In:
International Journal of Cancer, Wiley, Vol. 148, No. 3 ( 2021-02), p. 780-790
Abstract:
What's new? Traditional microscopic histopathology to distinguish malignant neoplasms in clear cell renal cell carcinoma (ccRCC) struggles to keep pace with diagnostic needs. Boosting diagnostic efficiency in ccRCC may be possible through the use of computerized image processing technology. Here, the authors extracted quantitative features from hematoxylin‐eosin stained images and used the features to construct ccRCC diagnostic and prognostic models based on computational recognition of digital pathology. A machine learning histopathological image signature derived from digital pathology demonstrated high accuracy in ccRCC diagnosis and survival prediction. The findings highlight the potential clinical utility of machine learning for histopathologic image analysis in ccRCC.
Type of Medium:
Online Resource
ISSN:
0020-7136
,
1097-0215
Language:
English
Publisher:
Wiley
Publication Date:
2021
detail.hit.zdb_id:
218257-9
detail.hit.zdb_id:
1474822-8