Dataset Information

Optimal transport- and kernel-based early detection of mild cognitive impairment patients based on magnetic resonance and positron emission tomography images.

ABSTRACT:

Background

To help clinicians provide timely treatment and delay disease progression, it is crucial to identify dementia patients during the mild cognitive impairment (MCI) stage and stratify these MCI patients into early and late MCI stages before they progress to Alzheimer's disease (AD). In the process of diagnosing MCI and AD in living patients, brain scans are collected using neuroimaging technologies such as computed tomography (CT), magnetic resonance imaging (MRI), or positron emission tomography (PET). These brain scans measure the volume and molecular activity within the brain resulting in a very promising avenue to diagnose patients early in a minimally invasive manner.

Methods

We have developed an optimal transport based transfer learning model to discriminate between early and late MCI. Combing this transfer learning model with bootstrap aggregation strategy, we overcome the overfitting problem and improve model stability and prediction accuracy.

Results

With the transfer learning methods that we have developed, we outperform the current state of the art MCI stage classification frameworks and show that it is crucial to leverage Alzheimer's disease and normal control subjects to accurately predict early and late stage cognitive impairment.

Conclusions

Our method is the current state of the art based on benchmark comparisons. This method is a necessary technological stepping stone to widespread clinical usage of MRI-based early detection of AD.

SUBMITTER: Liu Z

PROVIDER: S-EPMC8742368 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundDeep learning has recently shown great potential in medical image reconstruction tasks. For positron emission tomography (PET) images, the direct reconstruction from raw data to radioactivity images using deep learning without any constraint may lead to the production of nonexistent structures. The aim of this study was to specifically develop and test a flexibly deep learning-based reconstruction network guided by any form of prior knowledge to achieve high quality and high reliability reconstruction.MethodsWe developed a novel prior information-guided reconstruction network (PIGRN) with a dual-channel generator and a 2-scale discriminator based on a conditional generative adversarial network (cGAN). Besides the raw data channel, an additional channel is provided in the generator for prior information (PI) to guide the training phase. The PI can be reconstructed images obtained via conventional methods, nuclear medical images from other modalities, attenuation correction maps from time-of-flight-PET (TOF-PET) data, or any other physical parameters. For this study, the reconstructed images generated by filtered back projection (FBP) were chosen as the input of the additional channel. To improve the image quality, a 2-scale discriminator was adopted which can focus on both the coarse and fine field of the reconstruction images. Experiments were carried out on both a simulation dataset and a real Sprague Dawley (SD) rat dataset.ResultsTwo classic deep learning-based reconstruction networks, including U-Net and Deep-PET, were compared in our study. Compared with these two methods, our method could provide much higher quality PET image reconstruction in the study of the simulation dataset. The peak signal-to-noise ratio (PSNR) value reached 31.8498, and the structure similarity index measure (SSIM) value reached 0.9754. The real study on SD rats indicated that the proposed network also has strong generalization ability.ConclusionsThe flexible PIGRN based on cGAN for PET images combines both raw data and PI. The results of comparison experiments and a generalization experiment based on simulation and SD rat datasets demonstrated that the proposed PIGRN has the ability to improve image quality and has strong generalization ability.

Project description:Fluorine-18-fluoro-2-deoxy-D-glucose (FDG) is widely used as positron-emission-tomography (PET) radiotracer for the detection and staging of human cancer. Tumor uptake of FDG varies substantially between different cancer types and between patients with the same tumor type. The molecular basis for this heterogeneity is unknown. Using cancer cell lines and primary human tumors of distinct histologic origins, we here show that increased FDG uptake is universally associated with coordinate upregulation of genes within the glycolysis, pentose-phosphate, and other related metabolic pathways. In primary human breast cancers, this FDG signature shows significant overlap with established breast cancer signatures for the “basal-like” disease subtype and “poor prognosis”. FDG high breast cancer showed significantly more gene copy number alterations genome wide than FDG low cancers. About 50 % of primary breast cancers with high FDG uptake and FDG gene expression signature show DNA copy gain encompassing the c-myc gene locus and express gene sets regulated by the transcription factor MYC. Our data shows that FDG-PET marks a distinct subset of “basal-like” human breast cancer which is characterized by MYC and prognostically unfavorable gene expression signatures, suggesting that FDG-PET imaging may be useful to risk-stratify patients with locally advanced breast cancer. Our general strategy to identify molecular determinants of FDG-retention through a genome-wide approach consisted of FDG uptake measurements in cancer cell lines and primary human tumors, the selection of samples with particularly high versus low FDG-retention, and subsequent pathway-based analysis of RNA expression data collected from these samples. Cell line RNA was extracted from a 10 cm plate seeded simultaneously and at the same density as the wells for FDG-uptake assays. For primary human tumor samples, RNA was extracted from macrodissected frozen tumor tissue. All cell line RNA samples and the astrocytoma RNA aliquots were hybridized to Affymetrix U133 Plus 2.0 arrays. All primary breast cancer RNA samples were hybridized to Affymetrix U133A arrays.