10122- NI-9 DEEP-LEARNING-BASED RECONSTRUCTION OF DIFFUSION WEIGHTED IMAGES OF MALIGNANT BRAIN TUMORS.
Yusuke Sakaguchi, Satoshi Takahashi, Naoaki Ishiguro, Yuichi Suzuki, Hirokazu Takami, Masamichi Takahashi, Shunsaku Takayanagi, Mototaka Miyake, Masashi Nomura, Yosuke Kitagawa, Shota Tanaka, Yoshitaka Narita, Nobuhito Saito, Ryuji Hamamoto · 2024
Read 10122- NI-9 DEEP-LEARNING-BASED RECONSTRUCTION OF DIFFUSION WEIGHTED IMAGES OF MALIGNANT BRAIN TUMORS. by Yusuke Sakaguchi, Satoshi Takahashi, Naoaki Ishiguro, Yuichi Suzuki, Hirokazu Takami, Masamichi Takahashi, Shunsaku Takayanagi, Mototaka Miyake, Masashi Nomura, Yosuke Kitagawa, Shota Tanaka, Yoshitaka Narita, Nobuhito Saito, Ryuji Hamamoto (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11605611.txt.
Description
Yusuke Sakaguchi and thirteen co-authors use deep learning to make a slow brain-imaging method faster. Diffusion kurtosis imaging reads the microstructure of malignant brain tumors and helps classify them before surgery. But it needs scans at several settings across fifteen directions, which takes too long for routine use. The team asked whether the heaviest scan, at the highest diffusion weighting, could be synthesized from lighter ones.
They gathered 157 tumor cases from the University of Tokyo Hospital, spanning 2016 to 2023, and trained a ResViT image model on 282,600 scan sets, checking it with five-fold cross-validation. Reconstructed images scored 0.956 on a structural similarity index and about 31.5 decibels on signal-to-noise ratio, matching earlier studies. The authors conclude the synthetic scans are good enough to cut the method's imaging time, a step toward everyday clinical use.
Catalog record
| CREATOR | Yusuke Sakaguchi, Satoshi Takahashi, Naoaki Ishiguro, Yuichi Suzuki, Hirokazu Takami, Masamichi Takahashi, Shunsaku Takayanagi, Mototaka Miyake, Masashi Nomura, Yosuke Kitagawa, Shota Tanaka, Yoshitaka Narita, Nobuhito Saito, Ryuji Hamamoto |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |