Publications by authors named "Takahiro Tsuboyama"
Ventricular tachycardia (VT) is a severe arrhythmia commonly treated with implantable cardioverter defibrillators, antiarrhythmic drugs and catheter ablation (CA). Although CA is effective in reducing recurrent VT, its impact on survival remains uncertain, especially in patients with extensive scarring. Stereotactic arrhythmia radioablation (STAR) has emerged as a novel treatment for VT in patients unresponsive to CA, leveraging techniques from stereotactic body radiation therapy used in cancer treatments.
View Article and Find Full Text PDFIn this narrative review, we review the applications of artificial intelligence (AI) into clinical magnetic resonance imaging (MRI) exams, with a particular focus on Japan's contributions to this field. In the first part of the review, we introduce the various applications of AI in optimizing different aspects of the MRI process, including scan protocols, patient preparation, image acquisition, image reconstruction, and postprocessing techniques. Additionally, we examine AI's growing influence in clinical decision-making, particularly in areas such as segmentation, radiation therapy planning, and reporting assistance.
View Article and Find Full Text PDFPurpose: To compare image quality and visibility of anatomical structures on contrast-enhanced thin-slice abdominal CT images reconstructed using super-resolution deep learning reconstruction (SR-DLR), deep learning-based reconstruction (DLR), and hybrid iterative reconstruction (HIR) algorithms.
Materials And Methods: This retrospective study included 54 consecutive patients who underwent contrast-enhanced abdominal CT. Thin-slice images (0.
The integration of deep learning (DL) in breast MRI has revolutionized the field of medical imaging, notably enhancing diagnostic accuracy and efficiency. This review discusses the substantial influence of DL technologies across various facets of breast MRI, including image reconstruction, classification, object detection, segmentation, and prediction of clinical outcomes such as response to neoadjuvant chemotherapy and recurrence of breast cancer. Utilizing sophisticated models such as convolutional neural networks, recurrent neural networks, and generative adversarial networks, DL has improved image quality and precision, enabling more accurate differentiation between benign and malignant lesions and providing deeper insights into disease behavior and treatment responses.
View Article and Find Full Text PDFArticle Synopsis
- Interventional oncology uses image-guided therapies like tumor embolization and ablation to treat malignant tumors minimally invasively, and AI is gaining traction in this field.
- Recent literature shows a spike in studies exploring AI applications for tasks such as automatic segmentation, treatment simulation, and predicting treatment outcomes, with the latter being the most researched area.
- Although many AI methods are still in the research phase and not widely used in clinical settings, the rapid advancements indicate that AI technologies will likely be integrated into interventional oncology practices soon.
Article Synopsis
- - This review investigates the role of Large Language Models (LLMs) in nuclear medicine, particularly focusing on imaging techniques like PET and SPECT, highlighting recent advancements in both fields.
- - It discusses current developments in nuclear medicine and how LLMs are being used in related areas like radiology for tasks such as report generation and image interpretation, with the potential to improve medical practices.
- - Despite the promise of LLMs, challenges like reliability, explainability, and ethical concerns need to be addressed, making further research essential for integrating these technologies into nuclear medicine effectively.
Objectives: To create prediction models (PMs) for distinguishing between benign and malignant liver lesions using quantitative data from dual-energy CT (DECT) without contrast agents.
Materials And Methods: This retrospective study included patients with liver lesions who underwent DECT, including non-contrast-enhanced scans. Benign lesions included hepatic hemangioma, whereas malignant lesions included hepatocellular carcinoma, metastatic liver cancer, and intrahepatic cholangiocellular carcinoma.
Purpose: Minimal misregistration of fused PET and MRI images can be achieved with simultaneous positron emission tomography/magnetic resonance imaging (PET/MRI). However, the acquisition of multiple MRI sequences during a single PET emission scan may impair fusion precision of each sequence. This study evaluated the diagnostic utility of time-synchronized PET/MRI using an MR active trigger and a Bayesian penalized likelihood reconstruction algorithm (BPL) to assess the locoregional extension of endometrial cancer.
View Article and Find Full Text PDFArticle Synopsis
- Placental site trophoblastic tumor (PSTT) is a rare type of tumor arising from the placenta, and this study documented MRI findings in four cases, highlighting a specific feature known as "pseudo-myometrial thinning."
- The researchers analyzed MRIs and pathology results, measuring the thickness of myometrium (the muscular layer of the uterus) beneath the tumor compared to normal myometrium, finding that the MRI measurements showed significant thinning.
- Results indicated that while tumors appeared to invade deeply into the myometrium on imaging, they were actually localized within the superficial layer, suggesting that MRI could misrepresent the extent of tissue invasion, potentially due to compression effects.
Article Synopsis
- MRI is crucial for diagnosing pelvic issues related to organs like the prostate, bladder, and uterus, and uses RADS to standardize the process.
- AI technologies, including machine learning, are being integrated into pelvic MRI to enhance various steps of diagnosis, especially for prostate imaging.
- Recent multi-center studies highlight how AI can improve the effectiveness and reliability of pelvic MRI diagnostics by making findings more generalizable across different healthcare settings.
Article Synopsis
- The study aimed to assess how well 50-keV virtual monoenergetic images (VMI) can visualize abdominal arteries using photon-counting detector CT compared to 70-keV VMI.
- Fifty patients who had abdominal scans were analyzed for signal-to-noise and contrast-to-noise ratios across various arteries, along with 3D imaging to evaluate arterial lengths and visibility.
- Results showed that 50-keV VMI provided significantly better image quality and visibility of arterial branches than 70-keV VMI, indicating its potential benefits for clinical imaging of abdominal arteries.
Article Synopsis
- * This review examines the environmental challenges associated with AI systems, such as greenhouse gas emissions from data centers and electronic waste, while also proposing solutions like energy-efficient models and renewable energy usage.
- * It highlights the need for sustainable practices in AI deployment, suggesting policies, collaboration, and eco-friendly approaches, to ensure that AI advancements do not compromise environmental health.
Photon-counting CT has a completely different detector mechanism than conventional energy-integrating CT. In the photon-counting detector, X-rays are directly converted into electrons and received as electrical signals. Photon-counting CT provides virtual monochromatic images with a high contrast-to-noise ratio for abdominal CT imaging and may improve the ability to visualize small or low-contrast lesions.
View Article and Find Full Text PDFArticle Synopsis
- Deep Learning (DL) has advanced diagnostic radiology by improving image analysis, and the introduction of Transformer architecture and Large Language Models (LLMs) has further transformed this area.* -
- LLMs can streamline the radiology workflow, aiding in tasks like report generation and diagnostics, especially when combined with multimodal technology for enhanced applications.* -
- However, challenges like information inaccuracies and biases remain, and radiologists need to understand these technologies better to maximize their benefits while ensuring medical safety and ethical standards.*
Purpose: Liver and pancreatic fibrosis is associated with diabetes mellitus (DM), and liver fibrosis is associated with pancreatic fibrosis. This study aimed to investigate the relationship between the hepatic and pancreatic extracellular volume fractions (fECVs), which correlate with tissue fibrosis, and their relationships with DM and pre-DM (pDM).
Material And Methods: We included 100 consecutive patients with known or suspected liver and/or pancreatic diseases who underwent contrast-enhanced CT.
Article Synopsis
- The review discusses how artificial intelligence (AI) enhances radiation therapy by improving tumor segmentation and treatment planning, making processes much faster for oncologists.
- AI technologies like deep learning and knowledge-based planning can generate treatment plans comparable to human-created ones, and they can aid in quality control and monitoring during treatment.
- While challenges like data accumulation exist, the future of AI in radiation oncology looks promising, potentially leading to standardized treatments and better outcomes even in resource-limited areas.
Article Synopsis
- The study aimed to assess how ultra-high-resolution imaging and deep learning reconstruction affect the quality and diagnostic ability of MRI for rectal tumors using a specific technique called PROPELLER imaging.
- It involved 34 patients undergoing MRI, comparing four types of images based on varying slice thicknesses and reconstruction methods evaluated by three radiologists using a scoring system.
- Results showed that the 1.2-DLR imaging produced the best quality and clarity, enabling better detection of tumor spread and invasion compared to standard imaging techniques.
Article Synopsis
- The study aimed to compare the image quality and visibility of prostate lesions using three types of diffusion-weighted imaging (DWI): high-resolution multiplexed sensitivity-encoding diffusion-weighted imaging (MUSE-DWI), conventional DWI (c-DWI), and reduced field-of-view DWI (rFOV-DWI).
- Out of 47 patients evaluated, rFOV-DWI demonstrated significantly higher signal-to-noise ratio (SNR) for normal prostate tissue, while MUSE-DWI excelled in overall image quality and reduced distortion, showing better anatomical visibility.
- The apparent diffusion coefficient (ADC) values for normal tissue were lower with rFOV-DWI compared to MUSE-DWI and c-DWI, but
Article Synopsis
- The radiopharmaceutical FDG has been a key player in PET scans for over 20 years and is used in various medical fields like oncology and neurology.
- The integration of AI has improved the accuracy of imaging and diagnosis with FDG-PET, and new radiopharmaceuticals like PSMA and FAPI are being developed.
- Recent advances in nuclear medicine, including therapies like [Lu]-dotatate, show better results compared to traditional treatments, prompting a review of current evidence and future directions in the field.
Objective: To evaluate the image quality and lesion detectability of pancreatic phase thin-slice computed tomography (CT) images reconstructed with a deep learning-based reconstruction (DLR) algorithm compared with filtered-back projection (FBP) and hybrid iterative reconstruction (IR) algorithms.
Methods: Fifty-three patients who underwent dynamic contrast-enhanced CT including pancreatic phase were enrolled in this retrospective study. Pancreatic phase thin-slice (0.
Article Synopsis
- AI is a technology that mimics human intelligence and has gained traction over the past decade due to advancements in computing power and big data, particularly in the medical field.
- The article emphasizes the importance of developing explainable AI for diagnostic imaging, which can aid physicians in making informed decisions while recognizing AI's limitations.
- The focus of the review is on the application of AI in thoracic diagnostic imaging, such as lesion detection, to enhance the understanding and effectiveness for radiologists and clinicians.
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.
View Article and Find Full Text PDFArticle Synopsis
- MRI is widely used in clinical practice for examining head and neck diseases due to its ability to clearly show soft tissue details.
- Recent advancements in artificial intelligence, especially deep learning techniques like convolutional neural networks, are being explored for enhancing head and neck MRI diagnostics.
- The review highlights the benefits of these AI methods in image processing and disease assessment, while also addressing their limitations and future challenges in clinical application.