畑 豊

This paper proposes an automated procedure for segmenting an MR image of a human brain based on fuzzy logic, An MR volumetric image composed of many slice images consists of several parts: gray matter, white matter, cerebrospinal fluid, and others. Generally, the histogram shapes of MR volumetric images are different from person to person. Fuzzy information granulation of the histograms can lead to a series of histogram peaks. The intensity thresholds for segmenting the whole brain of a subject are automatically determined by finding the peaks of the intensity histogram obtained from the MR images. After these thresholds are evaluated by a procedure called region growing, the whole brain can be identified. A segmentation experiment was done on 50 human brain MR volumes. A statistical analysis showed that the automated segmented volumes were similar to the volumes manually segmented by a physician. Next, we describe a procedure for decomposing the obtained whole brain into the left and right cerebral hemispheres, the cerebellum and the brain stem, Fuzzy if-then rules can represent information on the anatomical locations, segmentation boundaries as well as intensities. Evaluation of the inferred result using the region growing method can then lead to the decomposition of the whole brain. We applied this method to 44 MR volumes, The decomposed portions were statistically compared with those manually decomposed by a physician, Consequently,our method can identify the whole brain, the left cerebral hemisphere, the right cerebral hemisphere, the cerebellum and the brain stem with high accuracy and therefore can provide the three dimensional shapes of these regions.

This paper shows an application of fuzzy information granulation (fuzzy IC) to medical image segmentation. Fuzzy IG is to derive fuzzy granules from information. In the case of medical image segmentation, information and fuzzy granules correspond to an image taken from a medical scanner, and anatomical parts, namely region of interests (ROIs), respectively. The proposed method to granulate information is composed of volume quantization and fuzzy merging. Volume quantisation is to gather similar neighboring voxels. The generated quanta are selectively merged according to degrees for pre-defined fuzzy models that represent anatomical knowledge of medical images. The proposed method was applied to blood vessel extraction from three-dimensional time-of-Right (TOF) magnetic resonance angiography (MRA) images of the brain. The volume data studied in this work is composed of about 100 contiguous and volumetric MM images. According to the fuzzy IG concept, information correspond to the volume data, fuzzy granules corresponds to the blood vessels and fat. The qualitative evaluation by a physician was done for two- and three-dimensional images generated from the obtained blood vessels. The evaluation shows that the method can segment MRA volume data, and that fuzzy IG is applicable to, and suitable for medical image segmentation.

This paper proposes an image segmentation method based on fuzzy if-then rules. It is a derivative of the conventional region growing method. This method represents expert's knowledge using fuzzy if-then rules, and embeds them as the growing criteria. To examine the proposed method, it has been applied to artificially generated images involving white Gaussian noise. In comparison with the conventional region growing method, the proposed method can segment region of interests(ROIs)with high robustness against to white noise. Moreover, it has been applied to dynamic mognetic resonance(MR)images of the Liver. The growing Criteria that represent physician's knowledge of MR images were derivedfrom the illustrated time-density curve of the liver, hepatic arteries, and veins after intravenous bolus injection. The experiments were done on three different normal volunteer with promising results.

In this paper, we propose a fuzzy inference based method to visualize three-dimensional (3-D) structure of a tube buried in a concrete. The nondestructive testing (NDT) with pulse-radar; which makes it possible to non-destructively unmask tubes in a concrete, is orle of the most remarkable techniques of NDT: However only expert can interpret the standard data. In our work we represent such expert's knowledge with fuzzy if-then rules. First the method estimates candidate points of a tube on the scanned data. Second 3-D links of the candidate points air constructed by inferring thf continuousness of the tube Thus, this method can extract the internal structure of the concrete. Our experimental result expressed the 3-D structure of tubes with high accuracy by comparing with the radiography result.

This paper proposes an architecture of a registration system for medical images. Image registration is the process of determining correspondence between all points in two images of the same scene, and is now widely used to medical images. In medical imaging, segmentation, registration and interpolation play primary roles. In those, registration is the most time consuming task because we must compare all voxel data and then evaluate the matching degree many times. Quantitative evaluation criterion of matching degree with multiple-valued coding of the image feature is proposed, and all architecture to save the processing time of the data comparison is described Finally, as a practical application, we described the summary of a registration of human brain MR volume data to diagnose brain disease.

This paper describes the benefit of utilizing the unary function generators in a multiple-valued Programmable Logic Array (PLA). We will clarify the most suitable PLA structure in terms of the array size. The multiple-valued PLA considered here has a structure with two types of function generators (literal and unary function generators), a first-level array and a second-level array. On investigating the effectiveness to reduce the array size, we can pick up four form PLAs: MAX-of-TPRODUCT form, MIN-of-TSUM-form, TSUM-of-TPRODUCT form and TPRODUCT-of-TSUM form PLAs among possible eight form PLAs constructing from the MAX, MIN, TSUM and TPRODUCT operators. The upper bound of the array sizes with v UGs is derived as ([log(2) p]-p upsilon + p(n - upsilon) + 1) p(n-1) to realize any n-variable p-valued function. Next, experiments to derive the smallest array sizes are done for 10000 randomly generated functions and 21 arithmetic functions. These results conclude that MAX-of-TPRODUCT form PLA is the most useful in reducing the array size among the four form PLAs.

最も多い疲労自覚症状は,朝が男女とも「集中力がない」(男子61.7%,女子69.1%),午後は男子が「体のどこかがだるい」(42.5%),女子は「座りたい」,「何もしたくない」(各52.7%)であった.疲労自覚症状の増加には,朝,午後とも男子が「部活動が厳しくてやめたい,もしくはやめた」,女子は「先生についての不満度が高い」が大きく影響していた

本論文では, ファジーコントローラに対するオンラインテストを提案する. 故障モデルには, メンバシップ関数の0故障及び1故障なる縮退型故障を仮定する. 本方法では, 1入力変数につき前件部に最大7個の検査用関数を付加し, 前件部と後件部のテストを並列に行う. 前件部検査では, 入力値と各関数とのマッチングで得られた関数値(ディグリー)の和を観測する. 後件部検査では, ファジー推論結果の面積, 適合度の和, 出力ファジー集合上のディグリー7個の和を観測する. これにより, 前件部と後件部に1個ずつ同時に生じた故障も検出対象とできる. また, 他方法との比較により, 本方法は対応可能な故障の数及び多入力コントローラへの適用容易性の観点から有利なことを示す.

本文では, トリー状結合プロセッサの再構成法及びレイアウト法を提案する. 本方法と従来法とを比較し, 最大配線長の観点から本方法が有利であることを示す.

This paper proposes a thresholding based segmentation method aided by Kleene Algebra. For a given image including some regions of interest (ROIs for short) with the coherent intensity level, assume that we can segment each ROI on applying thresholding technique. Three segmented states are then derived for every ROI: Shortage denoted by logic value 0, Correct denoted by 1 and Excess denoted by a. The segmented states for every ROI in the image can be then expressed on a ternary logic system. Our goal is then set to find "Correct (1)" state for every ROI. First, unate function, which is a model of Kleene Algebra, based procedure is proposed. However, this method is not complete for some cases, that is, correctly segmented ratio is about 70% for three and four ROI segmentation. For the failed cases, Brzozowski operations, which are defined on De Morgan algebra, can accommodate to completely find all "Correct" states. Finally, we apply these procedures to segmentation problems of a human brain MR image and a foot CT image. As the result, we can find all "1" states for the ROIs, i.e., we can correctly segment the ROIs.

本文では, 多段相互接続網(Multistage Interconnection Network:MIN)の一つであるべースライン網の耐故障設計法とその性能解析について述べる. 本方法では, スイッチ段数nのべースライン網に対し, 第1段と第n段のスイッチを多重化するとともに, 第2段と第(n-1)段にそれぞれ4入力2出力および2入力4出力のスイッチを用いる. これにより, 任意のターミナル間に経路が複数確保されるので, 耐故障性および性能が向上する. 本方法と従来法のMINを比較した結果, 本方法は最大でも1.34T倍程度となる比較的少ないハードウェア増加で故障時および非故障時のスループットを向上できることが示される.

本文では, 多段相互接続網(Multistage Interconnection Network:MIN)の一つであるべースライン網の耐故障設計法とその性能解析について述べる. 本方法では, スイッチ段数nのべースライン網に対し, 第1段と第n段のスイッチを多重化するとともに, 第2段と第(n-1)段にそれぞれ4入力2出力および2入力4出力のスイッチを用いる. これにより, 任意のターミナル間に経路が複数確保されるので, 耐故障性および性能が向上する. 本方法と従来法のMINを比較した結果, 本方法は最大でも1.34T倍程度となる比較的少ないハードウェア増加で故障時および非故障時のスループットを向上できることが示される.

本文では, 多段相互接続網(Multistage Interconnection Network:MIN)の一つであるべースライン網の耐故障設計法とその性能解析について述べる. 本方法では, スイッチ段数nのべースライン網に対し, 第1段と第n段のスイッチを多重化するとともに, 第2段と第(n-1)段にそれぞれ4入力2出力および2入力4出力のスイッチを用いる. これにより, 任意のターミナル間に経路が複数確保されるので, 耐故障性および性能が向上する. 本方法と従来法のMINを比較した結果, 本方法は最大でも1.34T倍程度となる比較的少ないハードウェア増加で故障時および非故障時のスループットを向上できることが示される.

This article shows a SD-reconstruction method of dynamic MRA images of the liver. The method is based on fuzzy if-then rules that represent expert's knowledge. The membership functions used are determined using accumulative histogram of given images. Thus, each of steps runs automatically with robustness. In the experimental result, the method is applied to three dynamic MRA data sets of the liver. Qualitative evaluation by physicians were done for reconstructed 3D images. It shows that the method segments the hepatic veins precisely, and given images are essentially for surgery planning.

In this paper, we propose a method to segment the menisci region from Tl-weighted and T2-weighted MR images. These images are taken continuously by the same system, so we can easily registrate them by manual. Our method is composed of two steps. First, we segment the candidate region of the menisci on the basis of the position of the cartilage from T2 weighted image. Second, we segment the meniscus voxels from the candidate based on fuzzy rules from Tl-weighted and T2-weighted images. Our method can successfully segment the menisci region from MR data sets. The generated visualizations will help medical doctor to diagnose the menisci with noninvasive.

The cerebral ventricle is a part of the brain region filled with cerebrospinal fluid (CSF). Some brain diseases may cause a change of the shape of the cerebral ventricle. Information of the shape and volume is useful for diagnosing hydrocephalus and Alzheimer's disease. The authors propose a fully automated procedure for segmenting the lateral ventricle from human brain MR volumes. In this method, we first decompose a segmented CSF into small parts (primitives) using watershed segmentation and then determine the primitives which belong to the lateral ventricle by fuzzy if-Then rules. We applied our method to 10 MR volumes (10 different persons). As a result, our method can segment the lateral ventricle with high accuracy and therefore provide the three dimensional shape.

This paper examines the uncertainty of answering questionnaire in elderly women. We derive a membership function demonstrating a robustness of the knee-raising test and height related to decreased instrumental activities of daily living (IADL) for the uncertainty of answering questionnaire. This result could be maintained if the number of movement were within range from -10 to +5 persons.

In this paper we discuss the reconfiguration of two-dimensional meshes embedded in hypercubes with link and/or node failures. First, we assume that only the link failures may occur. Our method consists of two stages. The first stage assigns dimensions of hypercube to two directions of mesh so that the losses of rows or columns would be as small as possible. The second stage establishes the mesh communication by assigning the Cartesian product of two Gray code sequences to every node. We generate these sequences with a depth-first search or generic algorithm. This method can be applied to node failures by regarding a faulty node as a node whose links are entirely faulty. Our simulation results show that our method can reconfigure large meshes with short computation time.

The paper introduces registration systems of multi-modality medical images and describes the practical systems related to brain science. A possibility for applying soft computing techniques is also shown. First we describe a registration system of computed tomography image and magnetic resonance angiography image of a human brain. This registration system is used to demonstrate anatomical location information of vascular lesion from the surface of the human skull. We next describe a registration system of magnetic resonance (MR) image and positron emission transmission (PET) image. The MR image can produce neuroanatomical information, and the PET image quantifies metabolic pathways in vivo. In both systems, we describe a possibility of soft computing techniques.

In this paper, we Proposes a method of reconfiguring 2D meshes embedded in hypercubes. Our reconfiguration for link failures consists of two stages. The first stage assigns the d dimensions of the hypercubes to two directions with respect to rows and columns in the mesh, so that the number of disconnected pairs with adjacent rows and columns becomes smaller. The second stage re-establishes the mesh communication by assigning the Cartesian product of two Gray code sequences, which represent the order of healthy rows and columns to every node. We introduce graphs with edges corresponding to connections between rows or columns, and search the sequences. Then either an approach based on the depth-first search or one based on a genetic algorithm is applied to the graphs. The approach is made valid for node failures by regarding a faulty node as a node without healthy links. Simulation results show that our method reconfigures embedded meshes efficiently with relatively short computation time.

In this paper we discuss the reconfiguration of two-dimensional meshes embedded in hypercubes with link and/or node failures. First, we assume that only the link failures may occur. Our method consists of two stages. The first stage assigns dimensions of hypercube to two directions of mesh so that the losses of rows or columns would be as small as possible. The second stage establishes the mesh communication by assigning the Cartesian product of two Gray code sequences to every node. We generate these sequences with a depth-first search or generic algorithm. This method can be applied to node failures by regarding a faulty node as a node whose links are entirely faulty. Our simulation results show that our method can reconfigure large meshes with short computation time.

This paper shows a novel medical image segmentation method applied to blood vessel segmentation from magnetic resonance angiography volume data. The principle idea of the method is fuzzy information granulation concept. The method consists of 2 parts: (1) quantization and feature extraction, (2) iterative fuzzy synthesis. In the first part, volume quantization is performed with watershed segmentation technique. Each quantum is represented by three features, vascularity, narrowness and histogram consistency. Using these features, we estimate the fuzzy degrees of each quantum for knowledge models about MRA volume data. In the second part, the method increases the fuzzy degrees by selectively synthesizing neighboring quantums. As a result, we obtain some synthesized quantums. We regard them as fuzzy granules and classify them into blood vessel or fat by evaluating the fuzzy degrees. In the experimental result, three dimensional images are generated using target maximum intensity projection (MIP) and surface shaded display. The comparison with conventional MIP images shows that the unclarity region in conventional images are clearly depict in our images. The qualitative evaluation done by a physician shows that our method can extract blood vessel region and that the results are useful to diagnose the cerebral diseases.

This paper describes some classes of fuzzy information granularity and their representation methods. Fuzzy information granularity introduced by Zadeh is that "granularity relates to clumpiness of structure, while granulation refers to partitioning an object into a collection of granules, with a granule being a clump of objects(points) drawn together by indistinguishability, similarity, proximity, or functionality." In this paper we show three classes of granularity structures, which are called Kleene class, Lukasiewicz class and probabilistic like class. Their meaning and representation methods are discussed. Their examples are also demonstrated. This paper would be a basis to research on the representation of fuzzy information granularity.

Injuries of the menisci are one of the most common internal derangement of the knee. To examine them with noninvasive, we propose an automated segmentation method of the menisci region from MR image. The method is composed of two steps based on fuzzy logic. First, we segment the cartilage region by thresholding of the intensity. We then extract the candidate region of the menisci as the region between the cartilages. Second, we segment the menisci voxels from the candidate region based on fuzzy if-then rules obtained from knowledge of location and intensity. We applied our method to five MR data sets. Three of them are the normal knees and the others are with some injures. Quantitative evaluation by a physician shows that this method can successfully segment the menisci for the all. The generated visualizations will help medical doctor to diagnose the menisci with noninvasive.

The paper introduces registration systems of multi-modality medical images and describes the practical systems related to brain science. A possibility for applying soft computing techniques is also shown. First we describe a registration system of computed tomography image and magnetic resonance angiography image of a human brain. This registration system is used to demonstrate anatomical location information of vascular lesion from the surface of the human skull. We next describe a registration system of magnetic resonance (MR) image and positron emission transmission (PET) image. The MR image can produce neuroanatomical information, and the PET image quantifies metabolic pathways in vivo. In both systems, we describe a possibility of soft computing techniques.

This paper describes useful fuzzy logic techniques for medical image segmentation. Specific methods to be reviewed include fuzzy information granulation, fuzzy inference and fuzzy cluster identification. Fuzzy information granulation is introduced as a powerful scheme to find the thresholds to obtain the whole brain region in MR data. Fuzzy inference technique succeeds to segment the brain region into the left cerebral hemisphere, right cerebral hemisphere, cerebellum and brain stem. The fuzzy inference aided segmentation procedure is also useful to human foot CT image. Fuzzy cluster identification is adapted to determine the obtained clusters into blood vessel or other tissues in MRA image.

This paper presents a feature extraction model 'MAGNET' to find the deepest point of branched sulcus. Our model demonstrates magnetic principle and consists of four types of ideal magnetic poles: an N-pole and three S-poles. According to attractive or repulsive Coulomb forces between their poles, one of the S-pules is pushed to the deepest point of the sulcus. First, we explain our model on the simple sulcus model. Second, we apply it to the sulcus with implicit branches. Our model can detect the target paints in every branch. Then an example to realize the model on a synthetic image is introduced. We apply our model to human brain MR images and human foot CT images. Experimental results on human brain MR images show that our method enable us to successfully detect the points.

This paper presents a feature extraction model 'MAGNET' to find the deepest point of branched sulcus. Our model demonstrates magnetic principle and consists of four types of ideal magnetic poles: an N-pole and three S-poles. According to attractive or repulsive Coulomb forces between their poles, one of the S-pules is pushed to the deepest point of the sulcus. First, we explain our model on the simple sulcus model. Second, we apply it to the sulcus with implicit branches. Our model can detect the target paints in every branch. Then an example to realize the model on a synthetic image is introduced. We apply our model to human brain MR images and human foot CT images. Experimental results on human brain MR images show that our method enable us to successfully detect the points.

本文では, ファジィインフォメーショングラニュレーション(fuzzy Information Granulation; fuzzy IG)による, 頭部MR画像からの脳領域抽出の為の濃度しきい値発見法を提案する.Fuzzy IGとは, Zadehが提唱する新しい概念である.ファジィ情報(fuzzy information)は, 幾つかのファジィグラニュール(fuzzy granule)で構成され, fuzzy IGによってfuzzy informationからfuzzy granuleが引き出される.本手法では, fuzzy informationを濃度ヒストグラムとして, fuzzy granuleを脳を構成する白質部, 灰白質部, 脳脊髄液のヒストグラム上のピークとする.Fuzzy IGは, 医師の知識をモデル化したヒストグラムと, 画像の濃度ヒストグラムとのファジィマッチングによって行う.得られたしきい値を用いて自動抽出した脳体積と, 手動で得られた体積とを, 50例のMR画像に対して比較した結果, 平均誤差率は2.3%であった.

<p>論理式の構造に依存しない簡単化アルゴリズムを提案する.本方法では対象とする論理式を実現するネットワークをニューラルネットワークを基に定義する.このネットワークに対してバックプロパゲーション法を適用し, 与えられた関数を実現するまで学習を行う.そしてそのネットワークから不要なユニットを削除し, 再度学習を行う.これをネットワークが論理関数を実現できなくなるまで繰り返す.その後, 最後に論理関数を表したネットワークの状態から論理式を導く.本文ではこの方法を2値論理式の簡単化に適用する.まず最初に, AND, OR, 及びEXOR演算を実現するニューロンモデルを定義し, そのモデルと論理式との対応を説明する.次に, これらのモデルを用いてAND-OR, OR-AND, 及びAND-EXORの各論理式を表現し, 簡単化を行う.そして, 本方法が論理式の構造に依存せず適用可能であることを示す.</p>

<p>本文ではファジィ推論に基づく脳部位の自動分割法を提案する.分割対象とする部位は右脳, 左脳, 小脳および脳幹である.本方法では各部位について位置, 形状および濃度の知識を与え, ボクセルが部位間境界に所属する度合いを推論する.推論は2段階で行われる.まず, 位置に関する知識で全体を大きく4つの領域に分割する.つぎに, 形状および濃度の知識が厳密な境界所属度を決定していく.得られた推論結果はリージョングローイングの過程で評価され, 各部位が自動的に抽出される.本方法を36人の脳MR画像に適用した結果, 医師による分割に対する平均誤差率は2.5%であった.</p>

This paper shows an application of fuzzy information granulation to medical image segmentation for MR angiography image. The method treats medical image as information, and the granules are the anatomical parts such as blood vessel, fat, etc. Our granulation method consists of two stages : (1) Quantum generation and (2) Integration of them to produce granules. Quantum generation is performed with watershed segmentation. Integration process is achievedby estimating the degree for predefined models. By granulating MR angiography image, we obtain the bloodvessel region. In the experimental results, we show the target M IP and shaded surface display images of the segmented region. They are useful for evaluating the lesions such as the areury.

This paper shows a method to segment the menisci regions from MR image by using fuzzy inference. The method is composed of two steps. First, we segment the cartiladge region by thresholding of the intensity. We extract the candidate region of the menisci as the region between the cartilages. Second, we segment the menisci voxels from the candidate region based on fuzzy if-then rules obtained from knowledge of location and intensity. Our method can successfully segment the menisci region from MR data sets. The generated visualizations will help medical doctor to diagnose the menisci with noninvasive.

This paper proposes a scheme of image granulation by fuzzy inference technique. For a region of interests(ROI) in a medical image, we describe knowledge needed to granulate the ROI, for example, knowledge of intensity, knowledge of location and so on. Generally, we cannot granulate the ROI without employing the whole of the knowledge. Fuzzy inference rules of the derived knowledge can accommodate the granulation. After the inference results are compiled to a total degree, a resultant data is obtained. Clustering or region growing technique is used to granulate the ROI. The experimental results on human brain MR images and human foot CT images show that our method can precisely granulate the ROI.