Cystic cervical lymph nodes of papillary thyroid carcinoma, tuberculosis and human papillomavirus positive oropharyngeal squamous cell carcinoma: utility of deep learning in their differentiation on CT
| Autor: | V. Carlota Andreu-Arasa, Keita Onoue, Bindu N. Setty, Osamu Sakai, Noriyuki Fujima |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Male
medicine.medical_specialty Tuberculosis education Diagnosis Differential Thyroid carcinoma 03 medical and health sciences Deep Learning 0302 clinical medicine Cervical lymphadenopathy medicine Humans Thyroid Neoplasms 030223 otorhinolaryngology Papillomaviridae Lymph node Squamous Cell Carcinoma of Head and Neck business.industry Papillomavirus Infections medicine.disease Primary tumor Oropharyngeal Neoplasms medicine.anatomical_structure Otorhinolaryngology Thyroid Cancer Papillary Cervical lymph nodes 030220 oncology & carcinogenesis Radiologist 2 Female Lymph Nodes Radiology Lymph medicine.symptom Tomography X-Ray Computed business Neck |
| Zdroj: | American Journal of Otolaryngology. 42:103026 |
| ISSN: | 0196-0709 |
| DOI: | 10.1016/j.amjoto.2021.103026 |
| Popis: | Objectives Cervical lymph nodes with internal cystic changes are seen with several pathologies, including papillary thyroid carcinoma (PTC), tuberculosis (TB), and HPV-positive oropharyngeal squamous cell carcinoma (HPV+OPSCC). Differentiating these lymph nodes is difficult in the absence of a known primary tumor or reliable medical history. In this study, we assessed the utility of deep learning in differentiating the pathologic lymph nodes of PTC, TB, and HPV+OPSCC on CT. Methods A total of 173 lymph nodes (55 PTC, 58 TB, and 60 HPV+OPSCC) were selected based on pathology records and suspicious morphological features. These lymph nodes were divided into the training set (n = 131) and the test set (n = 42). In deep learning analysis, JPEG lymph node images were extracted from the CT slice that included the largest area of each node and fed into a deep learning training session to create a diagnostic model. Transfer learning was used with the deep learning model architecture of ResNet-101. Using the test set, the diagnostic performance of the deep learning model was compared against the histopathological diagnosis and to the diagnostic performances of two board-certified neuroradiologists. Results Diagnostic accuracy of the deep learning model was 0.76 (=32/42), whereas those of Radiologist 1 and Radiologist 2 were 0.48 (=20/42) and 0.41 (=17/42), respectively. Deep learning derived diagnostic accuracy was significantly higher than both of the two neuroradiologists (P Conclusion Deep learning algorithm holds promise to become a useful diagnostic support tool in interpreting cervical lymphadenopathy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect