[vc_empty_space][vc_empty_space]
Automated Fluorescence as a System to Assist the Diagnosis of Retinal Blood Vessel Leakage
Valindria V.V.a, Mengko T.L.R.b, Sovani I.b
a Institut Teknologi Bandung(ITB), Imaging and Image Processing Group (I2PRG), Indonesia
b Cicendo Eye Hospital, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]Leakage in retinal blood vessel may cause retinal edema which is a sign of diabetic retinopathy. Diabetic retinopathy is a severe and widely spread eye disease which can be regarded as manifestation of diabetes on the retina. So far the most effective diagnosis for this eye disease is early detection through FFA (Fluorescence Fundus Angiography) regular screening that can lead to successful laser treatments in preventing visual loss. FFA is a fundus photography technique which captures the flow/circulation of contrast agent (fluorescence) in retinal blood vessel. The problem arises since the fluorescence is a costly contrast agent and has some side effects to the patients. Some patients felt nauseous and lose their consciousness when the substance was injected to their body. To lower the risks of such screening, the Automated Fluorescence (AF) system is developed to detect the presence of leakage in retinal images obtained from fundus camera, without contrast agent injection (non-invasive). An alternative method for automated detection of the vasculature in retinal images is introduced, which includes Gabor wavelet 2-D, scale addition, and Butterworth high-pass filtering. The experimental results demonstrate the accuracy of the algorithms in detecting both large and small vessels and the efficiency in reducing noise. Method for detection of retinal leakage consists of ANN (Artificial Neural Network), CLAHE (Contrast-Limited Adaptive Histogram Equalization), and morphological operation. The leakage feature in Gabor wavelet image is recognized by the trained ANN system, and this image is combined with CLAHE image in order to give a better detection result. Output images that have been tested by ophthalmologists, give 92% satisfaction in blood vessel detection and 75% correspondence with reference images in leakage detection.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Adaptive histogram equalization,ANN (artificial neural network),Blood vessel detection,Diabetic retinopathy,Gabor,Morphological operations,retina,Retinal blood vessels[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Artificial Neural Network,diabetic retinopathy,Gabor,leakage,retina[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1007/978-3-540-92841-6_23[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]