Dataset Information

Magnetic resonance imaging-based prediction models for tumor stage and cervical lymph node metastasis of tongue squamous cell carcinoma.

ABSTRACT:

Purpose

To evaluate the ability of preoperative MRI-based measurements to predict the pathological T (pT) stage and cervical lymph node metastasis (CLNM) via machine learning (ML)-driven models trained in oral tongue squamous cell carcinoma (OTSCC).

Materials and methods

108 patients with a new diagnosis of OTSCC were enrolled. The preoperative MRI study included post-contrast high-resolution T1-weighted images acquired in all patients. MRI-based depth of invasion (DOI) and tumor dimension-together with shape-based and intensity-based features-were extracted from the lesion volume segmentation. The entire dataset was randomly divided into a training set and a validation set, and the performances of different types of ML algorithms were evaluated and compared.

Results

MRI-based DOI and tumor dimension together with several shape-based and intensity-based signatures significantly discriminated the pT stage and LN status. The overall accuracy of the model for predicting the pT stage was 0.86 (95%CI, 0.78-0.92) and 0.81 (0.64-0.91) in the training and validation sets, respectively. There was no improvement in the model performance upon including shape-based and intensity-based features. The model for predicting CLNM based on DOI and tumor dimensions had a fair accuracy of 0.68 (0.57-0.78) and 0.69 (0.51-0.84) in the training and validation sets, respectively. The shape-based and intensity-based signatures have shown potential for improving the model sensitivity, with a comparable accuracy.

Conclusion

MRI-based models driven by ML algorithms could stratify patients with OTSCC according to the pT stages. They had a moderate ability to predict cervical lymph node metastasis.

SUBMITTER: Vidiri A

PROVIDER: S-EPMC10493896 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Magnetic resonance imaging-based prediction models for tumor stage and cervical lymph node metastasis of tongue squamous cell carcinoma.

Vidiri Antonello A Marzi Simona S Piludu Francesca F Lucchese Sonia S Dolcetti Vincenzo V Polito Eleonora E Mazzola Francesco F Marchesi Paolo P Merenda Elisabetta E Sperduti Isabella I Pellini Raul R Covello Renato R

Computational and structural biotechnology journal 20230824

<h4>Purpose</h4>To evaluate the ability of preoperative MRI-based measurements to predict the pathological T (pT) stage and cervical lymph node metastasis (CLNM) via machine learning (ML)-driven models trained in oral tongue squamous cell carcinoma (OTSCC).<h4>Materials and methods</h4>108 patients with a new diagnosis of OTSCC were enrolled. The preoperative MRI study included post-contrast high-resolution T1-weighted images acquired in all patients. MRI-based depth of invasion (DOI) and tumor ...[more]

PMID: 37701020

Similar Datasets

Project description:ObjectiveMET positivity is independently associated with survival in oral squamous cell carcinoma (OSCC). Since MET is a known orchestrator of invasive tumor growth, we investigated its association with LNM in early oral tongue squamous cell carcinoma (OTSCC). As it is recommended by the NCCN to use tumor depth of invasion (DOI) in making decisions on elective neck dissection (END), the results obtained for MET positivity were aligned with those for DOI > 4 mm. The cutoff value used in our institution.MethodsTumor samples from patients who underwent primary tumor resection and neck dissection between 1995 and 2013, were collected from the archives of the Leiden and Erasmus University Medical Center. Immunohistochemistry with D1C2 was performed to identify MET negative (< 10% uniform positivity) and MET positive (≥ 10% uniform positivity) cancers. ROC curve analysis and the Chi-squared test were used to investigate the association of MET positivity with LNM (pN+ and occult). Binary logistic regression was used to investigate the association of MET positivity with LNM.ResultsForty-five (44.1%) of the 102 cancers were MET positive. Ninety were cN0 of which 20 were pN+ (occult metastasis). The remaining 12 cancers were cN+, of which 10 were proven pN+ and 2 were pN0. MET positivity was associated with LNM with a positive predictive value (PPV) of 44.4% and a negative predictive value (NPV) of 82.5% for pN+. For the occult group, the PPV was 36.8% and the NPV was 88.5%. Regression analysis showed that MET positivity is associated with pN+ and occult LNM (p-value < 0.05).ConclusionMET positivity is significantly associated with LNM in early OTSCC, outperforming DOI. The added value of MET positivity could be in the preoperative setting when END is being considered during the initial surgery. For cases with DOI ≤ 4 mm, MET positivity could aid in the clinical decision whether regular follow-up, watchful waiting, or END is more appropriate. Realizing that these preliminary results need to be independently validated in a larger patient cohort, we believe that MET positivity could be of added value in the decision making on END in early OTSCC.

Project description:BackgroundLymph node metastasis is an important factor affecting the treatment and prognosis of patients with cervical cancer. However, the comparison of different algorithms and features to predict lymph node metastasis is not well understood. This study aimed to construct a non-invasive model for predicting lymph node metastasis in patients with cervical cancer based on clinical features combined with the radiomic features of magnetic resonance imaging (MRI) images.MethodsA total of 180 cervical cancer patients were divided into the training set (n = 126) and testing set (n = 54). In this cross-sectional study, radiomic features of MRI images and clinical features of patients were collected. The least absolute shrinkage and selection operator (LASSO) regression was used to filter the features. Seven machine learning methods, including eXtreme Gradient Boosting (XGBoost), Logistic Regression, Multinomial Naive Bayes (MNB), Support Vector Machine (SVM), Decision Tree, Random Forest, and Gradient Boosting Decision Tree (GBDT) are used to build the models. Receiver operating characteristics (ROC) curve and area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the performance of the models.ResultsOf these 180 patients, 49 (27.22%) patients had lymph node metastases. Five of the 122 radiomic features and 3 clinical features were used to build predictive models. Compared with other models, the MNB model was the most robust, with its AUC, specificity, and accuracy on the testing set of 0.745 (95%CI: 0.740-0.750), 0.900 (95%CI: 0.807-0.993), and 0.778 (95%CI: 0.667-0.889), respectively. Furthermore, the AUCs of the MNB models with clinical features only, radiomic features only, and combined features were 0.698 (95%CI: 0.692-0.704), 0.632 (95%CI: 0.627-0.637), and 0.745 (95%CI: 0.740-0.750), respectively.ConclusionThe MNB model, which combines the radiomic features of MRI images with the clinical features of the patient, can be used as a non-invasive tool for the preoperative assessment of lymph node metastasis.

Project description:BackgroundAdequate safe margin in tongue cancer radical surgery is one of the most important prognostic factors. However, the role of peritumoral tissues in predicting lymph node metastasis (LNM) and prognosis using radiomics analysis remains unclear.PurposeTo investigate whether magnetic resonance imaging (MRI)-based radiomics analysis with peritumoral extensions contributes toward the prediction of LNM and prognosis in tongue cancer.Study typeRetrospective.PopulationTwo hundred and thirty-six patients (38.56% female) with tongue cancer (training set, N = 157; testing set, N = 79; 37.58% and 40.51% female for each).Field strength/sequence1.5 T; T2-weighted turbo spin-echo images.AssessmentRadiomics models (Rprim , Rprim+3 , Rprim+5 , Rprim+10 , Rprim+15 ) were developed with features extracted from the primary tumor without or with peritumoral extensions (3, 5, 10, and 15 mm, respectively). Clinicopathological characteristics selected from univariate analysis, including MRI-reported LN status, radiological extrinsic lingual muscle invasion, and pathological depth of invasion (DOI) were further incorporated into radiomics models to develop combined radiomics models (CRprim , CRprim+3 , CRprim+5 , CRprim+10 , CRprim+15 ). Finally, the model performance was validated in the testing set. DOI was measured from the adjacent normal mucosa to the deepest point of tumor invasion.Statistical testsChi-square test, regression analysis, receiver operating characteristic curve (ROC) analysis, decision analysis, spearman correlation analysis. The Delong test was used to compare area under the ROC (AUC). P < 0.05 was considered statistically significant.ResultsOf all the models, the CRprim+10 reached the highest AUC of 0.995 in the training set and 0.872 in the testing set. Radiomics features were significantly correlated with pathological DOI (correlation coefficients, -0.157 to -0.336). The CRprim+10 was an independent indicator for poor disease-free survival (hazard ratio, 5.250) and overall survival (hazard ratio, 17.464) in the testing set.Data conclusionRadiomics analysis with a 10-mm peritumoral extension had excellent power to predict LNM and prognosis in tongue cancer.

Dataset Information

Magnetic resonance imaging-based prediction models for tumor stage and cervical lymph node metastasis of tongue squamous cell carcinoma.

Purpose

Materials and methods

Results

Conclusion

Publications

Magnetic resonance imaging-based prediction models for tumor stage and cervical lymph node metastasis of tongue squamous cell carcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets