Be first to read the latest tech news, Industry Leader's Insights, and CIO interviews of medium and large enterprises exclusively from Medical Tech Outlook
THANK YOU FOR SUBSCRIBING
By
MedTech Outlook | Wednesday, October 26, 2022
Although recent advances in artificial intelligence in dermatology have demonstrated the potential to improve skin cancer detection, dermatologists and other professionals have not optimised such technologies for skin cancer detection.
FREMONT, CA:Advancements in artificial intelligence (AI) and machine learning are continuously evolving, but dermatologists and other professionals have not leveraged such technologies for skin cancer detection yet.
Stay ahead of the industry with exclusive feature stories on the top companies, expert insights and the latest news delivered straight to your inbox. Subscribe today.
Recent AI advances in dermatology have highlighted the potential to improve skin cancer detection accuracy. In particular, the technology does not allow for improved diagnostics and skin cancer management. Scholars defining the fundamental AI terminology in dermatology, along with potential benefits, limitations, and relevant commercial applications, refer to AI as computer usage to perform tasks that would otherwise need human intelligence and decision-making.
Machine learning is an AI type marked by computers programmed to develop algorithms helping to complete human tasks. Most importantly, human programmers can supervise machine learning. The next advance in machine learning includes deep neural networks or DNNs.
In a DNN, nodes are arranged into multiple hidden layers, with machine learning occurring at every level, such as the neuron layers in a brain. The data is then analysed, enabling a trained algorithm to develop diagnosis probabilities of any individual skin lesion. DNNs were first used in research into skin lesions in 2016.
Although numerous smartphone applications and other technologies using DNNs have been investigated, only two products are currently approved by the FDA: MelaFind (MELA Science) and Nevisense (SciBase). MelaFind was approved in 2011 but discontinued for sale, and clinical use in 2017 as the product had low specificity, resulting in excessive biopsies. On the other hand, Nevisence received its premarket approval for melanoma detection for use only by dermatologists.
Along with the lack of approved devices, dermatologists are concerned that AI technology would disrupt the dermatologist-patient relationship. More research is required to investigate the different potential products that could eventually become FDA-approved. With the availability of more products on the market, non-dermatologists can also triage benign lesions and increase the detection of potentially cancerous lesions, easing the dermatologists' workload.
A clearer technological understanding reduces physician concerns about AI and promotes its use in the clinical setting. Ultimately, the development and validation of AI technologies, their approval by regulatory agencies and their widespread adoption by dermatologists and other clinicians enhance patient care. Technology-augmented skin cancer detection improves the quality of life, minimises health care costs by alleviating unnecessary procedures, and promotes greater access to high-quality skin assessment.
Although artificial intelligence systems for skin cancer detection have shown promise in research settings, more work is still needed before the technology is appropriate for real-world use. AI systems for skin cancer detection are still in their early phases. However, from dermatologists' perception, they need to know about these emerging apps and growing technologies and continue to embrace them.
More in News
I agree We use cookies on this website to enhance your user experience. By clicking any link on this page you are giving your consent for us to set cookies. More info
