Sökning: "unsupervised image-to-image translation"

Hittade 5 uppsatser innehållade orden unsupervised image-to-image translation.

1. 1. Domain Adaptation for Multi-Contrast Image Segmentation in Cardiac Magnetic Resonance Imaging

   Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

   Författare :Thomas Proudhon; [2023]
   Nyckelord :Cardiac Magnetic Resonance Imaging; Deep Learning; Domain Adaptation; Unsupervised Segmentation; Image-to-image Translation;

   Sammanfattning : Accurate segmentation of the ventricles and myocardium on Cardiac Magnetic Resonance (CMR) images is crucial to assess the functioning of the heart or to diagnose patients suffering from myocardial infarction. However, the domain shift existing between the multiple sequences of CMR data prevents a deep learning model trained on a specific contrast to be used on a different sequence. LÄS MER

3. 2. Using Generative Adversarial Networks for H&E-to-HER2 Stain Translation in Digital Pathology Images

   Master-uppsats, Linköpings universitet/Institutionen för medicinsk teknik

   Författare :William Tirmén; [2023]
   Nyckelord :Machine learning; Artificial intelligence; Digital pathology; Image processing; Generative adversarial networks; Image-to-image translation;

   Sammanfattning : In digital pathology, hematoxylin & eosin (H&E) is a routine stain which is performed on most clinical cases and it often provides clinicians with sufficient information for diagnosis. However, when making decisions on how to guide breast cancer treatment, immunohistochemical staining of human epidermal growth factor 2 (HER2 staining) is also needed. LÄS MER

4. 3. Unsupervised Image-to-image translation : Taking inspiration from human perception

   Magister-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

   Författare :Jens Jakob Sveding; [2021]
   Nyckelord :Artificial intelligence; Unsupervised learning; Image-to-Image translation; Generative Adversarial Networks; Structural Similarity Index Measure;

   Sammanfattning : Generative Artificial Intelligence is a field of artificial intelligence where systems can learn underlying patterns in previously seen content and generate new content. This thesis explores a generative artificial intelligence technique used for image-toimage translations called Cycle-consistent Adversarial network (CycleGAN), which can translate images from one domain into another. LÄS MER

5. 4. Generative Adversarial Networks to enhance decision support in digital pathology

   Master-uppsats, Linköpings universitet/Statistik och maskininlärning

   Författare :Alessia De Biase; [2019]
   Nyckelord :Generative Adversarial Networks; Digital Pathology; CycleGAN; Style Transfer;

   Sammanfattning : Histopathological evaluation and Gleason grading on Hematoxylin and Eosin(H&E) stained specimens is the clinical standard in grading prostate cancer. Recently, deep learning models have been trained to assist pathologists in detecting prostate cancer. LÄS MER

7. 5. GANtruth – a regularization method for unsupervised image-to-image translation

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Sebastian Bujwid; [2018]
   Nyckelord :GAN; unsupervised image-to-image translation; deep learning;

   Sammanfattning : In this work, we propose a novel and effective method for constraining the output space of the ill-posed problem of unsupervised image-to-image translation. We make the assumption that the environment of the source domain is known, and we propose to explicitly enforce preservation of the ground-truth labels on the images translated from the source to the target domain. LÄS MER