In contrast to tumor grading for lung adenocarcinomas2 (the most common type of NSCLC), there is currently no universally accepted method for the prognostic stratification of lung SCCs by histology.
This method can be applied to large, digitized whole slide images to detect invasive tissue regions, which could be integrated with other computerized solutions in digital pathology such as tumor grading.
One interesting aspect of our work is that the trained ConvNet classifier can be easily integrated into other computational frameworks such as automated tumor grading of ER+ breast cancer subtypes in histopathology images22.
APT has been demonstrated for tumor grading [43 46], differentiation of tumor from edema [15], and separation of tumor progression from radiation necrosis [42].
After adjusting for age, gender, tumor size, tumor grading, and tumor stage, multivariate analyses showed that NOTCH1 expression was an independent risk factor for survival.
Determination of tumor grading, ER, PR and HER2 status was performed by pathologists in the Department of Pathology in our hospital.
For tumor grading, paraffin blocks from pancreases of 5 mice/group were sectioned and 5 slides 50 µm apart were stained by H&E.
AMPA receptor expression was negatively correlated to tumor grading, i.e. oligodendrogliomas and astrocytomas showed higher expression of AMPARs as compared to the GBM samples (Figure 1B).
But tumor grading was a difficult business.
Moreover, CXCL8 expression revealed a close correlation with tumor grading.
Tumor diagnosis and tumor grading were performed by experienced neuropathologists.
