Classification Prediction of Alzheimer's Disease and Vascular Dementia Using Physiological Data and ECD SPECT Images.

Alzheimer's disease (AD) and vascular dementia (VaD) are the two most common forms of dementia. However, their neuropsychological and pathological features often overlap, making it difficult to distinguish between AD and VaD. In addition to clinical consultation and laboratory examinations, clinical dementia diagnosis in Taiwan will also include Tc-99m-ECD SPECT imaging examination. Through machine learning and deep learning technology, we explored the feasibility of using the above clinical practice data to distinguish AD and VaD. We used the physiological data (33 features) and Tc-99m-ECD SPECT images of 112 AD patients and 85 VaD patients in the Taiwanese Nuclear Medicine Brain Image Database to train the classification model. The results, after filtering by the number of SVM RFE 5-fold features, show that the average accuracy of physiological data in distinguishing AD/VaD is 81.22% and the AUC is 0.836; the average accuracy of training images using the Inception V3 model is 85% and the AUC is 0.95. Finally, Grad-CAM heatmap was used to visualize the areas of concern of the model and compared with the SPM analysis method to further understand the differences. This research method can quickly use machine learning and deep learning models to automatically extract image features based on a small amount of general clinical data to objectively distinguish AD and VaD.

Reproducibility of diffusion tensor imaging-derived parameters: implications for the streptozotocin-induced type 1 diabetic rats.

OBJECTIVE: Diffusion tensor imaging (DTI) is a useful approach for studying neuronal integrity in animals. However, the test-retest reproducibility of DTI techniques in animals has not been discussed. Therefore, the first part of this work was to systematically elucidate the reliability of DTI-derived parameters in an animal study. Subsequently, we applied the DTI approach to an animal model of diabetes in a longitudinal manner. MATERIALS AND METHODS: In Study 1, nine rats underwent two DTI sessions using the same scanner and protocols, with a gap of 4 weeks. The reliability of the DTI-derived parameters was evaluated in terms of sessions and raters. In Study 2, nine rats received a single intraperitoneal injection of 70 mg/kg streptozotocin (STZ) to develop diabetes. Longitudinal DTI scans were used to assess brain alterations before and 4 weeks after STZ administration. RESULTS: In the test-retest evaluation, the inter-scan coefficient of variation (CoV) ranged from 3.04 to 3.73% and 2.12-2.59% for fractional anisotropy (FA) and mean diffusivity (MD), respectively, in different brain regions, suggesting excellent reproducibility. Moreover, rater-dependence had minimal effects on FA and MD quantification, with all inter-rater CoV values less than 4%. Following the onset of diabetes, FA in striatum and cortex were noted to be significantly lower relative to the period where they had not developed diabetes (both P < 0.05). However, when compared to the control group, a significant change in FA caused by diabetes was detected only in the striatum (P < 0.05), but not in the cortex. CONCLUSION: These results demonstrate good inter-rater and inter-scan reliability of DTI in animal studies, and the longitudinal setting has a beneficial effect on detecting small changes in the brain due to diseases.

Differences in brain activity between normal and diabetic rats under isoflurane anesthesia: a resting-state functional MRI study.

BACKGROUND: Altered neural activity based on the fractional amplitude of low-frequency fluctuations (fALFF) has been reported in patients with diabetes. However, whether fALFF can differentiate healthy controls from diabetic animals under anesthesia remains unclear. The study aimed to elucidate the changes in fALFF in a rat model of diabetes under isoflurane anesthesia. METHODS: The first group of rats (n = 5) received a single intraperitoneal injection of 70 mg/kg streptozotocin (STZ) to cause the development of diabetes. The second group of rats (n = 7) received a single intraperitoneal injection of the same volume of solvent. Resting-state functional magnetic resonance imaging was used to assess brain activity at 4 weeks after STZ or solvent administration. RESULTS: Compared to the healthy control animals, rats with diabetes showed significantly decreased fALFF in various brain regions, including the cingulate cortex, somatosensory cortex, insula, and striatum (all P < 0.05). The decreased fALFF suggests the aberrant neural activities in the diabetic rats. No regions were detected in which the control group had a lower fALFF than that in the diabetes group. CONCLUSIONS: The results of this study demonstrated that the fALFF could be used to differentiate healthy controls from diabetic animals, providing meaningful information regarding the neurological pathophysiology of diabetes in animal models.

Analgesia Effect of Verum and Sham Acupuncture Treatments in Primary Dysmenorrhea: A MRI Pilot Study.

Acupuncture is an alternative treatment for primary dysmenorrhea (PDM). However, mechanisms by which acupuncture exerts its analgesic properties are still unclear. This study aimed to explore the cerebral blood flow (CBF) response to verum and sham acupuncture treatments, and further investigate whether pre-treatment CBF is capable of assessing symptom changes after interventions. A total of 11 PDM patients in the verum group and 12 patients in the sham group participated in this study. Pain rating index (PRI), CBF, and gonadal hormone levels were acquired before and after 8-week treatments. Both verum and sham acupuncture treatments exert its analgesic effect on PDM after intervention as PRI reduced (p < 0.05). Blood gonadal levels were not significantly different after acupuncture in both groups (all p > 0.05). In the verum group, intervention-related decreases in CBF were observed in the right dorsal anterior cingulate cortex. In the sham group, regions identified as showing reductions in CBF after acupuncture included the left ventromedial prefrontal cortex, left caudate, and left insula. Patients with higher baseline CBF in the left precuneus and right hippocampus were accompanied with worse treatment response to acupuncture intervention. Mechanisms of verum and sham acupuncture treatments are dissimilar as manifested by different brain responses.

Short- and long-term reproducibility of BOLD signal change induced by breath-holding at 1.5 and 3 T.

Cerebrovascular reactivity (CVR) can give insight into the cerebrovascular function. CVR can be estimated by measuring a blood-oxygen-level-dependent (BOLD) response combined with breath-holding (BH). The reproducibility of this technique has been addressed and existing studies have focused on short-term reproducibility using a 3 T magnetic resonance imaging (MRI) system. However, little is known about the long-term reproducibility of this procedure and the corresponding reproducibility using a 1.5 T MRI system. Here, we systematically examined the short- and long-term reproducibility of BOLD responses to BH across field strengths. Nine subjects participated in three MRI sessions separated by 30 minutes (sessions 1 and 2: short term) and 68-92 days (sessions 1 and 3, long term) at both 1.5 and 3 T MRI. Our findings revealed that significant differences between field strengths were detected in the activated gray matter volume and BOLD signal change (both P < 0.001), with smaller magnitudes at 1.5 T. However, activation patterns were reproducible, independent of the time interval, brain region or field strength. All interscan coefficient of variation values were below the 33% fiducial limit, and the intraclass correlation coefficient values were above 0.4, which is usually considered the acceptability limit in functional studies. These findings suggest that the response of BOLD signal to BH for assessing CVR is reproducible over time at 1.5 and 3 T. This technique can be considered a tool for monitoring longitudinal changes in patients with cerebrovascular diseases, and its use should be encouraged for clinical 1.5 T MRI systems.