JMJun Matsushima

Jun Matsushima

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jun Matsushima has a total of 56 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • The Use of Deep Learning-Based Computer Diagnostic Algorithm for Detection of Lymph Node Metastases of Gastric Adenocarcinoma

    by Jun Matsushima, Tamotsu Sato, Takashi Ohnishi, Yuichiro Yoshimura, Hiroyuki Mizutani, Shinichiro Koto, Jun-Ichiro Ikeda, Masayuki Kano, Hisahiro Matsubara, Hideki Hayashi

    Objectives. The diversifying modalities of treatment for gastric cancer raise urgent demands for the rapid and precise diagnosis of metastases in regional lymph nodes, thereby significantly impact the workload of pathologists. Meanwhile, the recent advent of whole-slide scanners and deep-learning techniques have enabled the computer-assisted analysis of histopathological images, which could help to alleviate this impact. Thus, we developed a deep learning-based diagnostic algorithm to detect lymph node metastases of gastric adenocarcinoma and evaluated its performance. Methods. We randomly selected 20 patients with gastric adenocarcinoma who underwent surgery as definitive treatment and were found to be node metastasis-positive. HEMATOXYLIN-eosin (HE) stained glass slides, including a total of 51 metastasis-positive nodes, were retrieved from the specimens of these cases. Other slides with 776 metastasis-negative nodes were also retrieved from other twenty cases with the same disease that were diagnosed as metastasis-negative by the final pathological examinations. All glass slides were digitized using a whole-slide scanner. A deep-learning algorithm to detect metastases was developed using the data in which metastasis-positive parts of the images were annotated by a well-trained pathologist, and its performance in detecting metastases was evaluated. Results. Cross-validation analysis indicated an area of 0.9994 under the receiver operating characteristic curve. Free-response receiver operating characteristic curve (FROC) analysis indicated a sensitivity of 1.00 with three false positives. Further evaluation using an independent dataset also showed similar level of accuracies. Conclusion. This deep learning-based diagnosis-aid system is a promising tool that can assist pathologists involved in gastric cancer care and reduce their workload.


  • Expression of SATB2 in Neuroendocrine Carcinomas of the Lung: Frequent Immunopositivity of Large Cell Neuroendocrine Carcinoma with a Diagnostic Pitfall

    by Hiromichi Inoue, Jun Matsushima, Satoru Kobayashi, Toshimi Sairenchi, Hirokuni Hirata, Masayuki Chida, Satoshi Ota, Shinichi Ban, Yuji Matsumura

    Small cell lung carcinoma (SCLC) and pulmonary large cell neuroendocrine carcinoma (LCNEC) are both classified as lung neuroendocrine carcinoma (NEC). It has recently been reported that the special AT-rich sequence-binding protein 2 (STAB2), known as a colorectal cancer marker, is also expressed in NECs occurring in various organs including the lung. However, few studies have examined any differences of SATB2 immunopositivity between SCLC and LCNEC. We investigated SATB2 expression in 45 SCLC and 14 LCNEC cases using immunohistochemistry as well as the expression of caudal-type homeobox 2 (CDX2) and keratin (KRT) 20. The LCNEC cases were more frequently positive for SATB2 (ten out of 14, 71%) than the SCLC ones (seventeen out of 45, 38%) with a statistically significance (P = 0.035). Furthermore, two LCNEC cases were positive for CDX2 while no positive findings were observed for any SCLC cases, the difference of which, however, was not statistically significant (P = 0.053). KRT20 was negative in all LCNEC and SCLC cases. These results require our attention when we use SATB2 and CDX2 as colorectal cancer markers because their expression in pulmonary NECs can lead to a misdiagnosis that the tumor is of metastatic colorectal adenocarcinoma, especially when the patient has a past history of colorectal cancer. Analyzing the relationship between the demographic/clinical variables and the SATB2 expression in the SCLC cases, just high Brinkman index (≥ 600) was significantly related to the positivity of SATB2 (P = 0.017), which is interesting considering the strong relationship between SCLC and smoking.


  • Open Access

    Histopathologic findings of TAFRO syndrome with immunohistochemical analysis of the kidney specimen: A case report

    by Taiki Sato, Yuko Ono, Jun Matsushima, Akiko Fujii, Yoko Sato, Yuji Hidaka, Shinya Kawamoto, Atsunori Yoshino, Tetsuro Takeda, Yoshihiko Ueda, et al.


  • Open Access

    Elevation of autoantibody level against PDCD11 in patients with transient ischemic attack

    by Yoichi Yoshida, Hao Wang, Takaki Hiwasa, Toshio Machida, Eiichi Kobayashi, Seiichiro Mine, Go Tomiyoshi, Rika Nakamura, Natsuko Shinmen, Hideyuki Kuroda, et al.

    Background: Disease specific autoantibodies have been detected in the sera of patients with atherosclerosis-related diseases, such as cerebral infarction, cardiovascular disease. In the present study, we aimed to identify novel autoantibodies responsible for transient ischemic attack (TIA), a prodromal condition for cerebral infarction.


  • Open Access

    Imaging Findings in AIDS-related Oral Kaposi's Sarcoma

    by Mamoru Wakoh, Yoshinori Sasaki, Mika Otonari-Yamamoto, Tazuko Goto, Satoru Ogane, Jun Matsushima, Yukio Nakatani

    Kaposi's sarcoma (KS) is one of the most common diseases in patients with acquired immunodeficiency syndrome, but is rarely encountered in dental practice in Japan. We encountered a case of oral KS (OKS) presenting in the hard palate, gingiva, and tongue in a 41-year-old man. We report the results of imaging, including computed tomography (CT), magnetic resonance imaging, and positron emission tomography/CT in this case. The process leading to an imaging diagnosis of OKS is discussed, emphasizing the importance of collating clinical, laboratory, pathological, and radiological findings. The present results suggest that mapping of accurate tumors is very important in cases of OKS, and that multiple or bilateral manifestations, ill-defined margins, osteolysis, and swollen lymph nodes, in particular, need to be taken into account.