Title |
Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features
|
---|---|
Published in |
Nature Communications, August 2016
|
DOI | 10.1038/ncomms12474 |
Pubmed ID | |
Authors |
Kun-Hsing Yu, Ce Zhang, Gerald J. Berry, Russ B. Altman, Christopher Ré, Daniel L. Rubin, Michael Snyder |
Abstract |
Lung cancer is the most prevalent cancer worldwide, and histopathological assessment is indispensable for its diagnosis. However, human evaluation of pathology slides cannot accurately predict patients' prognoses. In this study, we obtain 2,186 haematoxylin and eosin stained histopathology whole-slide images of lung adenocarcinoma and squamous cell carcinoma patients from The Cancer Genome Atlas (TCGA), and 294 additional images from Stanford Tissue Microarray (TMA) Database. We extract 9,879 quantitative image features and use regularized machine-learning methods to select the top features and to distinguish shorter-term survivors from longer-term survivors with stage I adenocarcinoma (P<0.003) or squamous cell carcinoma (P=0.023) in the TCGA data set. We validate the survival prediction framework with the TMA cohort (P<0.036 for both tumour types). Our results suggest that automatically derived image features can predict the prognosis of lung cancer patients and thereby contribute to precision oncology. Our methods are extensible to histopathology images of other organs. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 67 | 37% |
United Kingdom | 11 | 6% |
France | 6 | 3% |
India | 6 | 3% |
Canada | 4 | 2% |
Mexico | 3 | 2% |
Spain | 3 | 2% |
Belgium | 2 | 1% |
Brazil | 2 | 1% |
Other | 21 | 11% |
Unknown | 58 | 32% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 113 | 62% |
Scientists | 59 | 32% |
Practitioners (doctors, other healthcare professionals) | 7 | 4% |
Science communicators (journalists, bloggers, editors) | 4 | 2% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 4 | <1% |
United Kingdom | 3 | <1% |
France | 2 | <1% |
Germany | 2 | <1% |
Sweden | 2 | <1% |
Switzerland | 2 | <1% |
Turkey | 1 | <1% |
Brazil | 1 | <1% |
Spain | 1 | <1% |
Other | 1 | <1% |
Unknown | 800 | 98% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 146 | 18% |
Researcher | 130 | 16% |
Student > Master | 97 | 12% |
Student > Bachelor | 57 | 7% |
Other | 46 | 6% |
Other | 144 | 18% |
Unknown | 199 | 24% |
Readers by discipline | Count | As % |
---|---|---|
Medicine and Dentistry | 152 | 19% |
Computer Science | 137 | 17% |
Biochemistry, Genetics and Molecular Biology | 72 | 9% |
Engineering | 72 | 9% |
Agricultural and Biological Sciences | 61 | 7% |
Other | 95 | 12% |
Unknown | 230 | 28% |