Deep Learning-Based Malaria Parasite Image Classification on Real Microscopy Data

Francesco Branda, Lilia Andriani, Riccardo Lucis, Annamaria Defilippo, Ugo Lomoio, Barbara Puccio, Giancarlo Ceccarelli, Massimo Ciccozzi, Fabio Scarpa, Pierangelo Veltri, Pietro Hiram Guzzi · 2026

Read Deep Learning-Based Malaria Parasite Image Classification on Real Microscopy Data by Francesco Branda, Lilia Andriani, Riccardo Lucis, Annamaria Defilippo, Ugo Lomoio, Barbara Puccio, Giancarlo Ceccarelli, Massimo Ciccozzi, Fabio Scarpa, Pierangelo Veltri, Pietro Hiram Guzzi (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/PMC13512370.txt.

Description

Francesco Branda and ten co-authors compare three deep learning designs for naming malaria parasite species in microscope images, in 2026 work. Microscopy remains the standard test, yet it leans on scarce expert readers, above all where malaria hits hardest. All three models were trained from scratch on real thick blood smear images plus public sets, with no borrowed pre-trained weights.

A classic layered network took the top scores, with accuracy near ninety-seven percent and near-perfect separation scores. A transformer model that reads images as patch sequences scored a few points lower, and a hybrid joining both designs fell between in the checks reported. Cross-validation held steady for all three. The authors say automated species reading is close to dependable, while telling similar Plasmodium species apart remains the hardest part for field use.

Catalog record

CREATORFrancesco Branda, Lilia Andriani, Riccardo Lucis, Annamaria Defilippo, Ugo Lomoio, Barbara Puccio, Giancarlo Ceccarelli, Massimo Ciccozzi, Fabio Scarpa, Pierangelo Veltri, Pietro Hiram Guzzi
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE70 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13512370

Browse the full library · About the Tower of Babel