The clinical utility of teledermoscopy in the era of telemedicine

Uppal, S. K.; Beer, Jacob; Hadeler, Edward; Gitlow, Howard S.; Nouri, Keyvan

doi:10.1111/dth.14766

Cited by 26 publications

(24 citation statements)

References 14 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maps can be constructed from measurements done directly on the patient prior to lesion excision in cases where extensive surgery may be needed to remove the entire tumor in one step. VOCT and dermoscopic observations in conjunction with artificial intelligence can be used to diagnose difficult skin lesions and improve the clinical utility of teledermoscopy [ 39 ].…”

Section: Discussionmentioning

confidence: 99%

The “Virtual Biopsy” of Cancerous Lesions in 3D: Non-Invasive Differentiation between Melanoma and Other Lesions Using Vibrational Optical Coherence Tomography

Silver

Deshmukh²,

Kelkar³

et al. 2021

Dermatopathology

View full text Add to dashboard Cite

Early detection of skin cancer is of critical importance to provide five year survival rates that approach 99%. By 2050, one out of five Americans by age 70 will develop some form of skin cancer. This will result in a projected rate of 50 million skin biopsies per year given the current rate of escalation. In addition, the ability to differentiate between pigmented lesions and melanomas has proven a diagnostic challenge. While dermoscopy and visual analysis are useful in identifying many skin lesions, additional non-invasive techniques are needed to assist in the analysis of difficult to diagnose skin tumors. To augment dermoscopy data, we have developed 3D maps based on physical biomarker characteristics of benign and cancerous lesions using vibrational optical coherence tomography (VOCT). 3D images based on quantitative physical data involving changes in cellular and fibrous tissue stiffness along with changes in vascular quality are used to map and evaluate different types of cancers. 3D tumor maps constructed using quantitative VOCT data and OCT images have been used to characterize the differences between melanoma and other lesions. These characteristics can be used to plan the excision of difficult lesions where extensive surgery may be needed to remove the entire tumor in one step. In addition, it is now possible to use dermoscopy and VOCT to non-invasively differentiate between different cancerous lesion types using measurements of the resonant frequency of new cellular and vascular peaks. Quantitative VOCT information along with dermoscopic findings can be collected and analyzed remotely using artificial intelligence to improve cancerous tissue diagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

The “Virtual Biopsy” of Cancerous Lesions in 3D: Non-Invasive Differentiation between Melanoma and Other Lesions Using Vibrational Optical Coherence Tomography

Silver

Deshmukh²,

Kelkar³

et al. 2021

Dermatopathology

View full text Add to dashboard Cite

show abstract

“…Nouri et al reported lower telehealth use in Black/African American and Latinx patients in an urban safety net, highlighting the role of entrenched systemic racism in health care[ 21 ]. Health system level: Very few health care systems had robust telehealth use before the pandemic except tele-dermatology [ 22 ] and organizations like Kaiser Permanente [ 23 , 24 ] that had implemented telehealth visits before the pandemic. At the health system level, the clinic workflows designed for in-person visits need optimization for telehealth to ensure that critical care is not missed, and team-based care is seamlessly integrated into a telehealth model.…”

Section: Barriers To Telehealth Can Be Classified Into Four Different Levels Requiring Multilevel Approaches To Address Disparitiesmentioning

confidence: 99%

Disparities in telehealth use: How should the supportive care community respond?

Dixit

Sebille

Crawford

et al. 2021

Support Care Cancer

View full text Add to dashboard Cite

Telehealth use has increased in the setting of the COVID-19 pandemic. However, there are disparities in telehealth use based on age, income, race/ethnicity, low health, digital literacy, and limited English proficiency. There are multilevel barriers to telehealth use at the patient, health systems, telehealth portal, and policy levels. To ensure equity in telehealth services and to leverage these services to maximize the reach of health care services, concerted efforts are needed to design telehealth tools and workflows. It should include reimbursement for staff training, patient education, and technical support needed for telehealth use. Furthermore, ongoing monitoring and responsive modifications in the use of telehealth services are needed to promote telehealth equity.

show abstract

“…On the other hand. A hardware upgrade can also be a solution to this problem, there have been products such as the attachable dermatoscope that are made to fit mobile phones [33], this should theoretically solve the mobile image quality problem as well. However, its image quality will still have to be tested against the professional camera skin lesion images to prove its authenticity.…”

Section: Limitations and Future Workmentioning

confidence: 99%

A Deep learning based patient care application for skin cancer detection

Dong

Farid

2022

Preprint

View full text Add to dashboard Cite

Melanoma is one of the deadliest skin cancer. It can, however, be cured with a high success rate if found in the early stage. With the recent development in Artificial Intelligence (AI), there has been an increase in the research of Machine Learning (ML) and Deep Learning (DL) models for melanoma detection. However, such deployments are primarily trial-based and still waiting to gain wider acceptance from the practitioners. One of the primary reasons for such lower acceptance lies in the inherent approach and ethical concerns. To this end, our study designs a Deep Learning based recommendation application for the patients to advise whether they need to see a dermatologist based on provided skin lesion image. The traditional AI-based melanoma classifiers tend to be developed based on bulk image training and hence would classify images on an individual level. However, they neglect that a single skin lesion is merely a part of the patient. Thereby this research considers the contextual information between different lesions on the same patient. It produces a personalized patient classification rather than focusing on lesion level prediction. Several models are developed using ML and DL techniques, such as transfer learning and deep neural networks. These models are then tested on a real melanoma dataset with the true label provided. External benchmark is also established from recent similar studies using the same dataset. The best classifier achieves an 81.6% Area Under the Receiver Operating Characteristic Curve (AUROC) score using the patient's unique biological features.

show abstract

The clinical utility of teledermoscopy in the era of telemedicine

Cited by 26 publications

References 14 publications

The “Virtual Biopsy” of Cancerous Lesions in 3D: Non-Invasive Differentiation between Melanoma and Other Lesions Using Vibrational Optical Coherence Tomography

The “Virtual Biopsy” of Cancerous Lesions in 3D: Non-Invasive Differentiation between Melanoma and Other Lesions Using Vibrational Optical Coherence Tomography

Disparities in telehealth use: How should the supportive care community respond?

A Deep learning based patient care application for skin cancer detection

Contact Info

Product

Resources

About