Computer extracted gland features from H&E predicts prostate cancer recurrence comparably to a genomic companion diagnostic test: a large multi-site study
| Autor: | Robin Elliott, Anant Madabhushi, Kosj Yamoah, Ashutosh K. Tewari, Michael Feldman, Jessica Kim, Timothy R. Rebbeck, Natalie Nc Shih, Hannu J. Aronen, Francesca Khani, Lauri Eklund, Harri Merisaari, Mohammed Shahait, Priti Lal, Xavier Farre, Peter J. Boström, Otto Ettala, Eric A. Klein, Nafiseh Janaki, Andrei S. Purysko, Pekka Taimen, Patrick Leo, Sanjay Gupta, Andrew Janowczyk, Ivan Jambor, Brian D. Robinson, Kaustav Bera, David A. Lee, Ayah El-Fahmawi, Cristina Magi-Galluzzi, Pingfu Fu, Rakesh Shiradkar |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
0301 basic medicine
Biochemical recurrence Oncology Cancer Research medicine.medical_specialty medicine.medical_treatment H&E stain Article 03 medical and health sciences Prostate cancer Prognostic markers 0302 clinical medicine Prostate Internal medicine medicine Stage (cooking) RC254-282 Prostatectomy business.industry Hazard ratio Neoplasms. Tumors. Oncology. Including cancer and carcinogens medicine.disease 030104 developmental biology medicine.anatomical_structure 030220 oncology & carcinogenesis business Companion diagnostic |
| Zdroj: | NPJ Precision Oncology npj Precision Oncology, Vol 5, Iss 1, Pp 1-11 (2021) |
| ISSN: | 2397-768X |
| Popis: | Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue destructive, expensive, and not routinely available in most centers. We present a tissue non-destructive method for automated BCR prognosis, termed "Histotyping", that employs computational image analysis of morphologic patterns of prostate tissue from a single, routinely acquired hematoxylin and eosin slide. Patients from two institutions (n = 214) were used to train Histotyping for identifying high-risk patients based on six features of glandular morphology extracted from RP specimens. Histotyping was validated for post-RP BCR prognosis on a separate set of n = 675 patients from five institutions and compared against Decipher on n = 167 patients. Histotyping was prognostic of BCR in the validation set (p p n = 648). The combination of Histotyping, grade group, and preoperative PSA outperformed Decipher (c-index = 0.75 vs. 0.70, n = 167). These results suggest that a prognostic classifier for prostate cancer based on digital images could serve as an alternative or complement to molecular-based companion diagnostic tests. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|