Artificial Intelligence (AI) has donned a transformative role in skin cancer diagnostics, with dermatologists playing a key part in its responsible development and implementation. AI entails the potential to enhance the speed and accuracy of skin cancer diagnosis, thereby generating better outcomes for patients. According to Inkwood Research, the global skin cancer diagnostics market is set to garner a revenue of $7252.15 million by 2032, projecting a CAGR of 7.13% during 2023-2032.
This blog examines the existing and forthcoming AI-related diagnostic tools making their mark in the global skin cancer diagnostics market.
Mission Efficiency: Proscia’s DermAITM
DermAI™ was launched on 19th June 2019 by Proscia. It is a module on Proscia’s Concentriq™ platform. It leverages deep learning to classify and pre-screen skin biopsies to help enhance laboratory quality & efficiency and minimize costly errors.
This development is against the backdrop of declining medical professionals entering pathology. Besides, the standard diagnosis of the skin biopsies taken in the United States annually is based on a pathologist’s interpretation of tissue patterns through a microscope. This 150-year-old subjective and manual practice lags with regard to the rising demand for pathology diagnosis or critical data delivery for precision treatment.
The DermAI algorithm was trained and tested using patient biopsies from prominent commercial and academic dermis laboratories, including Thomas Jefferson University Hospital, University of Florida, Dermatopathology Laboratory of Central States, and Cockerell Dermatopathology. The multi-site study validated DermAI’s performance using more than 20,000 patient biopsy slides.
DermAI’s central capabilities include the following:
Improved Technical Component Reporting: It enables a dermatopathology lab to offer additional insights into its labwork. This will guide the lab in handling the professional component.
Automated QA: It analyses the entire caseload of the lab and provides an AI-based interpretation for every case. Also, DermAI offers an automated second layer of quality review across the lab.
Case Prioritization and Intelligent Workload Balancing: DermAI allows the lab to triage, sort, and prioritize cases. It optimizes the allocation of cases to dermatopathologists in a lab. The criteria include the order of cases to examine, subject matter expertise, and continuity.
Explains David West, CEO of Proscia, “To date, attempts to apply AI to pathology have been engineered in isolated development environments using toy datasets. The challenge in fulfilling the promise of deep learning in diagnostic medicine is bringing to market a solution that can perform in the real world where we face tremendous variability among labs, systems, and specimen. Proscia is the first to deliver on this promise.” (Source)
Eliminating Hassles Efficiently: MIT’s AI-Powered Tool for Melanoma Detection
As per MIT News, the researchers at MIT developed an AI-powered SPL (suspicious pigmented lesions) analysis system to precisely assess the pigmented lesion on the skin to detect anomalies. Physicians rely on visual inspection to identify SPLs, which can indicate skin cancer. SPLs’ early-stage identification can considerably minimize treatment costs and enhance melanoma prognosis.
However, a swift finding of SPLs is difficult, impeded by the large volume of pigmented lesions that need evaluation. Accordingly, researchers at MIT collaborated to devise a new artificial intelligence pipeline using deep convolutional neural networks (DCNNs). These were applied to SPLs analysis through wide-filed photography.
Further, the tool uses DCNNs to effectively identify early-stage melanoma using cameras. The system was trained using 20,388 wide-filed images from 133 patients at the Hospital Gregorio Maranon in Madrid. The dermatologists then visually classified the lesions for comparison. The system displayed over 90.3% sensitivity in distinguishing SPLs from nonsuspicious lesions, thereby eliminating the need for time-consuming and cumbersome individual lesion imaging.
Says Luis R. Soenksen, a postdoc and a medical device expert currently acting as MIT’s first Venture Builder in Artificial Intelligence and Healthcare, “Our research suggests that systems leveraging computer vision and deep neural networks, quantifying such common signs, can achieve comparable accuracy to expert dermatologists,” Soenksen explains. “We hope our research revitalizes the desire to deliver more efficient dermatological screenings in primary care settings to drive adequate referral.” (Source)
Enroute Equalized Coherence: Dermalyser by AI Medical Technology
On 7th February 2023, AI Medical Technology, a Swedish start-up, announced the clinical trial results of Dermalyser conducted at 37 Swedish primary facilities. Dermalyser (a mobile application) is a diagnostic decision support system authorized with advanced artificial intelligence. The study included 240 patients seeking primary care for melanoma-suspected cutaneous lesions.
Dermalyser showcased an exceptional performance of 86% specificity and 95% sensitivity, surpassing primary care dermatologists and physicians.
Says Christoffer Ekström, CEO of AI Medical Technology, “The remarkably high sensitivity and specificity levels demonstrate the clinical performance and benefit of Dermalyser, particularly since the study was conducted in a real world, primary care setting representing different demographics, personnel, and geographical location.” (Source)
Further, Olle Larkö, Professor in Dermatology & Venereology and former Dean at Sahlgrenska University, adds, “Indeed exciting results, these numbers show potential of not only improving future visual diagnostic accuracy, but also decreasing the amount of workload that dermatologist too often are dealing with in their daily practice. Nevertheless, additional studies are necessary to confirm the positive results.” (Source)
Future Implications of AI in Skin Cancer Diagnostics Market
One application of artificial intelligence (AI) in skin cancer diagnosis is the use of deep learning algorithms to analyze skin lesion images. These algorithms can be directed on large datasets of images, facilitating the accurate identification of features and patterns associated with skin cancer. Another application of AI is decision support systems, which provide clinicians with recommendations and information about skin cancer treatment and diagnosis.
Furthermore, the use of AI in skin cancer diagnosis has the potential to minimize healthcare costs and enhance patient outcomes. However, AI should not be treated as a substitute for clinical judgment. Human expertise still triumphs when interpreting the results generated by AI algorithms. Nevertheless, several AI-related developments and tools are making their mark in the global skin cancer diagnostics market.
By Akhil Nair
What are the different screening types used for skin cancer detection?
Dermatoscopy, biopsy imaging tests, lymph node, skin biopsy, and blood tests are the different screening types used for skin cancer detection
Which country projects promising growth potential for skin cancer diagnostics?
Germany projects promising growth potential for skin cancer diagnostics.