapy (NACT). Besides patient demographics and tumour variables, a radiologist retrospectively reviewed pre-operative MRI to measure tumour-to-skin distance. R core packages were used for univariate (χ2 and T-Wilcoxon tests) and bivariate logistic regression statistical analysis. RESULTS: Of 95 analysable datasets, patients' median age was 51 years (IQR: 42-61), 97% were symptomatic (rest screen detected), and the median tumour size was 43 mm (IQR, 26-52). On multivariate analysis, increasing invasive tumour size (p = 0.02), ER positivity (p = 0.007) and shorter tumour-to-skin distance (p = 0.05) correlated with nodal metastasis.  HER2 was not included in multivariate analysis as there was no association with nodal status on univariate analysis. In node-positive tumours, as tumour size increased, the tumour-to-skin distance decreased (r = - 0.34, p = 0.026). In node-negative tumours, there was no correlation (r = + 0.18, p = 0.23). CONCLUSION: This study shows that non-locally advanced cancers closer to the skin (and consequent proximity to subdermal lymphatics) are associated with a greater risk of nodal metastasis. Pre-operative identification of those more likely to be node positive may suggest the need for a second-look USS since a higher nodal stage may lead to a change in therapeutic strategies, such as upfront systemic therapy, node marking, and axillary clearance without the need to return to theatre following sentinel node biopsy.

Combination of 68 Ga-FAPI-04 and Dedicated Breast PET (MAMMI PET) Outperformed Breast MRI and 18 F-FDG PET/CT by Revealing Nipple and Skin Involvement of Breast Cancer.

ABSTRACT: A 41-year-old woman with newly diagnosed breast cancer had suspicious clinical findings of skin involvement on physical examination. The primary tumor had no FDG uptake in 18 F-FDG PET/CT. Nipple and skin had no pathologic enhancement for invasion in breast MRI. Because the T stage was unclear, the patient underwent 68 Ga-FAPI-04 PET/CT for further evaluation. Combination of 68 Ga-FAPI-04 with dedicated breast PET (MAMMI PET) showed nipple and skin involvement of breast cancer with intense FAPI uptake. Consequently, a skin-sparing mastectomy was performed. Histopathological examination confirmed invasive lobular carcinoma infiltration of the deep dermis in the nipple and skin tissue.

Skinly: A novel handheld IoT device for validating biophysical skin characteristics.

BACKGROUND: Recent advancements in artificial intelligence have revolutionized dermatological diagnostics. These technologies, particularly machine learning (ML), including deep learning (DL), have shown accuracy equivalent or even superior to human experts in diagnosing skin conditions like melanoma. With the integration of ML, including DL, the development of at home skin analysis devices has become feasible. To this end, we introduced the Skinly system, a handheld device capable of evaluating various personal skin characteristics noninvasively. MATERIALS AND METHODS: Equipped with a moisture sensor and a multi-light-source camera, Skinly can assess age-related skin parameters and specific skin properties. Utilizing state-of-the-art DL, Skinly processed vast amounts of images efficiently. The Skinly system's efficacy was validated both in the lab and at home, comparing its results to established "gold standard" methods. RESULTS: Our findings revealed that the Skinly device can accurately measure age-associated parameters, that is, facial age, skin evenness, and wrinkles. Furthermore, Skinly produced data consistent with established devices for parameters like glossiness, skin tone, redness, and porphyrin levels. A separate study was conducted to evaluate the effects of two moisturizing formulations on skin hydration in laboratory studies with standard instrumentation and at home with Skinly. CONCLUSION: Thanks to its capability for multi-parameter measurements, the Skinly device, combined with its smartphone application, holds the potential to replace more expensive, time-consuming diagnostic tools. Collectively, the Skinly device opens new avenues in dermatological research, offering a reliable, versatile tool for comprehensive skin analysis.

Automated Whole Slide Imaging for Label-Free Histology Using Photon Absorption Remote Sensing Microscopy.

OBJECTIVE: Pathologists rely on histochemical stains to impart contrast in thin translucent tissue samples, revealing tissue features necessary for identifying pathological conditions. However, the chemical labeling process is destructive and often irreversible or challenging to undo, imposing practical limits on the number of stains that can be applied to the same tissue section. Here we present an automated label-free whole slide scanner using a PARS microscope designed for imaging thin, transmissible samples. METHODS: Peak SNR and in-focus acquisitions are achieved across entire tissue sections using the scattering signal from the PARS detection beam to measure the optimal focal plane. Whole slide images (WSI) are seamlessly stitched together using a custom contrast leveling algorithm. Identical tissue sections are subsequently H&E stained and brightfield imaged. The one-to-one WSIs from both modalities are visually and quantitatively compared. RESULTS: PARS WSIs are presented at standard 40x magnification in malignant human breast and skin samples. We show correspondence of subcellular diagnostic details in both PARS and H&E WSIs and demonstrate virtual H&E staining of an entire PARS WSI. The one-to-one WSI from both modalities show quantitative similarity in nuclear features and structural information. CONCLUSION: PARS WSIs are compatible with existing digital pathology tools, and samples remain suitable for histochemical, immunohistochemical, and other staining techniques. SIGNIFICANCE: This work is a critical advance for integrating label-free optical methods into standard histopathology workflows.

Molecular skin fluorescence imaging: A tool for evaluating early melanoma development.

A novel approach to melanoma diagnosis-in vivo molecular skin fluorescence imaging (mSFI)-was developed to identify premalignant changes in the form of tissue remodeling related to melanoma development in humans by imaging the proximal microenvironment of lesions. The method was tested using a fluorescent peptide (ORL-1) which binds to αvß3 integrin, a molecule associated with invasive melanoma development. A cut off score of 7 was established, differentiating melanomas from nonmelanoma nevi with 100% sensitivity, and 95.7% specificity, while identifying dysplastic nevi with the potential for melanoma development.

Investigations on ultrasonography in the diagnosis of nodular localized cutaneous neurofibroma.

OBJECTIVE: To describe the ultrasound characteristics of nodular localized cutaneous neurofibroma (NLCN). MATERIALS AND METHODS: Clinical features and ultrasound characteristics of 43 lesions of 40 patients pathologically proven as NLCNs at Peking University Shenzhen Hospital from October 2014 to May 2022 were analyzed retrospectively. The location, length-to-thickness (L/T) ratio, thickness-to-width (T/W) ratio, shape, margin, capsule, echogenicity, echotexture, posterior features, vascularity, and "rat tail sign" were evaluated. RESULTS: All ultrasound findings showed almost perfect agreement. More than a half of NLCNs (n = 24, 55.8%, p < 0.001) were located in the subcutaneous fat layer wholly with well-demarcation from dermis and deep fascia. Most of the NLCNs were fusiform shape (n = 27, 62.8%, p < 0.001) in the long axis and oval shape (n = 35, 81.4%, p < 0.001) in the short axis. The other ultrasound findings of NLCNs included well-defined (n = 42, 97.7%, p < 0.001), encapsulated (n = 39, 90.7%, p < 0.001), predominately hypoechoic (n = 34, 79.1%, p < 0.001), homogeneous (n = 39, 90.7%, p < 0.001), posterior enhancement (n = 29, 67.4%, p = 0.033), and avascularity (n = 37, 86.0%, p < 0.001). Only a quarter (n = 11, 25.6%, p = 0.002) of lesions were recognized with the "rat tail sign." CONCLUSION: NLCNs present as fusiform shape in long axis and round shape in short axis. The common ultrasound findings of NLCNs are well-defined, encapsulated, predominately hypoechoic, homogeneous lesion with posterior enhancement, and poor blood supply. The "rat tail sign" has low sensitivity in NLCNs.

In Situ Monitoring and Assessment of Ischemic Skin Flap by High-Frequency Ultrasound and Quantitative Parameters.

Skin flap surgery is a critical procedure for treating severe skin injury in which post-surgery lesions must well monitored and cared for noninvasively. In the present study, attempts using high-frequency ultrasound imaging, quantitative parameters, and statistical analysis were made to extensively assess variations in the skin flap. Experiments were arranged by incising the dorsal skin of rats to create a skin flap using the chamber model. Measurements, including photographs, 30 MHz ultrasound B-mode images, skin thickness, echogenicity, Nakagami statistics, and histological analysis of post-surgery skin flap, were performed. Photograph results showed that color variations in different parts of the skin flap may readily correspond to ischemic states of local tissues. Compared to post-surgery skin flap on day 7, both integrated backscatter (IB) and Nakagami parameter (m) of the distal part of tissues were increased, and those of the skin thickness were decreased. Overall, relative skin thickness, IB, and m of the distal part of post-surgery skin flap varied from 100 to 67%, -66 to -61 dB, and 0.48 to 0.36, respectively. These results demonstrate that this modality and quantitative parameters can be feasibly applied for long-term and in situ assessment of skin flap tissues.

Non-invasive Skin Imaging in Cutaneous Lymphomas.

The diagnosis of cutaneous lymphomas is challenging and requires skin tissue for histology and immunophenotyping using immunohistochemistry and molecular studies. In recent years, the role of non-invasive imaging techniques has been described as part of the clinical assessment of cutaneous lymphoma lesions. Imaging modalities such as dermoscopy, reflectance confocal microscopy (RCM), and high frequency ultrasound (HFUS) have been shown to be very valuable in raising the clinical suspicion for lymphomas of the skin, and in distinguishing cutaneous lymphomas from inflammatory dermatoses such as lupus, psoriasis, or eczema. These non-invasive methods can be used to direct the clinician to the optimal biopsy site to maximize the histopathological results and minimize false negatives. These methods also have a potential place in monitoring treatment response. In this review we present a concise summary of the dermoscopic imaging, RCM, and HFUS features seen in cutaneous T-cell lymphomas (CTCL) and B-cell lymphomas (CBCL).