The latest medical research on Skin Cancer

Vulvar lichen sclerosus (VLS) is a chronic inflammatory disease initially involving anogenital areas. Noninvasive assessment is essential for precise management in VLS. We aim to analyze high-frequency ultrasound (HFUS) features and correlate HFUS with histopathological changes.

Forty patients with histopathologically confirmed VLS lesions were retrospectively identified from August 2020 to September 2021. The clinical manifestations, dermoscopic images as well as both 20 and 50 MHz HFUS images were assessed. HFUS assessment included epidermal morphology, hypoechoic dermal band thickness, and hypoechoic dermal band internal echo. We compared HFUS images with histopathology, and Pearson's correlation coefficient was used to assess the relationship between hypoechoic dermal band thickness and histopathological depth.

Hypoechoic dermal band was present in 100% (40/40) VLS lesions. There was a significant linear positive correlation between the histopathological depth and corresponding hypoechoic dermal band thickness, with a Pearson correlation coefficient of 0.685 (p < 0.001). Besides, 95% (38/40) lesions revealed smooth epidermis, and the internal echo of hypoechoic dermal band was assessed as homogeneous in 60% (24/40) and inhomogeneous in 40% (16/40) lesions.

HFUS characteristics, as well as measurable hypoechoic dermal band thickness, may provide valuable information in the precise diagnosis and the treatment monitoring of VLS.

Dermatofibrosarcoma protuberans (DFSP) is a kind of low-grade malignant spindle cell neoplasm, the diagnosis, and treatment, which have markedly attracted clinicians' attention for its repeated recurrence. High-resolution magnetic resonance imaging (HR-MRI) has shown unique capabilities in diagnosis of various cutaneous tumors.

Data of 29 patients with clinically suspected DFSPs and undergoing dynamic contrast-enhanced (DCE) HR-MRI preoperatively were prospectively collected. The HR-MRI qualitative features were evaluated and compared. The DCE-associated quantitative parameters and the time-signal intensity curve (TIC) types were provided using DCE sequences.

A total of 7 DFSPs, nine dermatofibromas (DF, including four cases of cellular variant [CDF]), 12 keloids, and one nodular fasciitis were enrolled. DFSP showed the largest major diameter and the deepest depth. Five DFSPs (71.4%) showed ill-defined margins as well as infiltration of peripheral adipose. All DFSPs showed irregular shape. Most DFSPs presented hyperintensity on T2 WI (71.4%) and iso-intensity on T1 WI (85.7%). Six cases (85.7%) had significant enhancement, and six cases (85.7%) had homogeneous enhancement. There were significant differences of Ktrans , Kep , Ve and iAUC values among DFSPs, DFs, and keloids, and DFSP had the highest values for these parameters. Six DFSPs (85.7%) and four CDFs (100%) showed type-III TICs, while the other lesions showed type-Ⅰor type-Ⅱ TICs.

DCE-HR-MRI could show the growth characteristics of DFSPs, which was of great value for the diagnosis and differential diagnosis of DFSPs and was helpful for the determination of treatment options, thereby to improve the prognosis of patients.

Acne is one of the most common skin lesions in adolescents. Some severe or inflammatory acne leads to scars, which may have major impacts on patients' quality of life or even job prospects. Grading acne plays an important role in diagnosis, and the diagnosis is made by counting the number of acne. It is a labor-intensive job and it is easy for dermatologists to make mistakes, so it is very important to develop automatic diagnosis methods. Ensemble learning may improve the prediction results of the base models, but its time complexity is relatively high. The ensemble pruning strategy may solve this computational challenge by removing the redundant base models.

This study proposed a novel ensemble pruning framework of deep learning models to accurately detect and grade acne using images. First, we train multi-base models and prune the redundancy models according to the performance and diversity of the models. Then, we construct the new features of the training data by the base models we select in the previous step. Next, we remove the redundancy models further by a feature selection algorithm. Finally, we integrate all the base models by classifiers. The ensemble pruning algorithm was proposed to prune the deep learning base models.

The experimental data showed that the ensemble pruned framework achieved a prediction accuracy of 85.82% on the acne dataset, better than the existing studies. To verify our method's effectiveness, we test our method in a skin cancer dataset and greatly outperform the state-of-the-art methods.

The method we proposed is used to grade acne. Our method's performance outperforms state-of-the-art methods on two datasets, and it can also remove redundancy models to reduce computational complexity.

Blood vessels called telangiectasia are visible in skin lesions with the aid of dermoscopy. Telangiectasia are a pivotal identifying feature of basal cell carcinoma. These vessels appear thready, serpiginous, and may also appear arborizing, that is, wide vessels branch into successively thinner vessels. Due to these intricacies, their detection is not an easy task, neither with manual annotation nor with computerized techniques. In this study, we automate the segmentation of telangiectasia in dermoscopic images with a deep learning U-Net approach.

We apply a combination of image processing techniques and a deep learning-based U-Net approach to detect telangiectasia in digital basal cell carcinoma skin cancer images. We compare loss functions and optimize the performance by using a combination loss function to manage class imbalance of skin versus vessel pixels.

We establish a baseline method for pixel-based telangiectasia detection in skin cancer lesion images. An analysis and comparison for human observer variability in annotation is also presented.

Our approach yields Jaccard score within the variation of human observers as it addresses a new aspect of the rapidly evolving field of deep learning: automatic identification of cancer-specific structures. Further application of DL techniques to detect dermoscopic structures and handle noisy labels is warranted.