---

Background and Objective: Dysfunction and loss of basal forebrain cholinergic neurons and their cortical projections are the earliest pathological events in the pathogenesis of alzheimer disease (AD). This study was done to evaluate the effect of donepezil hydrochloride on reference and working memory caused by mutual electrical lesion of the nucleus basalis magnocellularis (NBM) in animal model of AD.
Methods: In this experimental study, 56 adult male Wistar rats were allocated into 8 group (n=7) including: control (intact), NBM lesion group, which received electrically- induced lesion (0.5 m A, 3s) in NBM, Sham group (the electrode was impaled in to the NBM with no lesion), donepezil groups (lesion + 0.1, 1, 5, 10 mg/kg/bw of donepezil hydrochloride) and vehicle group (NBM lesion+ saline). Acquisition and retention testing were done by using an eight-radial arm maze, in which, the patterns of arm entries in each group was recorded for calculating correct choice, working memory errors, reference memory error and latency.
Results: The spatial learning of animals in the lesion of NBM group significantly reduced in compared to controls (P<0.05). Moreover, no effect on spatial learning was seen in the sham group compared with the lesion group. The post-lesion treatment with donepezil hydrochloride in dose-dependent manner improved the parameters of spatial memory errors in the acquisition and retention tasks in comparision with the lesion group (P<0.05).
Conclusion: Treatment with donepezil hydrochloride, dose-dependently improves cognitive impairment induced by the destruction of the nucleus basalis magnocellularis.

---

Background and Objective: Memantine (MEM) an uncompetitive N-methyl-D-aspartate receptor antagonist is used for treatment of patients with Alzheimer disease. This study aimed to examine the effect of Memantine on the spatial learning and memory in electrical lesion’s model of nucleus basalis magnocellularis (NBM) in animal model of Alzheimer's disease.
Methods: In this experimental study, 56 adult male Wistar rats were allocated into eight groups: control group; lesion group, which received bilateral electrically lesion (0.5 mA, 3s) in NBM; sham group (the electrode was entered into the NBM with no lesion); Memantine groups (lesion+1 mg/kg/bw of MEM; lesion+3 mg/kg/bw of  MEM; lesion+5 mg/kg/bw of  MEM; lesion+7 mg/kg/bw of MEM) and Vehicle group (lesion+0.2 mL saline). After one week, animals were trained to perform the Y-maze task for five days. Twenty five days after training, a retention test was performed to determine long-term memory.
Results: The bilateral lesion of NBM impaired the spatial learning compared to the control and sham groups (P<0.05). No effect on spatial learning was seen in saline group compared with the lesion group. The treatment with Memantine in  lesion+MEM 3 mg/kg/bw, lesion+MEM 5mg/kg/bw and lesion+MEM 7mg/kg/bw groups significantly improved spatial learning (P<0.05). Moreover, no significant difference of memory was observed between the results in the 5th day of training and the retention test of the 30th day.
Conclusion: Treatment with memantine improves spatial learning defects in electrical leisions model of NBM of Alzheimer's disease in dose dependent manner in animal model.

---

Background and Objective: Alzheimer is the most common form of dementia in elderly persons. Oxidative stress is one of the main pathological factors in Alzheimer’s disease. This study was done to investigate the effect of crosin on histological changes of hippocampus and memory impairment which induced by scopolamine in the male rats.
Methods: In this experimental study, 30 male rats were randomly allocated into 3 groups including: control, scopolamine and scopolamine with crosin treated groups. Scopolamine with dose of 3 mg/kg/bw for one week and crocin with dose of 30mg/kg for two weeks were administered, intraperitoneally. The learning and spatial memory parameters were evaluated by Morris water maze test. Then the animals were sacrificed and their hippocampi were removed immediately for histological evaluation.
Results: Scopolamine injection causes significantly increased the number of dark cells in CA1 region of hippocampus in compared to control group (P<0.05). Treatment with crocin decreased dark cells and increased light cells number in CA1 region of hippocampus (P<0.05). Also treatment with crocin decreased memory impairment that induced by scopolamine in rats (P<0.05).
Conclusion: It seems that treatment with crocin has protective effects against neuronal damage of CA1 region of hippocampus and memory impairment that induced by scopolamine.

---

Background and Objective: Early diagnosis of Alzheimer's disease (AD) seems necessary due to the high cost of care and treatment, the uncertainty of existing therapies, as well as the worrying future of the patient. This study was conducted to AD diagnosis by MRI images using artificial intelligence methods.
Methods: In this research, a computer system for early detection of AD with using machine learning algorithms is presented in the framework of computer-aided process. Conditional random field and Inception deep neural network have been adapted for brain MR images to detect AD. Since hippocampal tissue is one of the first tissues to be affected by AD, hence for the early detection of this disease, the hippocampus was located from other brain tissues firstly and then due to the extent to which this tissue is affected, the diagnosis was made. Conditional random field could accurately extract hippocampal fragments of different shapes in all three brain planes. These components serve as the basis for feature extraction by the deep network. The proposed method was tested on standard ADNI dataset images and its performance was demonstrated. The used Inception network has been trained on the huge ImageNet dataset. One of the important steps is knowledge transfer of the problem under consideration. To facilitate this, data augmentation process was applied according to the shape and structure of the hippocampus.
Results: The implemented method in this research, achieved to 98.51% accuracy for two-class classification of "Alzheimer" versus "Normal control" and achieved to 93.41% accuracy for two-class classification of "Mild cognitive impairment" versus "Normal control", which increased by 2.56% and 8.41%, compared with the rival methods, respectively.
Conclusion: The achieved results of this study showed that the using of artificial intelligence techniques has highly accurate in diagnosing AD according to MRI images.