Abstract
Multimodality neuroimages have been widely applied to diagnose mild cognitive impairment (MCI). However, the missing data problem is unavoidable. Most previously developed methods first train a generative adversarial network (GAN) to synthesize missing data and then train a classification network with the completed data. These methods independently train two networks with no information communication. Thus, the resulting GAN cannot focus on the crucial regions that are helpful for classification. To overcome this issue, we propose a hybrid deep learning method. First, a classification network is pretrained with paired MRI and PET images. Afterward, we use the pretrained classification network to guide a GAN by focusing on the features that are helpful for classification. Finally, we synthesize the missing PET images and use them with real MR images to fine-tune the classification model to make it better adapt to the synthesized images. We evaluate our proposed method on the ADNI dataset, and the results show that our method improves the accuracies obtained on the validation and testing sets by 3.84 and 5.82%, respectively. Moreover, our method increases the accuracies for the validation and testing sets by 7.7 and 9.09%, respectively, when we synthesize the missing PET images via our method. An ablation experiment shows that the last two stages are essential for our method. We also compare our method with other state-of-the-art methods, and our method achieves better classification performance.
Highlights
Alzheimer’s disease (AD) is one of the most common irreversible neurodegenerative diseases with progressive and irreversible characteristics, and sufferers of AD account for 50–80% (Guillon et al, 2017; Zhang et al, 2018; Alzheimer’s Association, 2019) of all types of dementia patients
(1) We integrate a classification network into a generative adversarial network (GAN) to generate images that are helpful for classification; (2) we use the synthesized images to fine-tune the classification model so that it can adapt to synthesized images; (3) we iteratively train the classification network and GAN to improve the performance of the two networks
The first two are single-modality networks that are trained by all magnetic resonance imaging (MRI) or positron emission tomography (PET) images, while the last one is a multimodal network that is trained by paired MRI and PET images
Summary
Alzheimer’s disease (AD) is one of the most common irreversible neurodegenerative diseases with progressive and irreversible characteristics, and sufferers of AD account for 50–80% (Guillon et al, 2017; Zhang et al, 2018; Alzheimer’s Association, 2019) of all types of dementia patients. Studies concentrated on single-modality data such as magnetic resonance imaging (MRI) or positron emission tomography (PET) images (Higdon et al, 2004; McEvoy et al, 2009). These studies ignored the inherently complementary information of different modalities, which could reduce the accuracy of early detection. Increasingly many studies have used multimodal data for the early diagnosis of AD and have shown that the proper use of different modalities of data can improve the accuracy of disease diagnosis (Zhang et al, 2011; Gray et al, 2013; Liu et al, 2018a; Zhou et al, 2019). Zhou et al (2019) presented a novel threestage deep feature learning and fusion framework to make full use of data with different modalities, and the results indicated that the multimodal method yielded a statistically significant improvement over the single-modality method
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
