小橋 昌司

整形外科手術は腹腟鏡手術や開腹手術と比較して手術工程および使用する手術器具が多く,外科手術中に医療器具の受け渡しを行う看護師は大きな負担を強いられている.我々は過去に人工膝関節置換術を対象とした整形外科手術における手術室看護師を支援するためのナビゲーションシステムを提案した.この研究では畳み込みニューラルネットワークを用いて手術画像全体に基づいた画像認識により手術工程の認識を試みたが,実用化に必要とされる精度には及ばなかった.本研究では整形外科手術における手術工程の認識精度の改善を実現するために,手術映像から取得したフレーム毎に物体検出(YOLO)を行い,器具のクラス情報と位置座標を検出する.スマートグラス(眼鏡型のデバイス)を用いて記録した整形外科手術映像は手術間で照明環境や撮影角度が大きく異なっており,それらの影響を低減させるための最適なデータの前処理法やデータ拡張法を検討した.(著者抄録)

人工膝関節置換術(Total knee arthroplasty, TKA)後の膝関節の動態解析は整形外科における研究において非常に重要な問題である．これまでの研究において2次元のX線透視画像と人工膝関節の3次元形状モデルを用いた2-D/3-D イメージマッチング手法が多く提案されているが，これらは静止画像による解析に留まり，膝関節の連続的な動作を動画像により解析する研究は少数である．また，従来の手法は高次元のパラメータ空間による局所解の問題があり，膝関節の連続的な動作は考慮されていない．本論文では，パーティクルフィルタを用いた人工膝関節の3次元動態解析システムを提案する．提案手法はパーティクルフィルタにより複数の候補を作成しパラメータの探索を行い2-D/3-D イメージマッチングを用いて人工膝関節の3次元位置姿勢を推定する．実験の結果，提案手法により膝関節の連続的な動作の解析，膝関節角度の推定が可能となった．

新生児脳疾患は脳形状の変化を伴うことが多いため，症状進行度の診断にはMR画像を用いた評価が有効である．しかし，手作業で複数のMR画像から脳表抽出を行うと医師に多大な負担が生じる．さらに，診断者間変動や診断者内変動が起こる可能性もある．そのため，新生児頭部MR画像から脳表を自動的に抽出する手法が求められている．これまでに成人頭部MR画像を対象とした脳表抽出法は多く提案されているが，新生児頭部MR画像を対象とした手法は少ない．本研究では，新生児頭部MR画像を対象とした粒子を用いる脳表抽出法を提案する．提案手法は，脳組織に見立てた3種類の粒子をMR信号値を基にして脳領域に配置し，周囲の粒子分布を基にして粒子の遷移，移動を行い，粒子の分布をMR画像と一致させることで脳表の抽出を行う．新生児頭部MR画像に対して提案手法を適用した結果，良好に脳表を抽出できた．

The brain shape is deformed regionally by kinds of cerebral diseases and the degree of progress. Therefore quantitative evaluation of the deformation using MR images is effective for diagnosis of cerebral diseases. To evaluate the cerebral deformation, almost conventional methods are based on normalization of the brain shape which deforms the evaluating brain into the standardized brain. Because the normalization process does not take into account anatomical features such as the cerebral sulci and gyri, in some cases the normalization process produces that one sulcus of the evaluating brain miss-corresponds to the other sulcus of the standardized brain. This paper proposes a homologous brain shape modeling method for quantitative evaluation of the brain shape in MR images. We define a new image feature called sulcal-distribution index (SDI) to represent the 3-D distribution of sulci, and the proposed method deforms a template brain model so that SDI of the deformed brain model calculated from the evaluating brain MR images is similar to SDI of the template brain model. By using SDI, the proposed method can take into account anatomical features of the cerebral sulci. The experimental results showed that the proposed method homologically modeled the brain shape with a mean displacement of 1.3 mm. ©2009 IEEE.

This paper proposes an ultrasonic system to determine thickness and wave speed of an object. In it, the authors newly develop a triangle probe system composed of three probes: a central probe and two side probes. The central probe straight transmits/receives ultrasonic waves and the right probe receives ultrasonic waves transmitted from the left one. In the authors' method, the triangle probe is moved to the depth direction of an object. Then, two peak intensities are revealed at the focal points of the surface and at the bottom of the object. The authors show a method to calculate the wave speed and the thickness of the objects from two focal points. In the experiment, the authors extract the two focal points aided by fuzzy logic. Then, they determine the wave speed and thickness of the object from these focal points. The experimental results on two hard phantoms show that the method can successfully determine the wave speed and the thickness of the object with high accuracy. Copyright © 2009 inderscience enterprises Ltd.

Because most of refractory patients with focal cortical dysplasia are candidate for epilepsy surgery, it is important to detect cortical dysplasia of epileptic children. This paper proposes an automated method for detecting cortical dysplasia using magnetic resonance (MR) images. To evaluate the cerebral cortex layer, the proposed method extracts texture features of a region which is perpendicular to the cerebral surface. Cortical dysplasia degree (C.D.D.) is estimated by using support vector machine (SVM). The experimental results for two subjects showed that the proposed method detected cortical dysplasia lesions with a mean sensitivity of 68.6%, a mean specificity of 67.0%, and a mean efficiency of 68.1%.

Total knee arthroplasty (TKA) is an orthopedic surgery which replaces the damaged knee joint with the artificial one. To diagnose the function of the implanted knee joint, it is effective to estimate 3-D knee kinematics in vivo. There are some conventional methods for estimating kinematics of the implanted knee using 2-D/3-D image registration for X-ray fluoroscopic images and 3-D geometrical models of the knee implant. However, these methods are based on static image analysis although the knee joint continuously moves. This paper proposes an analysis method of the knee kinematics using digital radiography images with Kalman filter. Use of Kalman filter enables us to take into account the continuous knee movement. The experimental results showed that the proposed method estimated the knee joint angles within a mean error of 0.31 deg.

This paper proposes a biometric personal authentication based on the pressure distribution while one step walking. We extract one step from a walk on a mat type load distribution sensor and use it to personal authentication. With this method, features which are based on weight movement and foot shape during walking are calculated, then a classifier is developed on the basis of fuzzy inference. We employed 30 volunteers. All volunteers are ranged from 20 to 85 years old. For each volunteer, we took walk data six times. Then, we evaluated this method by five training data and one test data. We obtained 6.1% EER (Equal Error Rate) and 13.9% FRR (False Rejection Rate) in verification (1:1 collation) and identification (1:N collation), respectively.

Cerebral surface extraction plays a fundamental role of computer aided diagnosis (CAD) for neonatal brain magnetic resonance (MR) images. However, cerebral sulci of the neonatal brains is complexity folded, and it is difficult to extract complete cerebral contour from MR images due to the limitation of spatial resolution and partial volume effect (PVE). This paper proposes a novel method to extract the cerebral contour based on fuzzy, thick rubber model (TRM). The TRM is deformed by using fuzzy control schemes so that the digitally synthesized MR images from the deforming TRM are identical to the given MR images. By synthesizing the MR images with respect to PVE, the proposed method is able to extract the cerebral contour with sub-voxel accuracy. The proposed method was applied to 7 subjects whose revised ages were from -17 days to 34 days. The root-mean-squared-error between the extracted contour and the manually delineated contour by two physicians was 1.09 +/- 0.48 mm from the truth contour. And, to demonstrate the clinical effective, gyral index was calculated using the extracted cerebral contour.

This paper describes a method for a respiratory rate monitoring system by an air pressure sensor. By using this sensor, we propose a detection method of a respiratory rate for human in bed by fuzzy logic. Our method was examined on four healthy, volunteers. We successfully detected the respiratory rate and the time of apnea state. In our method, fuzzy logic plays a primary role in the detection of respiratory points. The experimental results showed that the error ratio of respiratory rate was 1.3 % and the error of time of apnea state was 1.1 seconds. Consequently, this system can noninvasively detect the respiratory rate and the time of apnea state by using an unconstrained device.

皮質形成異常に起因する難治てんかんの外科的治療には，小児頭部MR画像からの皮質形成異常領域の検出は非常に有効である．しかし，皮質形成異常のMR画像上での画像特徴は明らかでなく，またその自動検出手法も未だ確立されていない．本文では，脳の皮質構造を評価するため，脳表に直交する評価単位領域を構築し，各領域のテクスチャ特徴量を算出し，Support Vector Machine (SVM) を用いて皮質形成異常度推定法を提案する．同提案法において，識別精度が最大となる特徴量の組み合わせを求めることで，皮質形成異常のMR画像上での画像特徴を調査する．また，本手法を適用した結果，皮質形成異常を有する小児頭部MR画像から，平均感度68％で皮質形成異常領域を検出できた．

睡眠時無呼吸症候群(SAS: Sleep Apnea Syndrome)などの睡眠障害により良質な睡眠をとれない人が近年増加している．現在，睡眠状態のモニタリングにはポリグラフ検査が一般的であるが，センサを体表につけて計測を行うため拘束性が高い．そこで本研究では非拘束に生体情報を取得する空気圧センサを用いて心拍と呼吸活動の検出を行う．空気圧センサはベッド上にいる人の生体情報を非拘束に取得することができる．提案法では取得したデータよりファジィ推論を用いて心拍・呼吸活動の検出を行う．本手法を成人男性に適用した結果，心拍は1.71%の誤差率，呼吸は2.08％の誤差率でそれぞれ検出することができた．

Measurement of cortical thickness using human brain magnetic resonance (MR) imaging can assist physicians in quantifying cerebral atrophy. Most of the conventional measurement methods assign the same class to all pixels with a similar MR signal independent of their locations, and are therefore unsuitable for MR images that have strong intensity nonuniformity (INU) artifact. We propose an automated method that locally segments the cerebral cortex using an adapted fuzzy spatial model representing the transit of MR signals from the cerebral cortex to the white matter. This method assigns fuzzy degrees belonging to brain tissues using the adaptive fuzzy spatial model for local intensity transition from the cerebral cortex to inside the cerebrum. We also introduce an evaluation method of cortex segmentation algorithms that consists of reproducibility, quantitative, and qualitative tests; we use this method to evaluate and discuss the proposed segmentation method in comparison with the conventional method.

Diagnostic imaging system is a necessity for brain diagnosis. Transcranial Ultrasonography can noninvasively image the intracranial blood flow and brain tissue in real time from only temple area of human head. However, the ultrasonic wave causes attenuation, decentration, and refraction in the skull, so the ultrasonography can not provide the transcranial brain surface image from arbitrary place. In this paper, we propose an imaging system of brain surface and skull from arbitrary places by considering the ultrasonic refraction of the skull. We do an experiment by using a cow scapula to imitate the skull bone and a biological phantom to imitate the cerebral sulcus. We first visualize the shape of scapula, and grasp the shape of scapula surface. We second remove the delay and the multi echoes of refracted wave. We third calculate the thickness of the scapula by using fuzzy inference. In the inference, we employ amplitude, correlation coefficient and the elapsed time. Finally, we calculate the refractive angle of ultrasonic wave and visualize the image referring to the refraction of ultrasonic wave. In the result of applying our method, we can estimate the thickness of scapula at all points, and successfully visualize the phantom surface image.

新生児低酸素性脳虚血性脳の進行度合いの定量化に,脳容積や脳回表面積の測定は非常に有効である.本研究ではMR画像を用いた脳容積計測,脳回表面積計測が可能な計算機診断支援システムを提案する.本提案システムでは,全脳形状や画像特徴に関する知識に基づくファジィ動的モデルを用いて全脳領域を自動抽出する.また脳回分割においては,操作者が脳表上で描画した脳回境界線を基に,ファジィ動的モデルにより脳回境界を自動検出する.提案システムを修正齢3週間から4歳2ヶ月の被験者8名に適用した結果,Sensitivity 97.72%, FPR 0.31%で全脳領域の抽出が行えた.また全被験者に対し各脳回の表面積計測が行えた.

ACL(anterior cruciate ligament; 前十字靭帯)損傷により生じる膝の回旋不安定性の評価手法として,主にpivot shift testが用いられる.同検査方法は簡便でACL損傷の程度と相関があり,今後の治療方針の決定に有用な指標であるが,同検査法は検者の主観的評価に基づいており,客観性,定量性が低いという問題点を有する.本研究では,小型で高時間分解能な慣性センサを用いた非拘束膝回旋不安定性定量化システムを提案する.同提案システムは,pivot shift test時の大腿部,下腿部運動を計測した時系列データの周波数解析により大腿-下腿の相対加速度を求めることで,pivot shift test現象の定量化を行う.本システムをACL損傷例1例に対して適用した結果,同時撮影したビデオ画像との比較により,pivot shift現象を正しく検出できたことを確認した.また,pivot shift現象時の大腿部に対する下腿部の相対運動の最大加速度は2.19±0.69m/s^2であり,検者の主観的評価であるGrade値との相関も示唆された.

Horticultural therapy (HT) is gaining attention as a form of rehabilitations in medical fields especially such as occupational therapy and nursing care, although its effectiveness has not been proven yet. This paper uses a strictly medical point of view to assess whether or not HT is effective for improvement of functional activities in the brains of brain-damaged patients. Five patients in Ishikawa Hospital with cerebrovascular diseases were invited to participate in HT for a month in addition to their routine medication and physical therapy (PT). The HT program was designed by horticultural therapists. The original purpose of the HT program was to monitor its effects on mental healing, cognitive re-organization, and training of sensory-motor function. The Functional Independence Measure (FIM) and the Self-Rating Depression Scale (SDS) were performed before and after HT to assess the patients’ physical activities of daily living (ADL) and to determine the patients’ mental changes in depressive states, respectively. Functional magnetic resonance imaging (fMRI) during recognition tasks was also measured before and after HT. The ADL of all patients significantly improved after HT; however, the depressive states in all patients did not change remarkably after the HT. fMRI examinations showed that the visual area, the inferior temporal area, the fusiform gyros, and the supramarginal gyros (SMG), in addition to the motor area, the supplementary motor area (SMA), the sensory area, and the cerebellum were activated after HT. These findings suggest that HT can accelerate an improvement of activities in the “visual and color processing areas” and the “association areas” as well as the sensory-motor areas of the brain in the patients with cerebrovascular diseases. HT, therefore, stimulates parts of brain, that are not always evoked through routine physical rehabilitation. HT can complement the routine physical rehabilitation and help to improve damaged brain function. © 2008, TSI® Press Printed in the USA.

Many studies showed that the hemodynamic response (HR) to brief neural activity caused by the blood oxygen level-dependent effect is delayed some seconds, and that the HR latency (= time to peak from neural activation) varies among activation sites. This paper proposes a novel method for estimating HR latency by analyzing event-related functional magnetic resonance images based on a continuous wavelet transform. The proposed method can simultaneously detect activation areas and estimate the HR latency. We also studied variability of the HR latency across subjects within the same activation sites, across acquisition days within a subject, and among activation sites within a subject. The experiments were done on 10 healthy subjects with hand-gripping tasks. We found no significant difference of HR latencies at a given activation site within a subject across acquisition days. And, we found significant differences of HR latency between the supplementary motor area (SMA) and the primary motor cortex (M1) in individual subjects, and among subjects. © 2008, TSI® Press Printed in the USA.

The aim of this paper is to assess whether horticultural therapy (HT) is effective for improvement of daily activity and brain functional activity in brain-damaged patients from a medical point of view. Five patients with cerebrovascular disorders were invited to participate in horticultural therapy for a month in Ishikawa Hospital. The Independence Scale in Activities of Daily Living (ISADL) and the Mini Mental State Examination (MMSE) were performed before and after a whole series of horticultural therapy program to assess a patient's activities of daily life and to determine the patient's cognitive function, respectively. Functional magnetic resonance imaging (fMRI) under recognition tasks were measured before and after the horticultural therapy. Independency of the daily activities and cognitive function tended to improve after the horticlutural therapy. fMRI examinations showed that the supramarginal gyrus (SMG), the motor area, the supplementary motor area (SMA), the sensory area, the visual area, the middle temporal gyrus, and the frontopolar area were activated after the therapy in most patients.

To diagnose total hip arthroplasty (THA) patients, it is important to analyze in-vivo kinematics of the implanted hip joint. There are some conventional analysis methods for estimating the pose/position of the implanted hip joint using 2-D/3-D image registration technique for 3-D multidetector raw CT (MDCT). images and 2-D X-ray radiograph images. One of the remained problems is that estimation results depend on the initial pose/position given manually. This paper proposes a fully automated method for estimating pose/position of the implants and the hip joint without giving initial pose/position. The proposed method releases us from manual interactions of giving initial pose/position by intervening between 3-D MDCT images and 2-D X-ray radiograph images with 3-D computer-aided design (CAD) model.

In this paper, a fuzzy Identification method for cellular quantity of Bone Marrow Stromal Cells (BMSCs) in artificial culture bones is proposed. We attempt to identify for cellular quantity with an ultrasonic system and fuzzy inference approach. We employ two characteristics: the amplitude and the frequency; the amplitude is obtained from the raw ultrasonic wave, and the frequency is calculated from frequency spectrum obtained by applying cross-spectrum method. The experimental results show that the proposed method identifies cellular quantity in artificial culture bone with high accuracy.

It is effective to measure the surface area of each gyrus for quantitative diagnosis of infantile brain diseases. This paper proposes an interactive gyrus labeling method for the infantile brain in magnetic resonance images. First, a user roughly gives guidelines of gyral boundaries on a 2-D projected image of the cerebral surface. The cerebral gyri are labeled by automatically determining gyral boundaries with respect to the user-given guidelines. The boundary deformation process is based on fuzzy rules. The automatically determined boundaries are validated by the user, and modified interactively. We applied the proposed method to 14 infantile subjects (3 weeks - 4 years 3 months old). The results showed that the cerebral gyri were successfully labeled with a mean sensitivity of 92.8% and a mean false positive rate of 0.1%.

We propose an ultrasonic system to determine thickness and wave speed of an object. In it, we develop a triangle probe system composed of three probes; a central probe and two side probes. The central probe straightly transmits/receives ultrasonic waves, and the right probe receives ultrasonic waves transmitted from the left one. We move the triangle probe to depth direction of an object. Then, two peak intensities are revealed at the focal points of the surface and the bottom of the object. We employ fuzzy logic to extract the two focal points, and determine the wave speed and thickness of the object from these focal point data. The experimental results on two hard phantoms show that the method can successfully determine the wave speed and the thickness of the object with high accuracy.

Computer aided diagnosis (CAD) system is an effective system of systems engineering (SoSE) in the medical field. The CAD system using medical images is constructed by integrating medical image acquisition system, medical image processing system, and clinical data analysis system, and it presents both of quantitative and qualitative data for physicians. This article proposes a CAD system for diagnosing neonatal and infantile brain disorders. The CAD system acquires intracranial images using MR scanner system, and segments the cerebral volume and surface using medical image processing systems, and produces cerebral volume and area, and 3-D rendering of cerebral surface. Especially, this article proposes medical image processing systems based on expert knowledge systems for neonatal/infantile brain MR images. To validate the proposed CAD system, it has been applied to three neonatal and five infantile MR images.

This paper describes a human health monitoring system by an air pressure sensor and an ultrasonic sensor system. The ultrasonic sensor system can obtain the state of a patient in bed by placing it under a bed frame. That is, we can determine whether or not a patient in the bed The air pressure sensor system can detect heart beats by placing it to the mattress on the bed By using two sensors complementary we can detect the behavior before getting out of bed aided by fuzzy inference technique. The system Of the two sensors can complementary defects the state, heart beat, a behavior before getting out of bed Thus, the system of the two sensor systems can noninvasively and unconsciously provide human health information with high accuracy aided by fuzzy logic.

Estimating 3-D pose/position of knee implants in-vivo is one of important methods for evaluation of total knee arthroplasty (TKA). It has been performed with 2-D/3-D image registration of knee implants' 3-D geometrical model (i.e., CAD; computer-aided design) and 2-D X-ray radiography image, which can take a projection image of TKA implants in-vivo. Although they have been producing valuable results, they cannot be applied without 3-D geometrical models. It is the critical limitation for clinical situations because most of physicians cannot have 3-D geometrical model. This paper proposes a novel system for evaluating knee implants without 3-D CAD models, and it uses 3-D digital radiology (DR) images. The system is based on a new method, called fuzzy visual hull, which is an extension of the conventional visual hull by introducing fuzzy logic. The new method can reconstruct 3-D object shape from 2-D silhouette images with vague contour of objects. The new method was evaluated by using TKA implants in-vitro and computer synthesized images. The results showed that fuzzy visual hull has high robustness for noises independently added to silhouette images.

This paper proposes a functional assessment system of autonomic nervous system using an air pressure sensor. The air pressure sensor can unconstraintly detect vital information by placing it under the mattress in bed. We perform functional assessment of autonomic nervous system by heart rate variability obtained by the system. In this system, we employ fuzzy membership functions with dynamic parameter to detect RR intervals. The experimental results show that we detect RR intervals with the correlation coefficient of 0.851 with comparison to that of electrocardiograph. Then the errors of the HF (index of parasympathetic system) and the LF/HF (index of sympathetic system) are 11.98% and 22.18%, respectively.

Volumetric cerebrum and measurement of cerebral surface area using MR images plays a fundamental role in computer-aided diagnosis (CAD) of neonatal cerebral diseases such as hypoxic ischemic encephalopathy. There are many conventional methods for brain extraction from adult MR images. However, it is hard to apply these methods for neonatal MR images that image features are different from adult one. This paper proposes a novel method for extracting neonatal cerebral surface with sub-voxel accuracy using Thick Rubber Model (TRM). This method extracts a cerebral surface by deforming TRM so that pseudo MR images synthesized from TRM are identical to the given MR images. Experimental results showed that the proposed method extracted the cerebral surface with higher accuracy (mean RMS distance was 9.0 mm) in comparison with the conventional method (mean RMS distance was 15.7).

We propose a thickness determination method of the intestine with the ultrasonic probe of 15MHz. We determine the surface point by calculating correlation coefficient between surface echo and an acquisition waveform. Next, we determine the bottom point by calculating amplitude of bottom echo, correlation with surface echo and bottom echo, and interval distance between surface echo and bottom echo. Finally, we calculate the thickness between the surface and the bottom points. As the result, we have obtained the thickness within an error rate of 5.09%.

In this paper, we propose a personal identification by sole pressure change. We obtain sole pressure change of multiple steps by using two pressure sensor sheets. Each pressure sensor sheet is inserted into each shoe as an inner sock. Then, we extract characteristics of sole pressure change from the obtained data. We make template data of both feet from the extracted characteristics. We propose a Euclidean distance based method for personal identification. As the experimental result, we have recognized one of ten volunteers with over 90% accuracy.

The pivot shift test has been performed to assess the instability of the knee caused by anterior cruciate ligament (ACL) injuries. However, the test depends on the clinician's subjective feeling. In this study, inertial and magnetic sensors have been introduced into quantitative evaluation of the pivot shift test. The analysis method extracts the knee movement of the pivot shift by using wavelet transformation. In the result of applying the proposed method to the ACL injured subject, pivot shift phenomenon was detected correctly in comparison with reference video images taken simultaneously. In the quantitative assessment, the mean of the maximum acceleration during the pivot shift was 2.19+/-0.69 m/s(2), and the maximum acceleration values were correlated with grade scores based on the examiner's subjective evaluation.

This paper describes a fuzzy processing method for a respiratory rate monitoring system by an optical fiber sensor. This optical fiber sensor has a part of sensor sheet and a polarization detector. It noninvasively detects vital signal of human on the sheet by obtaining polarization variations. By using this sensor, we propose a fuzzy processing method of a respiratory rate for human in the bed. Our method was tested on five volunteers. We successfully detected a respiratory rate. In it, fuzzy logic plays a primary role in the detection. Our system determines fuzzy membership functions by using characteristic of respiration. Consequently, this system can noninvasively detect a respiratory rate by using a constraint-free device.