Search Results for author: Azade Farshad

Found 22 papers, 5 papers with code

Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis

no code implementations30 Dec 2024 Yousef Yeganeh, Ioannis Charisiadis, Marta Hasny, Martin Hartenberger, Björn Ommer, Nassir Navab, Azade Farshad, Ehsan Adeli

Scaling by training on large datasets has been shown to enhance the quality and fidelity of image generation and manipulation with diffusion models; however, such large datasets are not always accessible in medical imaging due to cost and privacy issues, which contradicts one of the main applications of such models to produce synthetic samples where real data is scarce.

counterfactual Image Generation

Conformable Convolution for Topologically Aware Learning of Complex Anatomical Structures

no code implementations29 Dec 2024 Yousef Yeganeh, Rui Xiao, Goktug Guvercin, Nassir Navab, Azade Farshad

While conventional computer vision emphasizes pixel-level and feature-based objectives, medical image analysis of intricate biological structures necessitates explicit representation of their complex topological properties.

Medical Image Analysis

WiCV@CVPR2024: The Thirteenth Women In Computer Vision Workshop at the Annual CVPR Conference

no code implementations3 Nov 2024 Asra Aslam, Sachini Herath, Ziqi Huang, Estefania Talavera, Deblina Bhattacharjee, Himangi Mittal, Vanessa Staderini, Mengwei Ren, Azade Farshad

In this paper, we present the details of Women in Computer Vision Workshop - WiCV 2024, organized alongside the CVPR 2024 in Seattle, Washington, United States.

VISAGE: Video Synthesis using Action Graphs for Surgery

no code implementations23 Oct 2024 Yousef Yeganeh, Rachmadio Lazuardi, Amir Shamseddin, Emine Dari, Yash Thirani, Nassir Navab, Azade Farshad

The results of our experiments demonstrate high-fidelity video generation for laparoscopy procedures, which enables various applications in SDS.

Video Generation

Physics-Informed Latent Diffusion for Multimodal Brain MRI Synthesis

1 code implementation20 Sep 2024 Sven Lüpke, Yousef Yeganeh, Ehsan Adeli, Nassir Navab, Azade Farshad

Our approach utilizes latent diffusion models and a two-step generative process: first, unobserved physical tissue property maps are synthesized using a latent diffusion model, and then these maps are combined with a physical signal model to generate the final MRI scan.

SANGRIA: Surgical Video Scene Graph Optimization for Surgical Workflow Prediction

no code implementations29 Jul 2024 Çağhan Köksal, Ghazal Ghazaei, Felix Holm, Azade Farshad, Nassir Navab

Graph-based holistic scene representations facilitate surgical workflow understanding and have recently demonstrated significant success.

Disentanglement Graph Generation +1

PRISM: Progressive Restoration for Scene Graph-based Image Manipulation

no code implementations3 Nov 2023 Pavel Jahoda, Azade Farshad, Yousef Yeganeh, Ehsan Adeli, Nassir Navab

We take advantage of the outer part of the masked area as they have a direct correlation with the context of the scene.

Denoising Descriptive +2

SCOPE: Structural Continuity Preservation for Medical Image Segmentation

no code implementations28 Apr 2023 Yousef Yeganeh, Azade Farshad, Goktug Guevercin, Amr Abu-zer, Rui Xiao, Yongjian Tang, Ehsan Adeli, Nassir Navab

Although the preservation of shape continuity and physiological anatomy is a natural assumption in the segmentation of medical images, it is often neglected by deep learning methods that mostly aim for the statistical modeling of input data as pixels rather than interconnected structures.

Anatomy Image Segmentation +3

SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis

no code implementations28 Apr 2023 Azade Farshad, Yousef Yeganeh, Yu Chi, Chengzhi Shen, Björn Ommer, Nassir Navab

To address this limitation, we propose a novel guidance approach for the sampling process in the diffusion model that leverages bounding box and segmentation map information at inference time without additional training data.

Image Generation from Scene Graphs Segmentation +1

DIAMANT: Dual Image-Attention Map Encoders For Medical Image Segmentation

no code implementations28 Apr 2023 Yousef Yeganeh, Azade Farshad, Peter Weinberger, Seyed-Ahmad Ahmadi, Ehsan Adeli, Nassir Navab

Although purely transformer-based architectures showed promising performance in many computer vision tasks, many hybrid models consisting of CNN and transformer blocks are introduced to fit more specialized tasks.

Image Segmentation Medical Image Segmentation +1

DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulation

no code implementations10 Nov 2022 Azade Farshad, Yousef Yeganeh, Helisa Dhamo, Federico Tombari, Nassir Navab

Graph representation of objects and their relations in a scene, known as a scene graph, provides a precise and discernible interface to manipulate a scene by modifying the nodes or the edges in the graph.

Disentanglement Image Manipulation

Shape-Aware Masking for Inpainting in Medical Imaging

no code implementations12 Jul 2022 Yousef Yeganeh, Azade Farshad, Nassir Navab

Inpainting has recently been proposed as a successful deep learning technique for unsupervised medical image model discovery.

Anatomy Image Reconstruction +1

Adaptive Personlization in Federated Learning for Highly Non-i.i.d. Data

no code implementations7 Jul 2022 Yousef Yeganeh, Azade Farshad, Johann Boschmann, Richard Gaus, Maximilian Frantzen, Nassir Navab

Although most medical centers conduct similar medical imaging tasks, their differences, such as specializations, number of patients, and devices, lead to distinctive data distributions.

Clustering Federated Learning +3

Y-Net: A Spatiospectral Dual-Encoder Networkfor Medical Image Segmentation

1 code implementation15 Apr 2022 Azade Farshad, Yousef Yeganeh, Peter Gehlbach, Nassir Navab

Automated segmentation of retinal optical coherence tomography (OCT) images has become an important recent direction in machine learning for medical applications.

 Ranked #1 on Retinal OCT Layer Segmentation on Duke SD-OCT (using extra training data)

Image Segmentation Medical Image Segmentation +3

MIGS: Meta Image Generation from Scene Graphs

1 code implementation22 Oct 2021 Azade Farshad, Sabrina Musatian, Helisa Dhamo, Nassir Navab

We propose MIGS (Meta Image Generation from Scene Graphs), a meta-learning based approach for few-shot image generation from graphs that enables adapting the model to different scenes and increases the image quality by training on diverse sets of tasks.

Diversity Image Generation from Scene Graphs +2

MetaMedSeg: Volumetric Meta-learning for Few-Shot Organ Segmentation

no code implementations18 Sep 2021 Anastasia Makarevich, Azade Farshad, Vasileios Belagiannis, Nassir Navab

In this work, we present MetaMedSeg, a gradient-based meta-learning algorithm that redefines the meta-learning task for the volumetric medical data with the goal to capture the variety between the slices.

Image Segmentation Medical Image Segmentation +3

Unconditional Scene Graph Generation

no code implementations ICCV 2021 Sarthak Garg, Helisa Dhamo, Azade Farshad, Sabrina Musatian, Nassir Navab, Federico Tombari

Scene graphs, composed of nodes as objects and directed-edges as relationships among objects, offer an alternative representation of a scene that is more semantically grounded than images.

Anomaly Detection Graph Generation +3

Inverse Distance Aggregation for Federated Learning with Non-IID Data

no code implementations17 Aug 2020 Yousef Yeganeh, Azade Farshad, Nassir Navab, Shadi Albarqouni

Federated learning (FL) has been a promising approach in the field of medical imaging in recent years.

Federated Learning

Semantic Image Manipulation Using Scene Graphs

1 code implementation CVPR 2020 Helisa Dhamo, Azade Farshad, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari, Christian Rupprecht

In our work, we address the novel problem of image manipulation from scene graphs, in which a user can edit images by merely applying changes in the nodes or edges of a semantic graph that is generated from the image.

Image Inpainting Image Manipulation +1

Adversarial Network Compression

no code implementations28 Mar 2018 Vasileios Belagiannis, Azade Farshad, Fabio Galasso

Neural network compression has recently received much attention due to the computational requirements of modern deep models.

Neural Network Compression Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.