Alzheimer’s disease (AD), the most common form of dementia, is increasing all over the world. According to the World Alzheimer Report (Patterson, 2018), there were about 50 million people worldwide living with dementia in 2018, and this number is expected to more than triple by 2050. However, there are no effective treatments for AD, and recent drugs targeting tau pathology and amyloid-β at the mild or moderate dementia stage have failed to treat the disease (Doody et al., 2014; Salloway et al., 2014). Moreover, the difficulties of treating mild cognitive impairment (MCI) suggests that treatment should be applied at an earlier stage of the disease (Sperling et al., 2011; Cheng et al., 2017).

Subjective cognitive decline (SCD) has been described as the earliest at-risk state of AD and increases the risk for developing MCI and future AD (Jessen et al., 2014; Hu et al., 2017). It refers to individuals who have self-perceived persistent decline in cognition while neuropsychological tests remain within the normal range (Jessen et al., 2014). Recently, SCD has been receiving increased attention as a risk factor for the development of AD (Jessen et al., 2014).

In addition, studies have suggested that the recruitment sources for SCD studies may have a significant influence on study outcomes. For instance Kuhn et al. (2019) found higher atrophy progression over time and a relatively smaller proportion of APOE ε4 carriers in patients from an SCD clinic compared SCD patients from the community. This finding reinforced their previous study, which found that those who seek consultation are at a higher risk of developing Alzheimer’s clinical syndrome (Perrotin et al., 2017). It indicated that SCD-clinic patients may constitute a more vulnerable population than SCD-community patients. They may be at increased risk for cognitive decline and possibly Alzheimer’s clinical syndrome (Kuhn et al., 2019).

In recent years, brain imaging has been used to investigate the structural and functional alterations of individuals with SCD. A number of papers on SCD have revealved reduced volume in medial temporal lobe (MTL) structures, including the hippocampus and entorhinal cortex (Jessen, 2006; Striepens et al., 2010; Meiberth et al., 2015; Perrotin et al., 2015). These brain alterations are similar to those found in MCI patients, suggesting that SCD may be a pre-MCI stage (Ling et al., 2018). Functional changes have also been detected in individuals with SCD. For example, task-based fMRI studies (Rodda et al., 2010; Hu et al., 2017) have identified neural network disruptions during cognitive processes in SCD compared with controls.

To our knowledge, few studies have been applied on SCD-community individuals. In this study, we combined voxel-based morphometry (VBM) analysis and resting-state functional connectivity to investigate the patterns of structural and functional brain alterations in individuals with SCD recruited from the community compared with healthy controls. We hypothesized that functional connectivity disruption with or without hippocampal atrophy may be detected in SCD-community individuals compared with healthy controls (HC).

All research procedures were conducted in accordance with the Declaration of Helsinki, and the study was registered in http://www.chictr.org.cn.

In this study, we investigated the differences of brain morphometry and resting state functional connectivity (rsFC) between SCD (recruited from the community) and controls. We found that SCD is associated with a GMV decrease in the bilateral hippocampal tails and a GMV increase in the bilateral paracentral lobules. In addition, SCD subjects showed decreased hippocampus rsFC with the mPFC and TPJ.

Hippocampus plays an important role in memory processing and is considered among the first regions affected in AD pathological process (Bradley et al., 2002), of which the decreased volume is one of the most validated and widely used biomarkers of AD (de Flores et al., 2015). Converging evidences demonstrated total (Striepens et al., 2010) or partial (Cherbuin et al., 2015; Yue et al., 2018) hippocampus volume decreased in SCD. In the present study, we found decreased GMV of bilateral hippocampal tails in individuals with SCD which was consistent with previous studies. In addiction, the decreased left hippocampus tail GMV was significantly positive correlated with AVLT-dr scores which showed significant group difference. Studies revealed that AVLT is among the most sensitive episodic memory tests (Simard and van Reekum, 1999) and the delayed recall test was indicated to best identify early AD as well as predict the conversion to AD (Chen et al., 2000; Tierney et al., 2005). It is universally known that episodic memory is the first cognitive domain involved in the AD spectrum and the most sensitive neuropsychological indicator for early AD (Dubois et al., 2007). The AD pattern of gray matter was found in SCD which correlated with episodic memory decline (Peter et al., 2014), and RAVLT demonstrated significant association with the Hippocampal Occupancy Score and hippocampal volumes in the AD spectrum (Sudo et al., 2019). However, the change of hippocampus tends to be asymmetry in SCD, and the structural MRI studies revealed a decreased volume preferred the right hippocampus (Yue et al., 2018). While the verbal information may depend on the left hippocampus (Papanicolaou et al., 2002), which supports our result.

We also found an increased GMV in the paracentral lobule in individuals with SCD, which has not been previously reported. The paracentral lobule is comprised in the sensorimotor network and involved in the primary sensation and movement of the lower back, legs, and feet, as well as control of the bladder and bowel function. The alterations of pathology and structure in the sensorimotor cortices was least observed in aMCI and they are found to be preserved in AD relatively (Pearson et al., 1985; Frisoni et al., 2009). Accordingly, the increased ReHo found in the sensorimotor network might be interpreted as compensatory mechanism to the functional disruptions of other brain networks (Zhen et al., 2018). However, study with the result of functional abnormality in aMCI (Zhao et al., 2014) provided support to the assumption that part of the motor areas might have cognitive functions (Hanakawa et al., 2002). Decreased volume in the paracentral lobule was found in AD (Yi et al., 2009). A recent study revealed altered subnetworks including paracentral lobule which were correlated with the scores of the neurocognitive assessments in SCD (Kim et al., 2019). We speculate that the enlargement of the paracentral lobule may reflecting a potential compensatory mechanism. It is still uncertain whether it has underlying correlation with cognitive function or be affected indirectly by the disruption of other brain regions. Further studies are needed to validate our finding.

We identified significant disrupted connectivity between the hippocampal tail/whole hippocampus and the mPFC and TPJ, and these disruptions were negatively correlated with MoCA scores. These areas are all important regions of the default mode network (DMN) (Buckner et al., 2008), which has been vulnerable to AD. It is worth noting that using the whole hippocampus as a seed resulted in more extensive functional connectivity changes than using only the hippocampal tail as a seed. Studies suggest that hippocampal subregions may play different roles (Knierim et al., 2006; Zeidman and Maguire, 2016) and are affected differently in patients with AD (Arnold et al., 1991; Braak and Braak, 1991). Wang et al. (2006) and de Flores et al. (2017) used the hippocampal subfields or the whole hippocampus as seeds and revealed functional connectivity disruption in brain regions including the mPFC, posterior cingulate cortex, precuneus, temporal lobe, and angular cortex in AD and SCD. Our results are consistent with previous studies and provide indirect support for a previous hypothesis that functional abnormality may occur before structural alteration in patients with SCD (Sun et al., 2016).

Literature suggests that communication between the hippocampus and mPFC plays an important role in memory processes (van Kesteren et al., 2012; Kurczek et al., 2015; Tao et al., 2019). For instance, Van Kesteren et al. (van Kesteren et al., 2012, 2013) investigated how connections between the hippocampus and the mPFC relate to the incorporation of new memories into existing abstract frameworks. They found that hippocampus-mPFC connectivity is enhanced during and shortly after the successful encoding of novel information. Ries et al. (2012) found that functional connectivity between the hippocampal tail and mPFC was associated with accuracy of memory self-rating, which indicates that hippocampus-mPFC functional connectivity is closely related to memory. Investigators have also found decreased functional connectivity between the right hippocampus and superior mPFC in SCD (Hu et al., 2016). In a previous study, we found that mind-body intervention can significantly modulate hippocampus-mPFC rsFC and that this change is associated with memory function changes (Tao et al., 2016). Thus, our results align with previous findings.

The TPJ refers to an area of the cortex at the junction of the posterior superior temporal sulcus, inferior parietal lobule, and lateral occipital cortex. A brain imaging study (Donaldson et al., 2015) suggested that the TPJ is involved in various processes such as episodic memory retrieval, attention, language and speech, temporal processing, social cognition and resting state activity. Kucyi et al. (2012) investigated functional connectivity between the bilateral TPJ and other brain regions, such as the prefrontal, middle cingulate cortex, and insula, and found that the right TPJ functional connectivity was strongest with the ventral attention network, while left TPJ connectivity was strongest with the executive control network (ECN). Consequently, altered functional connectivity between the hippocampus and TPJ may contribute to the abnormal memory and attention function in SCD.

Montreal Cognitive Assessment is an efficient and rapid screening tool for cognitive dysfunction involving memory, executive function, and attention (Jiang et al., 2018) and has moderate specificity and high sensitivity (Mclennan et al., 2011). Previous studies have found that MoCA scores significantly correlate with both structural and functional brain alterations in SCD (Sun et al., 2016; Shu et al., 2017). We also observed a significant correlation between MoCA scores and both structural and functional alterations in the current study, which shed light on the significance of these brain function and morphometry findings.

There are several potential limitations to the present study. First, our results were limited by the relatively small sample sizes. Future studies with larger sample sizes are needed to further confirm our findings. Second, the participants involved in our study were only recruited from the community. SCD participants recruited from hospitals/clinics (i.e., medical help-seeking individuals) should be involved in future studies, and a comparison should be between these two groups. Third, we only included structural MRI and rs-fMRI. Future studies could incorporate relevant biomarkers such as β-amyloid and tau proteins. Finally, the present study was cross-sectional. A longitudinal study is needed to assess whether structural and functional alterations in SCD could predict the development of the disease.

In summary, we found that SCD individuals recruited from the community is associated with decreased GMV at the hippocampal tail, increased GMV at the paracentral lobules, and decreased hippocampus rsFC with the mPFC and TPJ. Our findings may shed new light on the neuroimaging biomarker of SCD.

The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation, to any qualified researcher.

The studies involving human participants were reviewed and approved by the Medicine Ethics Committee of the First Affiliated Hospital, Guangxi University of Chinese Medicine. The patients/participants provided their written informed consent to participate in this study. Written informed consent was obtained from the individual(s) for the publication of any potentially identifiable images or data included in this manuscript.

DD and JK provided the theory behind this work and designed the experiment. LL and LZ made substantial contributions to the present study and revised and handled the manuscript. GD was mainly responsible for image processing and statistical analysis. YW, CL, WM, JS, XN, and BY contributed to sample collection. JK and XM reviewed data and provided the critical comments or suggestions. GW had primary responsibility for final content.

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.