-
Indian Journal of Dermatology,... Apr 2024
PubMed: 38841957
DOI: 10.25259/IJDVL_1308_2023 -
Indian Journal of Dermatology,... Apr 2024
PubMed: 38841952
DOI: 10.25259/IJDVL_198_2023 -
Indian Journal of Dermatology 2024Leprosy is a chronic granulomatous infection with varied clinical presentations. Dermoscopy is a noninvasive technique widely used in the diagnosis of various skin...
INTRODUCTION
Leprosy is a chronic granulomatous infection with varied clinical presentations. Dermoscopy is a noninvasive technique widely used in the diagnosis of various skin diseases.
OBJECTIVE
To see the correlation between the clinical and dermoscopic features with the histopathological findings in leprosy.
MATERIALS AND METHODS
A prospective observational study was conducted on clinically suspected leprosy patients attending the dermatology outpatient department (OPD) for 18 months. Representative lesions were observed by dermoscopy, and a biopsy was performed, followed by histopathology for final diagnosis. Patients were categorized by Ridley-Jopling classification.
RESULTS
A total of 70 clinically suspected leprosy patients were included in the study. Amongst 70 cases, 56 cases were diagnosed as leprosy by dermoscopy, and 53 cases were confirmed as leprosy by histopathology (hematoxylin and eosin [H and E] staining and Fite-Faraco staining). The other six cases were diagnosed as other nonspecific dermatitis by histopathological findings. Eleven cases that were dermoscopically negative were also confirmed by histopathology to be truly negative. There are three inconclusive cases of dermoscopic findings, which were diagnosed as mid-borderline leprosy by histopathology. Dermoscopic and histopathological correlation was found above 87% in all types of leprosy except mid-borderline leprosy, which showed only a 25% correlation.
CONCLUSION
Dermoscopy is a useful noninvasive tool to assess lesions of leprosy, requires less time for diagnosis, skin features are magnified several times and may become evident before clinical presentation. It definitely helps to reduce the number of biopsies in case of diagnosis of leprosy. However, in doubtful cases, histopathology is required for definitive diagnosis as it is the gold standard to date.
PubMed: 38841251
DOI: 10.4103/ijd.ijd_559_23 -
Indian Journal of Dermatology 2024Pityriasis Rosea (PR) is a common, yet enigmatic, dermatological condition characterized by a distinctive clinical presentation. Despite its prevalence, the aetiology...
BACKGROUND
Pityriasis Rosea (PR) is a common, yet enigmatic, dermatological condition characterized by a distinctive clinical presentation. Despite its prevalence, the aetiology and pathogenesis of PR remain elusive.
AIMS
To study the epidemiological and clinical aspects of patients with PR. To study dermoscopic findings and carry out histopathological correlation.
METHODS
A cross-sectional study of 50 patients was conducted. A detailed clinical history was taken and an examination was done followed by a dermoscopy. Quantitative data like age and duration of disease are presented with the help of standard deviation. Qualitative risk factors, like gender, age groups, symptomatology, site of lesion, findings or cutaneous examination, dermoscopy findings, and histopathology findings, are presented with the help of frequency and percentages.
RESULTS
PR shows male preponderance and mean age of occurrence being 30.8 ± 15.7 years. Forty per cent of patients had an atypical clinical presentation. The most frequently seen dermoscopy findings were diffuse red background (58%), peripheral collarette scale (62%), and peripheral dotted vessels (50%). On histopathology, the most common findings were spongiosis (44%), parakeratosis (38%), irregular acanthosis (34%), perivascular lymphocytic infiltrate (56%), and red blood cell extravasation (36%).
LIMITATIONS
Sample size was less due to COVID. As this was a corss-sectional study follow up of patients could not be done.
CONCLUSION
While the diagnosis of PR is clinical, it is difficult in atypical cases where dermoscopy comes to the aid. It also helps identify the age of lesions, thus helping decide the treatment strategy for patients. Biopsy remains the gold standard in ruling out other differentials of PR.
PubMed: 38841213
DOI: 10.4103/ijd.ijd_1071_23 -
Scientific Reports Jun 2024Medical image segmentation has made a significant contribution towards delivering affordable healthcare by facilitating the automatic identification of anatomical...
Medical image segmentation has made a significant contribution towards delivering affordable healthcare by facilitating the automatic identification of anatomical structures and other regions of interest. Although convolution neural networks have become prominent in the field of medical image segmentation, they suffer from certain limitations. In this study, we present a reliable framework for producing performant outcomes for the segmentation of pathological structures of 2D medical images. Our framework consists of a novel deep learning architecture, called deep multi-level attention dilated residual neural network (MADR-Net), designed to improve the performance of medical image segmentation. MADR-Net uses a U-Net encoder/decoder backbone in combination with multi-level residual blocks and atrous pyramid scene parsing pooling. To improve the segmentation results, channel-spatial attention blocks were added in the skip connection to capture both the global and local features and superseded the bottleneck layer with an ASPP block. Furthermore, we introduce a hybrid loss function that has an excellent convergence property and enhances the performance of the medical image segmentation task. We extensively validated the proposed MADR-Net on four typical yet challenging medical image segmentation tasks: (1) Left ventricle, left atrium, and myocardial wall segmentation from Echocardiogram images in the CAMUS dataset, (2) Skin cancer segmentation from dermoscopy images in ISIC 2017 dataset, (3) Electron microscopy in FIB-SEM dataset, and (4) Fluid attenuated inversion recovery abnormality from MR images in LGG segmentation dataset. The proposed algorithm yielded significant results when compared to state-of-the-art architectures such as U-Net, Residual U-Net, and Attention U-Net. The proposed MADR-Net consistently outperformed the classical U-Net by 5.43%, 3.43%, and 3.92% relative improvement in terms of dice coefficient, respectively, for electron microscopy, dermoscopy, and MRI. The experimental results demonstrate superior performance on single and multi-class datasets and that the proposed MADR-Net can be utilized as a baseline for the assessment of cross-dataset and segmentation tasks.
Topics: Humans; Neural Networks, Computer; Deep Learning; Image Processing, Computer-Assisted; Algorithms; Magnetic Resonance Imaging
PubMed: 38830932
DOI: 10.1038/s41598-024-63538-2 -
AMIA Joint Summits on Translational... 2024Accurately determining and classifying different types of skin cancers is critical for early diagnosis. In this work, we propose a novel use of deep learning for...
Accurately determining and classifying different types of skin cancers is critical for early diagnosis. In this work, we propose a novel use of deep learning for classification of benign and malignant skin lesions using dermoscopy images. We obtained 770 de-identified dermoscopy images from the University of Missouri (MU) Healthcare. We created three unique image datasets that contained the original images and images obtained after applying a hair removal algorithm. We trained three popular deep learning models, namely, ResNet50, DenseNet121, and Inception-V3. We evaluated the accuracy and the area under the curve (AUC) receiver operating characteristic (ROC) for each model and dataset. DenseNet121 achieved the best accuracy (80.52%) and AUC ROC score (0.81) on the third dataset. For this dataset, the sensitivity and specificity were 0.80 and 0.81, respectively. We also present the SHAP (SHapley Additive exPlanations) values for the predictions made by different models to understand their interpretability.
PubMed: 38827104
DOI: No ID Found -
Journal of Cancer 2024This study has used machine learning algorithms to develop a predictive model for differentiating between dermoscopic images of basal cell carcinoma (BCC) and actinic...
Dermoscopy-based Radiomics Help Distinguish Basal Cell Carcinoma and Actinic Keratosis: A Large-scale Real-world Study Based on a 207-combination Machine Learning Computational Framework.
This study has used machine learning algorithms to develop a predictive model for differentiating between dermoscopic images of basal cell carcinoma (BCC) and actinic keratosis (AK). We compiled a total of 904 dermoscopic images from two sources - the public dataset (HAM10000) and our proprietary dataset from the First Affiliated Hospital of Dalian Medical University (DAYISET 1) - and subsequently categorised these images into four distinct cohorts. The study developed a deep learning model for quantitative analysis of image features and integrated 15 machine learning algorithms, generating 207 algorithmic combinations through random combinations and cross-validation. The final predictive model, formed by integrating XGBoost with Lasso regression, exhibited effective performance in the differential diagnosis of BCC and AK. The model demonstrated high sensitivity in the training set and maintained stable performance in three validation sets. The area under the curve (AUC) value reached 1.000 in the training set and an average of 0.695 in the validation sets. The study concludes that the constructed discriminative diagnostic model based on machine learning algorithms has excellent predictive capabilities that could enhance clinical decision-making efficiency, reduce unnecessary biopsies, and provide valuable guidance for further treatment.
PubMed: 38817855
DOI: 10.7150/jca.94759 -
Cureus Apr 2024Dermatological conditions often present diagnostic challenges due to their diverse manifestations and overlapping clinical features. In such cases, dermoscopy, a...
Dermatological conditions often present diagnostic challenges due to their diverse manifestations and overlapping clinical features. In such cases, dermoscopy, a non-invasive imaging technique, has emerged as a valuable tool to enhance diagnostic accuracy and guide clinicians in reaching an appropriate differential diagnosis. By visualizing subsurface skin structures and microvascular patterns, dermoscopy provides additional information that complements clinical examination, aiding in the recognition of specific dermatoses and the differentiation between benign and malignant skin lesions. Herein, we present a case that demonstrates the utility of dermoscopy in distinguishing between an initial broad list of differential diagnoses, namely, basal cell carcinoma, squamous cell carcinoma in situ, and other inflammatory dermatitides, such as psoriasis and atopic dermatitis, and narrowing down the differential diagnosis to just one likely diagnosis, which was basal cell carcinoma in our case.
PubMed: 38813281
DOI: 10.7759/cureus.59274 -
Dermatology Practical & Conceptual Apr 2024Scientific evidence supports dermoscopy as an essential tool in dermatological diagnosis.
INTRODUCTION
Scientific evidence supports dermoscopy as an essential tool in dermatological diagnosis.
OBJECTIVES
The objective is to know the factors that influence its use in Chilean dermatologists.
METHODS
Analytical cross-sectional study. An adapted version of the survey was submitted from the pan-European study by Forsea et al to members of the Chilean Society of Dermatology, between September and December 2020. Analysis using descriptive statistics and multivariate analysis with ordinal logistic regression looking for factors associated with greater use of.
RESULTS
One hundred and ninety-eight responses, mean age 46.3 years and 14.6 years on average practicing as dermatologists. 61.6% trained in dermoscopy during their residency. 98% use a dermatoscope. More than 80% consider dermoscopy useful for the diagnosis of melanomas, follow-up of melanocytic lesions, and diagnosis of pigmented and non-pigmented tumors. Between 50% and 70% consider it useful for monitoring non-melanocytic lesions, nail and hair pathologies. Greater confidence when evaluating pigmented and non-pigmented tumors and capillary pathology. Adjusting for age, sex, confidence, and education, participation in teaching was associated with greater use of dermoscopy in non-pigmented and pigmented tumors, and capillary pathology.
CONCLUSIONS
Percentage of participation in the survey and training in dermoscopy higher than in the reference study, recognizing the usefulness of dermoscopy for the diagnosis and follow-up of tumor pathologies. Participating in teaching is a strong independent factor that is associated with a greater use of dermoscopy in Chile. Dermoscopy is positioned as a tool widely used by Chilean dermatologists in their daily practice.
PubMed: 38810061
DOI: 10.5826/dpc.1402a71 -
Dermatology Practical & Conceptual Apr 2024Seborrheic keratoses (SK) are benign epidermal tumors with high sun exposure as a major risk factor. Vitamin D deficiency is also thought to play a role in its...
INTRODUCTION
Seborrheic keratoses (SK) are benign epidermal tumors with high sun exposure as a major risk factor. Vitamin D deficiency is also thought to play a role in its pathogenesis. There has been no data regarding SK, calcidiol level, vitamin D intake, and sun index (SI) among people living in coastal areas in Indonesia.
OBJECTIVES
To assess the correlation between 1) serum calcidiol levels with SI and vitamin D intake and 2) lesion size with SI and serum calcidiol level among SK patients living in a coastal area.
METHODS
This is a cross-sectional study. We performed interviews using the sun index questionnaire and semiquantitative food frequency questionnaire for vitamin D; physical examination; dermoscopy to determine the largest SK lesion size; and measurement of serum calcidiol levels in participants with SK living in Cilincing District, North Jakarta. Spearman correlation test was used to assess the relationship between variables.
RESULTS
Thirty-nine participants with SK aged 19-59 years were analyzed. The median of the SK largest diameter, SI, serum calcidiol, and vitamin D intake was 2 (1-10) mm, 3.95 (1.1-23.52), 14.3 (5.25-35.30) ng/ml, and 4.3 (0.1-30.1) mcg/day, respectively. SI and vitamin D intake were not significantly correlated with calcidiol levels. Similarly, SI and calcidiol levels were not significantly correlated with the largest SK lesion size.
CONCLUSIONS
We found low calcidiol levels and vitamin D intake in this coastal population. The SI and vitamin D intake had no correlations with calcidiol levels. Furthermore, calcidiol levels and SI had no correlations with the lesion largest diameter.
PubMed: 38810054
DOI: 10.5826/dpc.1402a37