Masashi Matsuzaka

Masashi Matsuzaka

Auto-generated profile, based on publicly available information

Masashi Matsuzaka

Department of Medical Informatics Hirosaki University Graduate School of Medicine Hirosaki Japan

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
3 February 2022 in Supportive Care in Cancer
Verified
Journal Article
Closed access
PDF file
HHHironobu Hata
Hironobu Hata
KIKenji Imamachi
Kenji Imamachi
MUMichihiro Ueda
Michihiro Ueda
MMMasashi Matsuzaka
Masashi Matsuzaka
HHHiroaki Hiraga
Hiroaki Hiraga
YKYoshimasa Kitagawa
Yoshimasa Kitagawa

10 June 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
NHNaoki Higuchi
Naoki Higuchi
HHHiroto Hiraga
Hiroto Hiraga
YSYoshihiro Sasaki
Yoshihiro Sasaki
NHNoriko Hiraga
Noriko Hiraga
SIShohei Igarashi
Shohei Igarashi
SFShinsaku Fukuda
Shinsaku Fukuda
Capsule endoscopy has been widely used as a non-invasive diagnostic tool for small or large intestinal lesions. In recent years, automated lesion detection systems using machine learning have been devised. This study aimed to develop an automated system for capsule endoscopic severity in patients with ulcerative colitis along the entire length of the colon using ResNet50. Capsule endoscopy videos from patients with ulcerative colitis were collected prospectively. Each single examination video file was partitioned into four segments: the cecum and ascending colon, transverse colon, descending and sigmoid colon, and rectum. Fifty still pictures (576 × 576 pixels) were extracted from each partitioned video. A patch (128 × 128 pixels) was trimmed from the still picture at every 32-pixel-strides. A total of 739,021 patch images were manually classified into six categories: 0) Mayo endoscopic subscore (MES) 0, 1) MES1, 2) MES2, 3) MES3, 4) inadequate quality for evaluation, and 5) ileal mucosa. ResNet50, a deep learning framework, was trained using 483,644 datasets and validated using 255,377 independent datasets. In total, 31 capsule endoscopy videos from 22 patients were collected. The accuracy rates of the training and validation datasets were 0.992 and 0.973, respectively. An automated evaluation system for the capsule endoscopic severity of ulcerative colitis was developed. This could be a useful tool for assessing topographic disease activity, thus decreasing the burden of image interpretation on endoscopists.

9 November 2021 in PLOS ONE
Verified
Journal Article
Open access
PDF file
TWTaiichi Wakiya
Taiichi Wakiya
KIKeinosuke Ishido
Keinosuke Ishido
NKNorihisa Kimura
Norihisa Kimura
HNHayato Nagase
Hayato Nagase
SKShunsuke Kubota
Shunsuke Kubota
KHKenichi Hakamada
Kenichi Hakamada
Massive intraoperative blood loss (IBL) negatively influence outcomes after surgery for pancreatic ductal adenocarcinoma (PDAC). However, few data or predictive models are available for the identification of patients with a high risk for massive IBL. This study aimed to build a model for massive IBL prediction using a decision tree algorithm, which is one machine learning method. One hundred and seventy-five patients undergoing curative surgery for resectable PDAC at our facility between January 2007 and October 2020 were allocated to training (n = 128) and testing (n = 47) sets. Using the preoperatively available data of the patients (34 variables), we built a decision tree classification algorithm. Of the 175 patients, massive IBL occurred in 88 patients (50.3%). Binary logistic regression analysis indicated that alanine aminotransferase and distal pancreatectomy were significant predictors of massive IBL occurrence with an overall correct prediction rate of 70.3%. Decision tree analysis automatically selected 14 predictive variables. The best predictor was the surgical procedure. Though massive IBL was not common, the outcome of patients with distal pancreatectomy was secondarily split by glutamyl transpeptidase. Among patients who underwent PD (n = 83), diabetes mellitus (DM) was selected as the variable in the second split. Of the 21 patients with DM, massive IBL occurred in 85.7%. Decision tree sensitivity was 98.5% in the training data set and 100% in the testing data set. Our findings suggested that a decision tree can provide a new potential approach to predict massive IBL in surgery for resectable PDAC.

11 June 2022 in Annals of Gastroenterological Surgery
Verified
Journal Article
Open access
HFHiroaki Fujita
Hiroaki Fujita
TWTaiichi Wakiya
Taiichi Wakiya
KIKeinosuke Ishido
Keinosuke Ishido
NKNorihisa Kimura
Norihisa Kimura
HNHayato Nagase
Hayato Nagase
KHKenichi Hakamada
Kenichi Hakamada
Background: The differential diagnosis between gallbladder cancer (GBC) and xanthogranulomatous cholecystitis (XGC) remains quite challenging, and can possibly lead to improper surgery. This study aimed to distinguish between XGC and GBC by combining computed tomography (CT) images and deep learning (DL) to maximize the therapeutic success of surgery.Methods: We collected a dataset, including preoperative CT images, from 28 cases of GBC and 21 XGC patients undergoing surgery at our facility. It was subdivided into training and validation (n = 40), and test (n = 9) datasets. We built a CT patch‐based discriminating model using a residual convolutional neural network and employed 5‐fold cross‐validation. The discriminating performance of the model was analyzed in the test dataset.Results: Of the 40 patients in the training dataset, GBC and XGC were observed in 21 (52.5%), and 19 (47.5%) patients, respectively. A total of 61 126 patches were extracted from the 40 patients. In the validation dataset, the average sensitivity, specificity, and accuracy were 98.8%, 98.0%, and 98.5%, respectively. Furthermore, the area under the receiver operating characteristic curve (AUC) was 0.9985. In the test dataset, which included 11 738 patches, the discriminating accuracy for GBC patients after neoadjuvant chemotherapy (NAC) (n = 3) was insufficient (61.8%). However, the discriminating model demonstrated high accuracy (98.2%) and AUC (0.9893) for cases other than those receiving NAC.Conclusion: Our CT‐based DL model exhibited high discriminating performance in patients with GBC and XGC. Our study proposes a novel concept for selecting the appropriate procedure and avoiding unnecessary invasive measures.

4 April 2008 in British Journal of Sports Medicine
Verified
Journal Article
Closed access
PDF file
YYY Yamamoto
Y Yamamoto
SNS Nakaji
S Nakaji
TUTakumi UMEDA
Takumi UMEDA
MMM Matsuzaka
M Matsuzaka
ITI Takahashi
I Takahashi
TOT Oyama
T Oyama
Objectives: To clarify the effects of high-intensity and high-frequency long-term/chronic training on neutrophil function and serum levels of myogenic enzymes in male university judoists. Methods: The subjects were 24 male judoists who had stopped judo training for 6 months and then restarted their training. The following parameters were examined before and after a 2 h unified exercise loading (UEL) at the beginning of the restarted quotidian training (pre-training) and at 2 months, 4 months and 6 months thereafter: myogenic enzymes, neutrophil and leucocyte counts, and neutrophil phagocytic activity (PA) and oxidative burst activity as a measure of reactive oxygen species (ROS) production capability. Results: Myogenic enzymes that were measured after UEL at all four points significantly increased except for creatine kinase at the 2-month point (p<0.01 in each) and neutrophil counts significantly increased after UEL at the pre-training, 2-month and 4-month points (p<0.01 in each), but these changes became smaller from the 2-month point. PA significantly decreased after UEL at the pre-training and 2-month points (p<0.01 in each), but no change was seen at the 4-month and 6-month points. On the other hand, no change in ROS production per cell after UEL was seen at the pre-training point, but it significantly increased after UEL at the 2-month, 4-month and 6-month points (p<0.01 in each). Conclusion: The changing rate of the levels of UEL-mediated myogenic enzymes, neutrophil mobilisation and neutrophil function was seen to decrease at the 2-month, 4-month and 6-month assessments, compared with the pre-training point: these may comprise at least some of the long-term training effects.

28 July 2021 in BMC Cancer
Verified
Journal Article
Open access
PDF file
KAKenichiro Asano
Kenichiro Asano
TFToshio Fumoto
Toshio Fumoto
MMMasashi Matsuzaka
Masashi Matsuzaka
SHSeiko Hasegawa
Seiko Hasegawa
NSNaoya Suzuki
Naoya Suzuki
HOHiroki Ohkuma
Hiroki Ohkuma
Background: This investigator-initiated, open-label, single-arm, single-institute study was conducted to investigate the effectiveness of induction combination chemoradiotherapy and long-term maintenance therapy with temozolomide (TMZ) plus interferon (IFN)-β for glioblastoma. Methods: The initial induction combination chemoradiotherapy comprised radiotherapy plus TMZ plus vincristine plus IFN-β. Maintenance chemotherapy comprised monthly TMZ, continued for 24–50 cycles, plus weekly IFN-β continued for as long as possible. The primary endpoint was 2-year overall survival (2y-OS). The study protocol was to be considered valid if the expected 2y-OS was over 38% and the lower limit of the 95% confidence interval (CI) was no less than 31.7% compared with historical controls, using Kaplan-Meier methods. Secondary endpoints were median progression-free survival (mPFS), median OS (mOS), 5-year OS rate (5y-OS), and mPFS and mOS classified according to MGMT promoter methylation status. Results: Forty-seven patients were analyzed. The 2y-OS was 40.7% (95%CI, 27.5–55.4%). The mPFS and mOS were 11.0 months and 18.0 months, respectively, and 5y-OS was 20.3% (95%CI, 10.9–34.6%). The mPFS in groups with and without MGMT promoter methylation in the tumor was 10.0 months and 11.0 months (p = 0.59), respectively, and mOS was 24.0 months and 18.0 months (p = 0.88), respectively. The frequency of grade 3/4 neutropenia was 19.1%. Conclusions: The 2y-OS with induction multidrug combination chemoradiotherapy and long-term maintenance therapy comprising TMZ plus IFN-β tended to exceed that of historical controls, but the lower limit of the 95%CI was below 31.7%. Although the number of cases was small, this protocol may rule out MGMT promoter methylation status as a prognostic factor. Trial registration: University Hospital Medical Information Network (number UMIN000040599).