Deep Learning Predicts Survival Across Squamous Tumor Entities From H&E Stains: Insights from Head and Neck, Esophagus, Lung and Cervical Cancer
Bitto, V.; Jiang, X.; Baumann, M.; Kather, J. N.; Kurth, I.
Show abstract
Computational pathology-based models are becoming increasingly popular for extracting biomarkers from images of cancer tissue. However, their validity is often only demonstrated on a single unseen validation cohort, limiting insights into their generalizability and posing challenges for explainability. In this study, we developed models to predict overall survival using haematoxylin and eosin (H&E) slides from FFPE samples in head and neck squamous cell carcinoma (HNSCC). By validating our models across diverse squamous tumor entities, including, head and neck (HR = 1.58, 95% CI = 1.17-2.12, p = 0.003), esophageal (non-significant), lung (HR = 1.31, 95% CI = 1.13-1.52, p < 0.001) and cervical (HR = 1.39, 95% CI = 1.10-1.75, p = 0.005) squamous cell carcinomas, we showed that the predicted risk score captures relevant information for survival beyond HNSCC. Correlation analysis indicated that the predicted risk score is strongly associated with various clinical factors, including human papillomavirus status, tumor volume and smoking history, although the specific factors vary across cohorts. These results emphasize the necessity for comprehensive validation and in-depth assessment of computational pathology-based models to better characterize the underlying patterns they learn during training.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Predicting Prognosis and IDH Mutation Status for Patients with Lower-Grade Gliomas Using Whole Slide Images 93%
- Survival Genie, a web platform for survival analysis across pediatric and adult cancers. 93%
- Deeper insights into long-term survival heterogeneity of Pancreatic Ductal Adenocarcinoma (PDAC) patients using integrative individual- and group-level transcriptome network analyses 93%
Similar papers in this journal
- Artificial intelligence-based histopathology image analysis identifies a novel subset of endometrial cancers with distinct genomic features and unfavourable outcome 95%
- The Impact of Digital Histopathology Batch Effect on Deep Learning Model Accuracy and Bias 94%
- Self-Supervised Learning Reveals Clinically Relevant Histomorphological Patterns for Therapeutic Strategies in Colon Cancer 94%
Similar papers in this journal
- Identification of Spatial Proteomic Signatures of Colon Tumor Metastasis: A Digital Spatial Profiling Approach 91%
- Detection of Colorectal Adenocarcinoma and Grading Dysplasia on Histopathologic Slides Using Deep Learning 91%
- KH-type splicing regulatory protein controls colorectal cancer cell growth and modulates the tumor microenvironment 90%
Similar papers in this journal
- Explainable, federated deep learning model predicts disease progression risk of cutaneous squamous cell carcinoma 94%
- Development and validation of a gene expression score to account for tumour purity and improve prognostication in breast cancer 93%
- Image-Based Consensus Molecular Subtyping in Rectal Cancer Biopsies and Response to Neoadjuvant Chemoradiotherapy 93%
Similar papers in this journal
- Deep learning-based tumor microenvironment segmentation is predictive of tumor mutations and patient survival in non-small-cell lung cancer 95%
- NSMCE2, a Novel Super-Enhancer Regulated Gene, is Linked to Poor Prognosis and Therapy Resistance in Breast Cancer 90%
- Genomic analysis reveals HDAC1 regulates clinically relevant transcriptional programs in pancreatic cancer 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.