Using Dermoscopy to Identify Melanoma and Improve Diagnostic Discrimination.
Ontology highlight
ABSTRACT:
SUBMITTER: Holmes GA
PROVIDER: S-EPMC6375419 | biostudies-literature | 2018 May
REPOSITORIES: biostudies-literature
Publications
Using Dermoscopy to Identify Melanoma and Improve Diagnostic Discrimination.
Holmes G Alden GA Vassantachart Janna M JM Limone Brittanya A BA Zumwalt Michael M Hirokane Jane J Jacob Sharon E SE
Federal practitioner : for the health care professionals of the VA, DoD, and PHS 20180501 Suppl 4
Use of dermoscopy and detection algorithms by primary care physicians can enhance assessment of clinically suspicious lesions compared with that of naked eye examinations. ...[more]
Similar Datasets
Project description:Background/purposeAcral melanoma is the most common type of melanoma in Asians, and usually results in a poor prognosis due to late diagnosis. We applied a convolutional neural network to dermoscopy images of acral melanoma and benign nevi on the hands and feet and evaluated its usefulness for the early diagnosis of these conditions.MethodsA total of 724 dermoscopy images comprising acral melanoma (350 images from 81 patients) and benign nevi (374 images from 194 patients), and confirmed by histopathological examination, were analyzed in this study. To perform the 2-fold cross validation, we split them into two mutually exclusive subsets: half of the total image dataset was selected for training and the rest for testing, and we calculated the accuracy of diagnosis comparing it with the dermatologist's and non-expert's evaluation.ResultsThe accuracy (percentage of true positive and true negative from all images) of the convolutional neural network was 83.51% and 80.23%, which was higher than the non-expert's evaluation (67.84%, 62.71%) and close to that of the expert (81.08%, 81.64%). Moreover, the convolutional neural network showed area-under-the-curve values like 0.8, 0.84 and Youden's index like 0.6795, 0.6073, which were similar score with the expert.ConclusionAlthough further data analysis is necessary to improve their accuracy, convolutional neural networks would be helpful to detect acral melanoma from dermoscopy images of the hands and feet.
| S-EPMC5841780 | biostudies-literature
Project description:The diagnostic accuracy of dermoscopy (DS) for scabies, a highly contagious parasitic disease, remains disputed. This study aimed to assess the diagnostic accuracy of DS in scabies, analyze the factors influencing DS, and explore its role in post-treatment evaluation. Patients with suspected scabies were randomly divided into 2 groups: 71 patients in the skin scraping (SS) group and 73 patients in the DS group. The diagnostic efficiencies of SS and DS in these groups were calculated. We also analyzed the influence of body part and investigator competence on the accuracy of DS. Then 16 body parts with typical signs of scabies were monitored by DS 2 and 4 day after sulfur ointment treatment. The sensitivity and specificity of DS were 98.3% and 88.5%, respectively. Hands, arms, and the abdomen had higher positivity rates than other body parts (P<0.001). The accuracy of dermatologists' interpretations of images negative for scabies in the intermediate- and high-level groups was higher than that in the low-level group (P<0.001). At follow-up, the mites were still visible on 43.8% to 62.5% of the skin lesions 2 and 4 day after sulfur ointment treatment. These results showed that DS could significantly increase the accuracy of diagnosing scabies owing to its high sensitivity and specificity. Therefore, it may be useful for monitoring clinical responses to anti-parasitic treatment.
| S-EPMC7806431 | biostudies-literature
Project description:ObjectivesEarly melanoma detection decreases morbidity and mortality. Early detection classically involves dermoscopy to identify suspicious lesions for which biopsy is indicated. Biopsy and histological examination then diagnose benign nevi, atypical nevi, or cancerous growths. With current methods, a considerable number of unnecessary biopsies are performed as only 11% of all biopsied, suspicious lesions are actually melanomas. Thus, there is a need for more advanced noninvasive diagnostics to guide the decision of whether or not to biopsy. Artificial intelligence can generate screening algorithms that transform a set of imaging biomarkers into a risk score that can be used to classify a lesion as a melanoma or a nevus by comparing the score to a classification threshold. Melanoma imaging biomarkers have been shown to be spectrally dependent in Red, Green, Blue (RGB) color channels, and hyperspectral imaging may further enhance diagnostic power. The purpose of this study was to use the same melanoma imaging biomarkers previously described, but over a wider range of wavelengths to determine if, in combination with machine learning algorithms, this could result in enhanced melanoma detection.MethodsWe used the melanoma advanced imaging dermatoscope (mAID) to image pigmented lesions assessed by dermatologists as requiring a biopsy. The mAID is a 21-wavelength imaging device in the 350-950 nm range. We then generated imaging biomarkers from these hyperspectral dermoscopy images, and, with the help of artificial intelligence algorithms, generated a melanoma Q-score for each lesion (0 = nevus, 1 = melanoma). The Q-score was then compared to the histopathologic diagnosis.ResultsThe overall sensitivity and specificity of hyperspectral dermoscopy in detecting melanoma when evaluated in a set of lesions selected by dermatologists as requiring biopsy was 100% and 36%, respectively.ConclusionWith widespread application, and if validated in larger clinical trials, this non-invasive methodology could decrease unnecessary biopsies and potentially increase life-saving early detection events. Lasers Surg. Med. 51:214-222, 2019. © 2019 The Authors. Lasers in Surgery and Medicine Published by Wiley Periodicals, Inc.
| S-EPMC6519386 | biostudies-literature
Project description:Desmoplastic melanoma (DM) is frequently misdiagnosed clinically and often associated with melanoma in situ (MIS).To improve the detection of DM using dermoscopy and reflectance confocal microscopy (RCM).A descriptive analysis of DM dermoscopy features and a case-control study within a melanoma population for RCM feature evaluation was performed blindly, using data obtained between 2005 and 2015. After retrospectively identifying all DM cases with RCM data over the study period (n = 16), a control group of non-DM melanoma patients with RCM data, in a ratio of at least 3 : 1, was selected. The control group was matched by age and primary tumour site location, divided into non-DM invasive melanomas (n = 27) and MIS (n = 27). Invasive melanomas were selected according to the melanoma subtypes associated with the DM cases. The main outcomes were the frequency of melanoma-specific features on dermoscopy for DM; and the odds ratios of RCM features to distinguish DM from MIS and/or other invasive melanomas; or MIS from the combined invasive melanoma group.At least one of the 14 melanoma-specific features evaluated on dermoscopy was found in 100% of DMs (n = 15 DM with dermoscopy). Known RCM melanoma predictors were commonly found in the DMs, such as pagetoid cells (100%) and cell atypia (100%). The RCM feature of spindle cells in the superficial dermis was more common in DM compared with the entire melanoma control group (OR 3.82, 95% CI 1.01-14.90), and particularly compared to MIS (OR 5.48, 95% CI 1.11-32.36). Nucleated cells in the dermis and the RCM correlate of dermal inflammation were also significant RCM features favouring DM over MIS, as well as invasive melanoma over MIS.Dermoscopy and RCM may be useful tools for the identification of DM. Certain RCM features may help distinguish DM from MIS and other invasive melanomas. Larger studies are warranted.
| S-EPMC5712285 | biostudies-other
Project description: Not available
| S-EPMC6517096 | biostudies-literature
Project description:ObjectiveMost skin lesions first present in primary care, where distinguishing rare melanomas from benign lesions can be challenging. Dermoscopy improves diagnostic accuracy among specialists and is promoted for use by primary care physicians (PCPs). However, when used by untrained clinicians, accuracy may be no better than visual inspection. This study aimed to undertake a systematic review of literature reporting use of dermoscopy to triage suspicious skin lesions in primary care settings, and challenges for implementation.DesignA systematic literature review and narrative synthesis.Data sourcesWe searched MEDLINE, Cochrane Central, EMBASE, Cumulative Index to Nursing and Allied Health Literature, and SCOPUS bibliographic databases from 1 January 1990 to 31 December 2017, without language restrictions.Inclusion criteriaStudies including assessment of dermoscopy accuracy, acceptability to patients and PCPs, training requirements, and cost-effectiveness of dermoscopy modes in primary care, including trials, diagnostic accuracy and acceptability studies.Results23 studies met the review criteria, representing 49 769 lesions and 3708 PCPs, all from high-income countries. There was a paucity of studies set truly in primary care and the outcomes measured were diverse. The heterogeneity therefore made meta-analysis unfeasible; the data were synthesised through narrative review. Dermoscopy, with appropriate training, was associated with improved diagnostic accuracy for melanoma and benign lesions, and reduced unnecessary excisions and referrals. Teledermoscopy-based referral systems improved triage accuracy. Only three studies examined cost-effectiveness; hence, there was insufficient evidence to draw conclusions. Costs, training and time requirements were considered important implementation barriers. Patient satisfaction was seldom assessed. Computer-aided dermoscopy and other technological advances have not yet been tested in primary care.ConclusionsDermoscopy could help PCPs triage suspicious lesions for biopsy, urgent referral or reassurance. However, it will be important to establish further evidence on minimum training requirements to reach competence, as well as the cost-effectiveness and patient acceptability of implementing dermoscopy in primary care.Trial registration numberCRD42018091395.
| S-EPMC6707687 | biostudies-literature
Project description:ImportanceSubungual melanoma in situ (SMIS) is a malignant neoplasm that requires early diagnosis and complete surgical excision; however, little is known about the usefulness of the detailed dermoscopic features of longitudinal melanonychia (LM) to predict the diagnosis of SMIS.ObjectivesTo investigate the characteristic dermoscopic findings of SMIS and to establish a predictive scoring model for the diagnosis of SMIS in patients with adult-onset LM affecting a single digit.Design, setting, and participantsA cohort study of 19 patients with biopsy-proven SMIS and 26 patients with benign LM diagnosed in a tertiary referral hospital in Seoul, South Korea, from September 1, 2013, to July 31, 2017.Main outcomes and measuresPatient demographics, frequency of specific dermoscopic findings, and a predictive scoring model.ResultsOf the total 45 patients with pigmented nails, the 19 patients with SMIS included 14 women and had a mean (SD) age of 52.0 (14.4) years, and the 26 patients with benign LM included 18 women and had a mean (SD) age of 48.1 (13.2) years. Asymmetry (odds ratio [OR], 34.00; 95% CI, 3.88-297.70), border fading (OR, 9.33; 95% CI, 2.37-36.70), multicolor (OR, 11.59; 95% CI, 2.21-60.89), width of the pigmentation of at least 3 mm (OR, 5.31; 95% CI, 1.01-28.07), and presence of the Hutchinson sign (OR, 18.18; 95% CI, 2.02-163.52) were features of LM that were significantly associated with SMIS. A predictive scoring model incorporating these dermoscopic features of SMIS was assessed. The model, ranging from 0 to 8 points, showed a reliable diagnostic value (the receiver operating characteristic curve had an area under the curve [C statistic] of 0.91) in differentiating SMIS from benign LM at a cutoff value of 3, with a sensitivity of 89% and a specificity of 62%.Conclusions and relevanceThis study suggests characteristic dermoscopic features for SMIS. A predictive scoring model based on these morphologic features may help differentiate SMIS from benign LM.
| S-EPMC6143019 | biostudies-literature
Project description:BackgroundMC1R polymorphisms interact with CDKN2A mutations modulating melanoma risk and contribute to a less suspicious clinical and dermoscopic appearance of melanomas. Different strategies, including dermoscopic comparative approach and digital monitoring, are used for the melanoma diagnosis in this context.ObjectiveTo analyse the diagnostic accuracy of the morphologic approach and comparative approach in dermoscopy, and to detect melanoma in familial melanoma (FamMM) patients according to different genetic backgrounds.MethodsTwo independent readers evaluated 415 lesions belonging to 25 FamMM: 26 melanomas (62% in situ, 36% early invasive) and 389 naevi, blinded for dermoscopic and histopathologic diagnosis, following two different steps. First step-Randomized: all lesions were randomly located in one single folder. Second step-Comparative approach: the lesions were clustered by patient. Sensitivity, specificity and number needed to excise (NNE) for melanoma diagnosis were calculated for both diagnostic strategies. Sensitivity and specificity were also assessed regarding the genetic background.ResultsThe comparative approach showed lower sensitivity compared to the morphologic approach (69.2 and 73.1 vs. 76.9 both readers) but better specificity (95.9 and 95.1 vs. 84.3 and 90.2, respectively). NNE was better in the comparative approach. The readers had more difficulties diagnosing lesions from CDKN2A mutation carriers with red hair colour (RHC) MC1R variants.ConclusionThe comparative approach can be useful in high-risk patients to decrease the NNE. Early melanomas in CDKN2A carriers with RHC polymorphisms are more difficult to diagnose even with the comparative approach and benefit from the detection of changes during digital dermoscopy monitoring for early diagnosis.
| S-EPMC9290446 | biostudies-literature
Project description:Multiple intravenous injections of a cDNA library, derived from human melanoma cell lines and expressed using the highly immunogenic vector vesicular stomatitis virus (VSV), cured mice with established melanoma tumors. Successful tumor eradication was associated with the ability of mouse lymphoid cells to mount a tumor-specific CD4(+) interleukin (IL)-17 recall response in vitro. We used this characteristic IL-17 response to screen the VSV-cDNA library and identified three different VSV-cDNA virus clones that, when used in combination but not alone, achieved the same efficacy against tumors as the complete parental virus library. VSV-expressed cDNA libraries can therefore be used to identify tumor rejection antigens that can cooperate to induce anti-tumor responses. This technology should be applicable to antigen discovery for other cancers, as well as for other diseases in which immune reactivity against more than one target antigen contributes to disease pathology.
| S-EPMC3891505 | biostudies-literature
Project description:When it comes to skin tumors and cancers, melanoma ranks among the most prevalent and deadly. With the advancement of deep learning and computer vision, it is now possible to quickly and accurately determine whether or not a patient has malignancy. This is significant since a prompt identification greatly decreases the likelihood of a fatal outcome. Artificial intelligence has the potential to improve healthcare in many ways, including melanoma diagnosis. In a nutshell, this research employed an Inception-V3 and InceptionResnet-V2 strategy for melanoma recognition. The feature extraction layers that were previously frozen were fine-tuned after the newly added top layers were trained. This study used data from the HAM10000 dataset, which included an unrepresentative sample of seven different forms of skin cancer. To fix the discrepancy, we utilized data augmentation. The proposed models outperformed the results of the previous investigation with an effectiveness of 0.89 for Inception-V3 and 0.91 for InceptionResnet-V2.
| S-EPMC10217211 | biostudies-literature