New deep learning framework improves tumor classification from MRI

Researchers have developed a novel Heterogeneity-Aware Deep Learning Classification (HA-DLC) framework designed to improve tumor classification from multiparametric MRI (mp-MRI). This framework explicitly models intra-tumoural heterogeneity by identifying and aligning sub-regions within tumors across different patients. The HA-DLC framework integrates local heterogeneity-aware features with global tumor representations, outperforming existing radiomics and deep learning methods on liver lesion and brain tumor datasets. AI

IMPACT This framework could lead to more accurate and personalized cancer diagnoses and treatment planning by better understanding tumor characteristics.

RANK_REASON Publication of a research paper on arXiv detailing a new deep learning framework for medical image analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• Heterogeneity-Aware Deep Learning Classification
• Hugging Face
• LLD-MMRI2023
• RSNA-ASNR-MICCAI 2021 Radiogenomic Brain Tumour

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →