ATAkiyo Takada

Akiyo Takada

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Akiyo Takada has a total of 49 co-authors. Here are the top co-authors by number of shared publications:

  • Hajime Yokota

    Diagnostic Radiology and Radiation Oncology, Graduate School of Medicine, Chiba University, Chiba, Japan

    3 shared publications
  • Caroline Reinhold

    Department of Radiology, McGill University Health Centre, Montreal, Canada

    2 shared publications
  • Evan McNabb

    Augmented Intelligence and Precision Health Laboratory (AIPHL), Research Institute of the McGill University Health Centre, Montréal, Québec, Canada

    2 shared publications
  • Hirokazu Usui

    Department of Obstetrics and Gynecology, Chiba University Hospital, Chiba University, Chiba, Japan; Department of Obstetrics and Gynecology, Reproductive Medicine, Chiba University Graduate School of Medicine, Chiba, Japan; Department of Gynecology, Chiba Cancer Center, Japan

    2 shared publications
  • Jérémy Dana

    Centre Hospitalier Universitaire de Montréal, QC, Canada

    2 shared publications
  • Katsuhiro Nasu

    Department of Radiology, Chiba University Hospital, Chiba, Japan

    2 shared publications

Latest Publications

  • Suspected Myelitis on MRI: Narrowing the Differential Diagnosis and Deciding What to Check Next

    by Hajime Yokota, Hiroki Mukai, Akiyo Takada, Mami Iima, Rintaro Ito, Shinji Naganawa

    Intramedullary T2 hyperintensity on spinal magnetic resonance imaging is not specific for myelitis; infarction, compression, venous congestion, tumor, and nutritional deficiency produce the same finding. Nearly half of the patients referred for transverse myelitis have a non-inflammatory cause, and compressive myelopathy and spinal arteriovenous fistula are often misdiagnosed as inflammatory or neoplastic disease, delaying treatment by months. Because the tests that establish a specific cause cannot be performed exhaustively and take time, the initial scan usually sets the direction of the work-up. This review shows radiologists reading a “suspected myelitis” scan what to consider first and what to ask the clinician to confirm or refute that suspicion. Two axes organize the assessment: the time from symptom onset to nadir, and the lesion distribution on sagittal, axial, and contrast-enhanced images. Eight imaging patterns defined by these axes are each linked to the first diagnosis to consider and to the single piece of information that changes the decision. A distinctive feature is the handling of numbers: published sensitivities and specificities in spinal cord disease mostly derive from small studies with restricted populations and comparators, and exceptions are common, so each number is presented with the population and comparator in which it was obtained and is used only within that range. The normal-appearing scan, discordance between antibody or rapid polymerase chain reaction results and imaging, and techniques that secure decision-changing images are also addressed. The report should state what the imaging supports, what cannot be excluded, and what to check next.

  • Physics Insights into Liver MRI: Educational Guidance for Protocol Optimization.

    by Jérémy Dana, Evan McNabb, Véronique Fortier, Khaled Alanazi, Akiyo Takada, Alice Fung, Amir A Borhani, Claude B Sirlin, An Tang, Caroline Reinhold, et al.

    MRI is the modality of choice for detection, characterization, and noninvasive diagnosis of focal liver observations. It offers excellent tissue contrast using multiple sequences and postcontrast multiphasic imaging. However, its diagnostic accuracy depends on appropriate selection of pulse sequences and imaging parameters. Poorly acquired images or suboptimal sequence parameter selection can lead to medical errors, such as missed lesions and inaccurate characterization of focal liver observations. A solid understanding of applied MRI physics can help optimize image quality and prevent such errors. In this educational review, the authors aim to (a) guide radiologists in assessing MRI quality, (b) promote effective communication using appropriate terminology when collaborating with technologists and medical physicists, and (c) establish a reference liver MRI protocol. First, they detail metrics of MRI quality-contrast-to-noise ratio, spatial resolution, and signal-to-noise ratio-along with the impact of key technical parameters on acquisition time and step-by-step guidance for improving image quality. Second, they review the range of pulse sequences used in liver MRI, discussing their respective strengths and limitations in achieving optimal imaging quality. Third, they address key ancillary considerations for performance of liver MRI, including fat suppression techniques, respiratory motion suppression strategies, and acceleration methods. ©RSNA, 2026 Supplemental material is available for this article.

  • Open Access

    Robustness of Deep Learning Segmentation Across Heterogeneous Uterine MRI Datasets: A Multi-Task Comparison of U-Net, Swin-UNETR, MedNeXt, and nnU-Net

    by Daniel A. Di Giovanni, Akiyo Takada, Evan McNabb, Jérémy Dana, Hajime Yokota, Takahiro Tsuboyama, Rita Zakarian, Martin Vallières, James Man Git Tsui, Caroline Reinhold

    Reliable medical image segmentation requires performance that is stable across tasks, acquisition settings, and evaluation domains. We evaluated U-Net, Swin-UNETR, and MedNeXt as manually configured architectures and nnU-Net as a self-configuring reference across three T2-weighted uterine MRI datasets: public multiclass uterine anatomy and fibroid segmentation (UMD, n=300), institutional endometrial cancer tumor segmentation (n=206), and institutional uterine mass lesion segmentation (n=234). A separate UMD-style cohort (n=12), relabeled to the same annotation ontology, was used to assess external domain shift. Fixed data partitions, fold ensembling, and matched evaluation were used across models. Performance was assessed with Dice, 95th-percentile Hausdorff distance, average symmetric surface distance, absolute volume difference, and paired bootstrap comparisons with within-dataset Holm correction. MedNeXt was the strongest manually configured architecture, whereas nnU-Net achieved the highest Dice on all internal datasets: 0.761 for UMD, 0.746 for endometrial cancer, and 0.814 for uterine mass segmentation, compared with 0.722, 0.726, and 0.789 for MedNeXt. The nnU-Net-MedNeXt separation was largest for multiclass UMD segmentation and smaller for the binary tasks. All models degraded substantially on external testing; Dice was 0.542 for nnU-Net, 0.490 for MedNeXt, 0.396 for U-Net, and 0.287 for Swin-UNETR. These findings show that architecture, task definition, and dataset-adaptive pipeline configuration jointly influence uterine MRI segmentation, while external domain shift remains a major source of failure.

  • Radiomic prediction of substantial LVSI in endometrial cancer using reduced field of view DWI- a feasibility study

    by Akiyo Takada, Daniel A. Di Giovanni, Takuro Horikoshi, Takahiro Tsuboyama, Hajime Yokota, Sakurako Harada-Kagitani, Evan McNabb, Jérémy Dana, Rita Zakarian, Haruto Sugawara, et al.


  • Open Access

    Novel Subtype Classification of Diffuse Uterine Leiomyomatosis Based on a Nationwide Survey in Japan

    by Hiroshi Ishikawa, Ryoko Asano, Masanori Ono, Mari Kitade, Maki Kusumi, Shunichiro Tsuji, Tomoko Nakamura, Ryo Maekawa, Yuki Goto, Akiyo Takada, et al.

    Aim: Diffuse uterine leiomyomatosis (DUL) is characterized by numerous uterine leiomyomas within and diffusely replacing the myometrium. However, because of its rarity, the prevalence, diagnostic criteria, and standard treatment for patients with DUL who wish to preserve their fertility remain unknown. This study aimed to clarify the current status of the diagnosis of DUL in Japan. Methods: We conducted a web‐based survey targeting 1080 Obstetrics and Gynecology training institutions registered with the Japanese Medical Specialty Board. We asked them whether they had treated patients with DUL over the past 10 years (2013–2022). We obtained magnetic resonance imaging (MRI) scans from institutions that reported clinical experience with DUL, and conducted a central review to determine whether each case was consistent with DUL. We also investigated whether DUL could be classified into subtypes. Results: Responses were obtained from 428 institutions, of which 128 reported clinical experience with DUL or DUL‐like multiple uterine leiomyomas, totaling 653 cases. MRI scans from 408 cases were centrally reviewed by a subcommittee, and 307 cases were confirmed as DUL. Based on the imaging characteristics, DUL was classified into three subtypes: total replacement, myometrial replacement, and submucosal‐dominant. Conclusions: This survey revealed that 653 cases of DUL or DUL‐like multiple uterine leiomyomas were managed over a 10‐year period in Japan. Based on a central review of MRI scans, DUL can be classified into three distinct subtypes. Given the differences between these subtypes, treatment approaches for patients wishing to preserve fertility may vary, highlighting the need for further investigation.


  • Open Access

    Prognosis prediction of uterine cervical cancer using changes in the histogram and texture features of apparent diffusion coefficient during definitive chemoradiotherapy

    by Akiyo Takada, Hajime Yokota, Miho Watanabe Nemoto, Takuro Horikoshi, Koji Matsumoto, Yuji Habu, Hirokazu Usui, Katsuhiro Nasu, Makio Shozu, Takashi Uno

    Objectives: We investigated prospectively whether, in cervical cancer (CC) treated with concurrent chemoradiotherapy (CCRT), the Apparent diffusion coefficient (ADC) histogram and texture parameters and their change rates during treatment could predict prognosis. Methods: Fifty-seven CC patients treated with CCRT at our institution were included. They underwent MRI scans up to four times during the treatment course (1st, before treatment [n = 41], 2nd, at the start of image-guided brachytherapy (IGBT) [n = 41], 3rd, in the middle of IGBT [n = 27], 4th, after treatment [n = 53]). The entire tumor was manually set as the volume of interest (VOI) manually in the axial images of the ADC map by two radiologists. A total of 107 image features (morphology features 14, histogram features 18, texture features 75) were extracted from the VOI. The recurrence prediction values of the features and their change rates were evaluated by Receiver operating characteristics (ROC) analysis. The presence or absence of local and distant recurrence within two years was set as an outcome. The intraclass correlation coefficient (ICC) was also calculated. Results: The change rates in kurtosis between the 1st and 3rd, and 1st and 2nd MRIs, and the change rate in grey level co-occurrence matrix_cluster shade between the 2nd and 3rd MRIs showed particularly high predictive powers (area under the ROC curve = 0.785, 0.759, and 0.750, respectively), which exceeded the predictive abilities of the parameters obtained from pre- or post-treatment MRI only. The change rate in kurtosis between the 1st and 2nd MRIs had good reliability (ICC = 0.765). Conclusions: The change rate in ADC kurtosis between the 1st and 2nd MRIs was the most reliable parameter, enabling us to predict prognosis early in the treatment course.