2010 IEEE EMBS Conference on Biomedical Engineering & Sciences (IECBES 2010), Kuala Lumpur, Malaysia, 30th November - 2nd December 2010. In Vivo 3D Thickness Measurement of Skin Lesion Ahmad Fadzil M Hani l , Hurriyatul Fitriyah, Esa Prakasa, V.S. Asirvadam Intelligent Signal and Imaging Research Centre, Electrical and Electronics Engineering Department Universiti Teknologi PETRONAS Perak, Malaysia I fadzmo@petronas.com.my S.H. Hussein Damansara Specialist Hospital Selangor, Malaysia Azura M.A. Dermatology Department, Hospital Kuala Lumpur Kuala Lumpur, Malaysia Abstract- Thickness is one of the morphological characteristic of skin lesion that represents severity condition. Dermatologists use tactile inspection to subjectively assess the thickness by feeling the alteration of the lesion from its surrounding normal skin. In this paper, a method to objectively measure the abnormal elevation occurs in skin lesions is presented. A 3D fringe projection scanner is used to obtain 3D surface profile of the lesion. Thickness of a lesion is defined as the elevations of lesion surface from its lesion base. The lesion base is determined from the neighboring normal skin using a 3D surface interpolation technique. The lesion elevations are determined in a 3D space grid by subtracting the elevation of the lesion surface proile from the interpolated lesion base proile at all corresponding locations thus giving lesion thickness as the average value of the elevations. The algorithm has been validated using 3D surface samples with an error of 0.031 mm ± SD 0.014 mm (95% Conidence Interval: ±0.0011 mm). The validated algorithm has been successfully applied to measure thicknesses of 450 psoriasis plaque lesions with severity level ranging from mild to severe and thickness ranging from 0.021 mm to 0.883 mm. From the measured thicknesses, Psoriasis Area and Severity Index (PASI) thickness scores 0 to 4 are then determined using unsupervised K-means Clustering. Keywords-in vivo 3D measurement; skin lesion; lesion thickness; PASI 1. INTRODUCTION Thickness is one of the morphological characteristic of the skin lesion which is measured by dermatologists in order to assess the severity level of skin lesion and treatment eicacy. Cyst, dermatoibroma, keloids, keratosis and psoriasis are example of skin lesion which result the abnormal skin elevation [1, 2]. In daily practice, the dermatologists touch the lesion several times in order to feel the alteration of the lesion's surface compared to the surrounding normal skin. Such assessment is subjective and does not result in a quantitative measurement hence inter rater and intra rater variation will occur. The work is sponsored under the Technofund grant (TF0308C041), Ministry of Science, Technology and Innovation, Malaysia. 978-1-4244-7600-8/10/$26.00 ©2010 IEEE 155 To overcome the subjectivity, it has been reported in the literature that objective methods have been developed to measure the lesion thickness by analysing the skin image captured using different imaging modalities [3-8]. Light microscope, X-ray radiation and ultrasound are among the imaging modalities used to capture the skin lesion structure. Light microscope captures the histology image of a lesion sample [3]. Lesion sample is taken using biopsy technique hence the technique is invasive. X-ray radiation is the earliest digital imaging technology used to take an in vivo image of a lesion [4, 5]. However, X-ray radiation is hazardous and should be limited to a minimum dose thus, ruling out daily or requent examination for the patient. Ultrasound imaging with 40 MHz, 20 MHz, and 10 MHz requency that overcomes the above limitations has been proposed instead [6-8]. The above imaging modalities i.e. microscope, X-ray, ultrasound, can be used to determine epidermal thickening in skin structure caused by the presence of a lesion. However in daily practice, the dermatologists use tactile inspection to feel the alteration of the skin lesion from the surrounding normal skin. The dermatologists' approach however is more suitable for analysing the surface proile of a skin lesion instead of the epidermal thickening in the skin structure. 3D digital imaging technology has been widely used in the dermatology to measure the texture properties of wrinkle and cellulite [9, 10], volume of ulcer wound [11] and roughness of skin lesion [12]. This paper proposes a method to measure lesion thickness as an abnormal skin surface alteration using 3D digital imagng. The proposed method measures lesion thickness rom elevations of lesion surface rom its lesion base. The lesion base is the expected normal skin proile below the lesion surface.