Deep learning for automated scoring of immunohistochemically stained tumour tissue sections - Validation across tumour types based on patient outcomes.

While manual scores provided significant prognostic information (MSS had shorter CSS than MSI) ( p = 0.039, 95 % CI 1.02–4.17), DL scores showed borderline significance ( p = 0.086, 95 % CI 0.90–3.96).

also in 7,017 other papers

4 a (D)), but the difference in CSS between the MSS and MSI groups did not reach statistical significance (HR = 1.89, 95 % CI 0.90–3.96), ( Table 2 ).

also in 111,027 other papers