Search

Purpose: To 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. Methods: All 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. Results: Among 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. Conclusion: The 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. [ABSTRACT FROM AUTHOR]

Simple Summary: Radiochemotherapy (RCT) in patients with locally advanced head and neck squamous cell carcinoma (HNSCC) causes side effects in healthy tissue such as the sternocleidomastoid muscle (SCM). These side effects depend on the interval between completion of RCT and restaging CT. For salvage surgery, the optimal time window for surgery is clinically postulated at between 6 and 12 weeks after completion of RCT. Thus, no extensive tissue fibrosis is to be expected. This interval is based on clinical studies exploring surgical complications. Studies directly exploring radiation-induced changes of the SCM in HNSCC patients are sparse. This study applied radiomics to quantify radiation-induced changes in the SCM and paravertebral musculature (PVM). In 98 locally advanced HNSCC patients, three radiomic key features (volume, mean positivity of pixels, uniformity) were analyzed in CT scans before and in the mean 8 weeks after treatment. No significant changes in radiomic key features were observed after adjustment for changes in body mass index (BMI). These data support the clinically postulated time window for salvage surgery of 6 to 12 weeks. Patients with locally advanced head and neck squamous cell carcinoma (HNSCC) frequently require primary radiochemotherapy (RCT). Despite intensity modulation, the desired radiation-induced effects observed in HNSCC may also be observed as side effects in healthy tissue, e.g., the sternocleidomastoid muscle (SCM). These side effects (e.g., tissue fibrosis) depend on the interval between the completion of RCT and restaging CT. For salvage surgery, the optimal time window for surgery is currently clinically postulated at between 6 and 12 weeks after completion of RCT. Thus, no extensive tissue fibrosis is to be expected. This interval is based on clinical studies exploring surgical complications. Studies directly exploring radiation-induced changes of the SCM in HNSCC patients are sparse. The present study quantified tissue alterations in the SCM and paravertebral musculature (PVM) after RCT, applying radiomics to determine the optimal time window for salvage surgery. Three radiomic key parameters, (1) volume, (2) mean positivity of pixels (MPP), and (3) uniformity, were extracted with mint LesionTM in the staging CTs and restaging CTs of 98 HNSCC patients. Of these, 25 were female, the mean age was 62 (±9.6) years, and 80.9% were UICC Stage IV. The mean restaging interval was 55 (±28; range 29–229) days. Only the mean volume significantly decreased after RCT, from 9.0 to 8.4 and 96.5 to 91.9 mL for the SCM and PVM, respectively (both p = 0.007, both Cohen's d = 0.28). In addition, the mean body mass index (BMI) decreased from 23.9 (±4.2) to 21.0 (±3.6) kg/m² (p < 0.001; Cohen's d = 0.9). The mean BMI decreased significantly and was correlated with the volume decrease for the SCM (r = 0.27; p = 0.007) and PVM (r = 0.41; p < 0.001). If t-test p-values were adjusted for the BMI decrease, no significant change in volumes for the SCM and PVM was observed (both p > 0.05). The present data support the clinically postulated optimal interval for salvage surgery of 6 to 12 weeks. [ABSTRACT FROM AUTHOR]

Simple Summary: Locally-advanced head and neck squamous cell carcinoma (HNSCC) is mainly defined by the presence of pathologic cervical lymph nodes (LNs). Radiologic criteria to classify LNs as pathologic or non-pathologic are shape-based. However, significantly more quantitative information is contained within images. This information could be exploited to classify LNs in patients with locally-advanced HNSCC by means of artificial intelligence (AI). The present work systematically reviews original articles that specifically explore the role of AI to classify LNs in locally-advanced HNSCC. Between 2001 and 2022, 13 retrospective studies were identified. AI's mean diagnostic accuracy for LN-classification was 86% (range: 43–99%). Consequently, all of the identified studies concluded AI to be a potentially promising diagnostic support tool for LN-classification in HNSCC. However, adequately powered, prospective, randomized control trials are urgently required to further assess AI's role in LN-classification in locally-advanced HNSCC. Locally-advanced head and neck squamous cell carcinoma (HNSCC) is mainly defined by the presence of pathologic cervical lymph nodes (LNs) with or without extracapsular spread (ECS). Current radiologic criteria to classify LNs as non-pathologic, pathologic, or pathologic with ECS are primarily shape-based. However, significantly more quantitative information is contained within imaging modalities. This quantitative information could be exploited for classification of LNs in patients with locally-advanced HNSCC by means of artificial intelligence (AI). Currently, various reviews exploring the role of AI in HNSCC are available. However, reviews specifically addressing the current role of AI to classify LN in HNSCC-patients are sparse. The present work systematically reviews original articles that specifically explore the role of AI to classify LNs in locally-advanced HNSCC applying Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines and the Study Quality Assessment Tool of National Institute of Health (NIH). Between 2001 and 2022, out of 69 studies a total of 13 retrospective, mainly monocentric, studies were identified. The majority of the studies included patients with oropharyngeal and oral cavity (9 and 7 of 13 studies, respectively) HNSCC. Histopathologic findings were defined as reference in 9 of 13 studies. Machine learning was applied in 13 studies, 9 of them applying deep learning. The mean number of included patients was 75 (SD ± 72; range 10–258) and of LNs was 340 (SD ± 268; range 21–791). The mean diagnostic accuracy for the training sets was 86% (SD ± 14%; range: 43–99%) and for testing sets 86% (SD ± 5%; range 76–92%). Consequently, all of the identified studies concluded AI to be a potentially promising diagnostic support tool for LN-classification in HNSCC. However, adequately powered, prospective, and randomized control trials are urgently required to further assess AI's role in LN-classification in locally-advanced HNSCC. [ABSTRACT FROM AUTHOR]