Papers - Tanaka, Toshiyuki

Region extraction method for skin grafts via image analysis

Wada D., Kato S., Yamaguchi Y., Tanaka T.

Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization 10 ( 1 ) 22 - 37 2022

Research paper (scientific journal), Joint Work, Corresponding author, Accepted,  ISSN  21681163

　View Summary

Dermal grafts are used for patients with severe burn injuries whose natural healing abilities are limited or exhausted. This paper proposes a method to segment burnt and grafted areas from images with meshed grafts. First, RGB colour input images are converted to images in the L*a*b* colour space. The transformed images are then segmented with the simple linear iterative clustering superpixel algorithm. Subsequently, the burnt and grafted areas are classified with a support vector machine, and the output area size is modified for all burnt areas. The segmentation results are compared with the areas identified by two dermatologists based on the concordance rate (CR), positive predictive value (PPV), sensitivity, and F-measure values. The proposed segmentation method yielded CRs equal to 84.3 % and 85.9 %, PPVs equal to 87.2 % and 87.9 %, sensitivities equal to 84.7 % and 86.4 %, and F-measure values equal to 85.8 % and 87.0 %. This study developed a segmentation method for classifying burnt and grafted areas from images with meshed grafts. The segmented areas obtained were significantly consistent with those identified by the two dermatologists.

• Access to Document (DOI)

Diagnosis support system for skin grafting using GrowCut with an automated seed selection

Ezaki K., Kato S., Yamaguchi Y., Tanaka T.

Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization (Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization)  11 ( 3 ) 942 - 959 2022

ISSN  21681163

　View Summary

This paper deals with a method of segmenting skin and skin grafts using GrowCut. The previous lacks system usability because the evaluating physician needed approximately 100–200 mouse clicks for each image to acquire training data. Therefore, we propose a method to automate the acquisition of training data while maintaining the accuracy of domain segmentation from the previous study. Based on the proposed method, the ratio of the two areas-of-interest was calculated as the burn ratio and used to evaluate treatment quantitatively. The results show that the segmentation of skin and skin grafts is as accurate as by mouse clicks. We think that automating the acquisition of training data as preprocessing will improve the usability of the system.

• Access to Document (DOI)

Objective and quantitative measurement of skin micro-relief by image analysis and application in age-dependent changes

Wu Y., Tanaka T.

Skin Research and Technology (Skin Research and Technology)  27 ( 6 ) 1072 - 1080 2021.11

Research paper (scientific journal), Joint Work, Corresponding author, Accepted,  ISSN  0909752X

　View Summary

Background: Skin micro-relief has been researched by a variety of devices and methods, which usually are expensive or complicated. On the other hand, skin micro-relief relates to quite a few parameters, and it is hard to evaluate all of them at the same time. In the study, all parameters related to skin micro-relief are extracted and evaluated by image analysis. Materials and Methods: Skin micro-relief evaluation was divided into four aspects: (a) Tamura features method was used to evaluate skin surface. (b) Morphological transform was applied to extract skin pores. (c) Watershed transform was applied to extract skin furrows. (d) labeling operation was used to evaluate the number, area and average area of skin closed polygons. Then, cheek images from 163 healthy Japanese females (0-70 years old) are analyzed to explore the age-dependent changes. Results: Most parameters increased as age went on with significant differences, such as skin surface coarseness, contrast, skin pore number, area, average area, skin furrow width, skin closed polygon area and skin closed polygon average area. Skin coarseness has a strong correlation with pore area. Conclusion: The method proposed in the study provided a comprehensive and effective assessment of skin micro-relief.

• Access to Document (DOI)

Quantitative Assessment of Age-dependent Changes in Porphyrins from Fluorescence Images of Ultraviolet Photography by Image Processing

Wu Y., Akimoto M., Igarashi H., Shibagaki Y., Tanaka T.

Photodiagnosis and Photodynamic Therapy 35 2021.09

Research paper (scientific journal), Joint Work, Accepted,  ISSN  15721000

　View Summary

Background: Skin is the first line of defense against harmful external environmental factors. Skin flora living on the skin surface impact skin health and skin disease. Bacteria, form part of the unique and complex skin micro-ecological system. For example, Propionibacterium acnes (P. acnes) is a member of the anaerobic organisms and is involved in the induction of skin acne. It produces porphyrins that absorb ultraviolet light and emit red fluorescence in response. As a result, fluorescence surveillance of the skin can be important in both the diagnosis of skin acne and the evaluation of therapeutic effects. Many different measurement methods for single skin biophysical properties have been reported. This study focused on the age-dependent changes in porphyrins for normal skin, and developed a novel algorithm to evaluate porphyrins using the fluorescence images by image processing quantitatively. Materials and methods: An extraction algorithm was proposed for the segmentation of porphyrin fluorescence images in OpenCV. The algorithm consisted primarily of preprocessing, conversion from RGB color space to HSV color space, and classification of fluorescence. There are 3595 healthy Japanese aged 16–85 years enrolled in the study and fluorescence images were acquired from their cheek sites under 375 nm UV-LED excitation. Age-related fluorescence variation was conducted applying the algorithm implemented. Results: A new extraction algorithm has been proposed with fluorescence image input and three indexes output, including the number of fluorescence, area of fluorescence, and mean intensity of fluorescence. Proposed algorithm was verified by three parameters, the accuracy, sensitivity, and precision, which refer to the ability of algorithm to detect the number of fluorescence correctly and repeatedly. The verification results were 71%, 72%, and 88% respectively, taking a validly fundamental step for skin health record and analysis. Furthermore, large-scale fluorescence image segmentation results revealed that similar trends were coming out for all three indexes in cheek as people get older. All the fluorescence number, area and mean intensity arrived at the highest at 30 years old and fell off since then. Conclusion: The number, area, and fluorescence intensity of porphyrins can be extracted well from fluorescence images with the proposed algorithm in the study, which has the potential to aid in thediagnosis of skin acne and predict skin conditions as an assisted tool. It is implicated that fluorescence status is influenced by age, which rises to the peak around 30 years old for normal cheek's skin.

• Access to Document (DOI)

3D Assessment of Facial Symmetry for Quantitative Diagnosis for Facial Paralysis

Ken Sudo, Toshiyuki Tanaka

Journal of Ergonomic Technology 21 ( 1 ) 1 - 11 2021.03

Research paper (scientific journal), Joint Work, Accepted,  ISSN  2432-1575

Utilization of Individual Typology Angle (ITA) and Hue Angle in the Measurement of Skin Color on Images

Yue Wu, Toshiyuki Tanaka, Makio Akimoto

Bioimages 28   1 - 8 2020.12

Research paper (scientific journal), Joint Work, Accepted,  ISSN  0919-2719

CNNを用いた肺腺癌再発予測のための腫瘍識別技術

服部　英春, 坂下　信悟, 石井　源一郎, 田中　敏幸

Medical Imaging Technology (日本医用画像工学会)  40 ( 5 ) 249 - 260 2020.11

Research paper (scientific journal), Joint Work, Corresponding author, Accepted,  ISSN  0288-450X

• Access to Document (DOI)

A study on automatic extraction of facial feature points in skin image analysis system

Yuto Mori, Toshiyuki Tanaka, Natsuki Takegama

Proceedings of the SICE Annual Conference 2020    691 - 694 2020.09

Research paper (international conference proceedings), Joint Work, Accepted

Age Evaluation Method by Extracting Wrinkle Area from Face Image

Takahiro Yamamoto, Toshiyuki Tanaka

Proceedings of the SICE Annual Conference 2020    1475 - 1478 2020.09

Research paper (international conference proceedings), Joint Work, Accepted

Machine learning-based histological classification that predicts recurrence of peripheral lung squamous cell carcinoma

Koike Y., Aokage K., Ikeda K., Nakai T., Tane K., Miyoshi T., Sugano M., Kojima M., Fujii S., Kuwata T., Ochiai A., Tanaka T., Suzuki K., Tsuboi M., Ishii G.

Lung Cancer (Lung Cancer)  147   252 - 258 2020.09

ISSN  01695002

　View Summary

Background: Cancer tissue is composed of both a cancer cell component and a stromal component. The aim of this study was to investigate if the component ratio predicts a prognosis for lung squamous cell carcinoma (SqCC) patients by using a machine learning method. Methods: A total of 135 peripheral SqCC cases (tumor size: 3−5 cm) were enrolled in this study. The areas of the cancer cell component, the necrotic component, and the stromal component were accurately measured via a machine learning method. Each case was divided into the following three subtypes: 1) predominant cancer cell, 2) predominant necrosis, and 3) predominant stroma. The study examined if a particular subtype had prognostic significance. Results: The number of cases per subtype of predominant cancer cell, predominant necrosis, and predominant stroma was 59, 6, and 70, respectively. Patients with the predominant stroma subtype had a significantly shorter recurrence free survival (RFS) than did those with the predominant cancer cell subtype (5-yr RFS: 42.3 % vs. 84.3 %,p < 0.01). Also, in pathological stage I patients, the 5-year RFS rate for the predominant stroma subtype was significantly shorter (5-yr RFS: 64.3 % vs. 88.4 %, p < 0.01). In the multivariate analysis of p-stage I patients, the predominant stroma subtype was confirmed to be an independent prognostic factor for RFS (p < 0.01). Conclusion: Using machine learning, the study confirmed that the predominant stroma subtype was an independent factor for RFS, suggesting that the ratio of the stromal component correlates with the malignant potential of SqCC.

• Access to Document (DOI)

Extraction of tongue coating area from tongue image for automated tongue diagnosis

Gou Nambu, Takao Namiki, Toshiya Nakaguchi, Toshiyuki Tanaka

Journal of Ergonomic Technology 20 ( 1 ) 1 - 9 2020.08

Research paper (scientific journal), Joint Work, Accepted,  ISSN  2432-1575

顕著性マップを用いた画質評価法

兒玉萌絵，田中敏幸

パーソナルコンピュータ利用技術学会論文誌 14 ( 1 ) 1 - 7 2020.03

Research paper (scientific journal), Accepted

Objective measurement and comparison of human facial skin color in East Asian females

Yue Wu, Fan Yi, Makio Akimoto, Toshiyuki Tanaka, Hong Meng

Skin Research and Technology (John Wiley & Sons Ltd.)  26 ( 4 ) 584 - 590 2020.01

Research paper (scientific journal), Joint Work, Accepted,  ISSN  0909752X

　View Summary

© 2020 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd Background: Skin color is an important physiological index of human skin that has essential significance in cosmetology and dermatological diagnoses and aesthetics, especially in East Asian culture, where the beauty standard is the whiter the skin, the more beautiful a person is. However, there has been a lack of objective comparisons of facial skin color in East Asian females. Materials and Methods: Skin color at the cheek site was measured in 445 healthy females, including 362 Chinese women in Beijing and 83 Japanese women in Tokyo, all aged 18-50 years. The parameters consisted of L*, a*, b*, individual typology angle (ITA°), and hue angle and were determined using noninvasive skin measurement instruments. Results: The skin color categories in East Asians ranged from very light (I) to brown (V), and the dark (VI) category was not observed; the main categories were light (II), intermediate (III), and tan (IV). The facial skin color of Chinese individuals was brighter, more reddish, and less yellowish than that of Japanese individuals. With age, L* values decreased, and a* values and hue angle increased in East Asians with significant differences. Chinese women showed the same differences as Japanese women for all parameters in all age groups. Conclusions: This study provides objective skin color measurements and examines significant differences with respect to geographic location and age.

• Access to Document (DOI)

Indoor location positioning measurement using only smartphone sensors

Sota K., Tanaka T.

Proceedings of the International Conference on Sensing Technology, ICST (Proceedings of the International Conference on Sensing Technology, ICST)  2019-December 2019.12

ISSN  9781728146317

　View Summary

© 2019 IEEE. In this research, we focus on positioning in places where radio waves from satellites can not reach, such as indoors. We aim at establishment and accuracy improvement of positioning using sensor data of smartphone. The number of steps, stride, and direction are important factors in this research. The previous research has a large error and can not estimate an accurate position. Therefore, we propose position estimation method by adding the newly studied method to the conventional method.

• Access to Document (DOI)

年齢推定を用いた顔画像における男女判別率の向上

須藤健，田中敏幸

国際ICT利用研究学会論文誌 3 ( 1 ) 3 - 10 2019.12

Research paper (scientific journal), Joint Work, Accepted

Automatic Extraction of Atypia Keratinocytes from Oral Cancer Cytodiagnosis Images

Shohei Yokoi, Toshiyuki Tanaka

Proceedings of the SICE Annual Conference 2019    148 - 150 2019.09

Research paper (international conference proceedings), Joint Work, Accepted

Proposal of Positioning Measurement Using Only Smartphone Sensor

Keitaro Sota, Toshiyuki Tanaka

Proceedings of the SICE Annual Conference 2019    1174 - 1175 2019.09

Research paper (international conference proceedings), Joint Work, Accepted

Skin Translation Evaluation System Based on Image Processing

K. Ezaki, S. Kato, Y. Yamaguchi and T. Tanaka

41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society  2019.07

Research paper (international conference proceedings), Accepted

Practice of Outpatient Rehabilitation by the Takizawa Method and Motivative Exercise

Toshiyuki Tanaka

The 16th International Biophilia Rehabilitation Conference  2019.06

Research paper (international conference proceedings), Single Work, Accepted

Assessment of Brain Activation at Motivative Exercise Using fNIRS and fMRI

Toshiyuki Tanaka

13th International Society of Physical and Rehabilitation Medicine World Congress  2019.06

Research paper (international conference proceedings), Single Work, Accepted