Yasushi Hirano

Classification of diffuse lung disease patterns on high-resolution computed tomography by a bag of words approach

Visual inspection of diffuse lung disease (DLD) patterns on high-resolution computed tomography (HRCT) is difficult because of their high complexity. We proposed a bag of words based method on the classification of these textural patters in order to improve the detection and diagnosis of DLD for radiologists. Six kinds of typical pulmonary patterns were considered in this work. They were consolidation, ground-glass opacity, honeycombing, emphysema, nodular and normal tissue. Because they were characterized by both CT values and shapes, we proposed a set of statistical measure based local features calculated from both CT values and the eigen-values of Hessian matrices. The proposed method could achieve the recognition rate of 95.85%, which was higher comparing with one global feature based method and two other CT values based bag of words methods.

Reciprocal attentive communication in remote meeting with a humanoid robot

In this paper, we investigate the reciprocal attention modality in remotecommunication. A remote meeting system with a humanoid robot avatar is proposedto overcome the invisible wall for a video conferencing system. Ourexperimental result shows that a tangible robot avatar provides more effectivereciprocal attention against video communication. The subjects in the experimentare asked to determine whether a remote participant with the avatar is activelylistening or not to the local presenters talk. In this system, the head motionof a remote participant is transferred and expressed by the head motion of ahumanoid robot. While the presenter has difficulty in determining the extentof a remote participants attention with a video conferencing system, she/he hasbetter sensing of remote attentive states with the robot. Based on theevaluation result, we propose a vision system for the remote user thatintegrates omni-directional camera and robot-eye camera images to provide a wideview with a delay compensation feature.

A pattern mining method for interpretation of interaction

This paper proposes a novel mining method for multimodal interactions to extract important patterns of group activities. These extracted patterns can be used as machine-readable event indices in developing an interaction corpus based on a huge collection of human interaction data captured by various sensors. The event indices can be used, for example, to summarize a set of events and to search for particular events because they contain various pieces of context information. The proposed method extracts simultaneously occurring patterns of primitive events in interaction, such as gaze and speech, that in combination occur more consistently than randomly. The proposed method provides a statistically plausible definition of interaction events that is not possible through intuitive top-down definitions. We demonstrate the effectiveness of our method for the data captured in an experimental setup of a poster-exhibition scene. Several interesting patterns are extracted by the method, and we examined their interpretations.

Computer-aided diagnosis of lung cancer: definition and detection of ground-glass opacity type of nodules by high-resolution computed tomography.

PurposeThe ground-glass opacity (GGO) of lung cancer is identified only subjectively on computed tomography (CT) images as no quantitative characteristic has been defined for GGOs. We sought to define GGOs quantitatively and to differentiate between GGOs and solid-type lung cancers semiautomatically with a computer-aided diagnosis (CAD).Methods and materialsHigh-resolution CT images of 100 pulmonary nodules (all peripheral lung cancers) were collected from our clinical records. Two radiologists traced the contours of nodules and distinguished GGOs from solid areas. The CT attenuation value of each area was measured. Differentiation between cancer types was assessed by a receiver-operating characteristic (ROC) analysis.ResultsThe mean CT attenuation of the GGO areas was −618.4 ± 212.2 HU, whereas that of solid areas was −68.1 ± 230.3 HU. CAD differentiated between solidand GGO-type lung cancers with a sensitivity of 86.0% and specificity of 96.5% when the threshold value was −370 HU. Four nodules of mixed GGOs were incorrectly classified as the solid type. CAD detected 96.3% of GGO areas when the threshold between GGO and solid areas was 194 HU.ConclusionObjective definition of GGO area by CT attenuation is feasible. This method is useful for semiautomatic differentiation between GGOs and solid types of lung cancer.

Classification of diffuse lung diseases patterns by a sparse representation based method on HRCT images

This paper describes a computer-aided diagnosis (CAD) method to classify diffuse lung diseases (DLD) patterns on HRCT images. Due to the high variety and complexity of DLD patterns, the performance of conventional methods on recognizing DLD patterns featured by geometrical information is limited. In this paper, we introduced a sparse representation based method to classify normal tissues and five types of DLD patterns including consolidation, ground-glass opacity, honeycombing, emphysema and nodular. Both CT values and eigenvalues of Hessian matrices were adopted to calculate local features. The 2360 VOIs from 117 subjects were separated into two independent set. One set was used to optimize parameters, and the other set was adopted to evaluation. The proposed technique has a overall accuracy of 95.4%. Experimental results show that our method would be useful to classify DLD patterns on HRCT images.

Semantic characteristics prediction of pulmonary nodule using Artificial Neural Networks

Since it is difficult to choose which computer calculated features are effective to predict the malignancy of pulmonary nodules, in this study, we add a semantic-level of Artificial Neural Networks (ANNs) structure to improve intuition of features selection. The works of this study include two: 1) seeking the relationships between computer-calculated features and medical semantic concepts which could be understood by human; 2) providing an objective assessment method to predict the malignancy from semantic characteristics. We used 60 thoracic CT scans collected from the Lung Image Database Consortium (LIDC) database, in which the suspicious lesions had been delineated and annotated by 4 radiologists independently. Corresponding to the two works of this study, correlation analysis experiment and agreement experiment were performed separately.

3DAV integrated system featuring arbitrary listening-point and viewpoint generation

In this paper, we propose two novel methods for arbitrary listening-point generation for 3D audio-video (3DAV) integration in a large-scale multipoint cameras and microphones system with abilities to process, and display information of any recorded 3D scene in realtime. With this system, users are able to control their own viewpoint/listening-point position, freely. Arbitrary listening-point can be generated by either (i) ray-space representation of sound wave field (i.e. source sound independent) for multi frequency layers, or (ii) acoustic transfer function estimation (i.e. source sound dependent) and blind separation of sources of sounds. Arbitrary viewpoint generation is based on ray-space method, which is enhanced by using multipass dynamic programming for geometry compensation. Integration is done by either (i) ray-space representation of sound wave and image together, or (ii) integrating each camera video signal and acoustic transfer function of the same location as integrated 3DAV data. The prototype system of integrated audio-visual viewer achieves both good image and sound qualities with 15 frames/second.

Extraction of tumor regions keeping boundary shape information from chest X-ray CT images and benign/malignant discrimination

Abstract In this paper, we propose a new method to extract tumor regions from thin-slice chest X-ray CT images. The tumor regions that are used for benign/malignant discrimination must keep boundary shape information as exactly as possible because the tumor regions specify the regions for which features are calculated. The proposed method is based on the thresholding of CT values and distance. Since the change of CT values suggest the existence of tumors, it is reasonable to use thresholding of CT values for extraction of tumor regions. We assume that the position of tumors are known beforehand because the thin-slice chest X-ray CT images are taken with the view to be used in the close medical examination. We applied the method to 78 practical CT images, and 67 tumors were extracted properly. Furthermore, the benign/malignant discrimination was carried out suitably using the tumor regions extracted by the proposed method. The correct classification rate was improved from 0.84 to 0.91. This shows the usefulness of the method developed here.

Automatic detection of GGO regions on CT images in LIDC dataset based on statistical features

Detection of pulmonary nodules with ground glass opacity (GGO) is a difficult task in radiology. Follow up is often required in medical fields. But diagnosis based on CT images are dependent on ability and experience of radiologists. In addition to that, enormous number of images increase their burden. So, to improve the detection accuracy and to reduce the burden of doctors, a CAD (Computer Aided Diagnosis) system is expected. So, in this paper, we propose an automatic algorithm for GGO detection on CT images. At first, vessel areas are removed from original CT images by using 3D Line Filter and then candidate regions are detected by threshold processing. After that, we calculate statistical features of segmented candidate regions and use artificial neural network (ANN) to distinguish final candidate regions. We applied the proposed method to 31 CT image sets in the Lung Image Database Consortium (LIDC) which is supplied by National Center Institute (NCI). In this paper, we show the experimental results and give discussions.

Particle System Based Adaptive Sampling on Spherical Parameter Space to Improve the MDL Method for Construction of Statistical Shape Models

Minimum description length (MDL) based group-wise registration was a state-of-the-art method to determine the corresponding points of 3D shapes for the construction of statistical shape models (SSMs). However, it suffered from the problem that determined corresponding points did not uniformly spread on original shapes, since corresponding points were obtained by uniformly sampling the aligned shape on the parameterized space of unit sphere. We proposed a particle-system based method to obtain adaptive sampling positions on the unit sphere to resolve this problem. Here, a set of particles was placed on the unit sphere to construct a particle system whose energy was related to the distortions of parameterized meshes. By minimizing this energy, each particle was moved on the unit sphere. When the system became steady, particles were treated as vertices to build a spherical mesh, which was then relaxed to slightly adjust vertices to obtain optimal sampling-positions. We used 47 cases of (left and right) lungs and 50 cases of livers, (left and right) kidneys, and spleens for evaluations. Experiments showed that the proposed method was able to resolve the problem of the original MDL method, and the proposed method performed better in the generalization and specificity tests.