研究者詳細 - 神谷　亨

論文 - 神谷　亨

分割表示757 件中 101 - 120 件目／全件表示 >>

Recognition of Plastic Bottle Using Improved U-Net 査読有り国際誌

Ideta D., Kamiya T.

International Conference on Control, Automation and Systems 2022-November 200 - 203 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

This paper focuses on separation rubbish, which is one of the causes of global warming. Currently, recyclable waste including garbage is sent to the waste disposal site in an unsorted state, and it is separated by human source. This is difficult work and a cause of manpower shortage. To overcome those problem, it is necessary to introduce automatic sorting algorithms on separation rubbish process. In this study, we focused on separation rubbish process especially plastic bottles based on image recognition technique using a deep learning approach. We implement an improved U-Net as the deep learning scheme to increase segmentation accuracy. As a result, we obtained the segmentation accuracy with 0.789 of cap part and 0.972 of body part on plastic bottle respectively.

DOI： 10.23919/ICCAS55662.2022.10003819

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146598114&origin=inward

Identification of abnormal tissue from CT images using improved ResNet34 査読有り国際誌

Honda N., Kamiya T., Kido S.

International Conference on Control, Automation and Systems 2022-November 532 - 536 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In recent years, CT examinations have been widely used as a screening method to detect lung cancer. However, reading enormous CT images become a heavy burden to the physician. To avoid this problem, computer-aided diagnosis systems have been introduced on CT screening. In general, physicians consider patient information in addition to image information when they make a diagnosis, new efforts are being made to improve the accuracy of diagnosis by mimicking this information with a machine. In this paper, we propose a method for identifying pulmonary nodules by adding medical record information to images to improve the accuracy of diagnosis. We classify nodules from unknown data by assigning branching information of vascular opacities, straight vascular shadows, and nodular shadows as labeled image, which are a cause of misrecognition based on image features in machine learning. In the experiment, the classification accuracy of the nodule class was improved by adding clinical information to 644 images including 161 nodal images.

DOI： 10.23919/ICCAS55662.2022.10003937

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146569950&origin=inward

Identification for Drinking Spout of Plastic Bottle Using Multi Eff-UNet 査読有り国際誌

Moritsuka S., Kamiya T.

International Conference on Control, Automation and Systems 2022-November 209 - 212 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Currently, the increase of general waste is a problem in Japan. It is garbage and human waste. One solution to this problem is to reuse the bodies of used plastic bottles to reduce the amount of plastic waste and the increase in general waste. For this purpose, some municipalities provide bags for disposing of plastic bottle bodies. However, in many cases, the bottles are not only discarded in these bags, but also with their caps attached. In such cases, the caps must be found and removed by hand in the sorting and processing facility at the waste treatment plant. This means that the same work is performed by person for a long time, causing problems such as overlooking caps due to fatigue. To solve these problems, we develop a method for automatic identification of plastic bottle bodies and caps using deep learning technique. In this paper, we propose a model that combines multiple Eff-UNets. Specifically, we combine EfficientNetB4 for local segmentation and EfficientNetB5 for global segmentation. By using our method, we conducted an experiment on images of plastic bottles collected from the internet and other sources. We obtained segmentation results of 97.9% for plastic bottle bodies and 86.0% for plastic bottle caps.

DOI： 10.23919/ICCAS55662.2022.10003920

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146540644&origin=inward

Generation of Super-Resolution Images from Satellite Images Based on Improved RCAN 査読有り国際誌

Morishima F., Lu H., Kamiya T.

International Conference on Control, Automation and Systems 2022-November 213 - 216 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Satellite images can be analyzed and used for a variety of purposes. In the future, satellite image analysis will become more important since the number of satellites launches, and the amount of satellite data increase every year. Under these circumstances, there are some problems to be solved. One is the existence of low-resolution satellite images. To analyze the lower resolution of satellite images there are some technical issues such as reduction of noise, misclassification of object recognition. Therefore, high-resolution images are necessary. However, high-resolution satellite images are expensive, and its images may not be available in the past satellite images. Super-resolution which is introduced in image processing is a method to solve these problems. Convolutional neural network (CNN)-based methods are effective, and there is a need for models that can perform super-resolution with higher accuracy. In this paper, we propose a method for super-resolving satellite images, based on the improved the RCAN (residual channel attention network) model with SRM (style-based recalibration module). The proposed method improves the PSNR (peak signal to noise ratio) by 0.0181 dB compared to the conventional RCAN model.

DOI： 10.23919/ICCAS55662.2022.10003856

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146557504&origin=inward

Extraction of Cervical Lymph Nodes using Improved U-Net++ 査読有り国際誌

Shime N., Kamiya T., Ishida T.

International Conference on Control, Automation and Systems 2022-November 562 - 565 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Early detection and treatment of the lymph node are important since swelling of the neck is a likely factor in systemic metastasis of cancer. One of the diagnoses of cervical swelling is a CT scan, which has a beneficial influence on the diagnosis of the disease. However, the reading of CT images is burdened by the large number of images, which increases the physician's workload. In addition, since it is based on the subjective judgment of the physician, there may be discrepancies in diagnostic results and undetected cases due to differences in experience. A means of solving these problems requires a CAD system that provides a second opinion to the physician. Therefore, this paper proposes a segmentation method of cervical lymph node region for the purpose of developing a CAD system for the diagnosis of cervical lymphadenopathy from CT images. The proposal method is a CNN model with U-Net++ as the backbone, introducing CBAM (convolution block attention module) and dual-branch multi-scale attention module. The proposed method was applied to CT images of 11 cases, yielding IoU of 62.29, confirming its validity.

DOI： 10.23919/ICCAS55662.2022.10003916

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146553025&origin=inward

Environment Recognition from Spherical Camera Images Based on Multi-Attention DeepLab 査読有り国際誌

Nishida Y., Guangxu L., Lu H., Kamiya T.

International Conference on Control, Automation and Systems 2022-November 204 - 208 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Electric wheelchair is an easy-to-operate means of transportation that does not require physical strength. With the number of electric wheelchair users increasing in recent years, the increase in traffic accidents becomes a problem. Therefore, by developing an autonomous electric wheelchair, it is expected that the risk of accidents will be reduced and the convenience of the electric wheelchair will be improved. Environment recognition is indispensable for the development of autonomous electric wheelchairs. We propose a semantic segmentation method for recognizing 16 objects in traffic environment. This paper examines the improvement of problems such as the high price of autonomous electric wheelchairs due to the increase in the number of sensors used, which has been a concern in related research. Therefore, we use panoramic images acquired by a spherical camera as input data, and extern the Multi-Attention Deep Lab algorithms fitting for the recognition of distorted images. A new CNN model is constructed using Deep Lab v3+, scSE Block, Pairwise Self-Attention, and Joint Pyramid Up-sampling. We conducted a recognition experiment using images taken on campus and verified its effectiveness. (Comparing to DeepLab v3+, IoU and Dice showed a 3.5% and 3.6% improvement in accuracy, respectively.)

DOI： 10.23919/ICCAS55662.2022.10003689

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146621100&origin=inward

Development of Temporal Subtraction Technique for Phalanges CR Image using Geometric-matching CNN 査読有り国際誌

Ono H., Kamiya T., Aoki T.

International Conference on Control, Automation and Systems 2022-November 558 - 561 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

We are developing a computer-aided diagnosis system for rheumatoid arthritis. X-rays images are widely used to diagnose the rheumatoid arthritis. However, it is difficult for physicians to read minute changes from the images. Therefore, we propose a method to visualize lesions in the phalangeal region by comparing past and current images of the same subject using a temporal subtraction technique. The proposed method consists of three steps: segmentation of phalanges, registration, and generation of subtraction images. First, the phalangeal region is extracted from the hand CR image using DeepLabv3+. Next, the past and current phalangeal region images are aligned by geometric-matching based on a CNN (convolutional neural networks) with instance-specific optimization. Finally, we apply the temporal subtraction technique to those images. We confirmed the effectiveness of the proposed registration method in an experiment using synthetic data. Also, the proposed method was applied to a pair of past and current image sets on same subject to generate a subtraction image. As a result, we confirmed that the proposed method can visualize changes between past and current images.

DOI： 10.23919/ICCAS55662.2022.10003828

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146633083&origin=inward

Detection of Driver Gene Mutations from Thoracic CT Images Based on LightGBM with Radiomics Features 査読有り国際誌

Watanabe S., Kamiya T., Terasawa T., Aoki T.

International Conference on Control, Automation and Systems 2022-November 542 - 545 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Lung cancer is one of the most common cancers worldwide and has become a general medical problem. To lessen the risk of death, early detection and treatment is particularly required. The patients can use molecularly targeted drugs when the driver gene mutations of the cancer are detected, but invasive biopsies are required. So, development of new methods to detect it noninvasively and in a short time are expected. we propose a new machine learning method for identifying the presence or absence of driver gene mutations of lung cancer on Thoracic CT Images that is a non-invasive, in a short time, and low-cost CAD (Computer Aided Diagnosis) system. In the proposed method, radiomics features are given as explanatory variables in addition to Thoracic CT Images, and supervised learning using LightGBM is performed to conduct binary classification with/without driver gene mutations.

DOI： 10.23919/ICCAS55662.2022.10003871

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146575218&origin=inward

Denoising on Low-Dose CT Image Using Deep CNN 査読有り国際誌

Sadamatsu Y., Murakami S., Li G., Kamiya T.

International Conference on Control, Automation and Systems 2022-November 546 - 549 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Computed Tomography (CT) scans are widely used in Japan, and they contribute to public health. On the other hand, there is also a risk of radiation exposure. To solve this problem, attempts are being made to reduce the radiation dose during imaging. However, reducing the radiation dose causes noise and degrades image quality. In this paper, we propose an image analysis method that efficiently removes noise by changing the activation function of Deep Convolutional Neural Network (Deep CNN). Experimental tests using full-body slice CT images of pigs and phantom CT images of lungs with Poisson noise show that the proposed method is helpful by comparing them with normal-dose CT images and evaluating image quality using peak signal-to-noise ratio (PSNR).

DOI： 10.23919/ICCAS55662.2022.10003847

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146610706&origin=inward

Classification the Root Resorption from Panoramic X-ray Image Using Center Loss Redefined in Angle Space 査読有り国際誌

Tamura K., Kamiya T., Oda M., Morimoto Y.

International Conference on Control, Automation and Systems 2022-November 570 - 573 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Root resorption is a pathological condition which is characterized by the loss of the tooth root. Root resorption is not painful in its early stages. As a result, many people who are potentially affected and the condition are often left untreated until it is detected during regular check-ups. If detected early, good treatment results can be achieved, whereas failure to treat the condition properly can lead to tooth extraction. However, the root resorption is currently difficult to detect on panoramic radiographs and may be treated as caries after it becomes painful. The aim of this paper is to identify root resorption from panoramic X-ray images using a deep metric learning algorithm. As a loss function for distance learning, it is known that the loss function in angle space is consistent. Therefore, a loss function is defined and trained using the cosine value of the angle between the feature and the center position to improve the discrimination performance. We obtained experimental results based on 150 image sets with 0.80 of accuracy, 0.62 of TPR, 0.19 of FPR and 0.78 of AUC, respectively.

DOI： 10.23919/ICCAS55662.2022.10003752

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146551688&origin=inward

Classification of CTC on Fluorescence Image Based on Improved AlexNet 査読有り国際誌

Kisanuki K., Guangxu L., Kamiya T.

International Conference on Control, Automation and Systems 2022-November 550 - 553 2022年11月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

These days, cancer has been the most primary cause of death in Japan. Cancer often progresses by repeating metastasis, so early detection and early treatment are important. Analysis of Circulating Tumor Cells (CTCs) has come to gather attention as a new biomarker that CTCs can detect primary cancer in human body. However, the number of CTCs in a billion blood cells is only a few, and detecting CTCs is very hard. Accordingly, we propose an automatic detection method of CTCs from fluorescence microscopy images to enable quantitative analysis by computer. This method consists of two parts. The first part, we use some series of filtering to the images and, new dividing method some overlapping nucleus then, from the images cut out the region of interest (ROI). The second part is distinguishing images by using CNN. We applied the proposed method to 5040 images of 6 samples. As a result, we obtained TPR:94.59%, FPR:6.544% by using AlexNet based model.

DOI： 10.23919/ICCAS55662.2022.10003905

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85146616673&origin=inward

Automatic Detection of Cervical Lymph Nodes from Non-Contrast CT Images Using the SSD 査読有り国際誌

Baba, Ishida, Kamiya

International Conference on Control, Automation and Systems 566 - 569 2022年11月

Automatic Identification of CTCs in Fluorescence Microscope Images Using Morphological Filtering to Detect Cell Nuclei 査読有り国際誌

Hashimoto, Park, Ha, Jung, Kamiya

International Conference on Control, Automation and Systems 554 - 557 2022年11月

Multi Eff-UNet＋を用いたペットボトルとキャップの識別

森塚、神谷

第8回画像関連学会連合会秋季大会 11 - 12 2022年11月

距離学習とアンサンブル学習を併用した歯根吸収の判別法

田村晃聖，神谷亨，小田昌史*,森本泰宏

北九州医工学術者協会誌 ( 北九州医工学術者協会誌 ) 62 11 - 14 2022年11月

Geometric Matching CNNによる指骨CR画像の位置合わせとその評価査読有り

小野、神谷、青木

Medical Imaging Technology ( Medical Imaging Technology ) 40 ( 5 ) 226 - 232 2022年11月

Three-dimensional quantification of postoperative facial asymmetry in patients with unilateral cleft lip and palate using facial symmetry plane 査読有り国際誌

Shiigi, Okawachi, Kamiya, Hosoki, Nomoto, Ratman, Amir, Ishihata, Nakamura

The Cleft Palate Craniofacial Journal 2022年09月

3次元点群データを用いた口唇裂の対称性解析

細木大祐, 神谷亨, 野元菜美子, 椎木綾乃, 大河内孝子, 中村典史

第21回情報科学技術フォーラム 525 - 526 2022年09月

Multi-organ Statistical Shape Model Building Using a Non-rigid ICP Based Surface Registration 査読有り国際誌

Wu J., Li G., Kamiya T.

Journal of Image and Graphics(United Kingdom) 10 ( 3 ) 95 - 101 2022年09月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

Landmark correspondence is one of the key steps in Statistical Shape Model (SSM) building. In this paper, a non-rigid iterative closest point surfaces registration method is introduced to seek proper corresponded landmarks in the multi-organ surface meshes. Surfaces of four abdominal organs are used in the experiment to build SSM from landmarks corresponded by five different registration strategies. The proposed method of individually non-rigid registration of single organs shows the least errors measured by Hausdorff distance and the best model quality of generalization ability, specificity, and compactness.

DOI： 10.18178/joig.10.3.95-101

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85138705827&origin=inward

Temporal Subtraction Technique for Thoracic MDCT Based on Residual VoxelMorph 査読有り国際誌

Miyake N., Lu H., Kamiya T., Aoki T., Kido S.

Applied Sciences (Switzerland) 12 ( 17 ) 2022年09月

担当区分：最終著者,　責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

The temporal subtraction technique is a useful tool for computer aided diagnosis (CAD) in visual screening. The technique subtracts the previous image set from the current one for the same subject to emphasize temporal changes and/or new abnormalities. However, it is difficult to obtain a clear subtraction image without subtraction image artifacts. VoxelMorph in deep learning is a useful method, as preparing large training datasets is difficult for medical image analysis, and the possibilities of incorrect learning, gradient loss, and overlearning are concerns. To overcome this problem, we propose a new method for generating temporal subtraction images of thoracic multi-detector row computed tomography (MDCT) images based on ResidualVoxelMorph, which introduces a residual block to VoxelMorph to enable flexible positioning at a low computational cost. Its high learning efficiency can be expected even with a limited training set by introducing residual blocks to VoxelMorph. We performed our method on 84 clinical images and evaluated based on three-fold cross-validation. The results showed that the proposed method reduced subtraction image artifacts on root mean square error (RMSE) by 11.3% (p < 0.01), and its effectiveness was verified. That is, the proposed temporal subtraction method for thoracic MDCT improves the observer’s performance.

DOI： 10.3390/app12178542

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85137919955&origin=inward

　前のページ - 次のページ　

<神谷 亨>

論文 - 神谷 亨

<神谷　亨>

論文 - 神谷　亨