-
Computers in Biology and Medicine Oct 2022Use of artificial intelligence to identify dermoscopic images has brought major breakthroughs in recent years to the early diagnosis and early treatment of skin cancer,...
BACKGROUND
Use of artificial intelligence to identify dermoscopic images has brought major breakthroughs in recent years to the early diagnosis and early treatment of skin cancer, the incidence of which is increasing year by year worldwide and poses a great threat to human health. Achievements have been made in the research of skin cancer image classification by using the deep backbone of the convolutional neural network (CNN). This approach, however, only extracts the features of small objects in the image, and cannot locate the important parts.
OBJECTIVES
As a result, researchers of the paper turn to vision transformers (VIT) which has demonstrated powerful performance in traditional classification tasks. The self-attention is to improve the value of important features and suppress the features that cause noise. Specifically, an improved transformer network named SkinTrans is proposed.
INNOVATIONS
To verify its efficiency, a three step procedure is followed. Firstly, a VIT network is established to verify the effectiveness of SkinTrans in skin cancer classification. Then multi-scale and overlapping sliding windows are used to serialize the image and multi-scale patch embedding is carried out which pay more attention to multi-scale features. Finally, contrastive learning is used which makes the similar data of skin cancer encode similarly so that the encoding results of different data are as different as possible.
MAIN RESULTS
The experiment is carried out based on two datasets, namely (1) HAM10000: a large dataset of multi-source dermatoscopic images of common skin cancers; (2)A clinical dataset of skin cancer collected by dermoscopy. The model proposed has achieved 94.3% accuracy on HAM10000 and 94.1% accuracy on our datasets, which verifies the efficiency of SkinTrans.
CONCLUSIONS
The transformer network has not only achieved good results in natural language but also achieved ideal results in the field of vision, which also lays a good foundation for skin cancer classification based on multimodal data. This paper is convinced that it will be of interest to dermatologists, clinical researchers, computer scientists and researchers in other related fields, and provide greater convenience for patients.
Topics: Artificial Intelligence; Dermatologists; Dermoscopy; Humans; Melanoma; Skin Neoplasms
PubMed: 36037629
DOI: 10.1016/j.compbiomed.2022.105939 -
Journal of the European Academy of... Dec 2022There is little understanding regarding the long-term natural history of melanocytic nevi among adults.
BACKGROUND
There is little understanding regarding the long-term natural history of melanocytic nevi among adults.
OBJECTIVE
The objective of the study was to describe the long-term natural history of individual nevi located on the torso of high-risk patients.
METHODS
All patients attending Memorial Sloan Kettering Cancer Center (MSKCC) who underwent two total body photography (TBP) sessions 15+ years apart were included ('retrospective' group). To account for a potential selection bias, we also included consecutive patients who had TBP 15+ years ago and consented to undergo follow-up TBP ('prospective' group). We compared baseline and follow-up torso images on the TBPs and evaluated the number of total, new and disappearing nevi; number of seborrheic keratoses and actinic keratoses; each nevus' diameter at both time points; each nevus' colour change; the presence of clinical atypia; and when dermoscopy was available, the dermoscopic features at each time point.
RESULTS
One hundred six patients were included in the study. Although the average age of the patients was 40 at baseline TBP, most patients developed new nevi between imaging sessions (median 16.4 years) with an average of 2.6 (SD = 4.8) nevi per participant. The average number of disappearing nevi was 0.3 (SD = 0.6). In addition, 62/106 (58%) patients had an absolute increase, and 9/106 (8%) patients had an absolute decrease in their total nevus count. Roughly half (49%: 1416/2890) of the nevi that could be evaluated at both time points increased in diameter by at least 25%. Only 6% (159/2890) of nevi shrunk in diameter by at least 25%. Patients with a history of melanoma had a higher rate of disappearing nevi, and their nevi were more likely to grow. Most nevi demonstrated no significant dermoscopic changes.
CONCLUSIONS
High-risk patients acquire new nevi throughout life with very few nevi disappearing over time. Contrary to prior reports, most nevi in adults increase in diameter, while few nevi shrink.
Topics: Adult; Humans; Dermoscopy; Skin Neoplasms; Nevus, Pigmented; Nevus, Epithelioid and Spindle Cell; Nevus
PubMed: 35881111
DOI: 10.1111/jdv.18470 -
The Journal of the American Osteopathic... Mar 2017Osteopathic physicians (ie, DOs) in primary care may play a critical role in the early detection of skin cancer. Dermoscopy improves diagnostic accuracy; however, its...
CONTEXT
Osteopathic physicians (ie, DOs) in primary care may play a critical role in the early detection of skin cancer. Dermoscopy improves diagnostic accuracy; however, its use among primary care DOs remains understudied.
OBJECTIVES
To document dermascope use among DOs in primary care, to examine physician and practice characteristics associated with having used and having heard of a dermascope, and to examine the barriers to dermascope use.
METHODS
Osteopathic physicians were recruited to complete an anonymous survey assessing demographic factors, physician and practice characteristics, confidence in differentiating skin lesions, knowledge and dermascope use, and barriers to dermascope use. Bivariate analyses were conducted, and the significant factors were entered into 2 separate logistic regressions.
RESULTS
A total of 768 participants were included in the study. Four hundred ten (54%) had heard of a dermascope, and 123 (15%) had used one. The statistically significant multivariate predictors for having used a dermascope (model 1) were graduating from medical school after 1989 and having greater confidence in differentiating skin lesions (OR, 2.2; 95% CI, 1.66-2.79). Those who graduated after 2009 were 9.5 times more likely and those graduating between 2000 and 2009 were 4.3 times more likely to have used a dermascope than those graduating before 1990 (95% CI, 4.29-20.90 and 95% CI, 2.04-9.23, respectively). Ever having heard of a dermascope (model 2) was associated with being female (OR, 1.4; 95% CI, 1.02-1.87); practicing in a group (OR, 1.6; 95% CI, 1.05-2.36), academic (OR, 2.2; 95% CI, 1.26-3.86), or community center (OR, 2.2; 95% CI, 1.20-4.00); and having greater confidence in differentiating skin lesions (OR, 1.3; 95% CI, 1.15-1.55). Both models were statistically significant and correctly classified 605 (84.1%) (model 1) and 444 (58.4%) participants (model 2).
CONCLUSION
Dermascope use could help primary care DOs improve their diagnostic accuracy for skin cancer and reduce unnecessary referrals to specialists. Efforts to disseminate knowledge about the benefits of using a dermascope to primary care DOs are needed.
Topics: Confidence Intervals; Cross-Sectional Studies; Dermoscopy; Early Detection of Cancer; Female; Humans; Logistic Models; Male; Odds Ratio; Osteopathic Physicians; Practice Patterns, Physicians'; Primary Health Care; Skin Neoplasms; Surveys and Questionnaires; United States
PubMed: 28241327
DOI: 10.7556/jaoa.2017.030 -
Journal of Biomedical Optics Jun 2022Accurate early diagnosis of malignant skin lesions is critical in providing adequate and timely treatment; unfortunately, initial clinical evaluation of similar-looking...
SIGNIFICANCE
Accurate early diagnosis of malignant skin lesions is critical in providing adequate and timely treatment; unfortunately, initial clinical evaluation of similar-looking benign and malignant skin lesions can result in missed diagnosis of malignant lesions and unnecessary biopsy of benign ones.
AIM
To develop and validate a label-free and objective image-guided strategy for the clinical evaluation of suspicious pigmented skin lesions based on multispectral autofluorescence lifetime imaging (maFLIM) dermoscopy.
APPROACH
We tested the hypothesis that maFLIM-derived autofluorescence global features can be used in machine-learning (ML) models to discriminate malignant from benign pigmented skin lesions. Clinical widefield maFLIM dermoscopy imaging of 41 benign and 19 malignant pigmented skin lesions from 30 patients were acquired prior to tissue biopsy sampling. Three different pools of global image-level maFLIM features were extracted: multispectral intensity, time-domain biexponential, and frequency-domain phasor features. The classification potential of each feature pool to discriminate benign versus malignant pigmented skin lesions was evaluated by training quadratic discriminant analysis (QDA) classification models and applying a leave-one-patient-out cross-validation strategy.
RESULTS
Classification performance estimates obtained after unbiased feature selection were as follows: 68% sensitivity and 80% specificity with the phasor feature pool, 84% sensitivity, and 71% specificity with the biexponential feature pool, and 84% sensitivity and 32% specificity with the intensity feature pool. Ensemble combinations of QDA models trained with phasor and biexponential features yielded sensitivity of 84% and specificity of 90%, outperforming all other models considered.
CONCLUSIONS
Simple classification ML models based on time-resolved (biexponential and phasor) autofluorescence global features extracted from maFLIM dermoscopy images have the potential to provide objective discrimination of malignant from benign pigmented lesions. ML-assisted maFLIM dermoscopy could potentially assist with the clinical evaluation of suspicious lesions and the identification of those patients benefiting the most from biopsy examination.
Topics: Dermoscopy; Humans; Machine Learning; Melanoma; Sensitivity and Specificity; Skin Neoplasms
PubMed: 35701871
DOI: 10.1117/1.JBO.27.6.066002 -
Computational and Mathematical Methods... 2022The objective of this study was to explore the image classification and case characteristics of pigmented nevus (PN) diagnosed by dermoscopy under deep learning. 268... (Randomized Controlled Trial)
Randomized Controlled Trial
The objective of this study was to explore the image classification and case characteristics of pigmented nevus (PN) diagnosed by dermoscopy under deep learning. 268 patients were included as the research objects and they were randomly divided into observation group ( = 134) and control group ( = 134). Image recognition algorithm was used for feature extraction, segmentation, and classification of dermoscopic images, and the image recognition and classification algorithm were studied as the performance and accuracy of fusion classifier were compared. The results showed that the classifier was optimized, and the linear kernel accuracy was 85.82%. The PN studied mainly included mixed nevus, junctional nevus, intradermal nevus, and acral nevus. The sensitivity under collaborative training was higher than that under feature training and fusion feature training, and the differences among three trainings were significant ( < 0.05). The sensitivity of the observation group was 88.65%, and the specificity was 90.26%, while the sensitivity and the specificity of the control group were 85.65% and 84.03%, respectively; there were significant differences between the two groups ( < 0.05). In conclusion, dermoscopy under deep learning could be applied as a diagnostic way of PN, which helped improve the accuracy of diagnosis. The dermoscopic manifestations of PN showed a certain corresponding relationship with the type of cases and could provide auxiliary diagnosis in clinical practice. It could be applied clinically.
Topics: Deep Learning; Dermoscopy; Humans; Melanoma; Nevus; Nevus, Pigmented; Skin Neoplasms
PubMed: 35669372
DOI: 10.1155/2022/9726181 -
Anais Brasileiros de Dermatologia 2017Dermoscopy is a non-invasive technique widely used to aid in the characterization and diagnosis of pigmented skin lesions. Recently, it has also been employed for the...
Dermoscopy is a non-invasive technique widely used to aid in the characterization and diagnosis of pigmented skin lesions. Recently, it has also been employed for the evaluation of non-pigmented skin tumours, and inflammatory and infectious cutaneous diseases. Although the diagnosis of cutaneous leishmaniasis is confirmed by the demonstration of amastigotes in infected skin or by the growth of promastigotes in culture medium, dermoscopy could be useful as a further diagnostic test. We report a patient with a nodular lesion located on the right cheek for almost two years. The lesion was clinically suggestive of cutaneous leishmaniasis. Dermoscopy showed yellow tears, erythema and vascular structures. The diagnosis was confirmed by the demonstration of amastigotes in a skin scraping sample.
Topics: Cheek; Child, Preschool; Dermoscopy; Facial Dermatoses; Female; Humans; Leishmaniasis, Cutaneous; Leprostatic Agents; Rifampin; Treatment Outcome
PubMed: 29364445
DOI: 10.1590/abd1806-4841.20174441 -
Skin Research and Technology : Official... Jan 2024Recognizing Langerhans cell histiocytosis (LCH) might be a challenge due to its rarity. Reflectance confocal microscopy (RCM) and dermoscopy were emergent promising...
BACKGROUND
Recognizing Langerhans cell histiocytosis (LCH) might be a challenge due to its rarity. Reflectance confocal microscopy (RCM) and dermoscopy were emergent promising non-invasive technique as auxiliary tools in diagnosis of different skin conditions. However, the RCM and dermoscopic features of LCH had been less investigated. To reveal the common RCM and dermoscopic features of LCH.
MATERIALS AND METHODS
Forty cases of LCH were retrospectively analyzed according to age, locations, clinical, RCM, and dermoscopic features from September 2016 to December 2022. To reveal the differences and common in clinical, RCM, and dermoscopic features that occur in different anatomic location.
RESULTS
In the study, sites of predilection include the trunk 31/40 (77.5%), extremity 21/40 (52.5%), face 14/40 (35%), scalp 11/40 (27.5%), vulvar 4/40 (10%), and nail 2/40 (5%). All LCHs had the common RCM features. There were significant differences in clinical and dermoscopic features for age and lesion anatomic site. The common dermoscopic features for scalp, face, trunk, and extremity were the erythematous scaly rash, purplish-red globules or patches, scar-like streaks with ectatic vessels. While the features for nail LCH were purpuric striae, onycholysis and purulent scaly rash, and the erosive erythematous plaque and purulent scaly rash for vulvar LCH. The common RCM features of all LCH showed a focal highly reflective dense image in the surface keratin layer, epidermis architectural disarray, obscuration of dermo-epidermal junction, numerous polygonal, large, medium reflective, short dendrites cells in the epidermis, and dermis. All LCH involving the vulvar and nail did not manifest skin lesions.
CONCLUSION
RCM and dermoscopy showed promising value for diagnosis and differentiation of LCH.
Topics: Humans; Skin Neoplasms; Melanoma; Dermoscopy; Retrospective Studies; Diagnosis, Differential; Microscopy, Confocal; Exanthema
PubMed: 38235933
DOI: 10.1111/srt.13584 -
The Journal of Investigative Dermatology Apr 2016In this article we discuss the development of noninvasive imaging modalities to help delineate tumor margins of basal cell carcinomas in the setting of Mohs micrographic... (Review)
Review
In this article we discuss the development of noninvasive imaging modalities to help delineate tumor margins of basal cell carcinomas in the setting of Mohs micrographic surgery. A review of the available literature reveals that dermoscopy can help delineate basal cell carcinomas before surgical removal but that it has no benefit over clinical inspection in reducing the number of Mohs stages. In contrast, fluorescence confocal microscopy has a sensitivity of 88-96% and specificity of 89-99% for the detection of basal cell carcinomas and can potentially serve as a rapid means for tumor evaluation on ex vivo specimens. Optical coherence tomography has shown some success in the presurgical evaluation of tumor margins in vivo, before surgical excision. With ongoing developments in device portability, speed of image retrieval, and image resolution, these technologies are likely to gain traction in cutaneous oncology research and practice. It is therefore important for dermatology clinicians and researchers to understand the mechanisms, principal uses, advantages, and limitations of each device.
Topics: Carcinoma, Basal Cell; Dermoscopy; Diagnostic Imaging; Humans; Microscopy, Confocal; Neoplasm Staging; Reproducibility of Results; Sensitivity and Specificity; Skin Neoplasms; Tomography, Optical Coherence
PubMed: 27012561
DOI: 10.1016/j.jid.2016.02.012 -
International Journal of Molecular... Dec 2020Melanoma is the deadliest form of skin cancer and remains a diagnostic challenge in the dermatology clinic. Several non-invasive imaging techniques have been developed... (Review)
Review
Melanoma is the deadliest form of skin cancer and remains a diagnostic challenge in the dermatology clinic. Several non-invasive imaging techniques have been developed to identify melanoma. The signal source in each of these modalities is based on the alteration of physical characteristics of the tissue from healthy/benign to melanoma. However, as these characteristics are not always sufficiently specific, the current imaging techniques are not adequate for use in the clinical setting. A more robust way of melanoma diagnosis is to "stain" or selectively target the suspect tissue with a melanoma biomarker attached to a contrast enhancer of one imaging modality. Here, we categorize and review known melanoma diagnostic biomarkers with the goal of guiding skin imaging experts to design an appropriate diagnostic tool for differentiating between melanoma and benign lesions with a high specificity and sensitivity.
Topics: Biomarkers, Tumor; Dermoscopy; Humans; Melanoma
PubMed: 33339193
DOI: 10.3390/ijms21249583 -
Dermatology (Basel, Switzerland) 2022Timely diagnosis is the cornerstone of melanoma morbidity and mortality reduction. 2D total body photography and dermoscopy are routinely used to assist with early...
BACKGROUND
Timely diagnosis is the cornerstone of melanoma morbidity and mortality reduction. 2D total body photography and dermoscopy are routinely used to assist with early detection of skin malignancies. Polarized 3D total body photography is a novel technique that enables fast image acquisition of almost the entire skin surface. We aimed to determine the added value of 3D total body photography alongside dermoscopy for monitoring cutaneous lesions.
METHODS
Lesion images from high-risk individuals were assessed for long-term substantial changes via dermoscopy and 3D total body photography. Three case studies are presented demonstrating how 3D total body photography may enhance lesion analysis alongside traditional dermoscopy.
RESULTS
3D total body photography can assist clinicians by presenting cutaneous lesions in their skin ecosystem, thereby providing additional clinical context and enabling a more holistic assessment to aid dermoscopy interpretation. For lesion cases where previous dermoscopy is unavailable, corresponding 3D images can substitute for baseline dermoscopy. Additionally, 3D total body photography is not susceptible to artificial stretch artefacts.
CONCLUSION
3D total body photography is valuable alongside dermoscopy for monitoring cutaneous lesions. Furthermore, it is capable of surveilling almost the entire skin surface, including areas not traditionally monitored by sequential imaging.
Topics: Adult; Aged; Dermoscopy; Female; Humans; Imaging, Three-Dimensional; Male; Melanoma; Middle Aged; Multimodal Imaging; Photography; Skin; Skin Neoplasms
PubMed: 34380140
DOI: 10.1159/000517900