Accès ouvert
2026
article
OpenAlex
Moegi Mochizuki, Akiko Ohno, Shiori Tsubata, Ryutaro Sumi et autres
ABSTRACT Objectives Image‐enhanced endoscopy may reduce colorectal cancer mortality by improving lesion detection. Narrow‐band imaging and texture and color enhancement imaging are widely used, but their diagnostic efficacy compared with white light imaging remains unclear. This study evaluated narrow‐band imaging and texture …
jp
(code pays fourni par la source)
Accès ouvert
2026
article
OpenAlex
Ryosuke Kaji, Akiko Ohno, Jun Miyoshi, Ryutaro Sumi et autres
A 30-year-old woman with upper gastrointestinal bleeding from a Dieulafoy lesion was treated using endoscopic hemostasis. A subsequent interview revealed that she had pseudoxanthoma elasticum (PXE) with an ABCC6 gene mutation, but she had not been under medical care for many years. …
jp
(code pays fourni par la source)
Accès ouvert
2026
article
OpenAlex
Mitsunori Kusuhara, Akiko Ohno, Jun Miyoshi, Shiori Tsubata et autres
Median arcuate ligament syndrome (MALS) involves compression of the celiac artery and it can cause a hemodynamic disturbance. We report a case of acute upper gastrointestinal bleeding from a Dieulafoy lesion arising from the collateral arterial circulation, considered secondary to MALS. Although …
jp
(code pays fourni par la source)
Accès ouvert
2025
article
OpenAlex
Takehisa Kijima, Mitsunori Kusuhara, Ryutaro Sumi, Shiori Tsubata et autres
An 80-year-old man underwent a colonoscopy after PET-CT for pulmonary squamous cell carcinoma (cT3N0M0, stage IIB) showed rectal uptake, revealing a 20-mm 0-IIa lesion (Rb). However, the lung cancer treatment was prioritized. Eight months later, another colonoscopy showed lesion progression to 25 …
jp
(code pays fourni par la source)
2025
conference-paper
OpenAlex
Takahiro Shirakawa, Tomoyuki Suzuki, Takuto Narumoto, Daichi Haraguchi
We introduce MG-Gen, a framework that generates motion graphics directly from a single raster image. MG-Gen decompose a single raster image into layered structures represented as HTML, generate animation scripts for each layer, and then render them into a video. Experiments confirm …
jp
(code pays fourni par la source)
Accès ouvert
2025
article
OpenAlex
Akiko Ohno, Jun Miyoshi, Mitsunori Kusuhara, Yoko Jinbo et autres
Abstract Color vision deficiency (CVD) may affect perception of color information in gastrointestinal endoscopy. However, the color-universal concept in endoscopy remains underappreciated. We hypothesized that image-enhanced endoscopy (IEE) could improve object/lesion visibility regardless of CVD and tested this hypothesis with volunteers of …
jp
(code pays fourni par la source)
2025
conference-paper
OpenAlex
Ryugo Morita, Stanislav Frolov, Brian B. Moser, Takahiro Shirakawa et autres
Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects are placed over a chroma key background, limiting their …
jp, de
(code pays fourni par la source)
2025
article
OpenAlex
Akiko Ohno, Shiori Tsubata, Ryutaro Sumi, Takahiro Shirakawa et autres
Accès ouvert
2024
preprint
OpenAlex
Ryugo Morita, Stanislav Frolov, Brian B. Moser, Takahiro Shirakawa et autres
Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects are placed over a chroma key background, limiting their …
Accès ouvert
2024
article
OpenAlex
Akiko Ohno, Naohiko Miyamoto, Ryosuke Kaji, Takahiro Shirakawa et autres
Abstract Objectives Although color information is important in gastrointestinal endoscopy, there are limited studies on how endoscopic images are viewed by people with color vision deficiency. We aimed to investigate the differences in the visibility of blood vessels during endoscopic submucosal dissection …
jp
(code pays fourni par la source)
2024
conference-paper
OpenAlex
Takahiro Shirakawa, Seiichi Uchida
Layout-aware text-to-image generation is a task to generate multi-object images that reflect layout conditions in addition to text conditions. The current layout-aware text-to-image diffusion models still have several issues, including mismatches between the text and layout conditions and quality degradation of generated …
jp
(code pays fourni par la source)
2024
article
OpenAlex
Akiko Ohno, Naohiko Miyamoto, Tomoya Hiratsuka, Ryosuke Kaji et autres