Takashi Obi

Takashi Obi

Auto-generated profile, based on publicly available information

Takashi Obi

Institute of Innovative Research, Tokyo Institute of Technology, Yokohama, Japan

Research Focus & Metrics

Academic Career Length

31Years (1996-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2004 in Journal of Biomedical Optics
Verified
Journal Article
Open access
PDF file
KGKazuhiro Gono
Kazuhiro Gono
TOTakashi Obi
Takashi Obi
MYMasahiro Yamaguchi
Masahiro Yamaguchi
NONagaaki Ohyama
Nagaaki Ohyama
HMHirohisa Machida
Hirohisa Machida
TETakao Endo
Takao Endo
This study was performed to examine the usefulness of medical endoscopic imaging utilizing narrow-band illumination. The contrast between the vascular pattern and the adjacent mucosa of the underside of the human tongue was measured using five narrow-band illuminations and three broadband illuminations. The results demonstrate that the pathological features of a vascular pattern are dependent on the center wavelength and the bandwidth of illumination. By utilizing narrow-band illumination of 415±30 nm, the contrast of the capillary pattern in the superficial layer was markedly improved. This is an important benefit that is difficult to obtain with ordinary broadband illumination. The appearances of capillary patterns on color images were evaluated for three sets of filters. The narrow, band imaging (NBI) filter set (415±30 nm, 445±30 nm, 500±30 nm) was selected to achieve the preferred appearance of the vascular patterns for clinical tests. The results of clinical tests in colonoscopy and esophagoscopy indicated that NBI will be useful as a supporting method for observation of the endoscopic findings of early cancer. © 2004 Society of Photo-Optical Instrumentation Engineers.

1 January 2020 in Healthcare Informatics Research
Verified
Journal Article
Open access
DTDara TITH
Dara TITH
JLJoong-Sun Lee
Joong-Sun Lee
HSHiroyuki Suzuki
Hiroyuki Suzuki
WWW. M. A. B. Wijesundara
W. M. A. B. Wijesundara
NTNaoko Taira
Naoko Taira
NONagaaki Ohyama
Nagaaki Ohyama
Electronic Health Record (EHR) systems are increasingly used as an effective method to share patients' records among different hospitals. However, it is still a challenge to access scattered patient data through multiple EHRs. Our goal is to build a system to access patient records easily among EHRs without relying on a centralized supervisory system. We apply consortium blockchain to compose a distributed system using Hyperledger Fabric incorporating existent EHRs. Peer nodes hold the same ledger on which the address of a patient record in an EHR is written. Individual patients are identified by unique certificates issued by a local certificate authorities that collaborate with each other in a channel of the network. To protect a patient's privacy, we use a proxy re-encryption scheme when the data are transferred. We designed and implemented various chaincodes to handle business logic agreed by member organizations of the network. We developed a prototype system to implement our concept and tested its performance including chaincode logic. The results demonstrated that our system can be used by doctors to find patient's records and verify patient's consent on access to the data. Patients also can seamlessly receive their past records from other hospitals. The access log is stored transparently and immutably in the ledger that is used for auditing purpose. Our system is feasible and flexible with scalability and availability in adapting to existing EHRs for strengthening security and privacy in managing patient records. Our research is expected to provide an effective method to integrate dispersed patient records among medical institutions.

31 October 2020 in Healthcare Informatics Research
Verified
Journal Article
Open access
PDF file
DTDara TITH
Dara TITH
JLJoong-Sun Lee
Joong-Sun Lee
HSHiroyuki Suzuki
Hiroyuki Suzuki
WWW. M. A. B. Wijesundara
W. M. A. B. Wijesundara
NTNaoko Taira
Naoko Taira
NONagaaki Ohyama
Nagaaki Ohyama
For the last decade, digital transformation has been an important development in all industries, and it is also happening rapidly in the healthcare field, bringing positive changes. Patient records are now more efficiently stored and transmitted. They can be effectively shared among hospitals where patient visits are logged through Electronic Health Record (EHR) systems, thus reducing the inconvenience and burden for patients. Stored patient data may be collected with the patient's permission to make a big data, which enables healthcare providers to analyze it and to offer personalized services. It is also expected to contribute to medical and

2 January 2024 in International Journal of Information Technology
Verified
Journal Article
Open access
PDF file
PJPei Jiang
Pei Jiang
TOTakashi Obi
Takashi Obi
YNYoshikazu Nakajima
Yoshikazu Nakajima
The big Artificial General Intelligence models inspire hot topics currently. The black box problems of Artificial Intelligence (AI) models still exist and need to be solved urgently, especially in the medical area. Therefore, transparent and reliable AI models with small data are also urgently necessary. To build a trustable AI model with small data, we proposed a prior knowledge-integrated transformer model. We first acquired prior knowledge using Shapley Additive exPlanations from various pre-trained machine learning models. Then, we used the prior knowledge to construct the transformer models and compared our proposed models with the Feature Tokenization Transformer model and other classification models. We tested our proposed model on three open datasets and one non-open public dataset in Japan to confirm the feasibility of our proposed methodology. Our results certified that knowledge-integrated transformer models perform better (1%) than general transformer models. Meanwhile, our proposed methodology identified that the self-attention of factors in our proposed transformer models is nearly the same, which needs to be explored in future work. Moreover, our research inspires future endeavors in exploring transparent small AI models.

8 June 2022 in Journal of Biomedical Optics
Verified
Journal Article
Open access
PDF file
EAEleni Aloupogianni
Eleni Aloupogianni
MIMasahiro Ishikawa
Masahiro Ishikawa
NKNaoki Kobayashi
Naoki Kobayashi
TOTakashi Obi
Takashi Obi
More people are diagnosed with skin cancer each year in the United States than all other cancers combined.1 Malignant melanoma (MM) and other skin cancer crude mortality rates increased up to twofold in Japan from 1999 to 2014, independent of the aging of the Japanese population.2 The increased workload demands increased effectiveness in the diagnosis and management of malignant lesions. Skin lesions of concern are evaluated clinically and/or histopathologically. Gross pathology, the intermediate stage between the two, remains a manual, labor-intensive, and non-standardized step in the diagnostic work flow,3 despite recent advances in digital pathology.4 Hyperspectral imaging (HSI) is an imaging modality that can assist gross pathology. HSI captures spectral signatures of tissue pixels dependent on substance concentrations inside the tissue and has been proven useful for staining and standardization in histopathology.5 In the past decade, several research groups have investigated applications of HSI and multispectral imaging (MSI) at the gross pathology stage, toward diagnosis and tumor classification of skin lesions, aiming to achieve noninvasive optical biopsies and increase diagnosis speed.

31 October 2022 in Journal of Biomedical Optics
Verified
Journal Article
Open access
PDF file
EAEleni Aloupogianni
Eleni Aloupogianni
TITakaya Ichimura
Takaya Ichimura
MHMei Hamada
Mei Hamada
MIMasahiro Ishikawa
Masahiro Ishikawa
TMTakuo Murakami
Takuo Murakami
TOTakashi Obi
Takashi Obi
In Japan, incidence and mortality rates of skin cancer have increased in the past decades, despite adjustments for an aging population.1 At the same time, the American Cancer Society estimates that malignant skin tumors comprise the majority of all cancers in the United States.2 Early diagnosis is key for the effective treatment of skin tumors. Dermoscopy and histology remain the golden standards for clinical detection and diagnosis, respectively. However, the intermediate stage of gross pathology hinders the digital flow. Gross pathology is a visual assessment stage that includes the manual preparation of ex-vivo tissue for histology. Despite advances in medical technology, gross pathology lacks digitization, automation, and standardization. At the same time, it is time-consuming and dependent on the skill of the pathologist. However, pigmented skin lesions (PSL), a group of pathologies with a high incidence rate, are rich in color information. Hyperspectral imaging (HSI) is a noninvasive imaging technique that can capture spectral signatures of a tissue sample, capable of discriminating malignancies.3 A noninvasive, nonionizing optical biopsy based on HSI could speed up diagnosis, reduce the number of re-excisions, enable telepathology, and increase treatment effectiveness.