Hybrid CNN Based Computer-Aided Diagnosis System for Choroidal Neovascularization, Diabetic Macular Edema, Drusen Disease Detection from OCT Images

Tuncer, Seda Arslan; Çınar, Ahmet; Fırat, Murat

doi:10.18280/ts.380314

Cited by 6 publications

(3 citation statements)

References 19 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Especially in the case of unbalanced distribution among class labels, the accuracy parameter alone is not sufficient. [ 35 - 37 ] Since the F1 score increase indicates an increase in the model’s success, the F1 score value is parallel to the accuracy value showing that the model is consistent. At the same time, the NPV value increase in the case of using SVM compared to using only Mask R-CNN clearly shows the model’s success in detecting the hemorrhage absence.…”

Section: Discussionmentioning

confidence: 99%

A revolutionary acute subdural hematoma detection based on two-tiered artificial intelligence model

Kaya

Gençtürk

Gülağız

2023

Ulus Travma Acil Cerrahi Derg

View full text Add to dashboard Cite

BACKGROUND: The article was planned to make the first evaluation in terms of acute subdural hemorrhages, thinking that it can help in appropriate pathologies by tomography interpretation with the artificial intelligence (AI) method, at least in a way to quickly warn the responsible doctor. METHODS: A two-level AI-based hybrid method was developed. The proposed model uses the mask-region convolutional neural network (Mask R-CNN) technique, which is a deep learning model, in the hemorrhagic region’s mask generation stage, and a problem-specific, optimized support vector machines (SVM) technique which is a machine learning model in the binary classification stage. Furthermore, the bee colony algorithm was used for the optimization of SVM algorithms’ parameters. RESULTS: In the first stage, the mean average precision (mAP) value was obtained as 0.754 when the intercept over union (IOU) value was taken as 0.5 with the Mask R-CNN architecture used. At the same time, when a 5-fold cross-validation was applied, the mAP value was obtained 0.736. With the hyperparameter optimization for both Mask R-CNN and the SVM algorithm, the accuracy of the two-level classification process was obtained as 96.36%. Furthermore, final false-negative rate and false-positive rate values were obtained as 6.20%, and 2.57%, respectively. CONCLUSION: With the proposed model, both the detection of hemorrhage and the presentation of the suspicious area to the physician were performed more successfully on two dimensional (2D) images with low cost and high accuracy compared to similar studies and today’s interpretations with telemedicine techniques.

show abstract

Section: Discussionmentioning

confidence: 99%

A revolutionary acute subdural hematoma detection based on two-tiered artificial intelligence model

Kaya

Gençtürk

Gülağız

2023

Ulus Travma Acil Cerrahi Derg

View full text Add to dashboard Cite

show abstract

“…The goal is to obtain the optimal separation hyperplane that will separate the classes from each other. In other words, it is to maximize the distance between support vectors belonging to different classes [30][31][32].…”

Section: Endmentioning

confidence: 99%

Determining the Type of Document Read Using Eye Movement Properties by Hybrid CNN Method

Çetintaş¹,

Tuncer²

2022

View full text Add to dashboard Cite

By examining the change of eye movements during reading, it is possible to determine the type of document read. Returning to the previous position (negative saccade), blink, fixation, and position are important indicators in determining the type of document being read. In this paper, a hybrid deep learning model is proposed to determine the type of document read. The MPIIDPEye dataset, which includes eye movement data of 10-minute comic, newspaper and text document readings from 20 participants, was used. First, the eye movements obtained over time were augmented by the non-linear interpolation technique. In order to process the data of each class with convolutional neural network, spectrogram images of the signals were created. Spectrogram images were given as input to Resnet architectures and the features in the Fc1000 layer were combined. Concatenated feature vectors were given as an input to feature selection algorithms. The most effective features in classification accuracy were determined and classified using the SVM algorithm. The classification was carried out for 3 different cases, and the highest accuracy of 98.41% was obtained for case-2, where Fixation, Position, and Blink properties were used.

show abstract

“…In people with diabetes, DME is the main factor contributing to visual loss and blindness [3]. Leaving it untreated for a year or more can result in significant vision loss [4]. For diagnosing specific diseases, scientists were forced to develop an advanced and effective technique in these situations [5].…”

Section: Introductionmentioning

confidence: 99%

Automated classification of age-related macular degeneration from optical coherence tomography images using deep learning approach

Nagamani,

Sudhakar

2023

IJ-AI

View full text Add to dashboard Cite

<p>Early detection of macular diseases can prevent vision loss. Manual screening can be unreliable due to the similarity in the pathological presentations of common retinal illnesses like age-related macular degeneration (AMD). Researchers are becoming more interested in the accurate automated computer-based detection of macular diseases. Using healthy optical coherence tomography (OCT) images, the drusens (early stage) and choroidal neovascularization (CNV) (late stage) of AMD are thus classified using a completely different approach in this paper. The new deep learning (DL) model is proposed for multiple OCT image segmentation of ophthalmological diseases using attention-based nested U-Net (ANU-Net). The flower pollination optimization algorithm (FPOA) is used to optimize the hyperparameters of the network. The SqueezeNet-based classification can be made in the pre-processed images. A dataset from the University of California San Diego (UCSD) is used to evaluate the proposed method. 98.7% accuracy, 99.8% specificity, and 99.7% sensitivity are achieved by the proposed method. The proposed method produces better identification results for automated preliminary diagnosis of macular diseases in hospitals and eye clinics due to the positive classification results.</p>

show abstract

Hybrid CNN Based Computer-Aided Diagnosis System for Choroidal Neovascularization, Diabetic Macular Edema, Drusen Disease Detection from OCT Images

Cited by 6 publications

References 19 publications

A revolutionary acute subdural hematoma detection based on two-tiered artificial intelligence model

A revolutionary acute subdural hematoma detection based on two-tiered artificial intelligence model

Determining the Type of Document Read Using Eye Movement Properties by Hybrid CNN Method

Automated classification of age-related macular degeneration from optical coherence tomography images using deep learning approach

Contact Info

Product

Resources

About