Dataset Information

Diagnosis of lymph node metastasis in head and neck squamous cell carcinoma using deep learning.

ABSTRACT:

Background

To build an automatic pathological diagnosis model to assess the lymph node metastasis status of head and neck squamous cell carcinoma (HNSCC) based on deep learning algorithms.

Study design

A retrospective study.

Methods

A diagnostic model integrating two-step deep learning networks was trained to analyze the metastasis status in 85 images of HNSCC lymph nodes. The diagnostic model was tested in a test set of 21 images with metastasis and 29 images without metastasis. All images were scanned from HNSCC lymph node sections stained with hematoxylin-eosin (HE).

Results

In the test set, the overall accuracy, sensitivity, and specificity of the diagnostic model reached 86%, 100%, and 75.9%, respectively.

Conclusions

Our two-step diagnostic model can be used to automatically assess the status of HNSCC lymph node metastasis with high sensitivity.

Level of evidence

NA.

SUBMITTER: Tang H

PROVIDER: S-EPMC8823170 | biostudies-literature | 2022 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Diagnosis of lymph node metastasis in head and neck squamous cell carcinoma using deep learning.

Tang Haosheng H Li Guo G Liu Chao C Huang Donghai D Zhang Xin X Qiu Yuanzheng Y Liu Yong Y

Laryngoscope investigative otolaryngology 20220122 1

<h4>Background</h4>To build an automatic pathological diagnosis model to assess the lymph node metastasis status of head and neck squamous cell carcinoma (HNSCC) based on deep learning algorithms.<h4>Study design</h4>A retrospective study.<h4>Methods</h4>A diagnostic model integrating two-step deep learning networks was trained to analyze the metastasis status in 85 images of HNSCC lymph nodes. The diagnostic model was tested in a test set of 21 images with metastasis and 29 images without metas ...[more]

PMID: 35155794

Similar Datasets

Project description:ObjectivesPrecise determination of cervical lymph node metastasis (CLNM) involvement in patients with early-stage thyroid cancer is fairly significant for identifying appropriate cervical treatment options. However, it is almost impossible to directly judge lymph node metastasis based on the imaging information of early-stage thyroid cancer patients with clinically negative lymph nodes.MethodsPreoperative US images (BMUS and CDFI) of 1031 clinically node negative PTC patients definitively diagnosed on pathology from two independent hospitals were divided into training set, validation set, internal test set, and external test set. An ensemble deep learning model based on ResNet-50 was built integrating clinical variables, BMUS, and CDFI images using a bagging classifier to predict metastasis of CLN. The final ensemble model performance was compared with expert interpretation.ResultsThe ensemble deep convolutional neural network (DCNN) achieved high performance in predicting CLNM in the test sets examined, with area under the curve values of 0.86 (95% CI 0.78-0.94) for the internal test set and 0.77 (95% CI 0.68-0.87) for the external test set. Compared to all radiologists averaged, the ensemble DCNN model also exhibited improved performance in making predictions. For the external validation set, accuracy was 0.72 versus 0.59 (p = 0.074), sensitivity was 0.75 versus 0.58 (p = 0.039), and specificity was 0.69 versus 0.60 (p = 0.078).ConclusionsDeep learning can non-invasive predict CLNM for clinically node-negative PTC using conventional US imaging of thyroid cancer nodules and clinical variables in a multi-institutional dataset with superior accuracy, sensitivity, and specificity comparable to experts.Critical relevance statementDeep learning efficiently predicts CLNM for clinically node-negative PTC based on US images and clinical variables in an advantageous manner.Key points• A deep learning-based ensemble algorithm for predicting CLNM in PTC was developed. • Ultrasound AI analysis combined with clinical data has advantages in predicting CLNM. • Compared to all experts averaged, the DCNN model achieved higher test performance.

Project description:BackgroundHead and neck squamous cell carcinoma (HNSCC) is one of the most serious diseases affecting populations worldwide and lymph node metastasis is a key pathological feature of HNSCC which predicts poor survival. However, the molecular mechanisms associated with the development of lymph node metastasis in HNSCC have not been fully elucidated.MethodsDifferentially expressed genes (DEGs) were identified in two HNSCC datasets (GES6631 and GES58911). Functional annotation analysis was constructed via Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses. Meanwhile, the protein-protein interaction (PPI) network and module analysis using Search Tool for the Retrieval of Interacting Genes/Proteins (STRING) and Cytoscape were carried out to identify the hub genes. The expression differences, overall survival (OS), and disease-free survival (DFS) of hub genes were analyzed by Gene Expression Profiling Interactive Analysis 2 (GEPIA2) and verified by immunohistochemistry (IHC) from Human Protein Atlas (HPA). Moreover, receiver operating characteristic (ROC) curve analysis was conducted to judge whether those hub genes had good diagnostic and prognostic ability, and the web tool Tumor Immune Estimation Resource (TIMER) was used to analyze the correlation of hub genes' expression and immune infiltration.ResultsIn total, 913 DEGs including 476 upregulated and 437 downregulated genes were identified. The genes Aurora kinase A (AURKA), CyclinB1 (CCNB1), Cyclin-dependent kinase regulatory subunit 1B (CKS1B), Serpin Family H Member 1(SERPINH1), and Transforming growth factor-beta-induced protein (TGFBI) were screened out as hub genes and were associated with lymph node metastasis, showing notably abnormal expression in HNSCC samples, and the high expression of all the hub genes in HNSCC patients was related to worse overall survival.ConclusionsThe genes AURKA, CCNB1, CKS1B, SERPINH1, and TGFBI may be involved in the lymph node metastasis of HNSCC and reveal the potential to serve as molecular biomarkers in the diagnosis of HNSCC. This study may help to elucidate the molecular mechanisms of the development of lymph node metastasis and facilitate the selection of targets for the treatment and diagnosis of HNSCC.

Dataset Information

Diagnosis of lymph node metastasis in head and neck squamous cell carcinoma using deep learning.

Background

Study design

Methods

Results

Conclusions

Level of evidence

Publications

Diagnosis of lymph node metastasis in head and neck squamous cell carcinoma using deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets