The FDA has approved MELA Sciences’ MelaFind^® Pre-Market Approval application for use in the United States. Following completion of a successful conformity assessment procedure MELA Sciences has also been granted CE Mark approval for sale of MelaFind^® in the European Union.

The FDA and MELA Sciences have agreed to the following labeled indications for use of MelaFind^®in the U.S.:

MelaFind^® is intended for use on clinically atypical cutaneous pigmented lesions with one or more clinical or historical characteristics of melanoma, excluding those with a clinical diagnosis of melanoma or likely melanoma.  MelaFind^® is designed to be used when a dermatologist chooses to obtain additional information for a decision to biopsy.  MelaFind^® should NOT be used to confirm a clinical diagnosis of melanoma.

MelaFind^® is only for use by physicians trained in the clinical diagnosis and management of skin cancer (i.e., dermatologists) who have also successfully completed a training program in the appropriate use of MelaFind^®.

The MelaFind^® result is one element of the overall clinical assessment of clinically atypical lesions.  A “High Disorganization” MelaFind^® output indicates lesions (which may include malignant melanoma, melanoma in situ, high grade dysplastic nevi and atypical melanocytic proliferation/hyperplasia) that should be considered for biopsy; the biopsy decision of a “Low Disorganization” MelaFind^® output should be based on the remainder of the entire clinical context.  Lesions that are “non-evaluable” by MelaFind^® should be carefully re-evaluated for biopsy.

MelaFind^® is indicated only for use on lesions with a diameter between 2 mm and 22 mm, lesions that are accessible by the Hand-Held component of MelaFind^®, lesions that are sufficiently pigmented (i.e. not for use on non-pigmented or skin-colored lesions), lesions that do not contain a scar or fibrosis consistent with previous trauma, lesions where the skin is intact (i.e., non-ulcerated or non-bleeding lesions), lesions greater than 1 cm away from the eye, lesions which do not contain foreign matter, and lesions not on special anatomic sites (i.e., not for use on acral, palmar, plantar, mucosal, or subungual areas).  MelaFind^® is not designed to detect pigmented non-melanoma skin cancers, so the dermatologist should rely on clinical experience to diagnose such lesions.

The Hand-Held component of MelaFind^®, used to capture multi-spectral data from beneath the surface of lesions, is made up of:

• An illuminator that shines light of 10 different specific wavelengths, including near infrared bands
• A lens system composed of 9 elements that creates multi-spectral data of the light scattered back from the lesions
• A photon (light) sensor

MelaFind’s automatic data analysis algorithms include:

• Calibration to reduce noise and artifacts in the data
• Quality control to automatically detect problems such as overexposure, underexposure, inappropriate lesion size or too much hair and when appropriate, direct the MelaFind^® operator to re-evaluate the lesion
• Lesion segmentation to identify portions of the data that belong to the lesion
• Feature extraction to compute parameters characterizing lesions
• Lesion classification to classify clinically atypical pigmented skin lesions based upon degree of 3D morphological disorganization providing an output of “High Disorganization” or “Low Disorganization”

Development and training of the lesion classification algorithm is an iterative process involving: (1) creation and enrichment of the lesion database and complementary gold-standard (pathology) information; (2) development of the lesion features that provide discrimination; (3) development of algorithms that enable computers to effectively “learn” based on examples; (4) training of the computer using these algorithms to arrive at the best-performing classifier; and (5) repeating the process. The performance of the lesion classification algorithm is directly related to the size of the database used in training, as well as the degree to which the training database is representative of the lesions that will be evaluated by MelaFind^® in a practice setting.

Proprietary Database of Pigmented Skin Lesions. The database includes in vivo multi-spectral data and corresponding histological results of over 10,000 biopsied lesions from over 7,000 patients at 40 clinical study sites. MELA Sciences believes this is the largest such database in the US and a substantial barrier to competition.

MelaFind^® Pivotal Trial Results.  The Company conducted numerous studies of the MelaFind^®system, including the landmark MelaFind^® pivotal trial, the largest prospective clinical study ever conducted in melanoma detection. For all subgroups analyzed in the pivotal study, the sensitivity of MelaFind^® was greater than 95% (95% lower confidence bound) and its specificity was statistically significantly higher than that of study clinicians.  For more information about MelaFind^® clinical studies, visit www.melafind.com.

The FDA has approved MELA Sciences’ MelaFind^® Pre-Market Approval application for use in the United States. Following completion of a successful conformity assessment procedure MELA Sciences has also been granted CE Mark approval for sale of MelaFind^® in the European Union.