ICHNO-ECHNO 2022 - Abstract Book

ICHNO-ECHNO 2022

S1

Keynote lecture: The good and bad of TNM8

SP-0001 The good and bad of TNM8 Brian O’Sullivan Canada

Abstract not available

Keynote lecture: Biomarker guided treatment and monitoring for head and neck cancers

SP-0002 Biomarker guided treatment and monitoring for head and neck cancers

R. Brakenhoff 1

1 Amsterdam UMC, Department of Otolaryngology -Head and Neck Surgery, Amsterdam, The Netherlands

Abstract Text Head and neck squamous cell carcinomas (HNSCC) develop in the mucosal lining of the upper aerodigestive tract. At present two separate disease entities are distinguished: HNSCCs caused by human papillomavirus (HPV) infection and those that do not contain HPV. These tumors are distinguished based on p16 immunostaining as surrogate biomarker, often combined with a HPV DNA and/or RNA assay. The presence of p16 immunostaining or HPV DNA are a most well accepted biomarkers for tumor classification. Staging has been adapted for HPV-positive tumors in the TNM 8th edition, but remarkably treatment not. According to the National Cancer Institute, a biomarker is “a biological molecule found in blood, other body fluids, or tissues that is a sign of a normal or abnormal process, or of a condition or disease,” such as cancer. Biomarkers can be applied for diagnosis, response prediction or treatment-guidance, and patient monitoring. Focus in this presentation are biomarkers associated with treatment response and disease monitoring. There are several trials in recurrent/metastatic disease to tailor treatment to mutations in the tumor, but results are far from optimal. Although the high-throughput genomics of head and neck cancer revealed intriguing new insights, these studies did not provide a wide array of novel therapeutic leads to be exploited on basis of the concept of oncogene addition. More complex synthetic and collateral lethality concepts have to be exploited, and recently an intriguing synthetic lethal interaction with the FAT1 tumor suppressor gene has been identified. Vice versa, for several routinely applied treatments such as cisplatin-based chemoradiotherapy, cetuximab-based bioradiotherapy, and anti-PD-(L)1 immune checkpoint inhibition biomarkers for response are urgently awaited, but are still lacking. Finally, a few disease monitoring approaches will be discussed. Most promising option is circulating tumor DNA analysis in blood and other liquid biopsies, but specifically early detection of recurrent disease is complex. Small tumor deposits are hard to detect, not only by imaging, but also by biomarkers. However techniques improve, and exciting new developments are underway.

Symposium: AI in head and neck oncology

SP-0003 AI guided pathological diagnosis Frederick Klauschen

Abstract not available

SP-0004 AI for better diagnosis and surgical treatment of head and neck cancer Cesare Piazza

Abstract not available

SP-0005 AI for head and neck radiation oncology

J. Bibault 1

1 Hôpital Européen Georges Pompidou, Radiation Oncology Department, Paris, France

Abstract Text Artificial Intelligence (AI) and Machine Learning (ML) have promising applications in radiation oncology. ML algorithms include data from many different sources that can be clinical, biological, radiologic, genomic and dosimetrics. They can be used to enhance the radiation oncology workflow management with automation of treatment planning steps such as automatic delineation or adaptive radiotherapy. They are also actively being explored as prognostic and predictive tools, correlated with histologic and genomic characteristics in several cancer types. In this presentation, each of these aspects will discussed: 1- Radiation Oncology Treatment Planning Radiotherapy treatment planning encompasses time consuming tasks such as delineation, dosimetric planification, and adaptive radiotherapy. Increasing automation of these tasks is a promising prospective. AI can also be used for Adaptive Radiation Therapy (ART) to take into account tumor shrinkage and patient emaciation during treatment. Benefits and