Dynamic kernel generation through hybrid involution and convolution neural networks for leukemia and white blood cell classification

Osama M. Alshehri, Ahmad Shaf, Unza Shakeel, Tariq Ali, Muhammad Irfan, Mohammed M. Jalal, Malik A. Altayar, Mohammed H. Abu-Alghayth, Humood Al Shmrany · 2025

Read Dynamic kernel generation through hybrid involution and convolution neural networks for leukemia and white blood cell classification by Osama M. Alshehri, Ahmad Shaf, Unza Shakeel, Tariq Ali, Muhammad Irfan, Mohammed M. Jalal, Malik A. Altayar, Mohammed H. Abu-Alghayth, Humood Al Shmrany (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-12706057.txt.

Description

Reading blood cancers from microscope images is slow and the differences between cell stages are subtle. Osama Alshehri and co-authors build in 2025 a hybrid neural network that pairs involution layers, which craft location-aware filters on the fly, with classic convolution layers that catch stable patterns. The two run side by side inside shared blocks.

The system staged leukemia with 99.5 percent accuracy and sorted white blood cell types at 98 percent, ahead of earlier models. Its confidence scores were well calibrated, and cross-class mistakes stayed under two percent. Training settled within fifty passes. The authors see it easing diagnostic doubt and speeding early detection.

Catalog record

CREATOROsama M. Alshehri, Ahmad Shaf, Unza Shakeel, Tariq Ali, Muhammad Irfan, Mohammed M. Jalal, Malik A. Altayar, Mohammed H. Abu-Alghayth, Humood Al Shmrany
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE77 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12706057

Browse the full library · About the Tower of Babel