Benchmarking deep learning models for laryngeal cancer staging using the LaryngealCT dataset

Nivea Roy, Son N. Tran, Atul Sajjanhar, K. Devaraja, Prakashini Koteshwara, Yong Xiang, Divya Rao · 2026

Read Benchmarking deep learning models for laryngeal cancer staging using the LaryngealCT dataset by Nivea Roy, Son N. Tran, Atul Sajjanhar, K. Devaraja, Prakashini Koteshwara, Yong Xiang, Divya Rao (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/PMC13554214.txt.

Description

Nivea Roy leads a seven-author team releasing a public scan set for throat cancer staging in a 2026 study. Research on this cancer lacked shared data, making model results hard to compare. Their set gathers 1,029 CT scans from six collections, all trimmed to the voice box at even spacing. Six deep learning models were then tested on two staging tasks.

A custom three-dimensional model won the early-versus-late staging task, with accuracy near eighty-five percent. The hardest task, spotting the most advanced tumours, tripped every model on pure sensitivity. One larger model recalled such cases best after tuning. Heat maps showed models looking near the cartilage, as doctors would, though overlap stayed modest. Shared data and code aim to make future results comparable.

Catalog record

CREATORNivea Roy, Son N. Tran, Atul Sajjanhar, K. Devaraja, Prakashini Koteshwara, Yong Xiang, Divya Rao
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE100544
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13554214

Browse the full library · About the Tower of Babel