Poster by H. Zhao at SPIE-ETAI, San Diego, 22 August 2023

Low dose and standard dose PET translation. (Image by H. Zhao.)
High quality PET image synthesis using GAN-transformer
Hang Zhao
Date: 21 August 2023
Time: 5:30 PM PDT

Amyloid-beta positron emission tomography (PET) is used for the diagnosis of Alzheimer’s disease (AD). However, the inherent radiation of radioactive tracers used for PET is potentially harmful to the human body. In this study, we present a deep-learning framework for generating high-quality standard-dose PET brain images from scans that have a simulated reduced injected dose of 12.5% of the standard injected dose, thus reducing radiation exposure without compromising image quality. This novel approach achieves remarkable similarity to full-dose images in both visual and quantitative aspects. Our method offers the potential of enabling safer and more accessible PET imaging for early Alzheimer’s disease detection.

Soft Matter Lab members present at SPIE Optics+Photonics conference in San Diego, 20-24 August 2023

The Soft Matter Lab participates to the SPIE Optics+Photonics conference in San Diego, CA, USA, 20-24 August 2023, with the presentations listed below.

Giovanni Volpe is also co-author of the presentations:

  • Jiawei Sun (KI): (Poster) Assessment of nonlinear changes in functional brain connectivity during aging using deep learning
    21 August 2023 • 5:30 PM – 7:00 PM PDT | Conv. Ctr. Exhibit Hall A
  • Blanca Zufiria Gerbolés (KI): (Poster) Exploring age-related changes in anatomical brain connectivity using deep learning analysis in cognitively healthy individuals
    21 August 2023 • 5:30 PM – 7:00 PM PDT | Conv. Ctr. Exhibit Hall A
  • Mite Mijalkov (KI): Uncovering vulnerable connections in the aging brain using reservoir computing
    22 August 2023 • 9:15 AM – 9:30 AM PDT | Conv. Ctr. Room 6C

Hang Zhao joins the Soft Matter Lab

(Photo by A. Argun.)
Hang Zhao starts his Ph.D. at the Physics Department of the University of Gothenburg on 5th, September 2022.

Hang has a Master’s degree in Biomedical Engineering from Linköping University, where he focused on machine learning and medical image processing.

In his PhD, he will focus on machine learning, graph theory, and neuroscience.

Presentation by Hang Zhao, 3 May 2022

Medical image segmentation using deep learning.
Hang Zhao
3 May 2022, 11:00

Image segmentation and synthesis of CT image based on deep learning: Deep learning methods for medical image segmentation are hindered by the lack of training data. This thesis aims to develop a method that overcomes this problem. Basic U-net trained on XCAT phantom data was tested first. The segmentation results were unsatisfactory even when artificial quantum noise was added. As a workaround, CycleGAN was used to add tissue textures to the XCAT phantom images by analyzing patient CT images. The generated images were used to train the network. The textures introduced by CycleGAN improved the segmentation, but some errors remained. Basic U-net was replaced with Attention U-net, which further improved the segmentation. More work is needed to fine-tune and thoroughly evaluate the method. The results obtained so far demonstrate the potential of this method for the segmentation of medical images. The proposed algorithms may be used in iterative image reconstruction algorithms in multi-energy computed tomography.

3D Cell nuclei segmentation using digital nuclei phantom and 3D deep learning methods : The analysis of microscopy image is helpful to pathological analysis. Nowadays, deep learning has shown the capabilities of processing the medical imaging data. However, developing deep learning methods in microscopy image analysis can be challenging because of the lack of ground truth and various resolution of microscopy image data. This project aims to build a digital nuclei phantom that simulates the actual microscopy images, including mitotic rate, nucleus size, noise, point spread function, and diverse resolutions. The phantom images were used to train 3D deep neural network for nuclei segmentation. The trained neural network was tested for segmentation on datasets with different resolutions. The neural network successfully performed segmentation on most resolutions in our dataset, and the segmentation results reflect the morphology and density of nuclei in microscopy images. The future work will focus on improving the nuclei phantom to generate more realistic phantom images, thereby further helping with segmentation.

Bio:
My name is Hang, I took my bachelor’s in China on radiophysics, and master’s at Linköping University on biomedical imaging. After I graduate, I joined Karolinska as a research assistant on 3D microscopy image processing. Now, I am working at Linköping university as a full time research engineer, contributing to cardiovascular MR image processing, supervised by Petter Dyverfeldt.