Sökning: "pix2pix"

Visar resultat 1 - 5 av 7 uppsatser innehållade ordet pix2pix.

1. 1. 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

3. 2. Deep Learning Based Out-of-focus Detection on Surveillance Footage

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Hanna Bengtsson; Teodora Kerac; [2023]
   Nyckelord :Deep Learning; CNN; Out-of-focus detection; Mathematics and Statistics;

   Sammanfattning : Loss of focus in surveillance cameras can occur due to factors such as environmental aspects, sabotage or system errors. The focus loss leads to degraded footage that is of no use for either post-investigation or automatic video analysis. LÄS MER

4. 3. 3D Dose Prediction from Partial Dose Calculations using Convolutional Deep Learning models

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

   Författare :Sergio Felipe Liberman Bronfman; [2021]
   Nyckelord :Machine learning; Modeling and simulation; Life and medical sciences; Predictive models; Artificial Neural Networks; Physics computing; Maskininlärning; Modellering och simulering; Livs och medicinska vetenskaper; Förutsägbara modeller; Artificiellt neurala nätverk; Fysikberäkning;

   Sammanfattning : In this thesis, the problem of predicting the full dose distribution from a partially modeled dose calculation is addressed. Two solutions were studied: a vanilla Hierarchically Densely Connected U-net (HDUnet) and a Conditional Generative Adversarial Network (CGAN) with HDUnet as a generator. LÄS MER

5. 4. Generating synthetic brain MR images using a hybrid combination of Noise-to-Image and Image-to-Image GANs

   Master-uppsats, Linköpings universitet/Statistik och maskininlärning

   Författare :Lennart Schilling; [2020]
   Nyckelord :Generative Adversarial Network; GAN;

   Sammanfattning : Generative Adversarial Networks (GANs) have attracted much attention because of their ability to learn high-dimensional, realistic data distributions. In the field of medical imaging, they can be used to augment the often small image sets available. LÄS MER

7. 5. Generating Synthetic Schematics with Generative Adversarial Networks

   Kandidat-uppsats, Högskolan Kristianstad/Fakulteten för naturvetenskap

   Författare :John Daley Jr; [2020]
   Nyckelord :Synthetic data; generative adversarial network; machine learning; convolutional neural network; python; tensorflow; blueprints; Pix2Pix;

   Sammanfattning : This study investigates synthetic schematic generation using conditional generative adversarial networks, specifically the Pix2Pix algorithm was implemented for the experimental phase of the study. With the increase in deep neural network’s capabilities and availability, there is a demand for verbose datasets. LÄS MER