Fig. 6: Significance testing of Top-1 accuracy (Prec@1(%)) for different NAS methods on the Gastric (i.e., Gastric Cancer) and Lung (i.e., Zenodo Lung Cancer) datasets, utilizing ShuffleNet and ViT backbones. | npj Digital Medicine

Fig. 6: Significance testing of Top-1 accuracy (Prec@1(%)) for different NAS methods on the Gastric (i.e., Gastric Cancer) and Lung (i.e., Zenodo Lung Cancer) datasets, utilizing ShuffleNet and ViT backbones.

From: Large language models driven neural architecture search for universal and lightweight disease diagnosis on histopathology slide images

Fig. 6

The x-axis displays the compared search methods, including random (i.e., Random Search), Cream, AutoFormer, and “ours'', grouped by dataset (Gastric, Lung) and backbone (ShuffleNet, ViT). The y-axis represents the Prec@1(%) performance. Asterisks indicate statistical significance levels assessed by independent two-sample Welch’s t tests: ** denotes p < 0.01 (highly significant), and *** denotes p < 0.001 (very highly significant). Prec@1: Top-1 accuracy. Prec@5: Top-5 accuracy.

Back to article page