scholarly journals Performance of Artificial Intelligence Imaging Models in Detecting Dermatological Manifestations in Higher Fitzpatrick Skin Color Classifications (Preprint)

2021 ◽  
Author(s):  
Pushkar Aggarwal
Keyword(s):  
Artificial Intelligence ◽  
Basal Cell Carcinoma ◽  
Cell Carcinoma ◽  
Image Recognition ◽  
Basal Cell ◽  
Predictive Value ◽  
Skin Color ◽  
Dermatological Diseases ◽  
Light Skin ◽  
Artificial Intelligence Models

BACKGROUND The performance of deep-learning image recognition models is below par when applied to images with Fitzpatrick classification skin types 4 and 5. OBJECTIVE The objective of this research was to assess whether image recognition models perform differently when differentiating between dermatological diseases in individuals with darker skin color (Fitzpatrick skin types 4 and 5) than when differentiating between the same dermatological diseases in Caucasians (Fitzpatrick skin types 1, 2, and 3) when both models are trained on the same number of images. METHODS Two image recognition models were trained, validated, and tested. The goal of each model was to differentiate between melanoma and basal cell carcinoma. Open-source images of melanoma and basal cell carcinoma were acquired from the Hellenic Dermatological Atlas, the Dermatology Atlas, the Interactive Dermatology Atlas, and DermNet NZ. RESULTS The image recognition models trained and validated on images with light skin color had higher sensitivity, specificity, positive predictive value, negative predictive value, and F1 score than the image recognition models trained and validated on images of skin of color for differentiation between melanoma and basal cell carcinoma. CONCLUSIONS A higher number of images of dermatological diseases in individuals with darker skin color than images of dermatological diseases in individuals with light skin color would need to be gathered for artificial intelligence models to perform equally well.

scholarly journals Performance of Artificial Intelligence Imaging Models in Detecting Dermatological Manifestations in Higher Fitzpatrick Skin Color Classifications

10.2196/31697 ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. e31697
Author(s):  
Pushkar Aggarwal
Keyword(s):  
Artificial Intelligence ◽  
Basal Cell Carcinoma ◽  
Cell Carcinoma ◽  
Image Recognition ◽  
Basal Cell ◽  
Predictive Value ◽  
Skin Color ◽  
Dermatological Diseases ◽  
Light Skin ◽  
Artificial Intelligence Models

Background The performance of deep-learning image recognition models is below par when applied to images with Fitzpatrick classification skin types 4 and 5. Objective The objective of this research was to assess whether image recognition models perform differently when differentiating between dermatological diseases in individuals with darker skin color (Fitzpatrick skin types 4 and 5) than when differentiating between the same dermatological diseases in Caucasians (Fitzpatrick skin types 1, 2, and 3) when both models are trained on the same number of images. Methods Two image recognition models were trained, validated, and tested. The goal of each model was to differentiate between melanoma and basal cell carcinoma. Open-source images of melanoma and basal cell carcinoma were acquired from the Hellenic Dermatological Atlas, the Dermatology Atlas, the Interactive Dermatology Atlas, and DermNet NZ. Results The image recognition models trained and validated on images with light skin color had higher sensitivity, specificity, positive predictive value, negative predictive value, and F1 score than the image recognition models trained and validated on images of skin of color for differentiation between melanoma and basal cell carcinoma. Conclusions A higher number of images of dermatological diseases in individuals with darker skin color than images of dermatological diseases in individuals with light skin color would need to be gathered for artificial intelligence models to perform equally well.

scholarly journals Differences in age and topographic distribution of the different histological subtypes of basal cell carcinoma, Taubaté (SP), Brazil

2013 ◽  
Vol 88 (5) ◽  
pp. 726-730 ◽  
Author(s):  
Flavia Regina Ferreira ◽  
Bruna da Costa Pevide ◽  
Rafaela Fabri Rodrigues ◽  
Luiz Fernando Costa Nascimento ◽  
Marcia Lanzoni de Alvarenga Lira
Keyword(s):  
Basal Cell Carcinoma ◽  
Cell Carcinoma ◽  
Basal Cell ◽  
Skin Color ◽  
Age Of Onset ◽  
The Body ◽  
University Hospital ◽  
Histological Subtype ◽  
Histological Subtypes ◽  
The Mean

BACKGROUND: Basal cell carcinoma is the most common form of cancer in humans. OBJECTIVES: To identify the epidemiology of basal cell carcinoma in Taubaté-SP and verify a possible association between topography and the different histological subtypes of this tumor. METHODS: This was a cross-sectional study conducted at The University Hospital of Taubaté between 01/01/08 and 12/31/09. The study included patients with a confirmed diagnosis of basal cell carcinoma, of both genders, without age restrictions. The variables studied were incidence of basal cell carcinoma, topography, histological subtype, skin color, age and gender. We employed the chi-square test to identify the association between histological subtype and topography, and the student's t test to compare the mean age of onset for the different histological subtypes. RESULTS: The study included 239 individuals. The mean age of the sample was 68.0 years. Male subjects (57.7%) and whites (87.1%) predominated in the study. The predominant histological subtype was nodular (34.7%), followed by the superficial subtype. The most frequent sites of involvement were the head and neck (areas exposed to light), with predominance of the nasal region. The superficial subtype was an exception, as it showed a strong association with unexposed areas like the trunk. The mean age of onset of superficial basal cell carcinoma also differed from that of the other histological subtypes, 63.0 and 69.0 years, respectively. CONCLUSION: The results of this study suggest an association of the superficial histological subtype with younger patients and unexposed areas of the body, linking this type of tumor with a pattern of intermittent sun exposure, more similar to the standard photocarcinogenesis of melanoma.

scholarly journals The Safety and Effectiveness of Elastic Scattering Spectroscopy and Machine Learning in the Evaluation of Skin Lesions for Cancer

Iproceedings ◽  
10.2196/35441 ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. e35441
Author(s):  
Cristiane Benvenuto-Andrade ◽  
A Cognetta ◽  
D Manolakos
Keyword(s):  
Squamous Cell Carcinoma ◽  
Elastic Scattering ◽  
Basal Cell Carcinoma ◽  
Cell Carcinoma ◽  
Squamous Cell ◽  
Basal Cell ◽  
Predictive Value ◽  
Prevalence Rate ◽  
Skin Lesions ◽  
Elastic Scattering Spectroscopy

Background Elastic scattering spectroscopy (ESS) is an optical biopsy technique that can distinguish between a normal and abnormal tissue in vivo without the need to remove it. The handheld device measures ESS spectra of skin lesions and classifies lesions as either malignant or benign with an output of “Investigate Further” or “Monitor,” respectively, with positive results accompanied by a spectral score output from 1 to 10, indicating how similar the lesion is to the malignant lesions the device was trained on. The algorithm was trained and validated with over 11,000 spectral scans from over 3500 skin lesions. Objective The purpose of this study was to evaluate the safety and effectiveness of the handheld ESS device in detecting the most common types of skin cancer. Methods A prospective, single-arm, investigator-blinded, multicenter study conducted at 4 investigational sites in the United States was performed. Patients who presented with skin lesions suggestive of melanoma, basal cell carcinoma, squamous cell carcinoma, and other highly atypical lesions were evaluated with the handheld ESS device. A validation performance analysis was performed with 553 lesions from 350 subjects with algorithm version 2.0. An independent test set of 281 lesions was selected and used to evaluate device performance in the detection of melanoma, basal cell carcinoma (BCC), and squamous cell carcinoma (SCC). Statistical analyses included overall effectiveness analyses for sensitivity and specificity as well as subgroup analyses for lesion diagnoses. Results The overall sensitivity of the device was 92.3% (95% CI: 87.1 to 95.5%). The sensitivity for subgroups of lesions was 95% (95% CI 75.1% to 99.9%) for melanomas, 94.4% (95% CI 86.3% to 98.4%) for BCCs, and 92.5% (95% CI 83.4% to 97.5%) for SCCs. The overall device specificity was 36.6% (95% CI 29.3% to 44.6%). There was no statistically significant difference between the dermatologist performance and the ESS device (P=.2520). The specificity of the device was highest for benign melanocytic nevi (62.5%) and seborrheic keratoses (78.2%). The overall positive predictive value (PPV) was 59.8%, and the negative predictive value (NPV) was 81.9% with the study’s malignancy prevalence rate of 51%. For a prevalence rate of 5%, the PPV was estimated to be 7.1%, and the NPV was estimated to be 98.9%. For a prevalence rate of 7%, the PPV was estimated to be 9.8%, and the NPV was estimated to be 98.4%. For a prevalence rate of 15%, the PPV was estimated to be 20.3%, and the NPV was 96.4%. Conclusions The handheld ESS device has a high sensitivity for the detection of melanoma, BCC, and SCC. Coupled with clinical exam findings, this device can aid physicians in detecting a variety of skin malignancies. The device output can aid teledermatology evaluations by helping frontline providers determine which lesions to share for teledermatologist evaluation as well as potentially benefitting teledermatologists’ virtual evaluation, especially in instances of suboptimal photo quality. Acknowledgments This study was sponsored by Dermasensor Inc. Conflicts of Interest None declared.

scholarly journals Coding and noncoding somatic mutations in basal cell carcinoma

2019 ◽  
Author(s):  
Maria Giovanna Maturo ◽  
Sivaramakrishna Rachakonda ◽  
Barbara Heidenreich ◽  
Cristina Pellegrini ◽  
Nalini Srinivas ◽  
...  
Keyword(s):  
Basal Cell Carcinoma ◽  
Reverse Transcriptase ◽  
Cell Carcinoma ◽  
Basal Cell ◽  
Skin Color ◽  
Human Cancer ◽  
Sun Exposure ◽  
European Ancestry ◽  
History Of ◽  
Promoter Mutations

AbstractBasal cell carcinoma (BCC) represents the most commonly diagnosed human cancer among persons of European ancestry with etiology mainly attributed to sun-exposure. In this study we investigated mutations in coding and flanking regions of the PTCH1 and TP53 genes and noncoding alterations in the TERT and DPH3 promoters in 191 BCC tumors. In addition, we measured CpG methylation within the TERT hypermethylated oncological region (THOR) and transcriptions levels of the reverse transcriptase subunit. We observed mutations in PTCH1 in 59% and TP53 in 31% of the tumors. Noncoding mutations in TERT and DPH3 promoters were detected in 59% and 38% of the tumors, respectively. We observed a statistically significant co-occurrence of mutations at the four investigated loci. While PTCH1 mutations tended to associate with decreased patient age at diagnosis; TP53 mutations were associated with light skin color and increased number of nevi; TERT and DPH3 promoter with history of cutaneous neoplasms in BCC patients. TERT promoter mutations but not THOR methylation associated with an increased expression of the reverse transcriptase subunit. Our study signifies, in addition to the protein altering mutations in the PTCH1 and TP53 genes, the importance of noncoding mutations in BCC, particularly functional alterations in the TERT promoter.

Predictive value of basal cell carcinoma biopsies with negative margins: A retrospective cohort study

2018 ◽  
Vol 79 (1) ◽  
pp. 42-46 ◽  
Author(s):  
Hal Bret Willardson ◽  
Jamie Lombardo ◽  
Matt Raines ◽  
Tina Nguyen ◽  
Jisuk Park ◽  
...  
Keyword(s):  
Cohort Study ◽  
Basal Cell Carcinoma ◽  
Cell Carcinoma ◽  
Basal Cell ◽  
Retrospective Cohort Study ◽  
Predictive Value ◽  
Retrospective Cohort

scholarly journals Diagnosis of aggressive subtypes of eyelid basal cell carcinoma by 2-mm punch biopsy: prospective and comparative study

2016 ◽  
Vol 43 (4) ◽  
pp. 262-269
Author(s):  
LUIZ ANGELO ROSSATO ◽  
Rachel Camargo Carneiro ◽  
Erick Marcet Santiago de Macedo ◽  
Patrícia Picciarelli de Lima ◽  
Ahlys Ayumi Miyazaki ◽  
...  
Keyword(s):  
Basal Cell Carcinoma ◽  
Cell Carcinoma ◽  
Basal Cell ◽  
Predictive Value ◽  
Gold Standard ◽  
Punch Biopsy ◽  
Surgical Specimen ◽  
Significant Difference ◽  
Group 2 ◽  
Group 1

ABSTRACT Objective : to compare the accuracy of preoperative 2-mm punch biopsy at one site and at two sites in the diagnosis of aggressive subtypes of eyelid basal cell carcinoma (BCC). Methods : we randomly assigned patients to Group 1 (biopsy at one site) and Group 2 (biopsy at two sites). We compared the biopsy results to the gold standard (pathology of the surgical specimen). We calculated the sensitivity, specificity, positive predictive value, negative predictive value, accuracy and Kappa coefficient to determine the level of agreement in both groups. Results : we analyzed 105 lesions (Group 1: n = 44; Group 2: n = 61). The agreement was 54.5% in Group 1 and 73.8% in Group 2 (p = 0.041). There was no significant difference between the groups regarding the distribution of quantitative and qualitative variables (gender, age, disease duration, tumor larger diameter, area and commitment of margins). Biopsy at two sites was two times more likely to agree with the gold standard than the biopsy of a single site. Conclusions : the accuracy and the performance indicators were better for 2-mm punch biopsy in two sites than in one site for the diagnosis of aggressive subtypes of eyelid BCC.

Sign in / Sign up

Export Citation Format

Share Document