no code implementations • 1 Feb 2024 • Salman Ul Hassan Dar, Marvin Seyfarth, Jannik Kahmann, Isabelle Ayx, Theano Papavassiliu, Stefan O. Schoenberg, Sandy Engelhardt
Generative latent diffusion models hold a wide range of applications in the medical imaging domain.
no code implementations • 3 Jul 2023 • Salman Ul Hassan Dar, Arman Ghanaat, Jannik Kahmann, Isabelle Ayx, Theano Papavassiliu, Stefan O. Schoenberg, Sandy Engelhardt
Despite the promise, the capacity of such models to memorize sensitive patient training data and synthesize samples showing high resemblance to training data samples is relatively unexplored.
1 code implementation • 23 May 2022 • Hasan Atakan Bedel, Irmak Şıvgın, Onat Dalmaz, Salman Ul Hassan Dar, Tolga Çukur
Encoding is performed on temporally-overlapped windows within the time series to capture local representations.
no code implementations • 13 Mar 2021 • Salman Ul Hassan Dar, Mahmut Yurt, Tolga Çukur
Deep neural networks (DNNs) have recently found emerging use in accelerated MRI reconstruction.
no code implementations • 18 Dec 2020 • Muzaffer Özbey, Mahmut Yurt, Salman Ul Hassan Dar, Tolga Çukur
Mainstream deep models for three-dimensional MRI synthesis are either cross-sectional or volumetric depending on the input.
no code implementations • 29 Nov 2020 • Mahmut Yurt, Salman Ul Hassan Dar, Muzaffer Özbey, Berk Tınaz, Kader Karlı Oğuz, Tolga Çukur
Here, we propose a novel semi-supervised deep generative model that instead learns to recover high-quality target images directly from accelerated acquisitions of source and target contrasts.
no code implementations • 27 Nov 2020 • Mahmut Yurt, Muzaffer Özbey, Salman Ul Hassan Dar, Berk Tınaz, Kader Karlı Oğuz, Tolga Çukur
Comprehensive demonstrations on mainstream MRI reconstruction and synthesis tasks show that ProvoGAN yields superior performance to state-of-the-art volumetric and cross-sectional models.
no code implementations • 25 Sep 2019 • Mahmut Yurt, Salman Ul Hassan Dar, Aykut Erdem, Erkut Erdem, Tolga Çukur
Multi-contrast MRI protocols increase the level of morphological information available for diagnosis.
no code implementations • 27 May 2018 • Salman Ul Hassan Dar, Mahmut Yurt, Mohammad Shahdloo, Muhammed Emrullah Ildız, Tolga Çukur
The proposed method preserves high-frequency details of the target contrast by relying on the shared high-frequency information available from the source contrast, and prevents feature leakage or loss by relying on the undersampled acquisitions of the target contrast.
2 code implementations • 5 Feb 2018 • Salman Ul Hassan Dar, Mahmut Yurt, Levent Karacan, Aykut Erdem, Erkut Erdem, Tolga Çukur
The proposed approach preserves high-frequency details via an adversarial loss; and it offers enhanced synthesis performance via a pixel-wise loss for registered multi-contrast images and a cycle-consistency loss for unregistered images.
no code implementations • 7 Oct 2017 • Salman Ul Hassan Dar, Muzaffer Özbey, Ahmet Burak Çatlı, Tolga Çukur
Methods: Neural networks were trained on thousands of samples from public datasets of either natural images or brain MR images.