Radiomics-Based Analysis in the Prediction of Occult Lymph Node Metastases in Patients with Oral Cancer: A Systematic Review

MRI-based deep learning and radiomics for prediction of occult cervical lymph node metastasis and prognosis in early-stage oral and oropharyngeal squamous cell carcinoma: a diagnostic study

INTRODUCTION

The incidence of occult cervical lymph node metastases (OCLNM) is reported to be 20-30% in early-stage oral cancer and oropharyngeal cancer. There is a lack of an accurate diagnostic method to predict occult lymph node metastasis and to help surgeons make precise treatment decisions.

AIM

To construct and evaluate a preoperative diagnostic method to predict OCLNM in early-stage oral and oropharyngeal squamous cell carcinoma (OC and OP SCC) based on deep learning features (DLFs) and radiomics features.

METHODS

A total of 319 patients diagnosed with early-stage OC or OP SCC were retrospectively enrolled and divided into training, test and external validation sets. Traditional radiomics features and DLFs were extracted from their MRI images. The least absolute shrinkage and selection operator (LASSO) analysis was employed to identify the most valuable features. Prediction models for OCLNM were developed using radiomics features and DLFs. The effectiveness of the models and their clinical applicability were evaluated using the area under the curve (AUC), decision curve analysis (DCA), and survival analysis.

RESULTS

Seventeen prediction models were constructed. The Resnet50 deep learning (DL) model based on the combination of radiomics and DL features achieves the optimal performance, with AUC values of 0.928 (95% CI: 0.881-0.975), 0.878 (95% CI: 0.766-0.990), 0.796 (95% CI: 0.666-0.927), and 0.834 (95% CI: 0.721-0.947) in the training, test, external validation set1, and external validation set2, respectively. Moreover, the Resnet50 model has great prediction value of prognosis in patients with early-stage OC and OP SCC.

CONCLUSION

The proposed MRI-based Resnet50 DL model demonstrated high capability in diagnosis of OCLNM and prognosis prediction in the early-stage OC and OP SCC. The Resnet50 model could help refine the clinical diagnosis and treatment of the early-stage OC and OP SCC.

Predicting nodal metastasis progression of oral tongue cancer using a hidden Markov model in MRI

Objectives

The presence of occult nodal metastases in patients with oral tongue squamous cell carcinomas (OTSCCs) has implications for treatment. More than 30% of patients will have occult nodal metastases, yet a considerable number of patients undergo unnecessary invasive neck dissection to confirm nodal status. In this work, we propose a probabilistic model for lymphatic metastatic spread that can quantify the risk of microscopic involvement at the lymph node level (LNL) given the location of macroscopic metastases and the tumor stage using the MRI method.

Materials and methods

A total of 108 patients of OTSCCs were included in the study. A hidden Markov model (HMM) was used to compute the probabilities of transitions between states over time based on MRI. Learning of the transition probabilities was performed via Markov chain Monte Carlo sampling and was based on a dataset of OTSCC patients for whom involvement of individual LNLs was reported.

Results

Our model found that the most common involvement was that of level I and level II, corresponding to a high probability of 𝑝b1 = 0.39 ± 0.05, 𝑝b2 = 0.53 ± 0.09; lymph node level I had metastasis, and the probability of metastasis in lymph node II was high (93.79%); lymph node level II had metastasis, and the probability of metastasis in lymph node III was small (7.88%). Lymph nodes progress faster in the early stage and slower in the late stage.

Conclusion

An HMM can produce an algorithm that is able to predict nodal metastasis evolution in patients with OTSCCs by analyzing the macroscopic metastases observed in the upstream levels, and tumor category.

Comparing the Diagnostic Accuracy of Ultrasonography, CT, MRI, and PET/CT in Cervical Lymph Node Metastasis of Oral Squamous Cell Carcinoma

(1) Background: In oral cancer staging, ultrasonography (US), computed tomography (CT), magnetic resonance imaging (MRI), and 2-deoxy-2-[fluorine-18]fluoro-D-glucose (FDG) with positron emission tomography/computed tomography (PET/CT) are routinely used in clinical practice. The present study is a retrospective examination of the diagnostic accuracy of cervical lymph node metastasis using US, CT, MRI, and PET/CT, with histopathological diagnosis as a reference, to compare the different diagnostic imaging modalities. (2) Methods: The participants included 16 patients with oral squamous cell carcinoma who underwent US-, CT-, MRI-, and PET/CT-based preoperative diagnostic imaging and simultaneous primary lesion resection and neck dissection, including 82 level regions and 424 lymph nodes. We compared the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of each imaging modality based on the imaging results and the pathology results of metastasis. (3) Results: Of the four diagnostic imaging modalities, PET/CT exhibited the highest sensitivity but the lowest specificity and accuracy. US, CT, and MRI had high specificities. Comparing each level region and lymph node showed that differences were observed in PET/CT. (4) Conclusions: PET/CT to diagnose lymph node metastasis requires a comprehensive evaluation because it produces more false positives than other diagnostic imaging modalities. Using US, CT, and MRI, which have excellent spatial resolution, improves diagnostic accuracy at the lymph node level.

A Radiomics Approach to Identify Immunologically Active Tumor in Patients with Head and Neck Squamous Cell Carcinomas

BACKGROUND

We recently developed a gene-expression-based HOT score to identify the hot/cold phenotype of head and neck squamous cell carcinomas (HNSCCs), which is associated with the response to immunotherapy. Our goal was to determine whether radiomic profiling from computed tomography (CT) scans can distinguish hot and cold HNSCC.

METHOD

We included 113 patients from The Cancer Genome Atlas (TCGA) and 20 patients from the Groupe Hospitalier Pitié-Salpêtrière (GHPS) with HNSCC, all with available pre-treatment CT scans. The hot/cold phenotype was computed for all patients using the HOT score. The IBEX software (version 4.11.9, accessed on 30 march 2020) was used to extract radiomic features from the delineated tumor region in both datasets, and the intraclass correlation coefficient (ICC) was computed to select robust features. Machine learning classifier models were trained and tested in the TCGA dataset and validated using the area under the receiver operator characteristic curve (AUC) in the GHPS cohort.

RESULTS

A total of 144 radiomic features with an ICC >0.9 was selected. An XGBoost model including these selected features showed the best performance prediction of the hot/cold phenotype with AUC = 0.86 in the GHPS validation dataset.

CONCLUSIONS AND RELEVANCE

We identified a relevant radiomic model to capture the overall hot/cold phenotype of HNSCC. This non-invasive approach could help with the identification of patients with HNSCC who may benefit from immunotherapy.