Prediction of cervical lymph node metastasis from immunostained specimens of tongue cancer using a multilayer perceptron neural network

• Published in: Cancer medicine (Malden, MA) MA), 2023-03, Vol.12 (5), p.5312-5322
• Main Authors: Kawamura, Kohei, Lee, Chonho, Yoshikawa, Takashi, Hani, Al‐Shareef, Usami, Yu, Toyosawa, Satoru, Tanaka, Susumu, Hiraoka, Shin‐Ichiro
• Format: Article
• Language: English
• Subjects: Angiogenesis; Antibodies; Back propagation; CCR7 protein; deep learning; Dissection; Head & neck cancer; Humans; immunohistochemistry; Lymph nodes; Lymph Nodes - pathology; lymphatic metastasis; Lymphatic Metastasis - pathology; Lymphatic system; Medical prognosis; Medical research; Metastases; Metastasis; Mouth Neoplasms - pathology; Multivariate analysis; neural network; Neural networks; Oral cancer; Oral carcinoma; Pathology; Proteins; Receptors, CCR7; Squamous cell carcinoma; Tomography; Tongue; tongue neoplasms; Tongue Neoplasms - pathology; Tumors; Vascular endothelial growth factor; Vascular endothelial growth factor C
• ISSN: 2045-7634; 2045-7634
• DOI: 10.1002/cam4.5343

Background Although cervical lymph node metastasis is an important prognostic factor for oral cancer, occult metastases remain undetected even by diagnostic imaging. We developed a learning model to predict lymph node metastasis in resected specimens of tongue cancer by classifying the level of immunohistochemical (IHC) staining for angiogenesis‐ and lymphangiogenesis‐related proteins using a multilayer perceptron neural network (MNN). Methods We obtained a dataset of 76 patients with squamous cell carcinoma of the tongue who had undergone primary tumor resection. All 76 specimens were IHC stained for the six types shown above (VEGF‐C, VEGF‐D, NRP1, NRP2, CCR7, and SEMA3E) and 456 slides were prepared. We scored the staining levels visually on all slides. We created virtual slides (4560 images) and the accuracy of the MNN model was verified by comparing it with a hue–saturation (HS) histogram, which quantifies the manually determined visual information. Results The accuracy of the training model with the MNN was 98.6%, and when the training image was converted to grayscale, the accuracy decreased to 52.9%. This indicates that our MNN adequately evaluates the level of staining rather than the morphological features of the IHC images. Multivariate analysis revealed that CCR7 staining level and T classification were independent factors associated with the presence of cervical lymph node metastasis in both HS histograms and MNN. Conclusion These results suggest that IHC assessment using MNN may be useful for identifying lymph node metastasis in patients with tongue cancer. Prediction of lymph node metastasis from resected specimens of tongue cancer is clinically useful; MNN can be highly accurate for simple classification with a small amount of training data. This method allows an automatic classification of the staining levels of immunochemically stained specimens, and a correlation was found between CCR7 staining levels and lymph node metastases. This is a potential new system for the assessment of lymph node metastases in patients with oral cancer.