Yazar "Firat, Murat" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    AI-Based Response Classification After Anti-VEGF Loading in Neovascular Age-Related Macular Degeneration
    (Mdpi, 2025) Firat, Murat; Firat, Ilknur Tuncer; Ustundag, Ziynet Fadillioglu; Ozturk, Emrah; Tuncer, Taner
    Background/Objectives: Wet age-related macular degeneration (AMD) is a progressive retinal disease characterized by macular neovascularization (MNV). Currently, the standard treatment for wet AMD is intravitreal anti-VEGF administration, which aims to control disease activity by suppressing neovascularization. In clinical practice, the decision to continue or discontinue treatment is largely based on the presence of fluid on optical coherence tomography (OCT) and changes in visual acuity. However, discrepancies between anatomic and functional responses can occur during these assessments. Methods: This article presents an artificial intelligence (AI)-based classification model developed to objectively assess the response to anti-VEGF treatment in patients with AMD at 3 months. This retrospective study included 120 patients (144 eyes) who received intravitreal bevacizumab treatment. After bevacizumab loading treatment, the presence of subretinal/intraretinal fluid (SRF/IRF) on OCT images and changes in visual acuity (logMAR) were evaluated. Patients were divided into three groups: Class 0, active disease (persistent SRF/IRF); Class 1, good response (no SRF/IRF and >= 0.1 logMAR improvement); and Class 2, limited response (no SRF/IRF but with <0.1 logMAR improvement). Pre-treatment and 3-month post-treatment OCT image pairs were used for training and testing the artificial intelligence model. Based on this grouping, classification was performed with a Siamese neural network (ResNet-18-based) model. Results: The model achieved 95.4% accuracy. The macro precision, macro recall, and macro F1 scores for the classes were 0.948, 0.949, and 0.948, respectively. Layer Class Activation Map (LayerCAM) heat maps and Shapley Additive Explanations (SHAP) overlays confirmed that the model focused on pathology-related regions. Conclusions: In conclusion, the model classifies post-loading response by predicting both anatomic disease activity and visual prognosis from OCT images.
  • Küçük Resim Yok
    Öğe
    Predicting HFA 30-2 Visual Fields with Deep Learning from Multimodal OCT-Fundus Feature Fusion and Structure-Function Discordance Analysis
    (Springer, 2026) Firat, Ilknur Tuncer; Firat, Murat; Erbali, Haci; Tuncer, Taner
    Glaucoma is a leading cause of irreversible vision loss. During clinical follow-up, visual field (VF) tests (Humphrey Field Analyzer 30-2) assesses functional loss, while optical coherence tomography (OCT) and fundus imaging provide structural information. However, VF measurement can be subjective, exhibit test-retest variability, and sometimes exhibit structure-function discordance (SFD). Therefore, predicting VF values from structural images may support clinical decision-making. To estimate Humphrey 30-2 measures (mean deviation (MD), pattern standard deviation (PSD), and point-wise threshold sensitivity (TS)) in glaucoma/ocular hypertension (OHT) using a ViT-B/32-based feature-fusion approach on OCT and fundus images, and to examine the effect of SFD via sensitivity analysis. Visual features were extracted from color optic disc photographs, red-free fundus images, retinal nerve fiber layer (RNFL) thickness map, and circular RNFL plots using Vision Transformer (ViT-B/32)-based models. These features were combined with demographic and clinical data to form a multimodal artificial intelligence model. Global VF indices (MD, PSD) were estimated with probabilistic regression that accounts for uncertainty, and point-wise TS values were predicted using a location-aware network. In a separate analysis, eyes exhibiting SFD were identified and excluded to assess model performance under OCT-VF concordance. Mean absolute errors (MAE) were 2.26, 1.42, and 2.96 dB for MD, PSD, and mean TS, respectively, and the proportions within +/- 2 dB were 59.65%, 75.44%, and 57.90%. After excluding SFD eyes, MAEs decreased to 1.82, 1.30, and 2.12 dB for MD, PSD, and mean TS, respectively; the proportions within +/- 2 dB increased to 66.7%, 76.5% and 62.7%, respectively. These findings indicate that discordance affects performance and that predictions are more reliable in clinically concordant cases. ViT-B/32-based deep feature fusion offers clinically meaningful accuracy for predicting VF metrics from multimodal structural images. SFD was frequently detected among the lowest-performing cases, and this possibility should be considered when interpreting low-performing outputs.
  • Küçük Resim Yok
    Öğe
    Prediction of Pentacam image after corneal cross-linking by linear interpolation technique and U-NET based 2D regression model
    (Pergamon-Elsevier Science Ltd, 2022) Firat, Murat; Cinar, Ahmet; Cankaya, Cem; Firat, Ilknur Tuncer; Tuncer, Taner
    Keratoconus is a common corneal disease that causes vision loss. In order to prevent the progression of the disease, the corneal cross-linking (CXL) treatment is applied. The follow-up of keratoconus after treatment is essential to predict the course of the disease and possible changes in the treatment. In this paper, a deep learningbased 2D regression method is proposed to predict the postoperative Pentacam map images of CXL-treated patients. New images are obtained by the linear interpolation augmentation method from the Pentacam images obtained before and after the CXL treatment. Augmented images and preoperative Pentacam images are given as input to U-Net-based 2D regression architecture. The output of the regression layer, the last layer of the U-Net architecture, provides a predicted Pentacam image of the later stage of the disease. The similarity of the predicted image in the final layer output to the Pentacam image in the postoperative period is evaluated by image similarity algorithms. As a result of the evaluation, the mean SSIM (The structural similarity index measure), PSNR (peak signal-to-noise ratio), and RMSE (root mean square error) similarity values are calculated as 0.8266, 65.85, and 0.134, respectively. These results show that our method successfully predicts the postoperative images of patients treated with CXL.
  • Küçük Resim Yok
    Öğe
    Quantifying Explainability in OCT Segmentation of Macular Holes and Cysts: A SHAP-Based Coverage and Factor Contribution Analysis
    (Mdpi, 2025) Firat, Ilknur Tuncer; Firat, Murat; Tuncer, Taner
    Background: Optical coherence tomography (OCT) can quantify the morphology and dimensions of a macular hole for diagnosis and treatment planning. Objective: The aim of this study was to perform automatic segmentation of macular holes (MHs) and cysts from OCT macular volumes using a deep learning-based model and to quantitatively evaluate decision reliability using the model's focus regions and GradientSHAP-based explainability. Methods: In this study, we automatically segmented MHs and cysts in OCT images from the open-access OIMHS dataset. The dataset comprises 125 eyes from 119 patients and 3859 OCT B-scans. OCT B-scan slices were input to a UNet-48-based model with a 2.5D stacking strategy. Performance was evaluated using Dice and intersection-over-union (IoU), boundary accuracy was evaluated using the 95th-percentile Hausdorff distance (HD95), and calibration was evaluated using the expected calibration error (ECE). Explainability was quantified from GradientSHAP maps using lesion coverage and spatial focus metrics: Attribution Precision in Lesion (APIL tau), which is the proportion of attributions (SHAP contributions) falling inside the lesion; Attribution Recall in Lesion (ARIL tau), which is the proportion of the true lesion covered by the attributions; and leakage (Leak tau = 1 - APIL tau), which is the proportion of attributions falling outside the lesion. Spatial focus was monitored using the center-of-mass distance (COM-dist), which is the Euclidean distance between the attribution center and the segmentation center. All metrics were calculated using the top tau% of the pixels with the highest SHAP values. SHAP features were clustered using PCA and k-means. Explanations were calculated using the clinical mask in ground truth (GT) mode and the model segmentation in prediction (Pred) mode. Results: The Dice/IoU values for holes and cysts were 0.94/0.91 and 0.87/0.81, respectively. Across lesion classes, HD95 = 6 px and ECE = 0.008, indicating good boundary accuracy and calibration. In GT mode (tau = 20), three regimes were observed: (i) retina-dominant: high ARIL (hole: 0.659; cyst: 0.654), high Leak (hole: 0.983; cyst: 0.988), and low COM-dist (hole: 7.84 px; cyst: 6.91 px), with the focus lying within the retina and largely confined to the retinal tissue; (ii) peri-lesional: highest ARIL (hole: 0.684; cyst: 0.719), relatively lower Leak (hole: 0.917; cyst: 0.940), and medium/high COM-dist (hole: 16.22 px; cyst: 10.17 px), with the focus located around the lesion; (iii) narrow-coverage: primarily seen for cysts in GT mode (ARIL: 0.494; Leak: 1.000; COM-dist: 52.02 px), with markedly reduced coverage. In Pred mode, the ARIL20 for holes increased in the retina-dominant cluster (0.758) and COM-dist decreased (6.24 px), indicating better agreement with the model segmentation. Conclusions: The model exhibited high accuracy and good calibration for MH and cyst segmentation in OCT images. Quantitative characterization of SHAP validated the model results. In the clinic, peri-lesion and narrow-coverage conditions are the key situations that require careful interpretation.