Takeshi Takata

Dr. Takeshi Takata

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
20 June 2025 in Computers in Biology and Medicine
Verified
Journal Article
Open access
TTTakeshi Takata
Takeshi Takata
KYKentaro Yamada
Kentaro Yamada
MYMasayoshi Yamamoto
Masayoshi Yamamoto
HKHiroshi Kondo
Hiroshi Kondo
Digital subtraction angiography (DSA) is an essential imaging technique in interventional radiology, enabling detailed visualization of blood vessels by subtracting pre- and post-contrast images. However, reduced contrast, either accidental or intentional, can impair the clarity of vascular structures. This issue becomes particularly critical in patients with chronic kidney disease (CKD), where minimizing iodinated contrast is necessary to reduce the risk of contrast-induced nephropathy (CIN). This study explored the potential of using a generative deep-learning-model based contrast enhancement technique for DSA. A text-conditioned image-to-image model was developed using Stable Diffusion, augmented with ControlNet to reduce hallucinations and Low-Rank Adaptation for model fine-tuning. A total of 1207 DSA series were used for training and testing, with additional low-contrast images generated through data augmentation. The model was trained using tagged text labels and evaluated using metrics such as Root Mean Square (RMS) contrast, Michelson contrast, signal-to-noise ratio (SNR), and entropy. Evaluation results indicated significant improvements, with RMS contrast, Michelson contrast, and entropy respectively increased from 7.91 to 17.7, 0.875 to 0.992, and 3.60 to 5.60, reflecting enhanced detail. However, SNR decreased from 21.3 to 8.50, indicating increased noise. This study demonstrated the feasibility of deep learning-based contrast enhancement for DSA images and highlights the potential for generative deep-learning-model to improve angiographic imaging. Further refinements, particularly in artifact suppression and clinical validation, are necessary for practical implementation in medical settings.

30 March 2023 in Journal of Medical Systems
Verified
Journal Article
Closed access
PDF file
TTTakeshi Takata
Takeshi Takata
KYKentaro Yamada
Kentaro Yamada
MYMasayoshi Yamamoto
Masayoshi Yamamoto
HKHiroshi Kondo
Hiroshi Kondo

25 September 2025 in Cancers
Verified
Journal Article
Open access
PDF file
TNTomoki Nishida
Tomoki Nishida
Yuichi SaitoYuichi Saito
Yuichi Saito
TTTakeshi Takata
Takeshi Takata
SMShizuka Morita
Shizuka Morita
RTRyo Takeyama
Ryo Takeyama
YSYukinori Sakao
Yukinori Sakao
Background/Objectives: Although surgeries employing cone-beam computed tomography (CBCT) for small lung lesions have been reported, the association between CBCT scan frequency and patient radiation exposure remains unclear. This study aimed to investigate patient radiation doses from CBCT during thoracic surgeries, and the patient radiation doses were compared with those from other preoperative marking methods. Methods: This multicenter prospective study included 81 patients who underwent surgery for small lung lesions requiring marking between January 2021 and June 2024 at three institutions. CBCT-guided surgeries involved the use of metal clips in a hybrid operating room with 1–4 scans, depending on the lesion. For other preoperative marking methods, hook-wire or virtual-assisted lung mapping (VAL-MAP) was used. Patient radiation doses were measured using wearable dosimeters at five anterior thorax sites, and the total dose was compared across methods. Results: The study included 81 patients: CBCT (n = 61), VAL-MAP (n = 10), and hook-wire (n = 10). CBCT cases were distributed as follows: single scan (n = 10), double scans (n = 34), triple scans (n = 15), and quadruple scans (n = 2). The radiation doses were 86.9 ± 61.7 mGy for hook-wire, 39.8 ± 27.5 mGy for VAL-MAP, and 11.0 ± 6.5 mGy for single-scan CBCT, 17.3 ± 7.8 mGy for double scans, 23.1 ± 14.0 mGy for triple scans, and 22.7 ± 0.1 mGy for quadruple scans. Although radiation exposure increased with more CBCT scans, performing up to triple scans resulted in significantly lower exposure compared to other methods. Conclusions: Intraoperative CBCT is a feasible and safe technique for identifying small lung lesions, providing lower radiation exposure compared to other preoperative localization methods.

1 May 2026 in Radiology
Verified
Journal Article
Closed access
THTakaki Hirano
Takaki Hirano
HKHiroshi Kondo
Hiroshi Kondo
TWTakeshi Wada
Takeshi Wada
TTTakeshi Takata
Takeshi Takata
MYMasayoshi Yamamoto
Masayoshi Yamamoto
HOHiroshi Oba
Hiroshi Oba
The results of this pilot study suggested that using subtraction CT combined with dynamic contrast-enhanced CT improved diagnostic accuracy in detecting extravasation in pelvic fractures and reduced reading time.