澳门六合彩历史记录

Study Shows 鈥楽weet Spot鈥 Could Improve Melanoma Diagnosis

Melanoma, Melanoma Diagnosis, Skin Cancer

Malignant melanoma and benign skin lesions often appear very similar to the untrained eye.


By gisele galoustian | 11/28/2017

Too much, too little, just right. It might seem like a line from 鈥淕oldilocks and the Three Bears,鈥 but actually describes an important finding from researchers in 鈥檚 . They have developed a technique using machine learning 鈥 a sub-field of artificial intelligence (AI) 鈥 that will enhance computer-aided diagnosis (CADx) of melanoma. Thanks to the algorithm they created 鈥 which can be used in mobile apps that are being developed to diagnose suspicious moles 鈥 they were able to determine the 鈥渟weet spot鈥 in classifying images of skin lesions.

This new finding, published in the Journal of Digital Imaging, will ultimately help clinicians more reliably identify and diagnose melanoma skin lesions, distinguishing them from other types of skin lesions. The research was conducted in the NSF Industry/University Cooperative Research Center for Advanced Knowledge Enablement () at 澳门六合彩历史记录 and was funded by the Center's industry members.

Melanoma is a particularly deadly form of skin cancer when left undiagnosed. In the United States alone, there were an estimated 76,380 new cases of melanoma and an estimated 6,750 deaths due to melanoma in 2016. Malignant melanoma and benign skin lesions often appear very similar to the untrained eye. Over the years, dermatologists have developed different heuristic classification methods to diagnose melanoma, but to limited success (65 to 80 percent accuracy). As a result, computer scientists and doctors have teamed up to develop CADx tools capable of aiding physicians to classify skin lesions, which could potentially save numerous lives each year.

鈥淐ontemporary CADx systems are powered by deep learning architectures, which basically consist of a method used to train computers to perform an intelligent task. We feed them massive amounts of data so that they can learn to extract meaning from the data and, eventually, demonstrate performance comparable to human experts 鈥 dermatologists in this case,鈥 said , Ph.D., lead author of the study and a professor in 澳门六合彩历史记录鈥檚 who specializes in machine cognition, medical imaging and health care technologies. 鈥淲e are not trying to replace physicians or other medical professionals with artificial intelligence. We are trying to help them solve a problem faster and with greater accuracy, in other words enabling augmented 颈苍迟别濒濒颈驳别苍肠别.鈥

Images of skin lesions often contain more than just skin lesions 鈥 background noise, hair, scars, and other artifacts in the image can potentially confuse the CADx system. To prevent the classifier from incorrectly associating these irrelevant artifacts with melanoma, the images are segmented into two parts, separating the lesion from the surrounding skin, hoping that the segmented lesion can be more easily analyzed and classified.

鈥淧revious studies have produced conflicting results: some research suggests that segmentation improves classification while other research suggests that segmentation is detrimental, due to a loss of contextual information around the lesion area,鈥 said Marques. 鈥淗ow much we segment an image can either help or impede skin lesion classification.鈥

With that in mind, Marques and his collaborators , Ph.D., a professor in 澳门六合彩历史记录鈥檚 Department of Electrical and Computer Engineering and Computer Science and director of the NSF-sponsored CAKE at 澳门六合彩历史记录; Jack Burdick, a second-year master鈥檚 student at 澳门六合彩历史记录; and Janet Weinthal, an undergraduate student at 澳门六合彩历史记录, tested their hypothesis: 鈥淗ow much segmentation is too much?鈥澛

To test their hypothesis, the researchers first compared the effects of no segmentation, full segmentation, and partial segmentation on classification and demonstrated that partial segmentation led to the best results. They then proceeded to determine how much segmentation would be 鈥渏ust right.鈥 To do that, they used three degrees of partial segmentation, investigating how a variable-sized non-lesion border around the segmented skin lesion affects classification results. They performed comparisons in a systematic and reproducible manner to demonstrate empirically that a certain amount of segmentation border around the lesion could improve classification performance.

Their findings suggest that extending the border beyond the lesion to include a limited amount of background pixels improves their classifier鈥檚 ability to distinguish melanoma from a benign skin lesion.

鈥淥ur experimental results suggest that there appears to be a 鈥榮weet spot鈥 in the degree to which the surrounding skin included is neither too great nor too small and provides a 鈥榡ust right鈥 amount of context,鈥 said Marques.

Their method showed an improvement across all relevant measures of performance for a skin lesion classifier. 聽

This research is supported by the NSF CAKE at 澳门六合彩历史记录 working in collaboration with industry partners as well as international collaborators from Universitat Polit猫cnica de Catalunya (UPC), Barcelona.聽

-澳门六合彩历史记录-