Deep learning predicts HPV association in oropharyngeal squamous cell carcinomas and identifies patients with a favorable prognosis using regular H&E stains

• Verfasst von: Klein, Sebastian [VerfasserIn]
• Verfasst von: Quaas, Alexander [VerfasserIn]
• Verfasst von: Quantius, Jennifer [VerfasserIn]
• Verfasst von: Löser, Heike [VerfasserIn]
• Verfasst von: Meinel, Jörn [VerfasserIn]
• Verfasst von: Peifer, Martin [VerfasserIn]
• Verfasst von: Wagner, Steffen [VerfasserIn]
• Verfasst von: Gattenlöhner, Stefan [VerfasserIn]
• Verfasst von: Wittekindt, Claus [VerfasserIn]
• Verfasst von: Knebel Doeberitz, Magnus von [VerfasserIn]
• Verfasst von: Prigge, Elena-Sophie [VerfasserIn]
• Verfasst von: Langer, Christine [VerfasserIn]
• Verfasst von: Noh, Ka-Won [VerfasserIn]
• Verfasst von: Maltseva, Margaret [VerfasserIn]
• Verfasst von: Reinhardt, Christian [VerfasserIn]
• Verfasst von: Büttner, Reinhard [VerfasserIn]
• Verfasst von: Klußmann, Jens Peter [VerfasserIn]
• Verfasst von: Würdemann, Nora [VerfasserIn]
• Titel: Deep learning predicts HPV association in oropharyngeal squamous cell carcinomas and identifies patients with a favorable prognosis using regular H&E stains
• Verf.angabe: Sebastian Klein, Alexander Quaas, Jennifer Quantius, Heike Löser, Martin Peifer, Steffen Wagner, Stefan Gattenlöhner, Claus Wittekindt, Magnus von Knebel Doeberitz, Elena-Sophie Prigge, Christine Langer, Ka-Won Noh, Margaret Maltseva, Hans Christian Reinhardt, Reinhard Büttner, Jens Peter Klussmann, Nora Wuerdemann
• E-Jahr: 2021
• Jahr: February 2021
• Umfang: 8 S.
• Fussnoten: Gesehen am 23.11.2021
• Titel Quelle: Enthalten in: Clinical cancer research
• Ort Quelle: Philadelphia, Pa. [u.a.] : AACR, 1995
• Jahr Quelle: 2021
• Band/Heft Quelle: 27(2021), 4, Seite 1131-1138
• ISSN Quelle: 1557-3265
• DOI: doi:10.1158/1078-0432.CCR-20-3596
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1778397727

Abstract

Purpose: Human papillomavirus (HPV) in oropharyngeal squamous cell carcinoma (OPSCC) is tumorigenic and has been associated with a favorable prognosis compared with OPSCC caused by tobacco, alcohol, and other carcinogens. Meanwhile, machine learning has evolved as a powerful tool to predict molecular and cellular alterations of medical images of various sources. - Experimental Design: We generated a deep learning-based HPV prediction score (HPV-ps) on regular hematoxylin and eosin (H&E) stains and assessed its performance to predict HPV association using 273 patients from two different sites (OPSCC; Giessen, n = 163; Cologne, n = 110). Then, the prognostic relevance in a total of 594 patients (Giessen, Cologne, HNSCC TCGA) was evaluated. In addition, we investigated whether four board-certified pathologists could identify HPV association (n = 152) and compared the results to the classifier. - Results: Although pathologists were able to diagnose HPV association from H&E-stained slides (AUC = 0.74, median of four observers), the interrater reliability was minimal (Light Kappa = 0.37; P = 0.129), as compared with AUC = 0.8 using the HPV-ps within two independent cohorts (n = 273). The HPV-ps identified individuals with a favorable prognosis in a total of 594 patients from three cohorts (Giessen, OPSCC, HR = 0.55, P < 0.0001; Cologne, OPSCC, HR = 0.44, P = 0.0027; TCGA, non-OPSCC head and neck, HR = 0.69, P = 0.0073). Interestingly, the HPV-ps further stratified patients when combined with p16 status (Giessen, HR = 0.06, P < 0.0001; Cologne, HR = 0.3, P = 0.046). - Conclusions: Detection of HPV association in OPSCC using deep learning with help of regular H&E stains may either be used as a single biomarker, or in combination with p16 status, to identify patients with OPSCC with a favorable prognosis, potentially outperforming combined HPV-DNA/p16 status as a biomarker for patient stratification.