Application of predictive model based on CT radiomics and machine learning in diagnosis for occult locally advanced esophageal squamous cell carcinoma before treatment: A two-center study

Hightlights

• •

  radiomics and machine learning enhance the precision of clinical staging for esophageal squamous cell carcinoma, thereby offering a more effective and non-invasive approach for patients.

• •

  The multilayer perceptron (MLP) demonstrates exceptional accuracy in the training set and exhibits outstanding performance in external validation.

• •

  The model also showed high accuracy for subgroup of patients (diagnosed by clinicians as cT _1–2N ₀M ₀), indicating better clinical applicability.

Abstract

Purpose

Development and validation of a radiomics model for predicting occult locally advanced esophageal squamous cell carcinoma (LA-ESCC) on computed tomography (CT) radiomic features before implementation of treatment.

Methods

The study retrospectively collected 574 patients with esophageal squamous cell carcinoma (ESCC) from two medical centers, which were divided into three cohorts for training, internal and external validation. After delineating volume of interest (VOI), radiomics features were extracted and subjected to feature selection using three robust methods. Subsequently, 10 machine learning models were constructed, among which the optimal model was utilized to establish a radiomics signature. Furthermore, a predictive nomogram incorporating both clinical and radiomics signatures was developed. The performance of these models was evaluated through receiver operating characteristic curves, calibration curves, decision curve analysis as well as measures including accuracy, sensitivity, and specificity.

Results

A total of 19 radiomics features were selected. The multilayer perceptron (MLP), which was found to be optimal, achieved an AUC of 0.919, 0.864 and 0.882 in the training, internal and external validation cohorts, respectively. Similarly, MLP showed good accuracy in distinguish occult LA-ESCC in subgroup of cT _1–2N ₀M ₀ diagnosed by clinicians with 0.803 and 0.789 in two validation cohorts respectively. By incorporating the radiomics signature with clinical signature, a predictive nomogram demonstrated superior prediction performance with an AUC of 0.877 and accuracy of 0.85 in external validation cohort.

Conclusion

The radiomics and machine learning model can offers improved accuracy in prediction of occult LA-ESCC, providing valuable assistance to clinicians when choosing treatment plans.