The Neck-Persistency-Net: a three-dimensional, convolution, deep neural network aids in distinguishing vital from non-vital persistent cervical lymph nodes in advanced head and neck squamous cell carcinoma after primary concurrent radiochemotherapy

被引：1

作者：

Santer, Matthias ^{[1
]}

Zelger, Philipp ^{[2
]}

Schmutzhard, Joachim ^{[1
]}

Freysinger, Wolfgang ^{[1
]}

Runge, Annette ^{[1
]}

Gottfried, Timo Maria ^{[1
]}

Troeger, Andrea ^{[1
]}

Vorbach, Samuel ^{[3
]}

Mangesius, Julian ^{[3
]}

Widmann, Gerlig ^{[4
]}

Graf, Simone ^{[2
]}

Hofauer, Benedikt Gabriel ^{[1
]}

Dejaco, Daniel ^{[1
]}

机构：

[1] Med Univ Innsbruck, Dept Otorhinolaryngol Head & Neck Surg, A-6020 Innsbruck, Austria

[2] Med Univ Innsbruck, Dept Hearing Voice & Speech Disorders, A-6020 Innsbruck, Austria

[3] Med Univ Innsbruck, Dept Radiat Oncol, A-6020 Innsbruck, Austria

[4] Med Univ Innsbruck, Dept Radiol, A-6020 Innsbruck, Austria

来源：

EUROPEAN ARCHIVES OF OTO-RHINO-LARYNGOLOGY | 2024年 / 281卷 / 11期

关键词：

HNSCC; Radiomics; Artificial intelligence; Machine learning; Salvage surgery; PET/CT; POSITRON-EMISSION-TOMOGRAPHY; INDUCTION CHEMOTHERAPY; DISSECTION; CHEMORADIOTHERAPY; MANAGEMENT; CANCER; PET/CT; SCANS;

D O I：

10.1007/s00405-024-08842-3

中图分类号：

R76 [耳鼻咽喉科学];

学科分类号：

100213 ;

摘要：

PurposeTo evaluate the diagnostic performance (DP) of the high-resolution contrast computed tomography (HR-contrast-CT) based Neck-Persistency-Net in distinguishing vital from non-vital persistent cervical lymph nodes (pcLNs) in patients with advanced head and neck squamous cell carcinoma (HNSCC) following primary concurrent chemoradiotherapy (CRT) with [18F]-fluorodeoxyglucose positron emission tomography and high-resolution contrast-enhanced computed tomography ([18F]FDG-PET-CT). Furthermore, the Neck-Persistency-Net's potential to justify omitting post-CRT neck dissection (ND) without risking treatment delays or preventing unnecessary surgery was explored.MethodsAll HNSCC patients undergoing primary CRT followed by post-CRT-ND for pcLNs recorded in the institutional HNSCC registry were analyzed. The Neck-Persistency-Net DP was explored for three scenarios: balanced performance (BalPerf), optimized sensitivity (OptSens), and optimized specificity (OptSpec). Histopathology of post-CRT-ND served as a reference.ResultsAmong 68 included patients, 11 were female and 32 had vital pcLNs. The Neck-Persistency-Net demonstrated good DP with an area under the curve of 0.82. For BalPerf, both sensitivity and specificity were 78%; for OptSens (90%), specificity was 62%; for OptSpec (95%), sensitivity was 54%. Limiting post-CRT-ND to negative results would have delayed treatment in 27%, 40%, and 7% for BalPerf, OptSens and OptSpec, respectively, versus 23% for [18F]FDG-PET-CT. Conversely, restricting post-CRT-ND to positive results would have prevented unnecessary post-CRT-ND in 78%, 60%, and 95% for BalPerf, OptSens and OptSpec, respectively, versus 55% for [18F]FDG-PET-CT.ConclusionThe DP of the Neck-Persistency-Net was comparable to [18F]-FDG-PET-CT. Depending on the chosen decision boundary, the potential to justify the omission of post-CRT-ND without risking treatment delays in false negative findings or reliably prevent unnecessary surgery in false positive findings outperforms the [18F]-FDG-PET-CT.

引用

页码：5971 / 5982

页数：12