Skip to content
DraconiticResearch
Search Sources API
197,688 studies31 sourcesUpdated 23 min ago
Peer-reviewedCC BY-NC-ND 4.0Cancer Medicine

MGP_HNSC32: A H&E Morphology‐Derived 32‐Gene Prognostic Signature in Head and Neck Squamous Cell Carcinoma

  • Di Zhao1
  • Zhiheng Huang1
  • Jing Xu2
  • Zheng Zhang3
  • Jochen Hess4,5
  • Bohai Feng4,6,7
7 affiliations
  1. 1Department of Otorhinolaryngology Second Affiliated Hospital of Zhejiang University School of Medicine Hangzhou China
  2. 2Department of Radiation Oncology Second Affiliated Hospital of Zhejiang University School of Medicine Hangzhou China
  3. 3Department of Pathology The Second Affiliated Hospital, Zhejiang University School of Medicine Hangzhou China
  4. 4Department of Otorhinolaryngology, Head and Neck Surgery University Hospital Heidelberg Heidelberg Germany
  5. 5Division Radiooncology/Radiobiology German Cancer Research Center (DKFZ) Heidelberg Germany
  6. 6Artificial Intelligence Research Center, Zhejiang Key Laboratory of Medical Epigenetics, Department of Cell Biology, School of Basic Medical Sciences Hangzhou Normal University Hangzhou China
  7. 7Jinshiyan Biotechnology Yongkang China
Read full textPDFDOICite

Abstract

Head and neck squamous cell carcinoma (HNSC) exhibits substantial molecular and morphological heterogeneity, yet current morphology‐based prognostic models often lack biological interpretability. We developed a transformer‐based computational framework (CTransPath) to virtually predict gene expression directly from hematoxylin and eosin (H&E) whole‐slide images. Morphology‐associated genes were identified from the TCGA‐HNSC cohort, and a 32‐gene morphology‐guided prognostic signature (MGP_HNSC32) based on H&E‐derived predicted gene expression was developed using Random Survival Forest and multivariable Cox regression modeling. In TCGA‐HNSC, the MGP_HNSC32 risk score significantly stratified patients by progression‐free interval (PFI; HR = 4.13, 95% CI: 2.84–6.02), overall survival (OS; HR = 2.42, 95% CI: 1.78–3.29), and disease‐specific survival (DSS; HR = 4.88, 95% CI: 2.95–8.06; all p < 0.001), and remained independently associated with prognosis after multivariable adjustment. High‐risk tumors were enriched for cell cycle, E2F, MYC, and epithelial‐mesenchymal transition pathways and displayed poorly differentiated histology with nuclear atypia and stromal desmoplasia. In contrast, low‐risk tumors showed keratinizing morphology and immune‐rich stroma, corresponding to differentiation‐ and metabolism‐related transcriptional programs. In the independent HANCOCK cohort (n = 701), risk scores calculated entirely from H&E‐derived predicted gene expression using the TCGA‐derived coefficients and prespecified cutoff were associated with progression‐free survival (HR = 1.40, 95% CI: 1.03–1.90, p = 0.034). However, the continuous risk score was not significantly associated with progression‐free survival (HR = 1.001, 95% CI: 0.999–1.003, p = 0.328). MGP_HNSC32 links histomorphology to transcriptional programs and demonstrates preliminary prognostic associations using routine H&E images. The H&E‐based gene‐expression prediction component should be considered proof‐of‐concept, and further independent and prospective validation is required before clinical implementation.

Related

  1. Identification of a necroptosis-related lncRNA prognostic signature and the hub RBP HNRNPK in esophageal squamous cell carcinoma
    Shaoyi Zheng, Haoshuai Yang, Wei Liu +4
    The Journal of International Medical ResearchPeer-reviewedCC BY-NC 4.0Full textOncologyPMC
  2. A mitoxyperilysis-derived spatial signature predicts immune exclusion and survival in oral squamous cell carcinoma
    J. Liu, D. Zhang, Z. Meng +1
    medRxivPreprintCC BY-NCFull textOncologymedRxiv
  3. An Eight-Gene Metabolic Prognostic Signature in Head and Neck Squamous Cell Carcinoma: Cross-Cohort Evaluation, Single-Cell Analysis, and Preliminary Functional Evaluation of PYGL and G6PD.
    Wanyi Kou, Ruixin Guo, Yifan Zhang +10
    Journal of CancerPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  4. Distinct Anaerobic Microbial Signature Differentiates Anal Squamous Cell Carcinoma From High-Grade Squamous Intraepithelial Lesions: A Prospective Metagenomic Study
    B. Nolasco, T. Lambert, K. Luo +8
    medRxivPreprintAll rights reservedFull textOncologymedRxiv
  5. Transcriptomic immune-related signature associated with chemoradiotherapy response in anal squamous cell carcinoma
    Soledad Iseas, Mariano Golubicki, Ezequiel Lacunza +7
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textSurgery & anaesthesiaCrossref

Cite

BibTeXRIS
BibTeX
@article{zhao2026mgphnsc32,
  title = {{MGP_HNSC32: A H&E Morphology‐Derived 32‐Gene Prognostic Signature in Head and Neck Squamous Cell Carcinoma}},
  author = {Di Zhao and Zhiheng Huang and Jing Xu and Zheng Zhang and Jochen Hess and Bohai Feng},
  journal = {Cancer Medicine},
  year = {2026},
  month = oct,
  doi = {10.1002/cam4.72427},
  url = {https://doi.org/10.1002/cam4.72427},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - MGP_HNSC32: A H&E Morphology‐Derived 32‐Gene Prognostic Signature in Head and Neck Squamous Cell Carcinoma
AU  - Di Zhao
AU  - Zhiheng Huang
AU  - Jing Xu
AU  - Zheng Zhang
AU  - Jochen Hess
AU  - Bohai Feng
PY  - 2026
DA  - 2026/10/25
JO  - Cancer Medicine
DO  - 10.1002/cam4.72427
UR  - https://doi.org/10.1002/cam4.72427
AB  - Head and neck squamous cell carcinoma (HNSC) exhibits substantial molecular and morphological heterogeneity, yet current morphology‐based prognostic models often lack biological interpretability. We developed a transformer‐based computational framework (CTransPath) to virtually predict gene expression directly from hematoxylin and eosin (H&E) whole‐slide images. Morphology‐associated genes were identified from the TCGA‐HNSC cohort, and a 32‐gene morphology‐guided prognostic signature (MGP_HNSC32) based on H&E‐derived predicted gene expression was developed using Random Survival Forest and multivariable Cox regression modeling. In TCGA‐HNSC, the MGP_HNSC32 risk score significantly stratified patients by progression‐free interval (PFI; HR = 4.13, 95% CI: 2.84–6.02), overall survival (OS; HR = 2.42, 95% CI: 1.78–3.29), and disease‐specific survival (DSS; HR = 4.88, 95% CI: 2.95–8.06; all p < 0.001), and remained independently associated with prognosis after multivariable adjustment. High‐risk tumors were enriched for cell cycle, E2F, MYC, and epithelial‐mesenchymal transition pathways and displayed poorly differentiated histology with nuclear atypia and stromal desmoplasia. In contrast, low‐risk tumors showed keratinizing morphology and immune‐rich stroma, corresponding to differentiation‐ and metabolism‐related transcriptional programs. In the independent HANCOCK cohort (n = 701), risk scores calculated entirely from H&E‐derived predicted gene expression using the TCGA‐derived coefficients and prespecified cutoff were associated with progression‐free survival (HR = 1.40, 95% CI: 1.03–1.90, p = 0.034). However, the continuous risk score was not significantly associated with progression‐free survival (HR = 1.001, 95% CI: 0.999–1.003, p = 0.328). MGP_HNSC32 links histomorphology to transcriptional programs and demonstrates preliminary prognostic associations using routine H&E images. The H&E‐based gene‐expression prediction component should be considered proof‐of‐concept, and further independent and prospective validation is required before clinical implementation.
SN  - 2045-7634
ER  -