Magnetic resonance (MR) imaging plays a highly important role in radiotherapy treatment planning for the segmentation of tumor volumes and organs. However, the use of MR is limited, owing to its high cost and the increased use of metal implants for patients. This study is aimed towards patients who are contraindicated owing to claustrophobia and cardiac pacemakers, and many scenarios in which only computed tomography (CT) images are available, such as emergencies, situations lacking an MR scanner, and situations in which the cost of obtaining an MR scan is prohibitive. From medical practice, our approach can be adopted as a screening method by radiologists to observe abnormal anatomical lesions in certain diseases that are difficult to diagnose by CT. The proposed approach can estimate an MR image based on a CT image using paired and unpaired training data. In contrast to existing synthetic methods for medical imaging, which depend on sparse pairwise-aligned data or plentiful unpaired data, the proposed approach alleviates the rigid registration of paired training, and overcomes the context-misalignment problem of unpaired training. A generative adversarial network was trained to transform two-dimensional (2D) brain CT image slices into 2D brain MR image slices, combining the adversarial, dual cycle-consistent, and voxel-wise losses. Qualitative and quantitative comparisons against independent paired and unpaired training methods demonstrated the superiority of our approach.

The classification of Alzheimer’s disease (AD) using deep learning methods has shown promising results, but successful application in clinical settings requires a combination of high accuracy, short processing time, and generalizability to various populations. In this study, we developed a convolutional neural network (CNN)-based AD classification algorithm using magnetic resonance imaging (MRI) scans from AD patients and age/gender-matched cognitively normal controls from two populations that differ in ethnicity and education level. These populations come from the Seoul National University Bundang Hospital (SNUBH) and Alzheimer’s Disease Neuroimaging Initiative (ADNI). For each population, we trained CNNs on five subsets using coronal slices of T1-weighted images that cover the medial temporal lobe. We evaluated the models on validation subsets from both the same population (within-dataset validation) and other population (between-dataset validation). Our models achieved average areas under the curves of 0.91–0.94 for within-dataset validation and 0.88–0.89 for between-dataset validation. The mean processing time per person was 23–24 s. The within-dataset and between-dataset performances were comparable between the ADNI-derived and SNUBH-derived models. These results demonstrate the generalizability of our models to different patients with different ethnicities and education levels, as well as their potential for deployment as fast and accurate diagnostic support tools for AD.

Acupuncture uses needles to stimulate certain parts of the body, inducing a specific sensation, termed DeQi, which regard as essential for acupuncture's therapeutic effect. Here, we used the newly developed tool, bodily sensation mapping, to investigate the spatial configuration of acupuncture-induced sensations throughout the body. Twenty-five participants randomly received acupuncture stimulation or tactile stimulation using a von Frey filament at four different acupoints (HT7, PC6, ST36, and SP10) on the left side of the body. Subjects evaluated the characteristics of DeQi sensations and marked the areas of induced sensations on a body outline. We compared the psychophysical responses of DeQi sensations and visualized the spatial patterns of these sensations using statistical parametric mapping. We found greater intensity of DeQi sensations following acupuncture stimulation compared with tactile stimulation, with relatively small differences among the four acupoints. The sensation maps exhibited similar spatial patterns for acupuncture and tactile stimulation in the areas close to the stimulated sites. However, acupuncture was associated with additional sensations in areas remote from the stimulated sites. This study demonstrates that acupuncture stimulation produces greater DeQi sensations than tactile stimulation and results in the spreading of sensations to areas remote from the stimulus sites. Investigating the spatial patterns of acupuncture-induced sensations may be crucial for understanding the underlying mechanisms of acupuncture.

BackgroundAlthough alopecia affects the quality of life, its pathogenesis is unknown, because cellular interactions in the hair follicle are complex. Several authors have suggested using herbal medicine to treat alopecia, and bioinformatics and network pharmacology may constitute a new research strategy in this regard because herbal medicines contain various chemical components. This study used association rule mining (ARM) and network analysis to analyze the combinations of medicinal herbs used to treat alopecia.MethodsWe searched Chinese, Korean, and English databases for literature about alopecia treatment, extracting the names of each herbal prescription and herb. The meridian tropism and classification category of each herb were also investigated. Using ARM, we identified frequently combined two-herb and three-herb sets. Using network analysis, we divided the herbs into several modules according to prescription pattern.ResultsFifty-six articles and 489 herbal medicines were included—312 internal and 177 external medicines. Among the 312 medicinal herbs used in internal medicine group, the most frequently combined two-herb set was Polygonum multiflorum Thunb. (何首烏) and Angelica sinensis (Oliv.) Dlels (當歸). The most frequently used three-herb combination was Polygonum multiflorum Thunb., Angelica sinensis (Oliv.) Dlels, and Ligusticum chuanxiong Hort. (川芎). In network analysis, three modules were identified. The herbs of Module 1 were related to the liver and kidney meridians, and those of Module 3 were related to the Stomach meridian.ConclusionsWe identified the frequency, characteristics, and functional modules of herb combinations frequently used in alopecia treatment. We confirmed the value of classical medicinal herb theory. This finding will prompt further bioinformatics and network pharmacology research on alopecia.Electronic supplementary materialThe online version of this article (10.1186/s12906-018-2269-7) contains supplementary material, which is available to authorized users.

Throughout the history of East Asian medicine, different kinds of acupuncture treatment experiences have been accumulated in classical medical texts. Reexamining knowledge from classical medical texts is expected to provide meaningful information that could be utilized in current medical practices. In this study, we used data mining methods to analyze the association between acupoints and patterns of disorder with the classical medical book DongUiBoGam of Korean medicine. Using the term frequency-inverse document frequency (tf-idf) method, we quantified the significance of acupoints to its targeting patterns and, conversely, the significance of patterns to acupoints. Through these processes, we extracted characteristics of each acupoint based on its treating patterns. We also drew practical information for selecting acupoints on certain patterns according to their association. Data analysis on DongUiBoGam's acupuncture treatment gave us an insight into the main idea of DongUiBoGam. We strongly believe that our approach can provide a novel understanding of unknown characteristics of acupoint and pattern identification from the classical medical text using data mining methods.