Detection of malignant melanoma, the most serious type of skin cancer, will soon be quicker and easier thanks to the work of researchers at Missouri University of Science and Technology.
The research, which is funded by the National Institutes of Health, recently received a patent titled “Automatic Detection of Critical Dermoscopy Features for Malignant Melanoma Diagnosis.” The patent applies to a method for computer-aided analysis of photographs of skin lesions to detect the cancer. Melanoma can be cured if it is diagnosed early enough.
“Right now it can take a few minutes to process the data from a photograph of a skin lesion,” says investigator Dr. Randy Moss, professor of electrical and computer engineering at Missouri S&T. “We’re working toward getting all the processing done within a few seconds.”
The process would also eliminate the need for many of the invasive and expensive biopsies currently being done on benign lesions.
Moss and his fellow researchers use photographs taken with a device called a dermatoscope. The scope contains a magnifier, a light source and a transparent plate, which is placed on skin coated with mineral oil, alcohol or a clear gel. The instrument illuminates the skin at a low angle in all directions, which makes the skin’s upper layers more transparent, thus making deeper pigment patterns and structures visible.
S&T’s program extracts a number of features (22 in one study) from the lesion image and uses them to assist in the diagnosis of malignant melanoma.
In 2006, 8,441 people in the United States died from melanoma, so improving early diagnosis of the disease could save many lives. “In one study, our method achieved a diagnostic accuracy rate of more than 94 percent on a set of 724 lesion images,” says Moss. “Without the use of technology, only 82-87 percent of lesions are correctly diagnosed.”
Moss and some of his colleagues, including Dr. William V. Stoecker, a local dermatologist, have been working on this research for nearly 30 years. Stoecker is also named on the patent and his company, Stoecker and Associates, shares ownership of the method with Missouri S&T. The medical devices company is developing software to make the process available to the medical community.
Moss says those working in the medical profession with little experience in diagnosing melanoma would benefit greatly from the software. Nurse practitioners and physician assistants could be trained to use the program.
Dr. R. Joe Stanley, associate professor of electrical and computer engineering at S&T and Dr. Bijaya Shrestha, associate teaching professor both in electrical and computer engineering and in mining and nuclear engineering at S&T, are also inventors named in the patent, along with S&T graduates Dr. Xiaohe Chen, Dr. Kapil Gupta and Pavani Jella.
Source: Missouri University of Science and Technology