A three-stage framework combines dual-head CNNs, saliency attribution, neuroanatomical atlas mapping, and LLMs to generate interpretable reports for brain tumor classification on MRI images.
IEEE transactions on neural networks and learning systems32(11), 4793–4813 (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bridging visual saliency and large language models for explainable deep learning in medical imaging
A three-stage framework combines dual-head CNNs, saliency attribution, neuroanatomical atlas mapping, and LLMs to generate interpretable reports for brain tumor classification on MRI images.