Using wide-field images and deep learning, researchers developed an analysis system of suspicious pigmented skin lesions for more effective and efficient skin cancer detection.
Image courtesy of the reseearchers
Using deep convolutional neural networks, researchers devise a system that quickly analyzes wide-field images of patients’ skin in order to more efficiently detect cancer.
Melanoma is a type of malignant tumor responsible for more than 70 percent of all skin cancer-related deaths worldwide. For years, physicians have relied on visual inspection to identify suspicious pigmented lesions (SPLs), which can be an indication of skin cancer. Such early-stage identification of SPLs in primary care settings can improve melanoma prognosis and significantly reduce treatment cost.
The challenge is that quickly finding and prioritizing SPLs is difficult, due to the high volume of pigmented lesions that often need to be evaluated for potential biopsies. Now, researchers from MIT and elsewhere have devised a new artificial intelligence pipeline, using deep convolutional neural networks (DCNNs) and applying them to analyzing SPLs through the use of wide-field photography common in most smartphones and personal cameras.
DCNNs are neural networks that can be used to classify (or “name”) images to then cluster them (such as when performing a photo search). These machine learning algorithms belong to the subset of deep learning.
Using cameras to take wide-field photographs of large areas of patients’ bodies, the program uses DCNNs to quickly and effectively identify and screen for early-stage melanoma, according to Luis R. Soenksen, a postdoc and a medical device expert currently acting as MIT’s first Venture Builder in Artificial Intelligence and Healthcare. Soenksen conducted the research with MIT researchers, including MIT Institute for Medical Engineering and Science (IMES) faculty members Martha J. Gray, W. Kieckhefer Professor of Health Sciences and Technology, professor of electrical engineering and computer science; and James J. Collins, Termeer Professor of Medical Engineering and Science and Biological Engineering.
Soenksen, who is the first author of the recent paper, “Using Deep Learning for Dermatologist-level Detection of Suspicious Pigmented Skin Lesions from Wide-field Images,” published in Science Translational Medicine, explains that “Early detection of SPLs can save lives; however, the current capacity of medical systems to provide comprehensive skin screenings at scale are still lacking.”
The paper describes the development of an SPL analysis system using DCNNs to more quickly and efficiently identify skin lesions that require more investigation, screenings that can be done during routine primary care visits, or even by the patients themselves. The system utilized DCNNs to optimize the identification and classification of SPLs in wide-field images.
Using AI, the researchers trained the system using 20,388 wide-field images from 133 patients at the Hospital Gregorio Marañón in Madrid, as well as publicly available images. The images were taken with a variety of ordinary cameras that are readily available to consumers. Dermatologists working with the researchers visually classified the lesions in the images for comparison. They found that the system achieved more than 90.3 percent sensitivity in distinguishing SPLs from nonsuspicious lesions, skin, and complex backgrounds, by avoiding the need for cumbersome and time-consuming individual lesion imaging. Additionally, the paper presents a new method to extract intra-patient lesion saliency (ugly duckling criteria, or the comparison of the lesions on the skin of one individual that stand out from the rest) on the basis of DCNN features from detected lesions.
“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 referrals.”
Doing so would allow for more rapid and accurate assessments of SPLS and could lead to earlier treatment of melanoma, according to the researchers.
Original Article: An artificial intelligence tool that can help detect melanoma
More from: Massachusetts Institute of Technology
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Stories of Loss and Survival with Melanomaon April 30, 2021 at 9:12 am
My story of loss began in August 2004 when my wife was diagnosed with melanoma. An unnoticed spot on her lower back scabbed over and bled. A biopsy in the office came back as testing positive as ...
- Dear Dr. Roach: Agent Orange linked to some cancers, but not melanomaon April 29, 2021 at 3:00 am
Your recent column on melanoma piqued my interest. My husband was exposed to Agent Orange in Vietnam in 1968. He had a melanoma on his neck removed ...
- AHN building new melanoma, skin cancer centeron April 28, 2021 at 9:15 pm
Jessica Rogowicz grew up playing outside and spending lots of time in the sun including yearly beach vacations in Ocean City, Md.
- Olatec Therapeutics Announces Results Showing Dapansutrile Reduces Tumor Growth in a Mouse Model of Melanomaon April 28, 2021 at 11:48 am
Olatec Therapeutics LLC (Olatec) today announced the first publication from its preclinical studies with dapansutrile in selected cancer models.
- Dr. Davies on Managing Melanoma During the COVID-19 Pandemicon April 28, 2021 at 10:25 am
Davies, MD, PhD, discusses the management of patients with melanoma during the COVID-19 pandemic. Michael A. Davies, MD, PhD, the Anne and John Mendelsohn Chair in Cancer Research; professor and chair ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
- Woman credits cat with detecting breast cancer: ‘If only pets could talk’on April 30, 2021 at 10:35 am
Kate King-Scribbins credits her pet cat Oggy for saving her life by detecting a cancerous lump growing inside her left breast. She says Oggy had been giving her warning signs of the malignancy for ...
- New liquid biopsy assay with RTP connection can detect breast cancer – it may soon be available for useon April 30, 2021 at 8:32 am
This "radar" can detect breast cancer. And it may soon be available to clinicians near you. Here are the details.
- Study evaluates first tumor-uninformed ctDNA assay to detect residual cancer cells after treatmenton April 29, 2021 at 10:21 pm
After patients with cancer undergo surgery to remove a tumor and sometimes additional chemotherapy, tools are used to identify patients at highest risk of recurrence.
- How The Guidelines Have Changed Regarding Lung Cancer Early Detection Effortson April 29, 2021 at 2:21 pm
Lung cancer is the leading cause of U.S. cancer deaths. The U.S. Preventive Services Task Force has expanded screening guidelines in an effort to help increase early detection rates. On CBSN Denver, ...
- New test detects residual cancer DNA in the blood without relying on tumor dataon April 29, 2021 at 1:43 pm
After patients with cancer undergo surgery to remove a tumor and sometimes additional chemotherapy, tools are used to identify patients at highest risk of recurrence. Non-invasive tools to detect ...