Ipek Oguz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ipek Oguz has a total of 91 co-authors. Here are the top co-authors by number of shared publications:
Dewei Hu
Vanderbilt University
9 shared publicationsHao Li
Vanderbilt University
8 shared publicationsYuankai K. Tao
Vanderbilt University
5 shared publications- Hao Li
Department of Computer Science, Vanderbilt University, Nashville, USA
4 shared publications - Jiacheng Wang
Vanderbilt University
4 shared publications Xing Yao
Vanderbilt University
4 shared publications
Latest Publications
- 1 October 2026
- Published by Springer Nature
- p. 191-209
From Minimal Clinical Prompts to 3D: Spacing-Aware Prompt Propagation for Multimodal Prostate Lesion Segmentation in bpMRI
- 1 October 2026
- Published by Springer Nature
- p. 191-209
From Minimal Clinical Prompts to 3D: Spacing-Aware Prompt Propagation for Multimodal Prostate Lesion Segmentation in bpMRI
- Open Access
- 8 July 2026
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 86
Towards Verified and Targeted Explanations through Formal Methods
As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations of model behavior that are not only interpretable but also trustworthy with formal guarantees. Existing XAI methods fall short of this requirement: heuristic attribution techniques (e.g., LIME, Integrated Gradients) highlight influential features for individual predictions but offer no mathematical guarantees about decision boundaries, while formal explanation methods verify robustness properties yet remain untargeted, analyzing the nearest boundary regardless of whether it represents a critical risk. In safety-critical systems, however, not all misclassifications carry equal consequences; confusing a “Stop” sign for a “60 kph” sign is far more dangerous than confusing it with a “No Passing” sign. Practitioners therefore lack a principled way to answer a fundamental safety question: how resilient is a model’s classification against a specific, high-risk alternative? We introduce ViTaX (Verified and Targeted Explanations), a formal XAI framework that addresses this gap by generating targeted semifactual explanations with mathematical guarantees. For a given input (class y) and a user-specified critical alternative (class t), ViTaX performs two key steps: (1) it identifies the minimal feature subset most sensitive to the y → t transition using class-specific sensitivity heuristics, and (2) it applies formal reachability analysis to guarantee that perturbing these features by ε is insufficient to flip the classification to t. This guarantee constitutes a verified semifactual: “even if these critical features change by ε classification y persists against t." We formalize this reasoning through Targeted ε-Robustness, a formal property that certifies whether an identified feature subset remains robust under perturbation toward a specific target class. By unifying semifactual explanations, class-specific targeting, and formal verification, ViTaX is the first method to provide formally guaranteed explanations of a model’s resilience against specific, user-identified alternatives. Our evaluations on image classification (MNIST, GTSRB, EMNIST) and regression (TaxiNet) demonstrate that ViTaX achieves significantly higher fidelity (e.g., over 30% improvement) and minimal explanation cardinality compared to existing methods. These results establish ViTaX as a scalable and trustworthy foundation for verifiable, targeted XAI.
- 8 July 2026
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 86
Open AccessTowards Verified and Targeted Explanations through Formal Methods
As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations of model behavior that are not only interpretable but also trustworthy with formal guarantees. Existing XAI methods fall short of this requirement: heuristic attribution techniques (e.g., LIME, Integrated Gradients) highlight influential features for individual predictions but offer no mathematical guarantees about decision boundaries, while formal explanation methods verify robustness properties yet remain untargeted, analyzing the nearest boundary regardless of whether it represents a critical risk. In safety-critical systems, however, not all misclassifications carry equal consequences; confusing a “Stop” sign for a “60 kph” sign is far more dangerous than confusing it with a “No Passing” sign. Practitioners therefore lack a principled way to answer a fundamental safety question: how resilient is a model’s classification against a specific, high-risk alternative? We introduce ViTaX (Verified and Targeted Explanations), a formal XAI framework that addresses this gap by generating targeted semifactual explanations with mathematical guarantees. For a given input (class y) and a user-specified critical alternative (class t), ViTaX performs two key steps: (1) it identifies the minimal feature subset most sensitive to the y → t transition using class-specific sensitivity heuristics, and (2) it applies formal reachability analysis to guarantee that perturbing these features by ε is insufficient to flip the classification to t. This guarantee constitutes a verified semifactual: “even if these critical features change by ε classification y persists against t." We formalize this reasoning through Targeted ε-Robustness, a formal property that certifies whether an identified feature subset remains robust under perturbation toward a specific target class. By unifying semifactual explanations, class-specific targeting, and formal verification, ViTaX is the first method to provide formally guaranteed explanations of a model’s resilience against specific, user-identified alternatives. Our evaluations on image classification (MNIST, GTSRB, EMNIST) and regression (TaxiNet) demonstrate that ViTaX achieves significantly higher fidelity (e.g., over 30% improvement) and minimal explanation cardinality compared to existing methods. These results establish ViTaX as a scalable and trustworthy foundation for verifiable, targeted XAI.
- Open Access
Endo-SemiS: Towards Robust Semi-Supervised Image Segmentation for Endoscopic Video
In this paper, we present Endo-SemiS, a semi-supervised segmentation framework for providing reliable segmentation of endoscopic video frames with limited annotation. EndoSemiS uses 4 strategies to improve performance by effectively utilizing all available data, particularly unlabeled data: (1) Cross-supervision between two individual networks that supervise each other; (2) Uncertainty-guided pseudo-labels from unlabeled data, which are generated by selecting high-confidence regions to improve their quality; (3) Joint pseudolabel supervision, which aggregates reliable pixels from the pseudo-labels of both networks to provide accurate supervision for unlabeled data; and (4) Mutual learning, where both networks learn from each other at the feature and image levels, reducing variance and guiding them toward a consistent solution. Additionally, a separate corrective network that utilizes spatiotemporal information from endoscopy video to improve segmentation performance. Endo-SemiS is evaluated on two clinical applications: kidney stone laser lithotomy from ureteroscopy and polyp screening from colonoscopy. Compared to state-of-the-art segmentation methods, Endo-SemiS substantially achieves superior results on both datasets with limited labeled data. The code is publicly available at https://github.com/MedICL-VU/Endo-SemiS
Open AccessEndo-SemiS: Towards Robust Semi-Supervised Image Segmentation for Endoscopic Video
In this paper, we present Endo-SemiS, a semi-supervised segmentation framework for providing reliable segmentation of endoscopic video frames with limited annotation. EndoSemiS uses 4 strategies to improve performance by effectively utilizing all available data, particularly unlabeled data: (1) Cross-supervision between two individual networks that supervise each other; (2) Uncertainty-guided pseudo-labels from unlabeled data, which are generated by selecting high-confidence regions to improve their quality; (3) Joint pseudolabel supervision, which aggregates reliable pixels from the pseudo-labels of both networks to provide accurate supervision for unlabeled data; and (4) Mutual learning, where both networks learn from each other at the feature and image levels, reducing variance and guiding them toward a consistent solution. Additionally, a separate corrective network that utilizes spatiotemporal information from endoscopy video to improve segmentation performance. Endo-SemiS is evaluated on two clinical applications: kidney stone laser lithotomy from ureteroscopy and polyp screening from colonoscopy. Compared to state-of-the-art segmentation methods, Endo-SemiS substantially achieves superior results on both datasets with limited labeled data. The code is publicly available at https://github.com/MedICL-VU/Endo-SemiS
- 12 September 2025
- Published by Springer Nature
- p. 477-496
ISL: Monitoring Image Segmentation Logic in Medical Imaging Analysis
- 12 September 2025
- Published by Springer Nature
- p. 477-496
ISL: Monitoring Image Segmentation Logic in Medical Imaging Analysis
- 17 January 2025
- Published by Springer Nature
- p. 119-129
Retinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging
- 17 January 2025
- Published by Springer Nature
- p. 119-129
Retinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging
- 3 October 2024
- Published by Springer Nature
- Vol. 15003, 389-399
PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts
In this paper, we present PRISM, a Promptable and Robust Interactive Segmentation Model, aiming for precise segmentation of 3D medical images. PRISM accepts various visual inputs, including points, boxes, and scribbles as sparse prompts, as well as masks as dense prompts. Specifically, PRISM is designed with four principles to achieve robustness: (1) Iterative learning. The model produces segmentations by using visual prompts from previous iterations to achieve progressive improvement. (2) Confidence learning. PRISM employs multiple segmentation heads per input image, each generating a continuous map and a confidence score to optimize predictions. (3) Corrective learning. Following each segmentation iteration, PRISM employs a shallow corrective refinement network to reassign mislabeled voxels. (4) Hybrid design. PRISM integrates hybrid encoders to better capture both the local and global information. Comprehensive validation of PRISM is conducted using four public datasets for tumor segmentation in the colon, pancreas, liver, and kidney, highlighting challenges caused by anatomical variations and ambiguous boundaries in accurate tumor identification. Compared to state-of-the-art methods, both with and without prompt engineering, PRISM significantly improves performance, achieving results that are close to human levels. The code is publicly available at https://github.com/MedICL-VU/PRISM.
- 3 October 2024
- Published by Springer Nature
- Vol. 15003, 389-399
PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts
In this paper, we present PRISM, a Promptable and Robust Interactive Segmentation Model, aiming for precise segmentation of 3D medical images. PRISM accepts various visual inputs, including points, boxes, and scribbles as sparse prompts, as well as masks as dense prompts. Specifically, PRISM is designed with four principles to achieve robustness: (1) Iterative learning. The model produces segmentations by using visual prompts from previous iterations to achieve progressive improvement. (2) Confidence learning. PRISM employs multiple segmentation heads per input image, each generating a continuous map and a confidence score to optimize predictions. (3) Corrective learning. Following each segmentation iteration, PRISM employs a shallow corrective refinement network to reassign mislabeled voxels. (4) Hybrid design. PRISM integrates hybrid encoders to better capture both the local and global information. Comprehensive validation of PRISM is conducted using four public datasets for tumor segmentation in the colon, pancreas, liver, and kidney, highlighting challenges caused by anatomical variations and ambiguous boundaries in accurate tumor identification. Compared to state-of-the-art methods, both with and without prompt engineering, PRISM significantly improves performance, achieving results that are close to human levels. The code is publicly available at https://github.com/MedICL-VU/PRISM.
- 1 September 2024
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 6 (5) , e230521
Deep Learning–based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets
To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various b values, to align with the style of images acquired using b values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (P < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (P < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (P < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (P < .001) for lesions with PI-RADS scores of 4 or greater. UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various b values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high b value). Keywords: Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, b Value Supplemental material is available for this article. © RSNA, 2024
- 1 September 2024
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 6 (5) , e230521
Deep Learning–based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets
To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various b values, to align with the style of images acquired using b values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (P < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (P < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (P < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (P < .001) for lesions with PI-RADS scores of 4 or greater. UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various b values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high b value). Keywords: Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, b Value Supplemental material is available for this article. © RSNA, 2024
- 1 August 2024
- Published by SAGE Publications in Journal of Endourology
- Vol. 38 (8) , 836-842
Automated Upper Tract Urothelial Carcinoma Tumor Segmentation During Ureteroscopy Using Computer Vision Techniques
Introduction: Endoscopic tumor ablation of upper tract urothelial carcinoma (UTUC) allows for tumor control with the benefit of renal preservation but is impacted by intraoperative visibility. We sought to develop a computer vision model for real-time, automated segmentation of UTUC tumors to augment visualization during treatment. Materials and Methods: We collected 20 videos of endoscopic treatment of UTUC from two institutions. Frames from each video ( N = 3387) were extracted and manually annotated to identify tumors and areas of ablated tumor. Three established computer vision models (U-Net, U-Net++, and UNext) were trained using these annotated frames and compared. Eighty percent of the data was used to train the models while 10% was used for both validation and testing. We evaluated the highest performing model for tumor and ablated tissue segmentation using a pixel-based analysis. The model and a video overlay depicting tumor segmentation were further evaluated intraoperatively. Results: All 20 videos (mean 36 ± 58 seconds) demonstrated tumor identification and 12 depicted areas of ablated tumor. The U-Net model demonstrated the best performance for segmentation of both tumors (area under the receiver operating curve [AUC-ROC] of 0.96) and areas of ablated tumor (AUC-ROC of 0.90). In addition, we implemented a working system to process real-time video feeds and overlay model predictions intraoperatively. The model was able to annotate new videos at 15 frames per second. Conclusions: Computer vision models demonstrate excellent real-time performance for automated upper tract urothelial tumor segmentation during ureteroscopy.
- 1 August 2024
- Published by SAGE Publications in Journal of Endourology
- Vol. 38 (8) , 836-842
Automated Upper Tract Urothelial Carcinoma Tumor Segmentation During Ureteroscopy Using Computer Vision Techniques
Introduction: Endoscopic tumor ablation of upper tract urothelial carcinoma (UTUC) allows for tumor control with the benefit of renal preservation but is impacted by intraoperative visibility. We sought to develop a computer vision model for real-time, automated segmentation of UTUC tumors to augment visualization during treatment. Materials and Methods: We collected 20 videos of endoscopic treatment of UTUC from two institutions. Frames from each video ( N = 3387) were extracted and manually annotated to identify tumors and areas of ablated tumor. Three established computer vision models (U-Net, U-Net++, and UNext) were trained using these annotated frames and compared. Eighty percent of the data was used to train the models while 10% was used for both validation and testing. We evaluated the highest performing model for tumor and ablated tissue segmentation using a pixel-based analysis. The model and a video overlay depicting tumor segmentation were further evaluated intraoperatively. Results: All 20 videos (mean 36 ± 58 seconds) demonstrated tumor identification and 12 depicted areas of ablated tumor. The U-Net model demonstrated the best performance for segmentation of both tumors (area under the receiver operating curve [AUC-ROC] of 0.96) and areas of ablated tumor (AUC-ROC of 0.90). In addition, we implemented a working system to process real-time video feeds and overlay model predictions intraoperatively. The model was able to annotate new videos at 15 frames per second. Conclusions: Computer vision models demonstrate excellent real-time performance for automated upper tract urothelial tumor segmentation during ureteroscopy.
- Open Access
Retinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging
We propose a novel framework for retinal feature point alignment, designed for learning cross-modality features to enhance matching and registration across multi-modality retinal images. Our model draws on the success of previous learning-based feature detection and description methods. To better leverage unlabeled data and constrain the model to reproduce relevant keypoints, we integrate a keypoint-based segmentation task. It is trained in a self-supervised manner by enforcing segmentation consistency between different augmentations of the same image. By incorporating a keypoint augmented self-supervised layer, we achieve robust feature extraction across modalities. Extensive evaluation on two public datasets and one in-house dataset demonstrates significant improvements in performance for modality-agnostic retinal feature alignment. Our code and model weights are publicly available at \url{https://github.com/MedICL-VU/RetinaIPA}.
Open AccessRetinal IPA: Iterative KeyPoints Alignment for Multimodal Retinal Imaging
We propose a novel framework for retinal feature point alignment, designed for learning cross-modality features to enhance matching and registration across multi-modality retinal images. Our model draws on the success of previous learning-based feature detection and description methods. To better leverage unlabeled data and constrain the model to reproduce relevant keypoints, we integrate a keypoint-based segmentation task. It is trained in a self-supervised manner by enforcing segmentation consistency between different augmentations of the same image. By incorporating a keypoint augmented self-supervised layer, we achieve robust feature extraction across modalities. Extensive evaluation on two public datasets and one in-house dataset demonstrates significant improvements in performance for modality-agnostic retinal feature alignment. Our code and model weights are publicly available at \url{https://github.com/MedICL-VU/RetinaIPA}.
- 6 April 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 95, 103164
Domain generalization for retinal vessel segmentation via Hessian-based vector field
- 6 April 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 95, 103164
Domain generalization for retinal vessel segmentation via Hessian-based vector field