Deep learning-based H&E-derived risk scores in colorectal cancer: associations with tumour morphology, biology, and predicted drug response.

Similarly, the proportion of stromal tissue, glandular luminal space, and vasculature did not significantly correlate with the DL‐based risk scores (Figure 3 and supplementary material, Figure S4 ), whereas the percentage of necrosis showed a trend towards a positive correlation with DL‐based risk scores ( p = 0.038, q = 0.150; Figure 3B,C ).

also in 24,698 other papers

Logistic regression analysis showed that SARIFA positivity was a strong and independent predictor of DL‐based high‐risk status (OR = 8.44, 95% CI 4.46–17.2, p < 0.0001), whereas nodal‐positive status showed a trend towards significance (OR = 1.58, 95% CI 0.96–2.61, p = 0.073), and locally advanced disease (T3/4) was not significant (OR = 0.77, 95% CI 0.44–1.36, p = 0.368).

also in 1,011 other papers