In this work,we aim to introduce some modifications to the Anam-Net deep neural network(DNN)model for segmenting optic cup(OC)and optic disc(OD)in retinal fundus images to estimate the cup-to-disc ratio(CDR).The CDR i...In this work,we aim to introduce some modifications to the Anam-Net deep neural network(DNN)model for segmenting optic cup(OC)and optic disc(OD)in retinal fundus images to estimate the cup-to-disc ratio(CDR).The CDR is a reliable measure for the early diagnosis of Glaucoma.In this study,we developed a lightweight DNN model for OC and OD segmentation in retinal fundus images.Our DNN model is based on modifications to Anam-Net,incorporating an anamorphic depth embedding block.To reduce computational complexity,we employ a fixed filter size for all convolution layers in the encoder and decoder stages as the network deepens.This modification significantly reduces the number of trainable parameters,making the model lightweight and suitable for resource-constrained applications.We evaluate the performance of the developed model using two publicly available retinal image databases,namely RIM-ONE and Drishti-GS.The results demonstrate promising OC segmentation performance across most standard evaluation metrics while achieving analogous results for OD segmentation.We used two retinal fundus image databases named RIM-ONE and Drishti-GS that contained 159 images and 101 retinal images,respectively.For OD segmentation using the RIM-ONE we obtain an f1-score(F1),Jaccard coefficient(JC),and overlapping error(OE)of 0.950,0.9219,and 0.0781,respectively.Similarly,for OC segmentation using the same databases,we achieve scores of 0.8481(F1),0.7428(JC),and 0.2572(OE).Based on these experimental results and the significantly lower number of trainable parameters,we conclude that the developed model is highly suitable for the early diagnosis of glaucoma by accurately estimating the CDR.展开更多
Purpose: To investigate the difference of stereometric parameters of optic nerve head between the normal subjects and patients with big-cupped disk and primary open angle glaucoma (POAG).Methods: Twenty-two cases (44 ...Purpose: To investigate the difference of stereometric parameters of optic nerve head between the normal subjects and patients with big-cupped disk and primary open angle glaucoma (POAG).Methods: Twenty-two cases (44 eyes) of normal subjects, 17 cases (34 eyes) of patients with big-cupped disk and 19 cases (37 eyes) of patients with POAG underwent Heidelberg Retina Tomograph (HRT) examination to get topography images and stereometric parameters of optic nerve head.Results: The stereometric parameters of optic nerve head of the normal, patients with big-cupped disk and POAG were 1) disk area (mm2): 1. 995± 0. 501, 2. 407±0. 661 and 2. 248±0.498; 2) cup area (mm2): 0.573±0.264, 1. 095±0. 673 and 1. 340±0. 516; 3) cup/disk ratio: 0. 25±0. 095, 0. 428±0. 176 and 0. 589±0.195; 4) rim area (mm2): 1.461±0.328, 1.312±0.418 and 0. 905± 0.409; 5)cup volume (mm3): 0. 108±0. 073, 0. 347±0. 346 and 0. 550 ±0. 394; 6) rim volume (mm3): 0. 421±0. 111, 0. 378±0. 225 and 0. 224±0. 189; 7) mean cup展开更多
目的探讨生理性大视杯随时间推移,有无形态学变化。方法对200只生理性大视杯眼进行随访,每间隔3个月随访1次,每眼至少随访12个月以上。随访项目包括,各视乳头参数、眼压、视野、眼轴长度以及屈光度等。结果符合上述随访要求的有148只生...目的探讨生理性大视杯随时间推移,有无形态学变化。方法对200只生理性大视杯眼进行随访,每间隔3个月随访1次,每眼至少随访12个月以上。随访项目包括,各视乳头参数、眼压、视野、眼轴长度以及屈光度等。结果符合上述随访要求的有148只生理性大视杯眼,平均随访16个月。发现视杯面积(P<0.05),杯盘面积比、视杯容积、盘沿容积、平均视杯深度、最大视杯深度、轮廓线高度变化、平均视网膜神经纤维层厚度、视网膜神经纤维层横截面积均变大(P<0.01);盘沿面积变小(P<0.05);视盘面积、杯形测量无显著性变化。眼压值变小(P<0.01),视野 MS 变大、MD 变小(P<0.01),眼轴变长(P<0.01),近视加深(P<0.01)。结论经随访,生理性大视杯形态结构参数有一定变化,但无青光眼性神经损害。(中国眼耳鼻喉科杂志,2006,6:164～166)展开更多
基金funded byResearchers Supporting Project Number(RSPD2024R 553),King Saud University,Riyadh,Saudi Arabia.
文摘In this work,we aim to introduce some modifications to the Anam-Net deep neural network(DNN)model for segmenting optic cup(OC)and optic disc(OD)in retinal fundus images to estimate the cup-to-disc ratio(CDR).The CDR is a reliable measure for the early diagnosis of Glaucoma.In this study,we developed a lightweight DNN model for OC and OD segmentation in retinal fundus images.Our DNN model is based on modifications to Anam-Net,incorporating an anamorphic depth embedding block.To reduce computational complexity,we employ a fixed filter size for all convolution layers in the encoder and decoder stages as the network deepens.This modification significantly reduces the number of trainable parameters,making the model lightweight and suitable for resource-constrained applications.We evaluate the performance of the developed model using two publicly available retinal image databases,namely RIM-ONE and Drishti-GS.The results demonstrate promising OC segmentation performance across most standard evaluation metrics while achieving analogous results for OD segmentation.We used two retinal fundus image databases named RIM-ONE and Drishti-GS that contained 159 images and 101 retinal images,respectively.For OD segmentation using the RIM-ONE we obtain an f1-score(F1),Jaccard coefficient(JC),and overlapping error(OE)of 0.950,0.9219,and 0.0781,respectively.Similarly,for OC segmentation using the same databases,we achieve scores of 0.8481(F1),0.7428(JC),and 0.2572(OE).Based on these experimental results and the significantly lower number of trainable parameters,we conclude that the developed model is highly suitable for the early diagnosis of glaucoma by accurately estimating the CDR.
文摘Purpose: To investigate the difference of stereometric parameters of optic nerve head between the normal subjects and patients with big-cupped disk and primary open angle glaucoma (POAG).Methods: Twenty-two cases (44 eyes) of normal subjects, 17 cases (34 eyes) of patients with big-cupped disk and 19 cases (37 eyes) of patients with POAG underwent Heidelberg Retina Tomograph (HRT) examination to get topography images and stereometric parameters of optic nerve head.Results: The stereometric parameters of optic nerve head of the normal, patients with big-cupped disk and POAG were 1) disk area (mm2): 1. 995± 0. 501, 2. 407±0. 661 and 2. 248±0.498; 2) cup area (mm2): 0.573±0.264, 1. 095±0. 673 and 1. 340±0. 516; 3) cup/disk ratio: 0. 25±0. 095, 0. 428±0. 176 and 0. 589±0.195; 4) rim area (mm2): 1.461±0.328, 1.312±0.418 and 0. 905± 0.409; 5)cup volume (mm3): 0. 108±0. 073, 0. 347±0. 346 and 0. 550 ±0. 394; 6) rim volume (mm3): 0. 421±0. 111, 0. 378±0. 225 and 0. 224±0. 189; 7) mean cup
文摘目的探讨生理性大视杯随时间推移,有无形态学变化。方法对200只生理性大视杯眼进行随访,每间隔3个月随访1次,每眼至少随访12个月以上。随访项目包括,各视乳头参数、眼压、视野、眼轴长度以及屈光度等。结果符合上述随访要求的有148只生理性大视杯眼,平均随访16个月。发现视杯面积(P<0.05),杯盘面积比、视杯容积、盘沿容积、平均视杯深度、最大视杯深度、轮廓线高度变化、平均视网膜神经纤维层厚度、视网膜神经纤维层横截面积均变大(P<0.01);盘沿面积变小(P<0.05);视盘面积、杯形测量无显著性变化。眼压值变小(P<0.01),视野 MS 变大、MD 变小(P<0.01),眼轴变长(P<0.01),近视加深(P<0.01)。结论经随访,生理性大视杯形态结构参数有一定变化,但无青光眼性神经损害。(中国眼耳鼻喉科杂志,2006,6:164～166)
