Node negative colorectal cancer patients: assesment of high-risk features on recurrence.

BACKGROUND: The introduction of population-based screening programs for colorectal cancer (CRC) results in less patients with advanced disease. There is an increase in the amount of node negative CRC, which makes adequate risk stratification for this particular group of patients necessary. The addition of more risk factors to the conventional histological high-risk factors is investigated in this retrospective study. PATIENTS AND METHODS: A cohort of 227 node negative (stage I and II) CRC patients who were not treated with adjuvant chemotherapy were selected from two previously conducted cohort studies. Detailed histopathological examination was performed by two independent observers and molecular background (BRAF/RAS mutations, microsatellite status (MSI)) was studied. Univariate analyses were used to analyse differences in histological and mutational characteristics between patients with and without recurrence. P-values below 0.05 were considered statistically significant. RESULTS: Poorly differentiated histology (p:0.002), BRAF mutation (p:0.002) and MSI status (p:0.006) were found significant relevant risk factors that were related to recurrent disease. Poorly differentiated histology was associated with intermediate/high tumor budding (TB) (p:0.001), a BRAF mutation (p:0.001) and MSI status (p:0.001). A combination of all three features (poorly differentiated histology, BRAF and MSI) was more often present in the recurrence group. CONCLUSIONS: Recurrence in node negative CRC patients could be better predicted when molecular features such as, BRAF mutation and MSI status are incorporated into a model with poorly differentiated CRC. Therefore, these features might help in the selection of patients who possibly will benefit from adjuvant treatment.

Correction to: Assessment of individual tumor buds using keratin immunohistochemistry: moderate interobserver agreement suggests a role for machine learning.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Assessment of individual tumor buds using keratin immunohistochemistry: moderate interobserver agreement suggests a role for machine learning.

Tumor budding is a promising and cost-effective biomarker with strong prognostic value in colorectal cancer. However, challenges related to interobserver variability persist. Such variability may be reduced by immunohistochemistry and computer-aided tumor bud selection. Development of computer algorithms for this purpose requires unequivocal examples of individual tumor buds. As such, we undertook a large-scale, international, and digital observer study on individual tumor bud assessment. From a pool of 46 colorectal cancer cases with tumor budding, 3000 tumor bud candidates were selected, largely based on digital image analysis algorithms. For each candidate bud, an image patch (size 256 × 256 µm) was extracted from a pan cytokeratin-stained whole-slide image. Members of an International Tumor Budding Consortium (n = 7) were asked to categorize each candidate as either (1) tumor bud, (2) poorly differentiated cluster, or (3) neither, based on current definitions. Agreement was assessed with Cohen's and Fleiss Kappa statistics. Fleiss Kappa showed moderate overall agreement between observers (0.42 and 0.51), while Cohen's Kappas ranged from 0.25 to 0.63. Complete agreement by all seven observers was present for only 34% of the 3000 tumor bud candidates, while 59% of the candidates were agreed on by at least five of the seven observers. Despite reports of moderate-to-substantial agreement with respect to tumor budding grade, agreement with respect to individual pan cytokeratin-stained tumor buds is moderate at most. A machine learning approach may prove especially useful for a more robust assessment of individual tumor buds.