- 3D Assessment of Facial Symmetry for Quantitative Diagnosis of Facial Paralysis
- 論文掲載日：2021/03/05 第21巻
- Objective: Facial paralysis is most commonly assessed using a 10-item, 40-point method, with a facial nerve grading system. It has been highlighted that while it is easy for inspectors to be subjective when using these methods, there are problems with objectivity and reproducibility. Furthermore, detailed evaluations using these methods are limited. This study aims to propose a novel objective method for evaluating facial paralysis, considering changes in the depth direction of the face.
Method: 3D shape data of the face are acquired using a Kinect sensor, and facial paralysis is evaluated using 3D shape assessment.
Results: Faces were photographed at rest and when performing facial exercises, such as inflating one cheek, tightly closing both eyes, and closing only one eye. The symmetry of facial movements was calculated using the distance between corresponding points, captured in the shape data point cloud, while at rest and during the facial exercises.
Conclusions: This study proposes a novel objective method to assess facial paralysis that considers changes in the depth direction of the face. The calculations of the symmetry of facial movements using a 3D shape data point cloud, obtained using a Kinect sensor to photograph eight varieties of facial exercises, confirmed that the proposed method objectively and quantitatively evaluates left-right motions.
Keywords: Facial paralysis, Yanagihara method, 3D quantitative evaluation method, Kinect sensor, ICP algorithm
- Points to note when beginners make Kumihimo using the Kumihimo Disk
-Factors affecting the evaluation of braided strings-
- 論文掲載日：2021/03/04 第21巻
- Purpose: Points to note when beginners make Kumihimo (a Japanese braid) using Kumihimo Disks were examined based on the relationships between the braided string's thickness and hardness.
Methods: University students braided the Yatsu-kongoh Z-spiral using the Kumihimo Disk, and the length and thickness of the braided strings were measured. The hardness and flexibility of the braided strings were evaluated by touching them using a five-point scale. The evaluations for flexibility and hardness were nearly consistent. Therefore, the flexibility was defined as the hardness of the string.
Results: Significant negative correlations were indicated between hardness and length, thickness, and thickness variation. The results of simple correlation analysis and multiple regression analysis indicated a significant effect of the number of mistakes and thickness variation on appearance evaluation. On the other hand, simple correlation analysis results indicated that the number of mistakes, thickness variations, and hardness significantly affected comprehensive evaluations. Moreover, multiple regression analysis results indicated a significant effect of the number of mistakes and thickness variations on the comprehensive evaluation.
Conclusion: Although appearance evaluation is essential from an aesthetic perspective, the string's hardness and thickness are critical when considering braided strings' functions in the comprehensive evaluation. The results of the present study indicated that harder and thinner strings were more highly evaluated. Therefore, beginners should try to braid harder and thinner strings.
Keywords: Kumihimo Disk, the thickness of braided strings, the hardness of braided strings, appearance evaluation, the evaluation of braided strings
- Reproducibility between robot and human movements: preliminary development of a robotic device reconstructing therapeutic motion
- 論文掲載日：2020/12/30 第20巻
- Purpose: Robot-mediated therapy is a promising approach for restoration of upper limb motor function after stroke, but it has not demonstrated the expected effects because of the inability to reproduce the flexibility and complexity, which are associated with assistance skills of therapists. The purpose of this study was to develop a preliminary dicephalus (DiC) system and provide preliminary data on the reproducibility between motions of a robot and therapist.
Subjects and Method: The assessment for each human and robotic assistance comprised 10 movement cycles, including elbow flexion and extension. Seven volunteers were seated with the right forearm and upper arm fixed to the DiC system. One therapist was ins structed to make 10 similar elbow flexion and extension movements to assist in patient elbow movements. After therapist assistance, the DiC system reproduced the 10 repetitive elbow flexions and extensions made by the therapist. The highest and lowest elbow angles in each flexion and extension cycle and the time at which those angles were obtained were measured.
Results: The intraclass correlation coefficients of the highest and lowest elbow angles was 0.96 (p < 0.0001) and of the time for obtaining those angles was 0.96 (p < 0.0001) between human and robot assistances. Bland-Altman plots showed interchangeable differences in the time between human and robot assistances (96.4% within 2 standard deviations).
Conclusions: The DiC system shows excellent reproducibility between human and robot assistances and may be effective for upper limb training in stroke patients. This system was preliminarily developed for the rehabilitation of upper limb motor dysfunction after stroke.
Keywords: robot assistances; occupational therapy; rehabilitation; stroke; upper limb
- Extraction of tongue coating area from tongue image for automated tongue diagnosis
- 論文掲載日：2020/08/03 第20巻
- Purpose: To automate tongue diagnosis, we propose a method utilizing machine learning to extract the tongue coating area from tongue images captured using a tongue image analysis system (TIAS).
Subjects and Methods: Tongue images were captured using a TIAS and a fluorescence imaging system from 11 participants (20 to 24 years old), and only the tongue coating area was extracted from the images. For extraction, the TIAS and fluorescence images were segmented into superpixels, machine learning was performed based on the features of the corresponding superpixels to obtain information regarding the presence of tongue coating, and the coating areas were extracted from the TIAS images. Furthermore, cross-validation of the leave-on-out and comparison of the performances of a support vector machine (SVM) and random forest (RF) were performed.
Results: Two machine learning classifiers were built for tongue coating extraction. With the use of these classifiers, which utilized the SVM and RF for learning the data, the percentage of correct responses was approximately 86% for both the classifiers, and this accuracy is similar to the those obtained in previous studies.
Conclusion: We proposed a tongue coating discrimination method utilizing feature analysis with an accuracy equal to or better than those of previous studies. Our proposed method is superior to the conventional method because it can analyze both the tongue as well as its peripheries. However, its accuracy is low for cases involving thin tongue coating (white coating, etc.), and the accurate extraction for cases involving white coating is difficult using our method, which forms a future direction of research.
Keywords: Machine learning, Tongue diagnosis, Eastern medicine, Support vector machine (SVM), Random Forest
- Choosing an Obi Suitable for Kimonos Eliciting a Sense of Hannari
- From a color-based perspective -
- 論文掲載日：2019/08/12 第19巻
- Purpose: Matching the color of a kimono with that of an obi is an important of creating a beautiful kimono arrangement. This experiment aims to clarify what particular "color" features of an obi fit with hannari eliciting kimono images. We used a thought algorithm based on a kimono-expert’s selection process for suitable obi, and examined whether the instructions were effective for a person with no kimono knowledge.
Participants and Methods: One kimono expert and 12 graduate students with no kimono knowledge were asked to select whether two top and bottom images were suitable for five kimono images. Next, the specialist's thought algorithm was clarified by protocol analysis. And we instructed a student in specialist's algorithmic thought process, and evaluated whether it was effective. Finally, RGB and u’v’ of obi images were requested, to clarify what kind of color characteristic there were in the obi that were considered to be suitable for the kimono images by discriminant analysis.
Results: Once RGB and u', v' characteristics of the colors of suitable obi were made clear, and the particular characteristics of the color was shown when a "suitable obi" was chosen by discriminant analysis. However, the instructions of the expert’s thought algorithm were not effective.
Conclusions: About 80% of "suitable obi" selected by students without knowledge of kimono are identifiable by "color" on discriminant analysis. For experts this was about 50%. This suggests that students who do not have knowledge of kimono chose based on their color preference, while experts considered factors such as “status" and "season".
Key Words: Kansei, Color, Kimono, Obi, Discriminant Analysis