News Column

Patent Issued for Hyperspectral Imaging for Detection of Skin Related Conditions

July 7, 2014



By a News Reporter-Staff News Editor at Robotics & Machine Learning -- According to news reporting originating from Alexandria, Virginia, by VerticalNews journalists, a patent by the inventors Burlina, Philippe M. (North Bethesda, MD); Banerjee, Amit (Burtonsville, MD); Vyas, Saurabh (Odenton, MD); Garza, Luis (Baltimore, MD), filed on September 25, 2012, was published online on June 24, 2014.

The assignee for this patent, patent number 8761476, is The Johns Hopkins University (Baltimore, MD).

Reporters obtained the following quote from the background information supplied by the inventors: "It is estimated that one person dies of melanoma, a severe form of skin cancer, every hour. Melanoma is characterized by rapid proliferation of melanocytes underneath the epidermis. During early stages of the disease, the tumor has a depth of about 1 mm and it can be excised completely with local surgery at a relatively high cure rate. However, the most common diagnostic for skin cancers, such as melanoma, is visual examination by a trained health care worker. Thus, the disease may often be missed or at least not draw attention while it is in its early stages. In the case of melanoma, this can mean the onset of distant metastasis--where the tumor moves to remote parts of the body through lymph vessels.

"Recently, there has been significant interest in developing potent, efficient, and non-invasive techniques capable of detecting early signs of cancer in human skin. Though several technologies, including reflectance confocal microscopy, dermoscopy, etc. have emerged, they typically suffer from limitations associated with single band imaging. These techniques, or others like them, may also be employed for detection of other skin related ailments. Accordingly, it may be desirable to continue to develop additional methods and systems for minimally-invasive pre-screening for skin ailments such as cancers so that the methods and systems may be useable to achieve detection during the early stages of the diseases."

In addition to obtaining background information on this patent, VerticalNews editors also obtained the inventors' summary information for this patent: "Accordingly, some example embodiments may enable the provision of a non-invasive approach to diagnosing skin cancers or other conditions related to changes in constitutive parameters of the skin. In this regard, some embodiments may enable a multi-band hyperpectral sensor to obtain images of the skin of a patient. From the data gathered, anomalies may be detected in the skin that may enable relatively early detection of skin cancers.

"In one example embodiment, a detection system is provided. The detection system may include a multiband hyperspectral sensor configured to obtain multi-spectral data and a parametric analyzer including processing circuitry. The processing circuitry may be configured to employ the multi-spectral data to map constitutive skin parameters to corresponding spectral signatures via a forward model that enables generation of a set of samples including a plurality of parameters mapped to a plurality of spectral signatures, utilize the set of samples to employ machine learning to generate an inverse model to enable mapping of a spectral signature of skin of a patient to corresponding skin parameters, estimate constitutive skin parameters of the skin of the patient based on the inverse model, and determine a distribution of the constitutive parameters for one or more skirt locations.

"In another example embodiment, a method of detecting a skin condition is provided. The method may include employing a multiband hyperspectral sensor to obtain multi-spectral data, employing the multi-spectral data to map constitutive skin parameters to corresponding spectral signatures via a forward model that enables generation of a set of samples including a plurality of parameters mapped to a plurality of spectral signatures, utilizing the set of samples to employ machine learning to generate an inverse model to enable mapping of a spectral signature of skin of a patient to corresponding skin parameters, estimating constitutive skin parameters of the skin of the patient based on the inverse model, and determining a distribution of the constitutive parameters for one or more skin locations.

"In another example embodiment, a computer program product comprising a computer-readable storage medium having computer-executable program code instructions stored therein is provided. The computer-executable program code instructions may include program code instructions for employing a multiband hyperspectral sensor to obtain multi-spectral data, employing the multi-spectral data to map constitutive skin parameters to corresponding spectral signatures via a forward model that enables generation of a set of samples including a plurality of parameters mapped to a plurality of spectral signatures, utilizing the set of samples to employ machine learning to generate an inverse model to enable mapping of a spectral signature of skin of a patient to corresponding skin parameters, estimating constitutive skin parameters of the skin of the patient based on the inverse model, and determining a distribution of the constitutive parameters for one or more skin locations."

For more information, see this patent: Burlina, Philippe M.; Banerjee, Amit; Vyas, Saurabh; Garza, Luis. Hyperspectral Imaging for Detection of Skin Related Conditions. U.S. Patent Number 8761476, filed September 25, 2012, and published online on June 24, 2014. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=8761476.PN.&OS=PN/8761476RS=PN/8761476

Keywords for this news article include: Cancer, Cyborgs, Oncology, Machine Learning, Emerging Technologies, The Johns Hopkins University.

Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2014, NewsRx LLC


For more stories covering the world of technology, please see HispanicBusiness' Tech Channel



Source: Robotics & Machine Learning


Story Tools






HispanicBusiness.com Facebook Linkedin Twitter RSS Feed Email Alerts & Newsletters