Clinical evaluation of novel deep learning‐based auto‐segmentation software: Utility and potential pitfalls
Ryota Tozuka, Masahide Saito, Masaki Matsuda, Tomoko Akita, Hikaru Nemoto, Zhe Chen, Takafumi Komiyama, Kazuma Mochizuki, Noriyuki Kadoya, Keiichi Jingu, Hiroshi Onishi · 2026
Read Clinical evaluation of novel deep learning‐based auto‐segmentation software: Utility and potential pitfalls by Ryota Tozuka, Masahide Saito, Masaki Matsuda, Tomoko Akita, Hikaru Nemoto, Zhe Chen, Takafumi Komiyama, Kazuma Mochizuki, Noriyuki Kadoya, Keiichi Jingu, Hiroshi Onishi (2026) 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-13504373.txt.
Description
Ryota Tozuka and ten co-authors grade a deep learn auto-draw tool for ray care plans on real ward cases. Their study appeared in twenty twenty-six. True line draws guard cure worth, but odd forms and gear marks can trip code tools. Sixty-nine chest and male hip cases were picked to span odd forms and marks like pace gear and fake joints.
In plain cases the tool held high truth marks. In odd packs truth fell, most with fake hip joints and one-side lung falls. Eye checks laid most flaws to form and marks. One dose miss was caught. Hand checks stay a must.
Catalog record
| CREATOR | Ryota Tozuka, Masahide Saito, Masaki Matsuda, Tomoko Akita, Hikaru Nemoto, Zhe Chen, Takafumi Komiyama, Kazuma Mochizuki, Noriyuki Kadoya, Keiichi Jingu, Hiroshi Onishi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |