Automated tumour annotation and analysis for molecular pathology using TissueMark (R)

P. Hamilton, Y. Wang, D. McCleary, James Diamond, E. Regan, N. Montgomery, J. Tunstall, D. Boyle, M. Loughrey, M. Salto-Tellez

Research output: Contribution to journalMeeting abstractpeer-review

1 Citation (Scopus)


Objective: Molecular pathology relies on identifying anomalies using PCR or analysis of DNA/RNA. This is important in solid tumours where molecular stratification of patients define targeted treatment. These molecular biomarkers rely on examination of tumour, annotation for possible macro dissection/tumour cell enrichment and the estimation of % tumour. Manually marking up tumour is error prone. Method: We have developed a method for automated tumour mark-up and % cell calculations using image analysis called TissueMark® based on texture analysis for lung, colorectal and breast (cases=245, 100, 100 respectively). Pathologists marked slides for tumour and reviewed the automated analysis. A subset of slides was manually counted for tumour cells to provide a benchmark for automated image analysis. Results: There was a strong concordance between pathological and automated mark-up (100 % acceptance rate for macro-dissection). We also showed a strong concordance between manually/automatic drawn boundaries (median exclusion/inclusion error of 91.70 %/89 %). EGFR mutation analysis was precisely the same for manual and automated annotation-based macrodissection. The annotation accuracy rates in breast and colorectal cancer were 83 and 80 % respectively. Finally, region-based estimations of tumour percentage using image analysis showed significant correlation with actual cell counts. Conclusion: Image analysis can be used for macro-dissection to (i) annotate tissue for tumour and (ii) estimate the % tumour cells and represents an approach to standardising/improving molecular diagnostics.
Original languageEnglish
Pages (from-to)S329-S329
Number of pages1
JournalVirchows Archiv
Issue number1
Publication statusPublished - 14 Aug 2014


Dive into the research topics of 'Automated tumour annotation and analysis for molecular pathology using TissueMark (R)'. Together they form a unique fingerprint.

Cite this