CNNs outperform GPT-4o and Llama3.2-vision on X-ray, MRI, and CT classification, but an added filtering step substantially improves GPT-4o's chest X-ray accuracy.
From this dataset, we first extract only those samples correspond- ing to the desired label (e.g., “normal” in the context of COVID classification)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can Large Language Models Challenge CNNs in Medical Image Analysis?
CNNs outperform GPT-4o and Llama3.2-vision on X-ray, MRI, and CT classification, but an added filtering step substantially improves GPT-4o's chest X-ray accuracy.