Simple fully convolutional network to detect Alzheimer’s Disease

Ninad Aithal, Neelam Sinha · 2025

Read Simple fully convolutional network to detect Alzheimer’s Disease by Ninad Aithal, Neelam Sinha (2025) 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-11716868.txt.

Description

Ninad Aithal and Neelam Sinha test a deliberately simple neural network for spotting Alzheimer's disease on brain MRI scans. Their fully convolutional design stacks thirteen layers in five blocks, with pooling that doubles channels and a final stage that squeezes the image down to a decision. The model trains on 807 scans from a public Alzheimer's initiative dataset.

Scans were cleaned, stripped of skull, and aligned to a standard brain template before training. Training ran one hundred passes over the data with a weighted loss that compensates for uneven class sizes. The authors argue that a lean design can separate patients from healthy controls without the heavy machinery of larger networks, which matters where computing power is limited.

Catalog record

CREATORNinad Aithal, Neelam Sinha
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE2 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11716868

Browse the full library · About the Tower of Babel