Computerized tumor multinucleation index (MuNI) is prognostic in p16+ oropharyngeal carcinoma

Can F Koyuncu ^1,2, Cheng Lu ¹, Kaustav Bera ¹

¹Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA.
²Louis Stokes Cleveland Veterans Affairs (VA) Medical Center, Cleveland, Ohio, USA.
³Nanjing University of Information Science and Technology, Nanjing, China.
⁴Cleveland Clinic Foundation, Cleveland, Ohio, USA.
⁵Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, Ohio, USA.
⁶Washington University in St. Louis, St. Louis, Missouri, USA.
⁷UCSD, San Diego, California, USA.
⁸University of Texas (UT) Southwestern Medical Center, Dallas, Texas, USA.
⁹Vanderbilt University Medical Center, Nashville, Tennessee, USA.
¹⁰Department of Otolaryngology, Head and Neck Surgery, Baylor College of Medicine, Houston, Texas, USA.
¹¹ENT Section, Operative Care Line, Michael E. DeBakey VA Medical Center, Houston, Texas, USA.
¹²Southern California Permanente Medical Group, Pasadena, California, USA.

⁰Department of Biomedical Engineering, Case Western Reserve University, Cleveland, Ohio, USA.

The Journal of Clinical Investigation +

|

March 2, 2021

View abstract on PubMed

Summary

A new deep-learning tool, the multinucleation index (MuNI), accurately predicts treatment failure in p16+ oropharyngeal squamous cell carcinoma (OPSCC). MuNI quantifies tumor cell multinucleation, offering a reliable biomarker for patient outcomes.

Area Of Science

Oncology
Digital Pathology
Biomarker Development

Background

p16+ oropharyngeal squamous cell carcinoma (OPSCC) patients can be cured with treatment, but lack reliable biomarkers for treatment failure.
Pathologist assessment of tumor cell multinucleation (MN) is prognostic but subjective and time-consuming.
Current methods for assessing MN in p16+ OPSCC have limitations in terms of speed, objectivity, and interobserver variability.

Purpose Of The Study

To develop and validate a deep-learning-based metric, the multinucleation index (MuNI), for prognostication in p16+ OPSCC.
To quantify tumor MN from digitized H&E-stained slides using an automated approach.
To establish MuNI as a reliable and objective biomarker for predicting treatment failure in p16+ OPSCC.

Main Methods

A deep-learning algorithm was developed to quantify tumor MN from whole-slide images of H&E-stained tissue.
The MuNI metric was optimized and validated using data from 1094 patients with previously untreated p16+ OPSCC across six institutions.
Multivariable analyses were performed to assess MuNI's prognostic value independent of clinical and pathological factors.

Main Results

The MuNI demonstrated significant prognostic value for disease-free survival (DFS), overall survival (OS), and distant metastasis-free survival (DMFS) in p16+ OPSCC.
MuNI's prognostic capability remained significant even after adjusting for age, smoking status, treatment, and tumor/node (T/N) stage.
The MuNI was also found to be prognostic for DFS, OS, and DMFS in patients with Stage I and Stage III OPSCC when analyzed separately.

Conclusions

The multinucleation index (MuNI) shows promise as a cost-effective, non-destructive digital biomarker for p16+ OPSCC.
MuNI can aid in patient counseling, treatment decisions, and surveillance strategies for p16+ OPSCC.
Further validation of MuNI in prospective clinical trials is warranted to confirm its utility.

Keywords:

Head and neck cancer Oncology

Related Concept Videos

Abnormal Proliferation

Under normal conditions, most adult cells remain in a non-proliferative state unless stimulated by internal or external factors to replace lost cells. Abnormal cell proliferation is a condition in which the cell's growth exceeds and is uncoordinated with normal cells. In such situations, cell division persists in the same excessive manner even after cessation of the stimuli, leading to persistent tumors. The tumor arises from the damaged cells that replicate to pass the damage to the...