Esa Prakasa

In vivo 3D thickness measurement of skin lesion

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 profile from the interpolated lesion base profile 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% Confidence 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.

Body surface area measurement and soft clustering for PASI area assessment

Psoriasis is a common skin disorder with a prevalence of 0.6 - 4.8% around the world. The most common is plaques psoriasis and it appears as red scaling plaques. Psoriasis is incurable but treatable in a long term treatment. Although PASI (Psoriasis Area and Severity Index) scoring is recognised as gold standard for psoriasis assessment, this method is still influenced by inter and intra-rater variation. An imaging and analysis system called α-PASI is developed to perform PASI scoring objectively. Percentage of lesion area to the body surface area is one of PASI parameter. In this paper, enhanced imaging methods are developed to improve the determination of body surface area (BSA) and lesion area. BSA determination method has been validated on medical mannequin. BSA accuracies obtained at four body regions are 97.80% (lower limb), 92.41% (trunk), 87.72% (upper limb), and 83.82% (head). By applying fuzzy c-means clustering algorithm, the membership functions of lesions area for PASI area scoring have been determined. Performance of scoring result has been tested with double assessment by α-PASI area algorithm on body region images from 46 patients. Kappa coefficients for α-PASI system are greater than or equal to 0.72 for all body regions (Head -0.76, Upper limb - 0.81, Trunk - 0.85, Lower limb -0.72). The overall kappa coefficient for the α-PASI area is 0.80 that can be categorised as substantial agreement. This shows that the α-PASI area system has a high reliability and can be used in psoriasis area assessment.

Implementation of fuzzy c-means clustering for Psoriasis Assessment on lesion erythema

Psoriasis is a skin disease that causes the appearance of reddish and scaly skin lesions. Lesion erythema, which refers to the inflammation (colour) of psoriasis lesion, is defined as one of Psoriasis Area and Severity Index (PASI) parameters. However, visual assessment by dermatologists is subjective and results in inter-rater variations. In this paper, an objective PASI erythema-scoring algorithm has been developed. The colour of lesion erythema was found to be dependent on the normal skin tone of the affected person. Normal skin tones are categorised into four groups (dark, brown, light brown and fair skins). A soft clustering is applied to solve the ambiguity problems at cluster boundaries. CIE L*a*b* data of lesions and their surrounding normal skin are used to calculate lesion erythema. The hue difference between lesion and normal skin corresponds to the lesion erythema. Two dedicated fuzzy c-means (FCM) algorithms are applied consecutively to classify normal skin tone and to score PASI erythema. 2,322 normal skin and 1,462 lesions samples from 204 recruited patients at Hospital Kuala Lumpur are used to build skin tone and PASI erythema score classifiers respectively. Agreement values between first and second assessments of 430 lesions for PASI erythema are determined to evaluate scoring performance. Kappa coefficients are found ≥ 0.70 for all skin tones (fair - 0.70, light brown - 0.8, brown - 0.79, and dark skin - 0.90). These agreement results show that the proposed method is reliable and objective, and thus can be used for clinical practices.

High order polynomial surface fitting for measuring roughness of psoriasis lesion

Scaliness of psoriasis lesions is one of the parameters to be determined during Psoriasis Area and Severity Index (PASI) scoring. Dermatologists typically use their visual and tactile senses to assess PASI scaliness. However, it is known that the scores are subjective resulting in inter- and intra-rater variability. In this paper, an objective 3D imaging method is proposed to assess PASI scaliness parameter of psoriasis lesions. As scales on the lesion invariably causes roughness, a surface-roughness measurement method is proposed for 3D curved surfaces. The method applies a polynomial surface fitting to the lesion surface to extract the estimated waviness from the actual lesion surface. Surface roughness is measured from the vertical deviations of the lesion surface from the estimated waviness surface. The surface roughness algorithm has been validated against 328 lesion models of known roughness on a medical mannequin. The proposed algorithm is found to have an error 0.0013 ± 0.0022 mm giving an accuracy of 89.30%. The algorithm is invariant to rotation of the measured surface. Accuracy of the rotated lesion models is found to be greater than 95%. System repeatability has been evaluated to successive measurements of 456 psoriasis lesions. The system repeatability can be accepted since 95.27% of the measurement differences are less than two standard deviation of measurement difference.

3D surface roughness measurement for scaliness scoring of psoriasis lesions

Psoriasis is an incurable skin disorder affecting 2-3% of the world population. The scaliness of psoriasis is a key assessment parameter of the Psoriasis Area and Severity Index (PASI). Dermatologists typically use visual and tactile senses in PASI scaliness assessment. However, the assessment can be subjective resulting in inter- and intra-rater variability in the scores. This paper proposes an assessment method that incorporates 3D surface roughness with standard clustering techniques to objectively determine the PASI scaliness score for psoriasis lesions. A surface roughness algorithm using structured light projection has been applied to 1999 3D psoriasis lesion surfaces. The algorithm has been validated with an accuracy of 94.12%. Clustering algorithms were used to classify the surface roughness measured using the proposed assessment method for PASI scaliness scoring. The reliability of the developed PASI scaliness algorithm was high with kappa coefficients>0.84 (almost perfect agreement).

Sample area for surface roughness determination of skin surfaces

A surface roughness algorithm has been developed and validated for determining roughness of psoriasis lesions. The algorithm extracts an estimated waviness surface from 3D rough surface of psoriasis lesion by applying high order polynomial surface fitting. Vertical deviations of the lesion are determined by subtracting its 3D surface from the estimated waviness surface. However, the performance of the algorithm is dependent on the area of skin surface. The objective of this paper is to determine the minimum area for optimal performance of the skin surface roughness algorithm. In the determined sample area, all significant roughness components must be covered for surface roughness determination. To find the minimum size of sampled area, skin surface roughness has been determined at several sampling area variations. Normal skin surfaces are used as input data in this evaluation. By referring to the plot of surface roughness dependency on sampled area variation, it can be shown that the threshold area is found to be 4.9×4.9 mm2 for skin surface roughness stability. Skin surface roughness variation is less for the sample areas larger than this threshold. However, there is a small surface roughness increment after the surface roughness stability. It is caused by fitting error at border regions of very large sample size.

Thickness Characterization of 3D Skin Surface Images Using Reference Line Construction Approach

Irregular elevation is commonly formed in skin surface during dermatological diseases. Thickness is one of the parameters to assess the severity. In this research, the thickness is defined as the elevation of lesion surface from its constructed reference line which is generated by smoothing the lesion surface using moving average filter. This method is applied in dermatological disease which caused by disorder cell growth. In the clinical trial, Dermatologist classifies the thickness severity into 4 classes. The classes are divided by its thickness appearance. Dermatologist assesses 40 3D images of skin lesion taken from 16 patients. The quantitative and objective measurement of the lesions performed in this research has characterized the thickness range of each class as well as met the doctors thickness classification.

3D-based skin roughness measurement for lesion classification

Skin surface roughness can be changed due to skin lesion progression. The evaluation of the damage of the skin is assessed on the base of clinical experience of dermatologists. Currently, the assessment of skin surface is made by running a finger across the skin. It is found that this tactile evaluation may result in inter and intra variations. The objective of our research is to develop an objective assessment tool in evaluation skin roughness. Psoriasis is used as a sample of skin lesion that can change skin surface roughness as its extents develop. 3D surface images of 120 psoriasis lesions scanned from 29 patients are analysed in the study. The lesions are previously grouped into four categorises based on its tactile characteristics by dermatologists. The proposed method converts the 3D images into 2D height maps. The 2D height maps are then fitted and filtered using averaging filter. Finally, Mean Square Error (MSE) between the fitted and filtered 2D height maps are computed and utilized as skin roughness descriptors. Results show that the proposed method has been able to differentiate each lesion according to its group perfectly.