Published papers

Recently, there has been an increasing need of a face alignment or facial feature point tracking for applying face recognition, facial expression estimation, face attributes prediction, and clinical face observation etc. This study proposes a robust facial feature tracking method against camera shake and face orientation changes. The method applies a cascaded composed learning (CCL) based facial feature point tracking method by incorporating optical flow for improving tracking accuracy and robustness. Experiments are conducted to show that efficient tracking is achieved by performing CCL combined with initial shape estimation via the optical flow.

In this paper, we evaluated the effects of olive oil on human's stress level. In recent years, mental stress from harsh working environment have been causing serious problems to human health, both mentally and physically. Symptoms of stress may include feelings of worthlessness, agitation, anxiety, lethargy, insomnia, and behavioral changes. Additionally, the harsh working environments may cause the workers to adopt unhealthy dietary habits, contributing to the health issue. On the other hand, olive oil has been known to provide stress-relieving effects both by ingestion and by inhaling the scent. Here, we examined the effects of extravirgin olive oil ingestion for mitigating stress from deskwork. Three best-selling extravirgin olive oil in Japan were tested, and typing task was selected to emulate deskwork situation. Near-infrared spectroscopy (NIRS) is utilized in this study to visualize the response in brain via cerebral blood flow analysis and to measure participants’ stress level. Statistical analysis showed that the stress levels were lower during the olive oil ingestion experiment compared to no-oil experiment, even when measured one hour after the ingestion.

Since 2019, a large number of people worldwide have been infected with severe acute respiratory syndrome coronavirus 2. Among those infected, a limited number develop severe coronavirus disease 2019 (COVID-19), which generally has an acute onset. The treatment of patients with severe COVID-19 is challenging. To optimize disease prognosis and effectively utilize medical resources, proactive measures must be adopted for patients at risk of developing severe COVID-19. We analyzed the data of COVID-19 patients from seven medical institutions in Tokyo and used mathematical modeling of patient blood test results to quantify and compare the predictive ability of multiple prognostic indicators for the development of severe COVID-19. A machine learning logistic regression model was used to analyze the blood test results of 300 patients. Due to the limited data set, the size of the training group was constantly adjusted to ensure that the results of machine learning were effective (e.g., recognition rate of disease severity > 80%). Lymphocyte count, hemoglobin, and ferritin levels were the best prognostic indicators of severe COVID-19. The mathematical model developed in this study enables prediction and classification of COVID-19 severity.

Purpose Herein, we propose the use of the “KeraVio Ring”, which is a portable, selfie-based, smartphone-attached corneal topography system that is based on the Placido ring videokeratoscope. The goal of this study was to evaluate and compare corneal parameters between KeraVio Ring and conventional corneal tomography images. Methods We designed the KeraVio Ring as a device comprising 3D-printed LED rings for generating Placido rings that can be attached to a smartphone. Two LED rings are attached to a cone-shaped device, and both corneas are illuminated. Selfies were taken using the KeraVio Ring attached to the smartphone without assistance from any of the examiners. Captured Placido rings on the cornea were analysed by intelligent software to calculate corneal parameters. Patients with normal, keratoconus, or LASIK-treated eyes were included. Anterior segment optical coherence tomography (AS-OCT) was also performed for each subject. Results We found highly significant correlations between the steepest and flattest keratometry, corneal astigmatism, and vector components obtained with the KeraVio Ring and AS-OCT. In subjects with normal, keratoconus, and LASIK-treated eyes, the mean difference in corneal astigmatism between the two devices was -0.8 ± 1.4 diopters (D) (95% limits of agreement (LoA), -3.6 to 2.0), -1.8 ± 3.7 D (95% LoA, -9.1 to 5.5), and -1.5 ± 1.3 D (95% LoA, -4.0 to 1.1), respectively. Conclusions The experimental results showed that the corneal parameters obtained by the KeraVio Ring were correlated with those obtained with AS-OCT. The KeraVio Ring has the potential to address an unmet need by providing a tool for portable selfie-based corneal topography.

Purpose To evaluate stress levels extracted from prefrontal electroencephalogram (EEG) signals and investigate their relationship with dry eye symptoms. Methods This prospective, cross-sectional, comparative study included 25 eyes of 25 patients with aqueous tear-deficient dry eye (low Schirmer group), 25 eyes of 25 patients with short tear breakup time dry eye (short breakup time group), and 24 eyes of 24 individuals without dry eye. An EEG test, the Japanese version of the Ocular Surface Disease Index (OSDI), and a stress questionnaire were administered. EEG-detected stress levels were assessed under three conditions: eyes closed, eyes open, and eyes open under ocular surface anesthesia. Results Stress levels were significantly lower when the eyes were closed than when they were open in all groups (all P < 0.05). Stress levels during eyes open under ocular surface anesthesia were significantly lower than those during eyes open without anesthesia only in the low Schirmer group; no differences were found between the short breakup time and control groups. OSDI scores were associated with EEG-detected stress levels (P = 0.06) and vital staining score (P < 0.05) in the low Schirmer group; they were not associated with EEG-detected stress (P > 0.05), but with subjective stress questionnaire scores and breakup time values in the short breakup time group (P < 0.05). Conclusions In the low Schirmer group, peripheral nerve stimulation caused by ocular surface damage induced stress reactions in the frontal lobe, resulting in dry eye symptoms. Conversely, in the short breakup time group, the stress response in the frontal lobe was not related to symptom development.