scholarly journals Hyperspectral Imaging of Head and Neck Squamous Cell Carcinoma for Cancer Margin Detection in Surgical Specimens from 102 Patients Using Deep Learning

Cancers ◽  
2019 ◽  
Vol 11 (9) ◽  
pp. 1367 ◽  
Author(s):  
Martin Halicek ◽  
James D. Dormer ◽  
James V. Little ◽  
Amy Y. Chen ◽  
Larry Myers ◽  
...  

Surgical resection of head and neck (H and N) squamous cell carcinoma (SCC) may yield inadequate surgical cancer margins in 10 to 20% of cases. This study investigates the performance of label-free, reflectance-based hyperspectral imaging (HSI) and autofluorescence imaging for SCC detection at the cancer margin in excised tissue specimens from 102 patients and uses fluorescent dyes for comparison. Fresh surgical specimens (n = 293) were collected during H and N SCC resections (n = 102). The tissue specimens were imaged with reflectance-based HSI and autofluorescence imaging and afterwards with two fluorescent dyes for comparison. A histopathological ground truth was made. Deep learning tools were developed to detect SCC with new patient samples (inter-patient) and machine learning for intra-patient tissue samples. Area under the curve (AUC) of the receiver-operator characteristic was used as the main evaluation metric. Additionally, the performance was estimated in mm increments circumferentially from the tumor-normal margin. In intra-patient experiments, HSI classified conventional SCC with an AUC of 0.82 up to 3 mm from the cancer margin, which was more accurate than proflavin dye and autofluorescence (both p < 0.05). Intra-patient autofluorescence imaging detected human papilloma virus positive (HPV+) SCC with an AUC of 0.99 at 3 mm and greater accuracy than proflavin dye (p < 0.05). The inter-patient results showed that reflectance-based HSI and autofluorescence imaging outperformed proflavin dye and standard red, green, and blue (RGB) images (p < 0.05). In new patients, HSI detected conventional SCC in the larynx, oropharynx, and nasal cavity with 0.85–0.95 AUC score, and autofluorescence imaging detected HPV+ SCC in tonsillar tissue with 0.91 AUC score. This study demonstrates that label-free, reflectance-based HSI and autofluorescence imaging methods can accurately detect the cancer margin in ex-vivo specimens within minutes. This non-ionizing optical imaging modality could aid surgeons and reduce inadequate surgical margins during SCC resections.

Oncology ◽  
2021 ◽  
pp. 1-7
Author(s):  
Nir Hirshoren ◽  
Issa Al-Kharouf ◽  
Jeffrey M. Weinberger ◽  
Ron Eliashar ◽  
Aron Popovtzer ◽  
...  

<b><i>Introduction:</i></b> Immune-checkpoint inhibitors have demonstrated a significant survival benefit in metastatic and non-resectable head and neck squamous cell carcinoma (HNSCC). Patients with a combined positivity score (CPS) of 20 and higher benefit the most from therapy. Inaccurate definition of the CPS category might lead to the incorrect stratification of patients to immunotherapy. This study’s main aim was to investigate programmed death-ligand 1 (PD-L1) antigen expression in HNSCC in diverse clinical situations and histological settings. <b><i>Materials and Methods:</i></b> This is a prospective cohort study conducted in a tertiary referral medical center. Tissues were investigated for PD-L1 expression using the FDA-approved 22C3 immunohistochemistry assay (Dako). We analyzed potential associations between the CPS category and meaningful demographic, clinical, and outcome metrics. Furthermore, we investigated morphologically separate sites for CPS scores in whole surgical tissue specimens and matched preoperative biopsies. <b><i>Results:</i></b> We analyzed 36 patients, of whom 26 had oral cavity SCC and 10 had laryngeal SCC. The overall, disease-specific, and progression-free survival of the HNSCC group of patients were not associated with the CPS category (<i>p</i> = 0.45, <i>p</i> = 0.31, and <i>p</i> = 0.88, respectively). There was a significant (18%, 95% CI 0.65–0.9) inconsistency between the CPS category determined in biopsies versus whole carcinoma analyses. We also found an uneven distribution of whole-tumor CPS attributed to spatial carcinoma invasiveness, tumor differentiation, and inflammatory cell infiltration heterogeneity. <b><i>Discussion and Conclusions:</i></b> Our data suggest that careful selection of tumor area for CPS analysis is important. PD-L1 antigen expression, clinically represented by CPS, may be up- or down-categorized in different clinical and pathological circumstances. The high whole-tissue CPS category scatter may clinically result in potential treatment modifications. We argue that CPS analysis requires not only adequacy (at least 100 viable tumor cells), but also correct representation of the tumor microenvironment.


Sign in / Sign up

Export Citation Format

Share Document