Modern smartphones have long ceased to be just communication terminals. Now these are multimedia centers, electronic libraries , and much more . Engineers have found a new, medical, application for smartphones – they help to recognize suspicious moles and marks on the skin. Nevertheless, in the event of such problems, it is still worth contacting a dermatologist.
Usually, recommendations for skin care appear on the eve of summer, but the skin can be damaged by ultraviolet rays regardless of the season and weather. The number of diagnoses of skin cancer exceeds the number of diagnoses of all other types of cancer each year. The good news is that early detection of the problem allows you to simply remove the mole and prevent it from developing into a malignant tumor that spreads throughout the body.
Several device and smartphone applications have appeared at once, which, according to their creators, help early detection of the problem. With these systems and regular self-diagnostics, users can have an idea of the condition of their skin. You can take pictures of suspicious moles yourself and observe them, or send the pictures to a dermatologist for evaluation. Either way, these apps can be useful, but they have their limitations. That is why it is important to follow generally accepted rules (for example, apply sunscreen to your skin) to protect yourself.
Important facts about skin cancer
Every year in the United States alone, doctors diagnose more than 4 million cases of non-melanoma (including basal and squamous cell) skin cancers. It is estimated that about 200,000 melanoma diagnoses will be made in America in 2020. Basal and squamous cell skin cancers develop on the outer layers of the skin and are more common, albeit less harmful, than melanoma.
Melanoma is considered the most deadly form of skin cancer. It is formed in cells responsible for skin pigmentation called melanocytes. This is an aggressive form of cancer, from which about 10 thousand people die each year in the United States. Even if detected early, it can be fatal.
Symptoms of all types of skin cancer include:
- change in the size or color of a mole or other spot on the skin;
- new growths on the skin;
- strange skin sensations such as constant itching or tenderness;
- spread of pigmentation beyond the border of the mole.
Skin cancer can develop due to a variety of factors, including genetics and exposure to toxic chemicals, but the most obvious link between skin cancer and UV exposure .
How an iPhone or Android smartphone can help detect skin cancer
Telemedicine is a growing area of focus and skin care. In recent years, many applications have been created that allow early detection of skin cancer. Smartphone and artificial intelligence help in this.
Some programs send pictures to the dermatologist, some provide instant feedback, and others offer helpful reminders to self-monitor your skin and schedule appointments with your doctor.
Here are some of these methods that you can use on iOS and Android.
Skinvine
This service was originally a telegram bot created by Belarusian developers , but now a full-fledged website has already appeared. Artificial intelligence allows you to identify skin neoplasms and classify them. To do this, in good lighting, from a distance of up to 10 centimeters, take a picture of a skin area and send the picture to the SkiniveBot bot . He will independently determine the percentage of the likelihood of the disease and will advise which doctor to contact with this problem: a dermatologist, cosmetologist or dermato-oncologist. If a high risk of disease is identified, the image will be processed manually, after which a recommendation will follow.
The bot is based on the authoritative Stanford study to determine melanoma in skin scans. Initially, the developers decided to try to implement this algorithm, and the successful result provided the basis for the detection of other common types of cancer – basal cell and squamous cell. On clear pictures, the forecast reliability reaches 90%.
Miiskin
This application uses a mole map to analyze your skin. Dermatologists create such a map during a clinical examination of the skin of the entire body using digital dermatoscopy. In fact, this is an enlarged digital photograph. The method allows you to identify all suspicious skin changes that are invisible to the normal eye.
Since high-resolution photographs allow dermatoscopy, they provide much more information than conventional digital photographs. The developers of Miiskin want to enable this technology to be used by ordinary consumers, which is why an application was created to take enlarged photographs of large areas of skin, for example, an entire leg. The app’s website says that anyone with a modern iPhone with iOS 10 or later, or a phone with Android 4.4 or later, can use Miiskin.
The application stores its photos separately from the usual smartphone library and allows you to evaluate changes in moles on the skin over time.
MoleScope
Like Miiskin, MoleScope uses magnified images to help people determine if they need to see a dermatologist for a skin check. The product was created by MetaOptima, a company that develops technologies for clinical dermatology. In fact, MoleScope is a device that connects to your smartphone and sends photos to a dermatologist for online checking.
And while MoleScope itself won’t analyze or diagnose your moles, you can use the dedicated ABCD guide in this app to track any suspicious moles. The program will allow you to document your moles with photos and send the images to a dermatologist who can evaluate them using the ABCD method. Here’s what the service is concerned about:
- Asymmetry : the shape of one half does not match the other.
- Border : Edges are jagged or blurry.
- Color : uneven shades of brown, black and brown; strange colors such as red or blue
- Diameter : resize beyond 6mm diameter.
Unlike Miiskin, you can only take pictures of one mole or small areas with multiple moles, not large areas such as the entire chest or back.
SkinVision
This app claims to help early detection of melanoma. SkinVision uses deep learning to analyze photographs of your skin and helps in the early detection of skin cancer. Photos are processed using a machine learning algorithm that filters image layers based on a simple, complex, and more abstract function. This uses a technology called convolutional neural network (CNN). SkinVision uses it to check small areas of your skin and identify high or low risk of affecting that area. And the analysis will take less than a minute.
SkinVision is backed by the Scientific Council of Dermatologists, but dermatologist Dr. Daniel Friedmann of Westlake Dermatology in Austin, Texas emphasizes that even an app with outstanding scientific support has limitations. He does not consider it necessary to completely abandon such programs, but advises patients to treat the results with cautious skepticism. It is best to assess suspicious skin lesions in your doctor’s office.
UMSkinCheck
This app was created by researchers at the University of Michigan (UM). The program allows you to self-test for full-body skin cancer and create and track a history of moles, growths and lesions.
The application will allow you to go through the verification step by step using graphic and text prompts. UMSkinCheck has access to informative videos and articles, as well as a melanoma risk calculator.
UMSkinCheck can send push reminders to get people to monitor their skin and check for lesions or tracked moles. You can decide how often you want to see these reminders in the app.
Research is promising, but its accuracy is not high enough
Of all the applications discussed here, SkinVision seems to have the most analyzes.
A 2014 study of an older version of SkinVision reported 81% accuracy in detecting melanoma. But this, according to experts, was not enough. But already in a new study from 2019, published in the journal of the European Academy of Dermatology and Venereology, it is established that SkinVision can detect 95% of skin cancers. It’s gratifying that the company continues to work on the accuracy of the cancer app, as early detection of skin cancer is the first step towards successful treatment.
In another study, researchers from the University of Pittsburgh analyzed four smartphone apps that claim to be able to detect skin cancer. The exact names of the programs are unknown, they are numbered. Three apps used algorithms to notify the owner of the risk of skin cancer, and a fourth app sent photos to a dermatologist.
Unsurprisingly, the researchers found the fourth app to be the most accurate. The other three applications have been found to misclassify a large number of skin lesions. At the same time, almost 30% of melanomas are absent in one of them, which defined them as lesions with a low health risk.
A 2018 article by the Cochrane Collaboration, which deals with the effectiveness of medical technology, says that artificial intelligence in detecting skin cancer is not yet showing the promised accuracy and efficiency, skipping melanomas.
Potential Benefits of Skin Cancer Detection Apps
Physicians emphasize two points related to skin cancer detection applications. First, there is concern that people may rely on apps and consumer devices to assess their risk of skin cancer. This can delay the diagnosis. On the other hand, such apps can be praised for raising awareness and encouraging people to take better care of their skin. The potential of the applications is to improve the connection between patient and doctor. The same images sent to the doctor can be the first step towards a professional examination. Nevertheless, it is worth remembering that home devices or applications still will not replace a doctor, in fact, the software developers warn about this.
The importance of annual checkups
The easiest and most effective way to detect skin cancer early is to self-examine the skin and visit a dermatologist regularly for check-ups. There are several classic factors that contribute to the development of the disease. If you have any of them, then you should see a dermatologist annually:
- Light skin, light eyes, and light or red hair.
- Skin that burns easily in the sun or with freckles.
- Family history of any type of skin cancer.
- Tanning bed history.
- A history of severe sunburn.
- Unusual moles or more than 50 moles on your body.