Publications by authors named "F Hashimoto"

Deep learning, particularly convolutional neural networks (CNNs), has advanced positron emission tomography (PET) image reconstruction. However, it requires extensive, high-quality training datasets. Unsupervised learning methods, such as deep image prior (DIP), have shown promise for PET image reconstruction.

View Article and Find Full Text PDF
Article Synopsis
  • Scientists studied a special type of PET scanner that can take pictures of multiple animals at once to save time and money.
  • They tested how well this scanner works by comparing images of four objects to images of one object, checking for things like clarity and accuracy.
  • The results showed that using the scanner with four animals didn't affect the image quality much, proving it's great for helping with drug research.
View Article and Find Full Text PDF