Fig. 6: Example use of HistoPathExplorer using filtering functionality. | npj Digital Medicine

Fig. 6: Example use of HistoPathExplorer using filtering functionality.

From: AI in Histopathology Explorer for comprehensive analysis of the evolving AI landscape in histopathology

Fig. 6

a-c From the Summary page, the user can obtain cancer-specific plots by filtering for breast cancer. Shown are the ‘Distribution of papers by task’ plot (a), ‘Distribution of papers by data origin’ plot (b) and ‘Distribution of papers by quality index parameters’ plot (c). d-e Plots from the Task page under Performance menu showing ‘Performance by clinical task’ when ‘Breast cancer’ with (d) ‘Sensitivity’ or (e) ‘Specificity’ are selected. f-i Results from the ‘Performance by network family’ plot from the Models page under Performance menu, selecting (f) ‘Diagnosis and subtyping’ task, (g) ‘Detection’, (h) ‘Diagnosis and subtyping’ task with ‘Sensitivity’ metric, or (i) ‘Breast cancer’. j Results from the ‘Performance by class balancing method’ plot on the Implementation page under Performance menu with breast cancer selected. k Importance of various features to the average performance of top-used models based on ReliefF feature selection algorithm in the Feature Ranking tool.

Back to article page