Yutaka Hata

© 2009 by Taylor & Francis Group, LLC. Ultrasonic techniques are widely applied in medicine. The most popular usage is to image the inside of the human body. Clinical ultrasonic treatment is also essential to disrupt objects such as gallstones. All systems consist of hardware and software. Current medical ultrasonic systems require system of systems engineering (SoSE) techniques comprising the hardware systems of an ultrasonic probe, a pulser and receiver, an A/D converter that can rapidly process large amounts of data, and the software systems of data synthesis, analysis, and image rendering. In this section, we introduce an ultrasonic SoS for clinical orthopedic surgery.

<p>In recent years, the trend of people marrying later in life has been significantly increasing. In the US, 60% of married women in their 40s reportedly have infertility. In half of these cases, a female factor is the cause. As a consequence, infertility treatments are widely performed. One such treatment is in-vitro fertilization. This technique directly removes a follicle from the ovary and ovum is fertilized it with sperm under a microscope by embryologist. Ovulation inducers can stimulate the growth of 10 to 15 follicles. However, 20% to 30% usually contain vacuoles and do not support ovary growth. In some cases, ova that are as much as 90% vacuolated do support ovary growth[1]. It thus cannot be determined whether a follicle has an ovum or is vacuolated unless the follicle is examined under a microscope. Consequently, it is useful to determine in advance whether a follicle has an ovum because follicle collection is painful for the woman. However, to date, a non-invasive method of identifying vacuolated ova does not exist. Therefore, we herein propose a method using ultrasound to determine whether a follicle has an ovum.</p>

© 2015 IEEE. In this paper, a method of analyzing relationships between items in specific health examination data is presented to cope with lifestyle-related diseases. The proposed method uses self-organizing maps, and focuses on twelve items such as hemoglobin A1c (HbA1c), glutamic-oxaloacetic transaminase (GOT), glutamic-pyruvic transaminase (GPT), gamma-glutamyl transpeptidase (γ-GPT), and triglyceride (TG). The proposed method picks up the data from the examination dataset according to the standard specified by some item values. The training data are then generated by calculating the difference between item values associated with successive two years and normalizing the values of this calculation. The proposed method labels neurons in the map by using item values of training data as parameters, and examine the relationships between items in the examination data by observing clusters formed in the map. Experimental results reveal the relationships among HbA1c, GOT, GPT, γ-GTP and TG both in the unfavorable case of HbA1c deteriorating and in the favorable case of HbA1c being improved.

In order to develop a computer-aided diagnosis system for neonatal cerebral disorders, some methods of brain segmentation from MR images using atlas model have been studied. As neonatal cerebrum deforms quickly by natural growth, single model cannot represent growth model properly. Due to the variation of newborn brain growth even at same age, age based model will not give appropriate result. In this paper, we propose a method for estimating growth index using manifold learning and generating fuzzy object growth model (FOGM). Brain anatomical landmarks are used for manifold learning. In addition, we propose a fuzzy connectedness segmentation method using FOGM to segment the brain region. In comparison with the previous single model based method, the proposed method improved the segmentation accuracy by using FOGM.

This paper gives a survey of intelligent computational techniques in medical and health care system. First, we briefly describe diagnosable techniques in medical image processing. Next, we demonstrate two ultrasonic surgery support systems for orthopedic and rectum cancer surgeons. In them, intelligent computational technique plays a primary role. Third, computational techniques are introduced in human health care system. Usually, this goal is not to apply clinical treatment but to home use to pay consciousness to health. In it, a simple ECG and respiration meter are introduced with a mat sheet which detects heart rate and respiration. Finally, a medical big data application is introduced, that is, body weight prediction is shown based on autoregressive model. Thus, we show that intelligent computing is effective and essential in modem medical and health care system.

This paper describes an ultrasonic system that estimates the cell quantity of an artificial culture bone, which is effective for appropriate treat with a composite of this material and Bone Marrow Stromal Cells. For this system, we examine two approaches for analyzing the ultrasound waves transmitted through the cultured bone, including stem cells to estimate cell quantity: multiple regression and fuzzy inference. We employ two characteristics from the obtained wave for applying each method. These features are the amplitude and the frequency; the amplitude is measured from the obtained wave, and the frequency is calculated by the cross-spectrum method. The results confirmed that the fuzzy inference method yields the accurate estimates of cell quantity in artificial culture bone. Using this ultrasonic estimation system, the orthopaedic surgeons can choose the composites that contain favorable number of cells before the implantation.

To develop a computer-aided diagnosis system for neonatal cerebral disorders, some literatures have shown atlas-based methods for segmenting parenchymal region in MR images. Because neonatal cerebrum deforms quickly by natural growth, we desire an atlas growth model. This paper proposes two methods for generating fuzzy object growth model (FOGM), which is an extension of fuzzy object model (FOM). The first method generates a growth-index weighted FOM in which the index is calculated from age. Because the growth index will be different from person to person even though the same age, the second method estimates the growth-index from MR images using manifold learning. To evaluate the proposed methods, we segment the parenchymal region of 16 neonatal subjects (revised age; 0-2 years old). The results showed that FOGM was superior to FOM, and manifold learning based method gave the best accuracy. And, the growth index estimated with manifold learning was significantly correlated with both of age and cerebral volume (p&lt;0.001).

MR image registration (IR) has been used in brain function analysis, voxel-based-morphometry, etc. The conventional IR methods mainly use MR signal based likelihood. However, they cannot prevent miss registration of different gyri because they do not evaluate correspondence of sulci. Also, we cannot directly apply methods for adult brain to neonatal brain because there are large differences in MR signal and sulcal width. This paper introduces a new feature called sulcal-distribution index (SDI) which is calculated from MR signal around the cerebral surface. Next, we propose a non-rigid 3D IR method using flattening with SDI. The likelihood used is mutual information of SDI. The new method evaluates the correspondence of cerebral sulci in IR. And, the method will be effective for neonatal brain in which the accurate delineation of cerebral surface is difficult because the method evaluates the MR signal around the cerebral surface. Results in 3 neonates (modified age; 3-5 weeks) showed the decrease of the angle between vectors of feature point direction.

This paper describes fuzzy evaluation method for criteria dependency in human health conditions by changing medical checkup reference. In our previous paper, we proposed an evaluation method based on fuzzy logic for health checkup data. This method converted health checkup data into fuzzy normal degree to evaluate multivariate data. We defined the fuzzy normal degree as an attribute value in closed interval [0, 1] by using fuzzy membership function which was defined by diagnostic criteria. Furthermore, total health indices which are defined by operation of the fuzzy normal degrees are treated as the same scale. These indices can express human health conditions in health checkup result using fuzzy set. In this paper, to investigate fuzzy normal degrees by changing to new reference interval, we employ new reference interval and form new diagnostic criteria, and visualized health changes by calculating the total health indices using our proposed method. As the result, we succeeded in visualizing health change by fuzzy normal degree and fuzzy health indices, and confirmed quantitatively that disease patients decrease by changing to new reference interval.

本論文では2つのサーマルアレイセンサを使用し，人の姿勢推定を行うシステムを提案する．本システムではサーマルアレイセンサを天井と壁に設置し，16×16の温度分布を測定する．サーマルアレイセンサは室内の状況を温度分布として取得可能である．姿勢推定は時系列の姿勢遷移図とある領域の温度の合計値を用いて行う．実験では，高齢者介護施設の個室を想定した部屋で温度分布の測定を行った．推定結果より，本システムは姿勢の推定に成功したことを確認した．

This paper describes fuzzy average difference imaging for ultrasonic nondestructive testing. In our experiment, we employ a piece of wind turbine blade as a specimen. The specimen has holes on back side as artificial damages. We acquire ultrasonic waveforms from scanning lines on surface of the specimen using an ultrasonic single probe. We make cross-section images of the specimen by correcting the each scanning line wave data. We set scanning lines so that specimen constructions under the lines are same each other. Therefore the images show same construction of inside of the specimen, we can enhance the damage echoes by using average difference imaging. To extract the damage echoes from the images, we applied damage extraction method aided by fuzzy logic and average difference imaging. As the results, we found the line image with all damage portions, and we estimated depth of damage surface with high accuracy. Therefore fuzzy average difference imaging showed effectiveness for extracting difference potions on similar images.

This paper proposes human movement trajectory (HMT) extraction system and a state of people estimation system by thermopile array sensors. In our systems, sensors are attached at the ceiling and acquire thermal distribution, which are two-dimensional temperatures. The system distinguishes humans, object and others by fuzzy inference based on human characteristics, such as body temperature and movement. Each human is classied by the connected-component labeling. In the HMT extraction system, it extracts HMT as label centroids trajectory. In the state of people estimation system, it distinguishes adjoining people based on shape of human distribution in label image and estimates the number of human as the number of labels. In the HMT extraction experiment, we employed an adult and he performed 15 movements. As the results, the system successfully extracted HMTs with 78[%] accuracy and positional error was 21.5[cm]. In the state estimation experiment, we employed 4 adults and they performed 4 movements. As the results, the system successfully estimated the number of humans with 52[%] accuracy.

Brain region segmentation in neonatal magnetic resonance (MR) images is an essential task for computer-aided diagnosis of neonatal brain disorders using MR images. We have proposed a neonatal brain segmentation method using a fuzzy object model (FOM), which represents a prior knowledge of brain shape and location. The FOM is constructed from multiple neonatal brain MR images whose revised age was between 0 and 4 weeks. The method segmented the brain region with a good accuracy for subjects whose age matches of the training data set. To enhance the method, we need multiple FOMs for each age. The other solution is to develop a growable model. This paper introduces 4-D FOM and applies it to neonatal brain segmentation. This paper introduces a neonatal brain segmentation method using 4-D FOM. The proposed method consists of three components. The first part proposes a method for estimating the brain development progress, called growth index in this study, from MR images based on Manifold learning. The second part shows a procedure for generating 4-D FOM using the estimated growth index. The third part is to segment brain region based on fuzzy-connectedness image segmentation using 4-D FOM. The proposed method was applied to 16 neonatal subjects. The results show that 4-D FOM is superior to stable 3-D FOM for segmenting neonatal brain region from MR images. © 2014 IEEE.

© Springer International Publishing Switzerland 2014. This paper proposes a muscular thickness measurement method using acoustic velocity dependency according to temperature. It is known that the acoustic velocity for temperature change depends on the materials is slower than warm ones. From this principal, we measured the muscular thickness. We employ a 1.0 MHz ultrasonic probe, and acquire two kind ultrasonic echoes from same position of body with temperature variation. From these echoes, we extract boundary surface echoes. From echoes, regions of muscular and fat are extracted by difference between the acoustic velocity-temperature characteristics of muscular and fat. In our experiment, we employ a piece of pork as an experimental phantom, and we acquire ultrasonic echoes reflected from the phantom. Our proposed method successfully measured the thicknesses in muscular and fat region.

© Springer International Publishing Switzerland 2014. This paper proposes a fuzzy ultrasonic imaging method for healthy seminiferous tubules. In our study, we employ thick or thin nylon lines as healthy or unhealthy seminiferous tubules. We make cross-section images that consist of multiplying fuzzy degrees depending on amplitude and frequency of line echoes. The images are healthy or unhealthy seminiferous tubules images (HSI or USI) that indicate distribution of healthy or unhealthy seminiferous tubules. For a performance test, we make a measurement object consisting of the nylon lines. For a phantom test, we make a phantom of a testicle. The phantom consists of a water filled rubber tube including the nylon lines. We scan and acquire ultrasonic reflection wave data of them. Next, we derive fuzzy IF-THEN rules, and make HSI and USI. In performance test, the images indicated distribution of the lines. In phantom test, HSI successfully extracted thick line echoes. Keywords: ultrasonic, seminiferous tubule, fuzzy, medical imaging.

MR image registration (IR) has been used in brain function analysis, voxel-based-morphometry, etc. The conventional IR methods mainly use MR signal based likelihood. However, they cannot prevent miss registration of different gyri because they do not evaluate correspondence of sulci. Also, we cannot directly apply methods for adult brain to neonatal brain because there are large differences in MR signal and sulcal width. This paper focuses on neonatal brain MR images, and introduces a new feature called sulcal-distribution index (SDI), which is calculated from MR signal around the cerebral surface. Next, this paper proposes a non-rigid 3-D IR method based on a flattening with SDI. The likelihood used is mutual information of SDI. The new method evaluates the correspondence of cerebral sulci. And, the method will be effective for neonatal brain in which the accurate delineation of cerebral surface is difficult because the method evaluates the MR signal around the cerebral surface. Results in 3 neonates (modified age; 3-5 weeks) showed that the method registered one brain with the other brain successfully. © 2014 IEEE.

© Springer International Publishing Switzerland 2014. This paper proposes a multi human movement trajectories (HMTs) extraction system with room layout estimation by a thermal sensor. In the system, the sensor is attached to the ceiling and it acquires 16 × 16 elements spatial temperatures – thermal distribution. The distributions are analyzed to extract HMTs. Firstly, room temperature is removed from thermal distribution. Secondly, human distribution is estimated with fuzzy inferences. In this procedure, an O-F (Object-Floor) map is employed to prevent miss detection of human positions based on room layout. Finally, multi HMTs are extracted by the Connected Component Labeling and the ordering by the distance between new acquired human position and past HMTs. In the experiment, we measured a room to evaluate detection ability of our system. As the experimental result, the system successfully extracted multi HMTs in the all data.

© Springer International Publishing Switzerland 2014. The number of asthmatic attacks was predicted by a time series data analysis in the areas divided into the coastal place and the inland place in Himeji city. As a result, SARIMA model obtained the highest total of CC=0.733, MAPE = 13.4 in inland place, and AR model obtained the highest total of CC=0.549, MAPE = 13.9 in coastal place. The prediction in inland place got enough precision. On the other hand, the prediction in the coastal place didn’t get enough precision. Therefore, it was confirmed that the prediction in some areas by time series models was difficult.

© 2014 IEEE. This paper describes a human posture estimation system by using two thermal array sensors. In the system, the sensors are attached to ceiling and wall of a room, and acquire temperature distributions by 16 × 16 elements. The temperature distributions represent a state of temperature in the room, and they are analyzed to estimate human posture. Human posture is estimated by time-series posture transition diagram and the sum of temperature. In our experiment, we measured the temperature distributions in a room modeled as private room in a nursing home. As the results, the system successfully estimated human posture.

© Springer International Publishing Switzerland 2014. This paper describes mobile health care managements in smart medical system. The transformation of electricity grids into smart grids has been widely remarked as a key for sustainable growth around the globe. The trend to smart grids comes at a time in which information and communication technologies have revolutionized personal communications and turned wireless communications into a commodity. Thus, it is no coincidence that communications technology will play an essential role in the implementation of smart grids. This study designs the mobile medical system to review data prior to patient access. Improved communication can also ease the process for patients, clinicians, and care-givers. As one of the implementations for smart medical system, the ultrasonic diagnosis and mobile communication system are proposed.

© 2014 IEEE. We investigate dependency of human health condition evaluation on changing medical checkup reference. In our previous paper, we proposed an evaluation method based on fuzzy set for health checkup data. This method converted health checkup data into fuzzy degree to operate a multivariate data analysis. The obtained fuzzy degree was considered as an attribute value in closed interval [0, 1]. Total health indices which are defined by operation of the fuzzy degrees are treated as the same scale. In this paper, to investigate fuzzy normal degrees by changing to new reference interval, we visualized health changes by calculating the total health indices using our proposed method. As the result, we succeeded in visualizing health change, and confirmed quantitatively that disease patients decrease by changing to new reference interval.

© Springer International Publishing Switzerland 2014. This paper proposes a blood pressure estimation system based on electrocardiogram (ECG). The ECG is unconstraintly measured by wearable sensor. The sensor provides acquired data to personal computer by wireless communication. For estimation, the system extracts heart rate, R-T intervals from the ECG. The heart rate is calculated from R-R intervals, and R-T intervals are extracted based on fuzzy logic. Form the information and body composition information of subject, the system estimates mean blood pressure. In our experiment, we employed six subjects, and estimated their mean blood pressure. As a result, our proposed method estimated the blood pressures with low estimation errors and high correlation coefficients.

© Springer International Publishing Switzerland 2014. The paper describes a blood pressure prediction model. The model predicts blood pressure of the subject based on trend of the blood pressure, body weight and number of steps. To predict it, we make autoregressive (AR) model, liner prediction model, body weight based prediction model and steps based prediction model. These models are boosted by fuzzy logic. The fuzzy degrees are calculated from mean absolute prediction error, correlation coefficient and variation amount for the learning data. In our experiment, we collected blood pressure, body weight and number of steps of 453 subjects from WellnessLINK which is an internet life-log service. Our proposed model predicted their blood pressures. The mean correlation coefficient between the predicted values and measurement systolic blood pressures was 0.895.

© Springer International Publishing Switzerland 2014. This paper proposes an energy visualization system by a camera. For monitoring, a single camera captures gas meter image at fixed intervals. The system applies edge detection and the connected-component labeling to extract numeral regions in counters of a gas mater. Gas consumption is estimated based on shape characteristics of numerals. The system uses number of endpoints and holes in numerical character, and it calculates a direction histogram and sum of absolute difference (SAD). The system recognizes the numeral by fuzzy inference from the acquired shape characteristic. When the system failed to recognize gas consumption by some accidents, the consumption is interpolated from time-serious data. In the result, our method estimated 32 and 29 numerals in 33 pieces for front and slant measurement respectively. For a continual monitoring in a day, the system successfully estimated dynamic gasconsumption change and visualized them.