A computer-aided healthcare system for cataract classification and grading based on fundus image analysis

Guo, Liye; Yang, Ji-Jiang; Peng, Lihui; Li, Jianqiang; Liang, Qingfeng

doi:10.1016/j.compind.2014.09.005

Cited by 123 publications

(54 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the appropriate weight of misclassifying positive is within a relatively narrow interval [4–6]. Specifically, when the weights of the misclassifying positive and negative samples were only set to four and one, respectively, the performance of the threshold-moving method (ACC: 91.18%, SPC: 92.50%, SEN: 87.62%, F1_M: 84.06%, and G_M: 89.99%) was almost equal to that of CS-ResCNN method.…”

Section: Resultsmentioning

confidence: 99%

“…Many computer-aided diagnosis methods can achieve satisfactory performance when the sample distribution is roughly uniform between different classes [5–8]. However, imbalanced datasets are inevitable in a variety of medical data analysis situations [6, 8–11], which causes the existing classifiers to exhibit a high false negative rate (FNR) or false positive rate (FPR). False-positive results can cause undue worry, economic burden and waste of medical resources, whereas false-negative misclassifications can lead to delayed treatment onset, cause poor treatment outcomes and hinder the use of artificial intelligence technology for diagnosis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network

et al. 2017

View full text Add to dashboard Cite

BackgroundOcular images play an essential role in ophthalmological diagnoses. Having an imbalanced dataset is an inevitable issue in automated ocular diseases diagnosis; the scarcity of positive samples always tends to result in the misdiagnosis of severe patients during the classification task. Exploring an effective computer-aided diagnostic method to deal with imbalanced ophthalmological dataset is crucial.MethodsIn this paper, we develop an effective cost-sensitive deep residual convolutional neural network (CS-ResCNN) classifier to diagnose ophthalmic diseases using retro-illumination images. First, the regions of interest (crystalline lens) are automatically identified via twice-applied Canny detection and Hough transformation. Then, the localized zones are fed into the CS-ResCNN to extract high-level features for subsequent use in automatic diagnosis. Second, the impacts of cost factors on the CS-ResCNN are further analyzed using a grid-search procedure to verify that our proposed system is robust and efficient.ResultsQualitative analyses and quantitative experimental results demonstrate that our proposed method outperforms other conventional approaches and offers exceptional mean accuracy (92.24%), specificity (93.19%), sensitivity (89.66%) and AUC (97.11%) results. Moreover, the sensitivity of the CS-ResCNN is enhanced by over 13.6% compared to the native CNN method.ConclusionOur study provides a practical strategy for addressing imbalanced ophthalmological datasets and has the potential to be applied to other medical images. The developed and deployed CS-ResCNN could serve as computer-aided diagnosis software for ophthalmologists in clinical application.Electronic supplementary materialThe online version of this article (10.1186/s12938-017-0420-1) contains supplementary material, which is available to authorized users.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network

et al. 2017

View full text Add to dashboard Cite

show abstract

“…In [3] the cataract affected image classification from fundus image is done using wavelet transform. It consists of fundus image pre-processing, feature extraction, followed by cataract classification and grading.…”

Section: Childhood Glaucoma-starts In Childhoodmentioning

confidence: 99%

Glaucoma detection from retinal images

Devi¹,

Sudha²,

Suraj

2015

2015 2nd International Conference on Electronics and Communication Systems (ICECS)

View full text Add to dashboard Cite

Glaucoma disease detection from retinal images using classifiers like least square -Support Vector Machine classifier, random forest, dual Sequential Minimal Optimization classifier, naive bayes classifier and artificial neural networks. The textual features obtained from retinal images are used for this classification. Energy distributions over wavelet sub bands provides these features. The proposed system is using discrete wavelet transform to extract different wavelet features obtained from the three filters symlets (sym3), daubechies (db3)and biorthogonal (bio3.3, bio3.5, and bio3.7) wavelet filters. The energy signatures obtained from 2-D discrete wavelet transform is used for classifying and detecting glaucomatous and normal retinal images.

show abstract

“…Assuming that the present children HMNs number of one RN is nodenum, and if nodenum is higher than the threshold number nodemax, the transmission power of the RN will adjust from 0 to according to formula (1). On the contrary, if the nodenum is lower than the minimum threshold nodemin, the transmission power of the RN will adjust according to formula (2). Consider…”

Section: Network Topology Managementmentioning

confidence: 99%

Implementation and Real-Time and Reliability Evaluation of a WHMS Improved by LHRP and SMAM

Sun

Fang

Zhao

et al. 2015

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

A dynamic heterogeneous and multihop (DHMH) wireless health monitoring system (WHMS) as a three-tier semi-self-organizing health monitoring network was presented. From bottom to top, the first tire of the network is the mobile data acquisition layer (DAL), the second tire of the network is the data transporting layer (DTL), and the third tire of the network is the data collection layer (DCL). A RF power control based topology management mechanism is proposed to balance the network load and to improve the network throughput. A lightweight hierarchical routing protocol (LHRP) was designed to reduce the transmission delay and improve the network throughput. For the mobile DAL nodes, the seamless mobile access mechanism (SMAM) was designed to ensure the low packet loss ratio. To evaluate the network performance, the end-to-end delay, the averaged reception ratio, and the network throughput of the DHMH were tested and the results proved that the network performance of the DHMH was improved.

show abstract

A computer-aided healthcare system for cataract classification and grading based on fundus image analysis

Cited by 123 publications

References 46 publications

Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network

Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network

Glaucoma detection from retinal images

Implementation and Real-Time and Reliability Evaluation of a WHMS Improved by LHRP and SMAM

Contact Info

Product

Resources

About