Deep learning for multi-contrast MRI synthesis
| buir.advisor | Çukur, Tolga | |
| dc.contributor.author | Yurt, Mahmut | |
| dc.date.accessioned | 2021-08-17T10:51:36Z | |
| dc.date.available | 2021-08-17T10:51:36Z | |
| dc.date.copyright | 2021-07 | |
| dc.date.issued | 2021-07 | |
| dc.date.submitted | 2021-08-06 | |
| dc.department | Department of Electrical and Electronics Engineering | en_US |
| dc.description | Cataloged from PDF version of article. | en_US |
| dc.description | Thesis (Master's): Bilkent University, Department of Electrical and Electronics Engineering, İhsan Doğramacı Bilkent University, 2021. | en_US |
| dc.description | Includes bibliographical references (leaves 81-97). | en_US |
| dc.description.abstract | Magnetic resonance imaging (MRI) possesses the unique versatility to acquire images under a diverse array of distinct tissue contrasts. Multi-contrast images, in turn, better delineate tissues, accumulate diagnostic information, and enhance radiological analyses. Yet, prolonged, costly exams native to multi-contrast pro-tocols often impair the diversity, resulting in missing images from some contrasts. A promising remedy against this limitation arises as image synthesis that recovers missing target contrast images from available source contrast images. Learning-based models demonstrated remarkable success in this source-to-target mapping due to their prowess in solving even the most demanding inverse problems. Main-stream approaches proposed for synthetic MRI were typically subjected to a model training to perform either one-to-one or many-to-one mapping. One-to-one models manifest elevated sensitivity to detailed features of the given source, but they perform suboptimally when source-target images are poorly linked. Meanwhile, many-to-one counterparts pool information from multiple sources, yet this comes at the expense of losing detailed features uniquely present in cer-tain sources. Furthermore, regardless of the mapping, they both innately demand large training sets of high-quality source and target images Fourier-reconstructed from Nyquist-sampled acquisitions. However, time and cost considerations put significant challenges in compiling such datasets. To address these limitations, here we first propose a novel multi-stream model that task-adaptively fuses unique and shared image features from a hybrid of multiple one-to-one streams and a single many-to-one stream. We then introduce a novel semi-supervised learning framework based on selective tensor loss functions to learn high-quality image synthesis directly from a training dataset of undersampled acquisitions, bypass-ing the undesirable data requirements of deep learning. Demonstrations on brain MRI images from healthy subjects and glioma patients indicate the superiority of the proposed approaches against state-of-the-art baselines. | en_US |
| dc.description.degree | M.S. | en_US |
| dc.description.statementofresponsibility | by Mahmut Yurt | en_US |
| dc.format.extent | xxiii, 97 leaves : illustrations (some color) ; 30 cm. | en_US |
| dc.identifier.itemid | B138667 | |
| dc.identifier.uri | http://hdl.handle.net/11693/76446 | |
| dc.language.iso | English | en_US |
| dc.publisher | Bilkent University | en_US |
| dc.rights | info:eu-repo/semantics/openAccess | en_US |
| dc.subject | MRI synthesis | en_US |
| dc.subject | Deep learning | en_US |
| dc.subject | Multi-stream | en_US |
| dc.subject | Semi-supervised | en_US |
| dc.title | Deep learning for multi-contrast MRI synthesis | en_US |
| dc.title.alternative | Çoklu kontrast MRG için derin öğrenme | en_US |
| dc.type | Thesis | en_US |