FILM: finding the location of microaneurysms on the retina

Akut, Rohan

doi:10.1007/s13534-019-00136-6

Cited by 17 publications

(18 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, to further verify the detection performance of the proposed algorithm for MAs, the automatic detection performance of MAs in fundus images was compared with that of previous studies with image processing methods [7], classifier methods [8,9], CNN to detect MAs [10], YOLO network to automatically detect MAs [14], and automatic segmentation of MAs using improved U-Net network [15]. The results are presented in Table 3.…”

Section: Resultsmentioning

confidence: 99%

“…As Table 3 only indicates that the proposed YOLOv4-Pro can effectively detect the existence of MA, it does not reflect the accurate positioning ability of the proposed algorithm for MAs. IoU and AP were used to evaluate its accurate positioning ability, and its positioning performance was compared to that of the previous study including study [10,14]. MAs were detected by CNN in study [10] and by YOLO network in study [14].…”

Section: Resultsmentioning

confidence: 99%

“…IoU and AP were used to evaluate its accurate positioning ability, and its positioning performance was compared to that of the previous study including study [10,14]. MAs were detected by CNN in study [10] and by YOLO network in study [14]. Based on an IoU of 0.5, test the performance of three models for detecting MAs at intervals of 0.1, and list their best detection results in Table 4.…”

Section: Resultsmentioning

confidence: 99%

“…Dai et al [13] proposed a clinical report guided multi screening convolution neural network, which used a small amount of supervision information in the clinical report to identify potential MAs through image to text map in feature space. Furthermore, Akut [14] proposed an automatic MA detection and location algorithm based on YOLO. Xu et al [15] proposed an automatic MA segmentation algorithm based on improved U-Net network.…”

Section: Literature Reviewmentioning

confidence: 99%

See 3 more Smart Citations

Detection and location of microaneurysms in fundus images based on improved YOLOv4 with IFCM

Gao

Fan

Fang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is one of the leading causes of blindness for people suffering from diabetes. Microaneurysm (MA) is the initial symptom of DR. MA is a lesion based disease which starts as small red spots on the retina and increases in size as the DR progresses which finally leads to blindness. So eliminating the lesion can effectively prevent DR at an early stage. However, due to complex retinal structure, different brightness and contrast of fundus images with effects of factors such as different patients, environment changes, and difference in acquisition equipment, it is difficult for existing detection algorithms to achieve accurate results of MA detection and location. Therefore, the detection algorithm of improved YOLOv4 (YOLOv4‐Pro) was proposed. First, an improved Fuzzy C‐Means (IFCM) clustering algorithm was proposed to optimize anchor parameters of target samples to improve matching results between anchors and feature graphs. In order to control noise and improve efficiency, a median filtering method was employed to update the criterion function of the original FCM algorithm, and a K‐means algorithm was employed to initialize clustering. Second, a SENet attention module was added in the backbone of YOLOv4 to enhance key information and suppress background, improving the confidence of MA effectively. Finally, the spatial pyramid pooling (SPP) module was added to the neck to enhance the acceptance domain of the output characteristics of the backbone network, and profits separating of important context information. The improved YOLOv4 with IFCM was verified on the Kaggle DR dataset and compared with other methods. Experimental results show that optimizing the prior frame with the IFCM algorithm can make it suitable to frame the Kaggle DR dataset, which improves the detection accuracy of the network by nearly 5%, and provides a nice performance on detection and location of MA in fundus images. This would help ophthalmologists finding the exact location of MA on retina, thereby simplifying the process and eliminating any manual intervention.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Detection and location of microaneurysms in fundus images based on improved YOLOv4 with IFCM

Gao

Fan

Fang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…As deep learning is an emerging computer vision application in medical image processing and proving to be of great help to mankind in machine learning [15], several MA detection methods based on convolutional neural networks (CNN) [8,[29][30][31][32] were proposed. The main limitation of CNN is the requirement of larger training time [15].…”

mentioning

confidence: 99%

Microaneurysms detection in color fundus images using machine learning based on directional local contrast

Long

Chen

et al. 2020

BioMed Eng OnLine

View full text Add to dashboard Cite

Background: As one of the majorcomplications of diabetes, diabetic retinopathy (DR) is a leadingcause of visual impairment and blindness due to delayed diagnosisand intervention. Microaneurysms appear as the earliest symptom ofDR. Accurate and reliable detection of microaneurysms in colorfundus images has great importance for DR screening.Methods: A microaneurysms' detection methodusing machine learning based on directional local contrast (DLC) isproposed for the early diagnosis of DR. First, blood vessels wereenhanced and segmented using improved enhancement function based onanalyzing eigenvalues of Hessian matrix. Next, with blood vesselsexcluded, microaneurysm candidate regions were obtained using shapecharacteristics and connected components analysis. After imagesegmented to patches, the features of each microaneurysm candidatepatch were extracted, and each candidate patch was classified intomicroaneurysm or non-microaneurysm. The main contributions of ourstudy are (1) making use of directional local contrast inmicroaneurysms' detection for the first time, which does make sensefor better microaneurysms' classification.(2) Applying threedifferent machine learning techniques for classification andcomparing their performance for microaneurysms' detection. Theproposed algorithm was trained and tested on e-ophtha MA database,and further tested on another independent DIARETDB1 database.Results of microaneurysms' detection on the two databases wereevaluated on lesion level and compared with existing algorithms. Results:The proposed method has achieved better performance compared with existing algorithms on accuracy and computation time. On e-ophtha MA and DIARETDB1 databases, the area under curve (AUC) of receiver operating characteristic (ROC) curve was 0.87 and 0.86, respectively. The free-response ROC (FROC) score on the two databases was 0.374 and 0.210, respectively. The computation time per image with resolution of 2544×1969, 1400×960 and 1500×1152 is 29 s, 3 s and 2.6 s, respectively. Conclusions:The proposed methodusing machine learning based on directional local contrast of imagepatches can effectively detect microaneurysms in color fundus imagesand provide an effective scientific basis for early clinical DRdiagnosis.

show abstract