Explore the vast range of titles available.

The marked increase in the incidence of melanoma coupled with the rapid drop in the survival rate after metastasis has promoted the investigation into improved diagnostic methods for melanoma. High-frequency ultrasound (US), optical coherence tomography (OCT), and photoacoustic imaging (PAI) are three potential modalities that can assist a dermatologist by providing extra information beyond dermoscopic features. In this study, we imaged a swine model with spontaneous melanoma using these modalities and compared the images with images of nearby healthy skin. Histology images were used for validation.

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.

Until now, the clinical differentiation between a nevus and a melanoma is still challenging in some cases. Line-field confocal optical coherence tomography (LC-OCT) is a new tool with the aim to change that. The aim of the study was to evaluate LC-OCT for the discrimination between nevi and melanomas. A total of 84 melanocytic lesions were examined with LC-OCT and 36 were also imaged with RCM. The observers recorded the diagnoses, and the presence or absence of the 18 most common imaging parameters for melanocytic lesions, nevi, and melanomas in the LC-OCT images. Their confidence in diagnosis and the image quality of LC-OCT and RCM were evaluated. The most useful criteria, the sensitivity and specificity of LC-OCT vs. RCM vs. histology, to differentiate a (dysplastic) nevus from a melanoma were analyzed. Good image quality correlated with better diagnostic performance (Spearman correlation: 0.4). LC-OCT had a 93% sensitivity and 100% specificity compared to RCM (93% sensitivity, 95% specificity) for diagnosing a melanoma (vs. all types of nevi). No difference in performance between RCM and LC-OCT was observed (McNemar’s p value = 1). Both devices falsely diagnosed dysplastic nevi as non-dysplastic (43% sensitivity for dysplastic nevus diagnosis). The most significant criteria for diagnosing a melanoma with LC-OCT were irregular honeycombed patterns (92% occurrence rate; 31.7 odds ratio (OR)), the presence of pagetoid spread (89% occurrence rate; 23.6 OR) and the absence of dermal nests (23% occurrence rate, 0.02 OR). In conclusion LC-OCT is useful for the discrimination between melanomas and nevi.

Diagnosing clinically unclear basal cell carcinomas (BCCs) can be challenging. Line-field confocal optical coherence tomography (LC-OCT) is able to display morphological features of BCC subtypes with good histological correlation. The aim of this study was to investigate the accuracy of LC-OCT in diagnosing clinically unsure cases of BCC compared to dermoscopy alone and in distinguishing between superficial BCCs and other BCC subtypes. Moreover, we addressed pitfalls in false positive cases. We prospectively enrolled 182 lesions of 154 patients, referred to our department to confirm or to rule out the diagnosis of BCC. Dermoscopy and LC-OCT images were evaluated by two experts independently. Image quality, LC-OCT patterns and criteria, diagnosis, BCC subtype, and diagnostic confidence were assessed. Sensitivity and specificity of additional LC-OCT were compared to dermoscopy alone for identifying BCC in clinically unclear lesions. In addition, key LC-OCT features to distinguish between BCCs and non-BCCs and to differentiate superficial BCCs from other BCC subtypes were determined by linear regressions. Diagnostic confidence was rated as “high” in only 48% of the lesions with dermoscopy alone compared to 70% with LC-OCT. LC-OCT showed a high sensitivity (98%) and specificity (80%) compared to histology, and these were even higher (100% sensitivity and 97% specificity) in the subgroup of lesions with high diagnostic confidence. Interobserver agreement was nearly perfect (95%). The combination of dermoscopy and LC-OCT reached a sensitivity of 100% and specificity of 81.2% in all cases and increased to sensitivity of 100% and specificity of 94.9% in cases with a high diagnostic confidence. The performance of LC-OCT was influenced by the image quality but not by the anatomical location of the lesion. The most specific morphological LC-OCT criteria in BCCs compared to non-BCCs were: less defined dermoepidermal junction (DEJ), hyporeflective tumor lobules, and dark rim. The most relevant features of the subgroup of superficial BCCs (sBCCs) were: string of pearls pattern and absence of epidermal thinning. Our diagnostic confidence, sensitivity, and specificity in detecting BCCs in the context of clinically equivocal lesions significantly improved using LC-OCT in comparison to dermoscopy only. Operator training for image acquisition is fundamental to achieve the best results. Not only the differential diagnosis of BCC, but also BCC subtyping can be performed at bedside with LC-OCT.

Clinical treatment of skin lesion is primarily dependent on timely detection and delimitation of lesion boundaries for accurate cancerous region localization. Prevalence of skin cancer is on the higher side, especially that of melanoma, which is aggressive in nature due to its high metastasis rate. Therefore, timely diagnosis is critical for its treatment before the onset of malignancy. To address this problem, medical imaging is used for the analysis and segmentation of lesion boundaries from dermoscopic images. Various methods have been used, ranging from visual inspection to the textural analysis of the images. However, accuracy of these methods is low for proper clinical treatment because of the sensitivity involved in surgical procedures or drug application. This presents an opportunity to develop an automated model with good accuracy so that it may be used in a clinical setting. This paper proposes an automated method for segmenting lesion boundaries that combines two architectures, the U-Net and the ResNet, collectively called Res-Unet. Moreover, we also used image inpainting for hair removal, which improved the segmentation results significantly. We trained our model on the ISIC 2017 dataset and validated it on the ISIC 2017 test set as well as the PH2 dataset. Our proposed model attained a Jaccard Index of 0.772 on the ISIC 2017 test set and 0.854 on the PH2 dataset, which are comparable results to the current available state-of-the-art techniques.

Skin lesion segmentation is crucial for identifying and diagnosing skin diseases. Accurate segmentation aids in identifying and localizing diseases, monitoring morphological changes, and extracting features for further diagnosis, especially in the early detection of skin cancer. This task is challenging due to the irregularity of skin lesions in dermatoscopic images, significant color variations, boundary blurring, and other complexities. Artifacts like hairs, blood vessels, and air bubbles further complicate automatic segmentation. Inspired by U-Net and its variants, this paper proposes a Multiscale Input Fusion Residual Attention Pyramid Convolution Network (MRP-UNet) for dermoscopic image segmentation. MRP-UNet includes three modules: the Multiscale Input Fusion Module (MIF), Res2-SE Module, and Pyramid Dilated Convolution Module (PDC). The MIF module processes lesions of different sizes and morphologies by fusing input information from various scales. The Res2-SE module integrates Res2Net and SE mechanisms to enhance multi-scale feature extraction. The PDC module captures image information at different receptive fields through pyramid dilated convolution, improving segmentation accuracy. Experiments on ISIC 2016, ISIC 2017, ISIC 2018, PH2, and HAM10000 datasets show that MRP-UNet outperforms other methods. Ablation studies confirm the effectiveness of its main modules. Both quantitative and qualitative analyses demonstrate MRP-UNet’s superiority over state-of-the-art methods. MRP-UNet enhances skin lesion segmentation by combining multiscale fusion, residual attention, and pyramid dilated convolution. It achieves higher accuracy across multiple datasets, showing promise for early skin disease diagnosis and improved patient outcomes.

Early skin disease detection significantly improves patient survival rates, yet limited access to dermatological expertise creates an urgent need for automated diagnostic systems. In this paper, we develop a dual-branch deep learning framework that simultaneously performs skin lesion segmentation and classification from dermoscopic images. The proposed segmentation branch uses a modified EfficientNet-B7 encoder with Atrous Spatial Pyramid Pooling (ASPP) for multi-scale feature extraction and transformer blocks for global context modeling. Attention gates and Squeeze-and-Excitation blocks enhance feature selection and boundary precision. The classification branch fuses DenseNet-121 visual features with morphological characteristics extracted from predicted segmentation masks, creating a hybrid appearance-morphology analysis approach. The proposed framework achieved strong and consistent segmentation performance across five benchmark datasets. On HAM10000, the highest Dice score (0.9568) and IoU (0.9242) were recorded, with an accuracy of 0.9708. PH2 achieved a Dice of 0.9250 and a sensitivity of 0.9734, while ISIC 2016 reached a Dice of 0.9298 and an IoU of 0.8811. For ISIC 2017 and ISIC 2018, Dice scores were 0.8972 and 0.9020, respectively. All datasets reported high specificity (> 0.93) and accuracy (> 0.95), confirming the model’s robustness and generalization capability. Our dual-branch framework achieves state-of-the-art accuracy by effectively integrating visual appearance and structural morphological features for comprehensive skin lesion analysis. The consistent high performance across diverse datasets indicates strong potential for clinical deployment as a diagnostic support tool.

This study presents an augmented hybrid approach for improving the diagnosis of malignant skin lesions by combining convolutional neural network (CNN) predictions with selective human interventions based on prediction confidence. The algorithm retains high-confidence CNN predictions while replacing low-confidence outputs with expert human assessments to enhance diagnostic accuracy. A CNN model utilizing the EfficientNetB3 backbone is trained on datasets from the ISIC-2019 and ISIC-2020 SIIM-ISIC melanoma classification challenges and evaluated on a 150-image test set. The model’s predictions are compared against assessments from 69 experienced medical professionals. Performance is assessed using receiver operating characteristic (ROC) curves and area under curve (AUC) metrics, alongside an analysis of human resource costs. The baseline CNN achieves an AUC of 0.822, slightly below the performance of human experts. However, the augmented hybrid approach improves the true positive rate to 0.782 and reduces the false positive rate to 0.182, delivering better diagnostic performance with minimal human involvement. This approach offers a scalable, resource-efficient solution to address variability in medical image analysis, effectively harnessing the complementary strengths of expert humans and CNNs.

Due to advances in high-frequency ultrasound technology, it is easier to detect fine structures of skin lesions. The aim of this study was to examine the ultrasonographic features and use recurrence risk stratification to assess the diagnostic performance of pre-operative ultrasound examination of basal cell carcinoma (BCC). This was a retrospective study. Forty-six BCC lesions underwent pre-operative ultrasound examination using 50- and 20-MHz probes. Ultrasonographic shape, margin, internal echoes, hyper-echoic spots, posterior echoes, and depth of the lesion were evaluated and correlated with the risk of recurrence based on histological features. Forty-two patients had 46 skin lesions in total. The high-risk (n = 6) and low-risk (n = 40) groups exhibited considerable overlap in the ultrasonographic manifestations and no significant difference in margin (χ = 3.231, P = 0.072), internal echo (χ = 1.592, P = 0.207), or posterior echo (P = 0.169). However, high-risk BCCs tended to be irregular in shape than low-risk lesions (χ = 4.313, P = 0.038). Both types presented hyper-echoic spots (χ = 1.850, P = 0.174). Additionally, 78% of low-risk lesions were confined to the dermis (31/40), and 100% of high-risk lesions infiltrated into the sub-cutaneous tissue, resulting in a significant difference between the two groups (χ = 10.951, P = 0.001). Ultrasound detected sub-clinical lesions in five patients. High-frequency ultrasound can provide important information for pre-operative evaluation of risk in BCC foci and reveal hidden lesions. The technique may play a crucial role in guiding therapeutic options for BCC.

Deep learning can exceed dermatologists’ diagnostic accuracy in experimental image environments. However, inaccurate segmentation of images with multiple skin lesions can be seen with current methods. Thus, information present in multiple-lesion images, available to specialists, is not retrievable by machine learning. While skin lesion images generally capture a single lesion, there may be cases in which a patient’s skin variation may be identified as skin lesions, leading to multiple false positive segmentations in a single image. Conversely, image segmentation methods may find only one region and may not capture multiple lesions in an image. To remedy these problems, we propose a novel and effective data augmentation technique for skin lesion segmentation in dermoscopic images with multiple lesions. The lesion-aware mixup augmentation (LAMA) method generates a synthetic multi-lesion image by mixing two or more lesion images from the training set. We used the publicly available International Skin Imaging Collaboration (ISIC) 2017 Challenge skin lesion segmentation dataset to train the deep neural network with the proposed LAMA method. As none of the previous skin lesion datasets (including ISIC 2017) has considered multiple lesions per image, we created a new multi-lesion (MuLe) segmentation dataset utilizing publicly available ISIC 2020 skin lesion images with multiple lesions per image. MuLe was used as a test set to evaluate the effectiveness of the proposed method. Our test results show that the proposed method improved the Jaccard score 8.3% from 0.687 to 0.744 and the Dice score 5% from 0.7923 to 0.8321 over a baseline model on MuLe test images. On the single-lesion ISIC 2017 test images, LAMA improved the baseline model’s segmentation performance by 0.08%, raising the Jaccard score from 0.7947 to 0.8013 and the Dice score 0.6% from 0.8714 to 0.8766. The experimental results showed that LAMA improved the segmentation accuracy on both single-lesion and multi-lesion dermoscopic images. The proposed LAMA technique warrants further study.