TY - JOUR
T1 - Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients
AU - Klein, Sebastian
AU - Wuerdemann, Nora
AU - Demers, Imke
AU - Kopp, Christopher
AU - Quantius, Jennifer
AU - Charpentier, Arthur
AU - Tolkach, Yuri
AU - Brinker, Klaus
AU - Sharma, Shachi Jenny
AU - George, Julie
AU - Hess, Jochen
AU - Stögbauer, Fabian
AU - Lacko, Martin
AU - Struijlaart, Marijn
AU - van den Hout, Mari F C M
AU - Wagner, Steffen
AU - Wittekindt, Claus
AU - Langer, Christine
AU - Arens, Christoph
AU - Buettner, Reinhard
AU - Quaas, Alexander
AU - Reinhardt, Hans Christian
AU - Speel, Ernst-Jan
AU - Klussmann, Jens Peter
PY - 2023/8/19
Y1 - 2023/8/19
N2 - Human Papilloma Virus (HPV)-associated oropharyngeal squamous cell cancer (OPSCC) represents an OPSCC subgroup with an overall good prognosis with a rising incidence in Western countries. Multiple lines of evidence suggest that HPV-associated tumors are not a homogeneous tumor entity, underlining the need for accurate prognostic biomarkers. In this retrospective, multi-institutional study involving 906 patients from four centers and one database, we developed a deep learning algorithm (OPSCCnet), to analyze standard H&E stains for the calculation of a patient-level score associated with prognosis, comparing it to combined HPV-DNA and p16-status. When comparing OPSCCnet to HPV-status, the algorithm showed a good overall performance with a mean area under the receiver operator curve (AUROC)?=?0.83 (95% CI?=?0.77-0.9) for the test cohort (n?=?639), which could be increased to AUROC?=?0.88 by filtering cases using a fixed threshold on the variance of the probability of the HPV-positive class - a potential surrogate marker of HPV-heterogeneity. OPSCCnet could be used as a screening tool, outperforming gold standard HPV testing (OPSCCnet: five-year survival rate: 96% [95% CI?=?90-100%]; HPV testing: five-year survival rate: 80% [95% CI?=?71-90%]). This could be confirmed using a multivariate analysis of a three-tier threshold (OPSCCnet: high HR?=?0.15 [95% CI?=?0.05-0.44], intermediate HR?=?0.58 [95% CI?=?0.34-0.98] p?=?0.043, Cox proportional hazards model, n?=?211; HPV testing: HR?=?0.29 [95% CI?=?0.15-0.54] p?<?0.001, Cox proportional hazards model, n?=?211). Collectively, our findings indicate that by analyzing standard gigapixel hematoxylin and eosin (H&E) histological whole-slide images, OPSCCnet demonstrated superior performance over p16/HPV-DNA testing in various clinical scenarios, particularly in accurately stratifying these patients.
AB - Human Papilloma Virus (HPV)-associated oropharyngeal squamous cell cancer (OPSCC) represents an OPSCC subgroup with an overall good prognosis with a rising incidence in Western countries. Multiple lines of evidence suggest that HPV-associated tumors are not a homogeneous tumor entity, underlining the need for accurate prognostic biomarkers. In this retrospective, multi-institutional study involving 906 patients from four centers and one database, we developed a deep learning algorithm (OPSCCnet), to analyze standard H&E stains for the calculation of a patient-level score associated with prognosis, comparing it to combined HPV-DNA and p16-status. When comparing OPSCCnet to HPV-status, the algorithm showed a good overall performance with a mean area under the receiver operator curve (AUROC)?=?0.83 (95% CI?=?0.77-0.9) for the test cohort (n?=?639), which could be increased to AUROC?=?0.88 by filtering cases using a fixed threshold on the variance of the probability of the HPV-positive class - a potential surrogate marker of HPV-heterogeneity. OPSCCnet could be used as a screening tool, outperforming gold standard HPV testing (OPSCCnet: five-year survival rate: 96% [95% CI?=?90-100%]; HPV testing: five-year survival rate: 80% [95% CI?=?71-90%]). This could be confirmed using a multivariate analysis of a three-tier threshold (OPSCCnet: high HR?=?0.15 [95% CI?=?0.05-0.44], intermediate HR?=?0.58 [95% CI?=?0.34-0.98] p?=?0.043, Cox proportional hazards model, n?=?211; HPV testing: HR?=?0.29 [95% CI?=?0.15-0.54] p?<?0.001, Cox proportional hazards model, n?=?211). Collectively, our findings indicate that by analyzing standard gigapixel hematoxylin and eosin (H&E) histological whole-slide images, OPSCCnet demonstrated superior performance over p16/HPV-DNA testing in various clinical scenarios, particularly in accurately stratifying these patients.
U2 - 10.1038/s41746-023-00901-z
DO - 10.1038/s41746-023-00901-z
M3 - Article
SN - 2398-6352
VL - 6
JO - npj Digital Medicine
JF - npj Digital Medicine
IS - 1
M1 - 152
ER -