Hermawan Nugroho

Analysis of retinal fundus images for grading of diabetic retinopathy severity.

Diabetic retinopathy (DR) is a sight threatening complication due to diabetes mellitus that affects the retina. In this article, a computerised DR grading system, which digitally analyses retinal fundus image, is used to measure foveal avascular zone. A v-fold cross-validation method is applied to the FINDeRS database to evaluate the performance of the DR system. It is shown that the system achieved sensitivity of >84%, specificity of >97% and accuracy of >95% for all DR stages. At high values of sensitivity (>95%), specificity (>97%) and accuracy (>98%) obtained for No DR and severe NPDR/PDR stages, the computerised DR grading system is suitable for early detection of DR and for effective treatment of severe cases.

Analysis of foveal avascular zone in colour fundus images for grading of diabetic retinopathy severity

Diabetic retinopathy (DR) is a sight threatening complication due to diabetes mellitus that affects the retina. At present, the classification of DR is based on the International Clinical Diabetic Retinopathy Disease Severity. In this paper, FAZ enlargement with DR progression is investigated to enable a new and an effective grading protocol DR severity in an observational clinical study. The performance of a computerised DR monitoring and grading system that digitally analyses colour fundus image to measure the enlargement of FAZ and grade DR is evaluated. The range of FAZ area is optimised to accurately determine DR severity stage and progression stages using a Gaussian Bayes classifier. The system achieves high accuracies of above 96%, sensitivities higher than 88% and specificities higher than 96%, in grading of DR severity. In particular, high sensitivity (100%), specificity (>98%) and accuracy (99%) values are obtained for No DR (normal) and Severe NPDR/PDR stages. The system performance indicates that the DR system is suitable for early detection of DR and for effective treatment of severe cases.

Gaussian Bayes classifier for medical diagnosis and grading: Application to diabetic retinopathy

Data from medical imaging system need to be analysed for diagnostics and clinical purposes. In a computerized system, the analysis normally involves classification process to determine disease and its condition. In an earlier work based on a database of 315 fundus images (FINDeRS), it is found that the foveal avascular zone (FAZ) enlargement strongly correlates with diabetic retinopathy (DR) progression having a correlation factor up to 0.883 at significant levels better than 0.01. However, it is also found that the FAZ areas can belong to different DR severity but with different levels of certainty having a Gaussian distribution. In this research work, the suitability of the Gaussian Bayes classifier in determining DR severity level is investigated. A v-fold cross-validation (VFCF) process is applied to the FINDeRS database to evaluate the performance of the classifier. It is shown that the classifier achieved sensitivity of >84%, specificity of >97% and accuracy of >95% for all DR stages. At high values of sensitivity (>95%), specificity (>97%) and accuracy (>98%) obtained for No DR and Severe NPDR/PDR stages, the Gaussian Bayes classifier is suitable as part of a computerised DR grading and monitoring system for early detection of DR and for effective treatment of severe cases.

Determination of Retinal Pigments from Fundus Images using Independent Component Analysis

In the macular area, there are fovea and foveal avascular zone. Foveal avascular zone is the fovea devoid of capillaries. Enlargement of the foveal avascular zone is found to be related to the severity of diabetic retinopathy. Particular colours observed in the retinal image correspond to the optical properties of the pigments and the structure of the retinal layers. In this work, we use independent component analysis to determine retinal pigments from fundus images. The results show that independent component analysis can be used to determine retinal pigments, namely haemoglobin, melanin, and macular pigment. This technique allows us to determine retinal blood vessels and the macula based on the distribution of haemoglobin and macular pigment. Contrast enhancement factor of 3.5 for digital retinal images is achieved. This improvement in contrast reduces the need of applying contrasting agent on patients.

Enhancement of colour fundus image and FFA image using RETICA

Diabetic Retinopathy (DR) is a vision loss impairment due to complications arising from the diabetic condition and affects the retina and resulting pathologies can be monitored by analysing the colour fundus image. However, in retinal fundus images, the contrast between the retinal vasculature and the background is very low and varies within the image making visualisation and analysis of small retinal vasculatures difficult. Therefore, enhancement of the fundus image is important to provide the best visualization of the retinal blood vessels. Fluorescein angiogram overcomes this imaging problem but it is invasive and leads to other physiological problems. In this research work, a non-invasive digital image enhancement technique called RETICA has been developed that overcomes the problem of varied and low contrast in fundus images. RETICA first normalises the varied contrast using a Retinex based method that separates the illumination from the reflectance part of the image followed by ICA that forms the original retinal pigment makeup namely the macular, haemoglobin and melanin retinal pigment. The haemoglobin image exhibits the highest contrast for retinal vessels. Results based on a dataset of 13 fundus images show that RETICA successfully normalises the low and varied contrast and enhances the retinal vessels. It achieved a better average contrast improvement factor of up to 5.56 compared to the invasive FFA with 5.34. This improvement in contrast reduces the need for fluorescein angiogram in DR assessment.

Toward a Fully Automated DR Grading System

Diabetic retinopathy (DR) is a sight threatening complication due to diabetes mellitus that affects the retina. Research shows that the foveal avascular zone (FAZ) could be used to diagnose DR as it enlarges in DR cases due to the loss of capillaries in the perifoveal capillary network. A computerised DR monitoring and grading system based on analysis of FAZ enlargement in colour fundus image has been developed and has high values of sensitivity, specificity and accuracy. However the system is still semi automated. A user interruption is needed in the selection of retinal vessel endpoints to determine the FAZ. Therefore, the objective of this paper is to improve the FAZ determination so that the computerised DR grading system is fully automated. Results show the fully automated system consistently maintains high sensitivity (>73%), specificity (>77%) and accuracy (>77%) for all DR stages. This indicates that the fully automated DR monitoring and grading system has a potential to be used for early detection of DR and for effective treatment of severe cases.

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.

Computerised image analysis of vitiligo lesion: evaluation using manually defined lesion areas

Vitiligo is a cutaneous pigmentary disorder characterized by depigmented macules and patches that result from loss of epidermal melanocytes. Physician evaluates the efficacy of treatment by comparing the extent of vitiligo lesions before and after treatment based on the overall visual impression of the treatment response. This method is called the physicians global assessment (PGA) which is subjective. In this article, we present an innovative digital image processing method to determine vitiligo lesion area in an objective manner.