Deep learning models benchmarked for lung cancer histopathology analysis

Researchers have developed a two-stage deep learning framework for analyzing lung cancer histopathology images. The framework systematically compares state-of-the-art architectures for both tissue classification and region segmentation. For classification, YOLO11 demonstrated the highest performance, achieving 98.38% accuracy. In segmentation tasks, DeepLabV3+ yielded the best results with a 0.80 Intersection over Union, though YOLO11-seg offered comparable performance with significantly fewer parameters. AI

IMPACT Provides a benchmark for deep learning models in medical imaging, potentially accelerating adoption in pathology.

RANK_REASON The cluster contains an academic paper detailing a new benchmarking methodology and results for deep learning models applied to a specific domain (medical imaging). [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Deeplabv3 Plus
• DenseNet
• LC25000
• LungHist700
• MobileNetV3
• ResNet-encoder U-Net
• U-Net
• Vgg16
• vision transformer
• YOLO11
• YOLO11-seg

• paper
• model release

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