Malaria Parasite Cell Classification Using Transfer Learning with State-of-the-Art CNN Architectures
Azhar Ali Laghari, Wazir Muhammad, Mudasar Latif Memon, Ayaz Hussain, Akash Kumar, Cecilia Perez Brandán · 2025
Read Malaria Parasite Cell Classification Using Transfer Learning with State-of-the-Art CNN Architectures by Azhar Ali Laghari, Wazir Muhammad, Mudasar Latif Memon, Ayaz Hussain, Akash Kumar, Cecilia Perez Brandán (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-12731172.txt.
Description
Laghari and co-authors tested whether pretrained image networks can sort malaria parasites in blood smear photos, a job now done slowly by experts under a microscope. They used transfer learning: eight well-known convolutional networks, first trained on a large general image set, were fine-tuned on labeled photos of infected and clean blood cells. The models included the VGG, Inception, ResNet, and Xception families.
ResNet-50 and ResNet-101 reached about 89 percent accuracy, and Xception about 88 percent, with balanced detection of infected cells. VGG-16 scored lower overall because it missed more infected cells, despite being precise when it did flag them. The authors conclude that fine-tuned deep networks can support faster, more consistent malaria diagnosis, which matters where expert microscopists are scarce. The catalog byline lists one more name than the text itself; team framing is used here.
Catalog record
| CREATOR | Azhar Ali Laghari, Wazir Muhammad, Mudasar Latif Memon, Ayaz Hussain, Akash Kumar, Cecilia Perez Brandán |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |