DermEngine's AI: Answers To Your Most Frequently Asked Questions

by The DermEngine Team on Apr 5, 2019

DermEngine utilizes the latest innovations in artificial intelligence (AI) to provide its users with cutting-edge technology for imaging, analyzing and documenting within their daily practice. As part of our initiative to provide innovative services, we'd like to take this opportunity to answer your important questions about our algorithms and their usage within DermEngine.

How does DermEngine's Visual Search* work?
By integrating AI decision support tools into DermEngine, we have provided an accessible way for doctors to access additional educational information when making a diagnosis. Features such as Visual Search provide an easy workflow for doctors to query an image of a skin lesion under investigation against our large database of pre-labelled skin images which were previously identified following excision and pathological analysis or by our expert dermatologists for certain benign cases. Visual Search will return a list of the most visually similar lesions and statistics on their aggregate results.

How were the algorithms tested?
Our skin lesion classification algorithm won the international ISIC 2018 Skin Lesion Diagnosis challenge by a large margin. Participants were provided with a held-out test set to predict the diagnosis of 1512 skin lesions from 7 possible disease classes. Our method scored and balanced accuracy across all 7 classes with 88.5% and is now ready to undergo clinical trials for further evaluation of its use in a clinical setting. When complete, this holds the potential to be utilized as an invaluable second opinion tool capable of screening a large number of skin lesions, allowing for the most concerning cases to receive priority attention. However, the algorithms utilized within the Visual Search tool are to be used in an educational capacity to show similar cases and help as a learning tool for identification and matching.

Do the images I take get used to enhance DermEngine’s AI?
DermEngine is an intelligent system that is designed to use the power of data to improve its services to its users. DermEngine may use fully-anonymized data to enhance its services to the providers subject to privacy regulations and based on our Terms of Service. However, no data will be transferred or sold to a third party. You can read more in our Privacy Policy.

Do other clinics see my images?
Your patient data is private and it belongs to your patients and their providers. However anonymized data may be used to optimize the algorithms of DermEngine’s smart tools for your use. Additionally, DermEngine's AI is designed to help with your workflow and offers smart features such as Smart Snap in which the algorithms are used to match cases for you quickly identify spots.  MetaOptima does not use patients’ personal information or disclose their personal data and images to any third party, however anonymized images may be used to optimize the system for your clinical use and improving the efficiency of DermEngine.

Do I need to get consent from patients because you might use those images to enhance AI?
No, dermoscopic images are not considered personal health information in most jurisdictions (observe local regulations if necessary), since it is not possible to identify an individual by looking at dermoscopic images. You only need consent to collect, use and disclose identifiable health information.

What if I don't want my images to contribute to AI enhancements in DermEngine?
According to DermEngine Terms of Service, MetaOptima retains the right to use or share any Aggregated Data generated by anyone using our Site, including our users, for the purpose of enhancing and providing the Services.  “Aggregated Data” means data does not contain personal information and which has been manipulated or combined to provide generalized, anonymous information. Where you choose to utilize our Services, you agree that MetaOptima can use data to enhance its Services as an automatic feature on the system.

Where can I find more scientific information about Visual Search?
Would you like to learn more about MetaOptima's research in the areas of artificial intelligence in dermatology? Click the publication links below:

  1. Tschandl, P., Argenziano, G., Razmara, M., Yap, J. (2018). Diagnostic accuracy of content‐based dermatoscopic image retrieval with deep classification features. British Journal of Dermatology
  2. Yap, J., Yolland, W., Tschandl, P. (2018). Multimodal skin lesion classification using deep learning. Experimental Dermatology


Knowledge Base Links
Are you already a member on DermEngine? Visit our Knowledge Base to learn more about getting started with Visual Search:

How Do I Use Visual Search?
How Do I Use Region Search?
How Can I Revise My Results On Visual Search?

-The MetaOptima Team

Do you have any additional questions about DermEngine, it's artificial intelligence algorithms or our policies? Email us today and one of our experts will get back to you shortly

Request A Demo 

 

*Please note that Visual Search is for educational purposes only. It is not a diagnostic tool and does not replace the consultation of a trained medical professional.

Topics: Dermatology Artificial Intelligence AI Advanced Dermatology Artificial Intelligence in Dermatology AI In Healthcare Dermatology EMR Dermatology Software Dermatology EMR Software