Faculty Profiles - MATSUI Yusuke

Papers - MATSUI Yusuke

Division display 21 - 40 of about 133 ／ All the affair displays >>

Revolutionizing radiation therapy: the role of AI in clinical practice Reviewed

Mariko Kawamura, Takeshi Kamomae, Masahiro Yanagawa, Koji Kamagata, Shohei Fujita, Daiju Ueda, Yusuke Matsui, Yasutaka Fushimi, Tomoyuki Fujioka, Taiki Nozaki, Akira Yamada, Kenji Hirata, Rintaro Ito, Noriyuki Fujima, Fuminari Tatsugami, Takeshi Nakaura, Takahiro Tsuboyama, Shinji Naganawa

Journal of Radiation Research 2023.11

Publishing type：Research paper (scientific journal) Publisher：Oxford University Press (OUP)

Abstract

This review provides an overview of the application of artificial intelligence (AI) in radiation therapy (RT) from a radiation oncologist’s perspective. Over the years, advances in diagnostic imaging have significantly improved the efficiency and effectiveness of radiotherapy. The introduction of AI has further optimized the segmentation of tumors and organs at risk, thereby saving considerable time for radiation oncologists. AI has also been utilized in treatment planning and optimization, reducing the planning time from several days to minutes or even seconds. Knowledge-based treatment planning and deep learning techniques have been employed to produce treatment plans comparable to those generated by humans. Additionally, AI has potential applications in quality control and assurance of treatment plans, optimization of image-guided RT and monitoring of mobile tumors during treatment. Prognostic evaluation and prediction using AI have been increasingly explored, with radiomics being a prominent area of research. The future of AI in radiation oncology offers the potential to establish treatment standardization by minimizing inter-observer differences in segmentation and improving dose adequacy evaluation. RT standardization through AI may have global implications, providing world-standard treatment even in resource-limited settings. However, there are challenges in accumulating big data, including patient background information and correlating treatment plans with disease outcomes. Although challenges remain, ongoing research and the integration of AI technology hold promise for further advancements in radiation oncology.

DOI： 10.1093/jrr/rrad090

researchmap

Time course of complications after small renal mass biopsy: evaluation of initial follow-up images Reviewed

Soichiro Kajita, Toshihiro Iguchi, Yusuke Matsui, Koji Tomita, Mayu Uka, Noriyuki Umakoshi, Takahiro Kawabata, Kazuaki Munetomo, Takao Hiraki

Japanese Journal of Radiology 2023.11

Publishing type：Research paper (scientific journal) Publisher：Springer Science and Business Media LLC

Abstract

Purpose

To retrospectively assess the time course of complications after image-guided small renal mass biopsy using initial follow-up imaging.

Materials and methods

A total of 190 masses (mean, 2.1 ± 0.70 cm; range, 0.6–3.8 cm) were assessed using initial computed tomography (43 non-enhanced and 141 enhanced) or magnetic resonance imaging (five non-enhanced and one enhanced) after biopsy. Initial follow-up imaging was classified into two groups (i.e., with or without hematoma) and various factors were compared.

Results

The masses were histologically diagnosed in all patients except one. Post-procedural complications included 129 Grade I hematomas, 1 Grade I hemothorax, 9 Grade II hematomas, and 1 Grade IIIa pneumothorax. Residual 28 Grade I and 6 Grade II hematomas and 8 new complications (6 small hematomas, 1 pseudoaneurysm, and 1 arteriovenous fistula) were observed on the initial follow-up imaging obtained at a median of 21 days (3–90 days) after the biopsy. On the initial follow-up imaging, the groups with and without hematoma differed significantly in the following factors: age (P = 0.04), size (P = 0.02), guided images (P < 0.01), hematoma at the end of the procedure (P < 0.01), and days after biopsy (P < 0.01). Although three masses exhibited > 25% shrinkage, no significant change was observed in mass diameter on initial follow-up imaging (mean, 2.1 ± 0.71 cm; P = 0.90).

Conclusion

Initial follow-up imaging after a biopsy revealed improvements in most of the complications, a few new complications, and an unchanged mass diameter.

DOI： 10.1007/s11604-023-01509-9

researchmap

Other Link： https://link.springer.com/article/10.1007/s11604-023-01509-9/fulltext.html

Prospective evaluation of core number of biopsy for renal tumor: are multiple cores preferable? Reviewed

Toshihiro Iguchi, Yusuke Matsui, Tomohiro Toji, Jun Sakurai, Koji Tomita, Mayu Uka, Noriyuki Umakoshi, Takahiro Kawabata, Kazuaki Munetomo, Toshiharu Mitsuhashi, Takao Hiraki

Japanese Journal of Radiology 2023.10

Publishing type：Research paper (scientific journal) Publisher：Springer Science and Business Media LLC

Abstract

Purpose

This single-center, single-arm, prospective, open-label study was conducted to evaluate the optimal number of cores (single or multiple) in renal tumor biopsy.

Materials and methods

Forty-four biopsies of 44 tumors (mean diameter, 2.7 ± 1.0 cm; range, 1.6–5.0 cm) were included. Biopsy was performed under ultrasound or computed tomography fluoroscopy guidance using an 18-gauge cutting needle and the co-axial method. Two or more specimens were obtained, which were divided into first and subsequent specimens. “First specimen” and “all specimens” were histologically evaluated (i.e., appropriateness of specimen, histological diagnosis, subtype, and Fuhrman grade of renal cell carcinoma [RCC]) blindly and independently by two board-certified pathologists.

Results

Multiple specimens were successfully and safely obtained in all the biopsies. All tumors were histologically diagnosed; 40 malignancies included 39 RCCs and 1 solitary fibrous tumor, and 4 benign lesions included 2 angiomyolipomas, 1 oncocytoma, and 1 capillary hemangioma. In all RCCs, the subtype could be determined (32 clear cell RCCs, 4 chromophobe RCCs, and 3 papillary RCCs), and the Furman grade was determined in 38 RCCs. When only the first specimen was evaluated, 22.7% of the specimens were inappropriate for diagnosis, and 34 (77.3%) were histologically diagnosed. The diagnostic yield was significantly lower than that of all specimens (P = 0.0044). Univariate analysis revealed that smaller lesions were a significant predictor of diagnostic failure (P = 0.020).

Conclusion

Biopsy with multiple cores significantly improved diagnostic yield. Thus, operators should obtain multiple cores during renal tumor biopsy.

DOI： 10.1007/s11604-023-01496-x

researchmap

Other Link： https://link.springer.com/article/10.1007/s11604-023-01496-x/fulltext.html

From FDG and beyond: the evolving potential of nuclear medicine Reviewed

Kenji Hirata, Koji Kamagata, Daiju Ueda, Masahiro Yanagawa, Mariko Kawamura, Takeshi Nakaura, Rintaro Ito, Fuminari Tatsugami, Yusuke Matsui, Akira Yamada, Yasutaka Fushimi, Taiki Nozaki, Shohei Fujita, Tomoyuki Fujioka, Takahiro Tsuboyama, Noriyuki Fujima, Shinji Naganawa

Annals of Nuclear Medicine 2023.9

New trend in artificial intelligence-based assistive technology for thoracic imaging Reviewed

Masahiro Yanagawa, Rintaro Ito, Taiki Nozaki, Tomoyuki Fujioka, Akira Yamada, Shohei Fujita, Koji Kamagata, Yasutaka Fushimi, Takahiro Tsuboyama, Yusuke Matsui, Fuminari Tatsugami, Mariko Kawamura, Daiju Ueda, Noriyuki Fujima, Takeshi Nakaura, Kenji Hirata, Shinji Naganawa

La radiologia medica 2023.8

Publishing type：Research paper (scientific journal) Publisher：Springer Science and Business Media LLC

Abstract

Although there is no solid agreement for artificial intelligence (AI), it refers to a computer system with intelligence similar to that of humans. Deep learning appeared in 2006, and more than 10 years have passed since the third AI boom was triggered by improvements in computing power, algorithm development, and the use of big data. In recent years, the application and development of AI technology in the medical field have intensified internationally. There is no doubt that AI will be used in clinical practice to assist in diagnostic imaging in the future. In qualitative diagnosis, it is desirable to develop an explainable AI that at least represents the basis of the diagnostic process. However, it must be kept in mind that AI is a physician-assistant system, and the final decision should be made by the physician while understanding the limitations of AI. The aim of this article is to review the application of AI technology in diagnostic imaging from PubMed database while particularly focusing on diagnostic imaging in thorax such as lesion detection and qualitative diagnosis in order to help radiologists and clinicians to become more familiar with AI in thorax.

DOI： 10.1007/s11547-023-01691-w

researchmap

Other Link： https://link.springer.com/article/10.1007/s11547-023-01691-w/fulltext.html

Evaluation of the ear ossicles with photon-counting detector CT Reviewed

Yuka Takahashi, Fumiyo Higaki, Akiko Sugaya, Yudai Asano, Katsuhide Kojima, Yusuke Morimitsu, Noriaki Akagi, Toshihide Itoh, Yusuke Matsui, Takao Hiraki

Japanese Journal of Radiology 2023.8

Publishing type：Research paper (scientific journal) Publisher：Springer Science and Business Media LLC

Abstract

Recently, computed tomography with photon-counting detector (PCD-CT) has been developed to enable high-resolution imaging at a lower radiation dose. PCD-CT employs a photon-counting detector that can measure the number of incident X-ray photons and their energy. The newly released PCD-CT (NAEOTOM Alpha, Siemens Healthineers, Forchheim, Germany) has been in clinical use at our institution since December 2022. The PCD-CT offers several advantages over current state-of-the-art energy-integrating detector CT (EID-CT). The PCD-CT does not require septa to create a detector channel, while EID-CT does. Therefore, downsizing the anode to achieve higher resolution does not affect the dose efficiency of the PCD-CT. CT is an indispensable modality for evaluating ear ossicles. The ear ossicles and joints are clearly depicted by PCD-CT. In particular, the anterior and posterior legs of the stapes, which are sometimes unclear on conventional CT scans, can be clearly visualized. We present cases of congenital anomalies of the ossicular chain, ossicular chain dislocation, tympanosclerosis, and cholesteatoma in which PCD-CT was useful. This short article reports the usefulness of PCD-CT in the 3D visualization of the ear ossicles.

DOI： 10.1007/s11604-023-01485-0

researchmap

Other Link： https://link.springer.com/article/10.1007/s11604-023-01485-0/fulltext.html

Fairness of artificial intelligence in healthcare: review and recommendations Reviewed

Daiju Ueda, Taichi Kakinuma, Shohei Fujita, Koji Kamagata, Yasutaka Fushimi, Rintaro Ito, Yusuke Matsui, Taiki Nozaki, Takeshi Nakaura, Noriyuki Fujima, Fuminari Tatsugami, Masahiro Yanagawa, Kenji Hirata, Akira Yamada, Takahiro Tsuboyama, Mariko Kawamura, Tomoyuki Fujioka, Shinji Naganawa

Japanese Journal of Radiology 2023.8

Publishing type：Research paper (scientific journal) Publisher：Springer Science and Business Media LLC

Abstract

In this review, we address the issue of fairness in the clinical integration of artificial intelligence (AI) in the medical field. As the clinical adoption of deep learning algorithms, a subfield of AI, progresses, concerns have arisen regarding the impact of AI biases and discrimination on patient health. This review aims to provide a comprehensive overview of concerns associated with AI fairness; discuss strategies to mitigate AI biases; and emphasize the need for cooperation among physicians, AI researchers, AI developers, policymakers, and patients to ensure equitable AI integration. First, we define and introduce the concept of fairness in AI applications in healthcare and radiology, emphasizing the benefits and challenges of incorporating AI into clinical practice. Next, we delve into concerns regarding fairness in healthcare, addressing the various causes of biases in AI and potential concerns such as misdiagnosis, unequal access to treatment, and ethical considerations. We then outline strategies for addressing fairness, such as the importance of diverse and representative data and algorithm audits. Additionally, we discuss ethical and legal considerations such as data privacy, responsibility, accountability, transparency, and explainability in AI. Finally, we present the Fairness of Artificial Intelligence Recommendations in healthcare (FAIR) statement to offer best practices. Through these efforts, we aim to provide a foundation for discussing the responsible and equitable implementation and deployment of AI in healthcare.

DOI： 10.1007/s11604-023-01474-3

researchmap

Other Link： https://link.springer.com/article/10.1007/s11604-023-01474-3/fulltext.html

A Case of Small Bowel Arteriovenous Malformation Diagnosed Using Multiphase CT Angiography and Digital Subtraction Angiography Reviewed

Soichiro Okamoto, Yusuke Matsui, Hiroyuki Sakae, Keiichiro Oshima, Takao Hiraki

Cureus 2023.7

Image-Guided Ablation Therapies for Extrahepatic Metastases from Hepatocellular Carcinoma: A Review Invited Reviewed

Noriyuki Umakoshi, Yusuke Matsui, Koji Tomita, Mayu Uka, Takahiro Kawabata, Toshihiro Iguchi, Takao Hiraki

Cancers 15 ( 14 ) 3665 - 3665 2023.7

Publishing type：Research paper (scientific journal) Publisher：MDPI AG

The most common sites of extrahepatic metastases from hepatocellular carcinoma (HCC) are the lungs, intra-abdominal lymph nodes, bones, and adrenal glands, in that order. Although systemic therapies are a common treatment for patients with extrahepatic metastases, local ablative therapies for the extrahepatic metastatic lesions can be performed in selected patients. In this article, the literature on image-guided thermal ablation for metastasis to each organ was reviewed to summarize the current evidence. Radiofrequency ablation was the most commonly evaluated technique, and microwave ablation, cryoablation, and percutaneous ethanol injection were also utilized. The local control rate of thermal ablation therapy was relatively favorable, at approximately 70–90% in various organs. The survival outcomes varied among the studies, and several studies reported that the absence of viable intrahepatic lesions was associated with improved survival rates. Since only retrospective data from relatively small studies has been available thus far, more robust studies with prospective designs and larger cohorts are desired to prove the usefulness of thermal ablation for extrahepatic metastases from HCC.

DOI： 10.3390/cancers15143665

researchmap

Recent advances in artificial intelligence for cardiac CT: Enhancing diagnosis and prognosis prediction Reviewed

Fuminari Tatsugami, Takeshi Nakaura, Masahiro Yanagawa, Shohei Fujita, Koji Kamagata, Rintaro Ito, Mariko Kawamura, Yasutaka Fushimi, Daiju Ueda, Yusuke Matsui, Akira Yamada, Noriyuki Fujima, Tomoyuki Fujioka, Taiki Nozaki, Takahiro Tsuboyama, Kenji Hirata, Shinji Naganawa

Diagnostic and Interventional Imaging 2023.7

Clinical applications of artificial intelligence in liver imaging. Reviewed

Akira Yamada, Kamagata K, Hirata K, Ito R, Nakaura T, Ueda D, Fujita S, Fushimi Y, Fujima N, Matsui Y, Tatsugami F, Nozaki T, Fujioka T, Yanagawa M, Tsuboyama T, Kawamura M, Naganawa S

La Radiologia medica 2023.5

Publishing type：Research paper (scientific journal)

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.

DOI： 10.1007/s11547-023-01638-1

PubMed

researchmap

Robotic systems in interventional oncology: a narrative review of the current status Invited Reviewed

Yusuke Matsui, Tetsushi Kamegawa, Koji Tomita, Mayu Uka, Noriyuki Umakoshi, Takahiro Kawabata, Kazuaki Munetomo, Toshihiro Iguchi, Takayuki Matsuno, Takao Hiraki

International Journal of Clinical Oncology 2023.4

Renal cryoablation combined with prior transcatheter arterial embolization in non-dialysis patients with stage 4 or 5 chronic kidney disease: a retrospective study Reviewed

Noriyuki Umakoshi, Toshihiro Iguchi, Yusuke Matsui, Koji Tomita, Mayu Uka, Takahiro Kawabata, Kazuaki Munetomo, Shoma Nagata, Hideo Gobara, Motoo Araki, Takao Hiraki

Japanese Journal of Radiology 2023.4

Publishing type：Research paper (scientific journal) Publisher：Springer Science and Business Media LLC

Abstract

Purpose

To retrospectively evaluate cryoablation combined with prior transcatheter arterial embolization (TAE) for renal cell carcinoma (RCC) in non-dialysis patients with stage 4 or 5 chronic kidney disease (CKD).

Materials and methods

Patients with stage 4 or 5 CKD undergoing TAE and cryoablation for RCC between May 2012 and October 2021 were included. TAE was selectively performed using iodized oil with absolute ethanol or gelatin sponge 1–14 days before cryoablation. Local efficacy, safety, and changes in renal function were evaluated.

Results

Nine patients (seven men and two women; median age, 64 years; range 52–88 years) with nine RCCs (mean diameter, 3.0 ± 1.0 cm; range 1.7–4.7 cm) were included. The mean pre-treatment estimated glomerular filtration rate (eGFR) was 24.2 ± 5.6 ml/min/1.73 m² (range 10.4–29.2 ml/min/1.73 m²). The mean amount of contrast medium used in TAE was 58 ± 29 ml (range 40–128 ml). Except in one patient (grade 3 pyelonephritis), no grade ≥ 3 complications occurred. During the follow-up period (median, 18 months; range 7–54 months), no local tumor progression occurred. In two patients with pre-treatment eGFR of < 20 ml/min/1.73 m², hemodialysis was initiated at 3 and 19 months after cryoablation. At their last follow-up, the remaining seven patients showed a decrease of 6.2 ± 5.3 ml/min/1.73 m² (range 0.7–17.2 ml/min/1.73 m²) in their eGFR.

Conclusion

Cryoablation combined with TAE for RCC in non-dialysis patients with stage 4 or 5 CKD was effective and safe, with an acceptable impact on renal function.

DOI： 10.1007/s11604-023-01416-z

researchmap

Other Link： https://link.springer.com/article/10.1007/s11604-023-01416-z/fulltext.html

Complications of Percutaneous Cryoablation for Renal Tumors and Methods for Avoiding Them. Reviewed

Toshihiro Iguchi, Yusuke Matsui, Koji Tomita, Mayu Uka, Noriyuki Umakoshi, Takahiro Kawabata, Kazuaki Munetomo, Shoma Nagata, Motoo Araki, Takao Hiraki

Acta medica Okayama 77 ( 2 ) 121 - 129 2023.4

Language：English Publishing type：Research paper (scientific journal)

Percutaneous cryoablation of renal tumors is widely used because of its high efficacy and safety. This high safety can be attributed, at least in part, to the visibility of the ablated area as an "ice ball". This therapy has fewer complications (incidence, 0-7.2%) and is less invasive than surgery. Minor bleeding is inevitable in most kidney-related procedures, and indeed the most common complication of this therapy is bleeding (hematoma and hematuria). However, patients require treatment such as transfusion or transarterial embolization in only 0-4% of bleeding cases. Various other complications such as ureteral or collecting system injury, bowel injury, nerve injury, skin injury, infection, pneumothorax, and tract seeding also occur, but they are usually minor and asymptomatic. However, operators should know and avoid the various complications associated with this therapy. This study aimed to summarize the complications of percutaneous cryoablation for renal tumors and provide some techniques for achieving safe procedures.

DOI： 10.18926/AMO/65141

PubMed

researchmap

Navicular Bone Fracture after Radiofrequency Ablation in a Patient with Osteoid Osteoma. Reviewed

Koji Tomita, Toshihiro Iguchi, Yusuke Matsui, Mayu Uka, Eiji Nakata, Takao Hiraki

Acta medica Okayama 77 ( 1 ) 81 - 84 2023.2

Language：English

Osteoid osteoma (OO) is a benign bone tumor that presents with nocturnal pain. Computed tomography (CT)- guided radiofrequency ablation (RFA) has been widely performed for OO, and major adverse events post-RFA are rare. We report a case of OO in the left navicular bone of a 15-year-old male. He underwent RFA for OO, and the pain improved temporarily. At the 1-month follow-up, the patient complained of left foot pain, and a CT examination revealed a fracture of the ablated navicular bone. Fractures are rare but must be taken into account after bone RFA.

DOI： 10.18926/AMO/64366

PubMed

researchmap

Current State of Artificial Intelligence in Clinical Applications for Head and Neck MR Imaging Reviewed

Noriyuki Fujima, Koji Kamagata, Daiju Ueda, Shohei Fujita, Yasutaka Fushimi, Masahiro Yanagawa, Rintaro Ito, Takahiro Tsuboyama, Mariko Kawamura, Takeshi Nakaura, Akira Yamada, Taiki Nozaki, Tomoyuki Fujioka, Yusuke Matsui, Kenji Hirata, Fuminari Tatsugami, Shinji Naganawa

Magnetic Resonance in Medical Sciences 2023

Magnetic Resonance Imaging Guidance for Percutaneous Needle Intervention Invited Reviewed

Mayu Uka, Yusuke Matsui, Toshihiro Iguchi, Toshi Matsushita, Koji Tomita, Noriyuki Umakoshi, Takahiro Kawabata, Masanori Yamada, Takao Hiraki

Interventional Radiology 2023

Is ChatGPT a “Fire of Prometheus” for Non-Native English-Speaking Researchers in Academic Writing? Reviewed

Sung Il Hwang, Joon Seo Lim, Ro Woon Lee, Yusuke Matsui, Toshihiro Iguchi, Takao Hiraki, Hyungwoo Ahn

Korean Journal of Radiology 24 ( 10 ) 952 - 952 2023

Early enlarging cavitation after percutaneous radiofrequency ablation of lung tumors: Incidence, risk factors and outcome Reviewed

Koji Tomita, Toshihiro Iguchi, Yusuke Matsui, Mayu Uka, Noriyuki Umakoshi, Toshiharu Mitsuhashi, Jun Sakurai, Hideo Gobara, Susumu Kanazawa, Takao Hiraki

Diagnostic and Interventional Imaging 103 ( 10 ) 464 - 471 2022.10

Evidence on percutaneous radiofrequency and microwave ablation for liver metastases over the last decade Invited Reviewed

Koji Tomita, Yusuke Matsui, Mayu Uka, Noriyuki Umakoshi, Takahiro Kawabata, Kazuaki Munetomo, Shoma Nagata, Toshihiro Iguchi, Takao Hiraki

Japanese Journal of Radiology 2022.9

Publishing type：Research paper (scientific journal) Publisher：Springer Science and Business Media LLC

Abstract

Purpose

This review aimed to summarize the treatment outcomes of percutaneous radiofrequency ablation (RFA) and microwave ablation (MWA) for metastatic liver tumors based on the findings of published studies over the last decade.

Materials and methods

Literature describing the survival outcomes of ablation therapy for liver metastases was explored using the PubMed database on April 26, 2022, and articles published in 2012 or later were selected. The included studies met the following criteria: (i) English literature, (ii) original clinical studies, and (iii) literature describing overall survival (OS) of thermal ablation for metastatic liver tumors. All case reports and cohort studies with fewer than 20 patients and those that evaluated ablation for palliative purposes were excluded.

Results

RFA was the most commonly used method for ablation, while MWA was used in several recent studies. RFA and MWA for liver metastases from various primary tumors have been reported; however, majority of the studies focused on colorectal cancer. The local control rate by RFA and MWA varied widely among the studies, ranging approximately 50–90%. Five-year survival rates of 20–60% have been reported following ablation for colorectal liver metastases by a number of studies, and several reports of 10-year survival rates were also noted.

Conclusion

Comparative studies of local therapies for colorectal liver metastases demonstrated that RFA provides comparable survival outcomes to surgical metastasectomy and stereotactic body radiation therapy.

DOI： 10.1007/s11604-022-01335-5

researchmap

Other Link： https://link.springer.com/article/10.1007/s11604-022-01335-5/fulltext.html

　 PREV - NEXT 　

< MATSUI Yusuke >

Papers - MATSUI Yusuke