Since the increasing population of aging, cognitive training is focused as one of the non-pharmacological preventive approach of cognitive decline. Although the accumulation of the knowledge, they hardly reflect to the programs for clinical use. We developed a task set named "Atama-no-dojo," designed to activate multiple cognitive functions and enhance motivational incentives. The objective of our study is to confirm the effect of our program through a 6 months group intervention program. The intervention program conducted in a day service center for 6 months in the duration of 45 minutes per day, 4 days per month for a total of 25 sessions. Participants worked to the tasks on the screen all together with filling in the answering sheet. Neuropsychological tests, SF36 and GDS were assessed at pre-/post-intervention periods. Participants filled in a questionnaire about impression to the program at the last training session. Fourteen women (82.2 ± 2.9 years old) were analyzed and significant changes were found in the improvement of memory, attention, inhibition, GDS and some items of SF36. All participants recognized the program as fun and wanted to continue. Some of the participants' positive impressions to the program correlated to cognitive improvement. The improved cognitive functions by 6 months intervention of "Atama-no-dojo" were mainly related to prefrontal cortex and the motivational incentives seemed supported the effect of task contents. We recognized the importance of task difficulty setting and motivational incentives to reduce frustration from working on difficult tasks and enhance the effects of improvement from activating brain function.
Recently, breast types were categorized into four types based on the Breast Imaging Reporting and Data System (BI-RADS) atlas, and evaluating them is vital in clinical practice. A Japanese guideline, called breast composition, was developed for the breast types based on BI-RADS. The guideline is characterized using a continuous value called the mammary gland content ratio calculated to determine the breast composition, therefore allowing a more objective and visual evaluation. Although a discriminative deep convolutional neural network (DCNN) has been developed conventionally to classify the breast composition, it could encounter two-step errors or more. Hence, we propose an alternative regression DCNN based on mammary gland content ratio. We used 1476 images, evaluated by an expert physician. Our regression DCNN contained four convolution layers and three fully connected layers. Consequently, we obtained a high correlation of 0.93 (p < 0.01). Furthermore, to scrutinize the effectiveness of the regression DCNN, we categorized breast composition using the estimated ratio obtained by the regression DCNN. The agreement rates are high at 84.8%, suggesting that the breast composition can be calculated using regression DCNN with high accuracy. Moreover, the occurrence of two-step errors or more is unlikely, and the proposed method can intuitively understand the estimated results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.