Correction: Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy

Multimodal radiomics and nomogram-based prediction of axillary lymph node metastasis in breast cancer: An analysis considering optimal peritumoral region

PURPOSE

To explore the optimal peri-tumoral regions on ultrasound (US) images and investigate the performance of multimodal radiomics for predicting axillary lymph node metastasis (ALNM).

METHODS

This retrospective study included 326 patients (training cohort: n = 162, internal validation cohort: n = 74, external validation cohort: n = 90). Intra-tumoral region of interests (ROIs) were delineated on US and digital mammography (DM) images. Peri-tumoral ROI (PTR) on US images were gained by dilating actual 0.5, 1.0, 1.5, 2.0, 2.5, 3.0 and 3.5 mm radius surrounding the tumor. Support vector machine (SVM) method was used to calculate the importance of radiomics features and to pick the 10 most important. Recursive feature elimination-SVM was used to evaluate the efficacy of models with different feature numbers used.

RESULTS

The PTR0.5mm yielded a maximum AUC of 0.802 (95% confidence interval (CI): 0.676-0.901) within the validation cohort using SVM classifier. The multimodal radiomics (intra-tumoral US and DM and US-based PTR0.5mm radiomics model) achieved the highest predictive ability (AUC = 0.888/0.844/0.835 and 95% CI = 0.829-0.936/0.741-0.929/0.752-0.896 for training/internal validation/external validation cohort, respectively).

CONCLUSION

The PTR0.5mm could be the optimal area for predicting ALNM. A favorable predictive accuracy for predicting ALNM was achieved using multimodal radiomics and its based nomogram.

Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential

The high-throughput extraction of quantitative imaging features from medical images for the purpose of radiomic analysis, i.e., radiomics in a broad sense, is a rapidly developing and emerging research field that has been attracting increasing interest, particularly in multimodality and multi-omics studies. In this context, the quantitative analysis of multidimensional data plays an essential role in assessing the spatio-temporal characteristics of different tissues and organs and their microenvironment. Herein, recent developments in this method, including manually defined features, data acquisition and preprocessing, lesion segmentation, feature extraction, feature selection and dimension reduction, statistical analysis, and model construction, are reviewed. In addition, deep learning-based techniques for automatic segmentation and radiomic analysis are being analyzed to address limitations such as rigorous workflow, manual/semi-automatic lesion annotation, and inadequate feature criteria, and multicenter validation. Furthermore, a summary of the current state-of-the-art applications of this technology in disease diagnosis, treatment response, and prognosis prediction from the perspective of radiology images, multimodality images, histopathology images, and three-dimensional dose distribution data, particularly in oncology, is presented. The potential and value of radiomics in diagnostic and therapeutic strategies are also further analyzed, and for the first time, the advances and challenges associated with dosiomics in radiotherapy are summarized, highlighting the latest progress in radiomics. Finally, a robust framework for radiomic analysis is presented and challenges and recommendations for future development are discussed, including but not limited to the factors that affect model stability (medical big data and multitype data and expert knowledge in medical), limitations of data-driven processes (reproducibility and interpretability of studies, different treatment alternatives for various institutions, and prospective researches and clinical trials), and thoughts on future directions (the capability to achieve clinical applications and open platform for radiomics analysis).

Exploratory ensemble interpretable model for predicting local failure in head and neck cancer: the additive benefit of CT and intra-treatment cone-beam computed tomography features

BACKGROUND

Local failure (LF) following chemoradiation (CRT) for head and neck cancer is associated with poor overall survival. If machine learning techniques could stratify patients at risk of treatment failure based on baseline and intra-treatment imaging, such a model could facilitate response-adapted approaches to escalate, de-escalate, or switch therapy.

METHODS

A 1:2 retrospective case control cohort of patients treated at a single institution with definitive radiotherapy for head and neck cancer who failed locally, in-field at a primary or nodal structure were included. Radiomic features were extracted from baseline CT and CBCT scans at fractions 1 and 21 (delta) of radiotherapy with PyRadiomics and were selected for by: reproducibility (intra-class correlation coefficients ≥0.95), redundancy [maximum relevance and minimum redundancy (mRMR)], and informativeness [recursive feature elimination (RFE)]. Separate models predicting LF of primaries or nodes were created using the explainable boosting machine (EBM) classifier with 5-fold cross-validation for (I) clinical only, (II) radiomic only (CT1 and delta features), and (III) fused models (clinical + radiomic). Twenty-five iterations were performed, and predicted scores were averaged with a parallel ensemble design. Receiver operating characteristic curves were compared between models with paired-samples t-tests.

RESULTS

The fused ensemble model for primaries (using clinical, CT1, and delta features) achieved an AUC of 0.871 with a sensitivity of 78.3% and specificity of 90.9% at the maximum Youden J statistic. The fused ensemble model trended towards improvement when compared to the clinical only ensemble model (AUC =0.788, P=0.134) but reached significance when compared to the radiomic ensemble model (AUC =0.770, P=0.017). The fused ensemble model for nodes achieved an AUC of 0.910 with a sensitivity of 100.0% and specificity of 68.0%, which also trended towards improvement when compared to the clinical model (AUC =0.865, P=0.080).

CONCLUSIONS

The fused ensemble EBM model achieved high discriminatory ability at predicting LF for head and neck cancer in independent primary and nodal structures. Although an additive benefit of delta radiomics over clinical factors could not be proven, the results trended towards improvement with the fused ensemble model, which are promising and worthy of prospective investigation in a larger cohort.

Prediction of Locoregional Recurrence-Free Survival of Oesophageal Squamous Cell Carcinoma After Chemoradiotherapy Based on an Enhanced CT-Based Radiomics Model

BACKGROUND AND PURPOSE

Chemoradiotherapy is the standard treatment for moderate and advanced oesophageal cancer. The aim of this study was to establish a predictive model based on enhanced computed tomography examination, and to evaluate its clinical value for detecting locoregional recurrence-free survival (LRFS) in cases of oesophageal squamous cell carcinoma after radiotherapy.

MATERIALS AND METHODS

In total, 218 patients with pathologically diagnosed oesophageal squamous cell carcinoma who received radical chemoradiotherapy from July 2016 to December 2017 were collected in this study. Patients were randomly divided into either a training group (n=153) or a validation group (n=65) in a 7:3 ratio. Clinical patient information was then recorded. The enhanced computed tomography scan images of the patients were imported into 3D-slicer software (version 4.8.1), and the radiomic features were extracted by the Python programme package. In the training group, the dimensionality reduction of the radiomic features was implemented by Lasso regression, and then a radiological label, the model of predicting LRFS, was established and evaluated. To achieve a better prediction performance, the radiological label was combined with clinical risk factor information to construct a radiomics nomogram. A receiver operating characteristic curve was used to evaluate the efficacy of different models. Calibration curves were used to assess the consistency between the predicted and observed recurrence risk, and the Hosmer-Lemeshow method was used to test model fitness. The C-index evaluated the discriminating ability of the prediction model. Decision curve analysis was used to determine the clinical value of the constructed prediction model.

RESULTS

Of the 218 patients followed up in this study, 44 patients (28.8%) in the training group and 21 patients (32.3%) in the validation group experienced recurrence. There was no difference in LRFS between the two groups (χ2 = 0.525, P=0.405). Lasso regression was used in the training group to select six significant radiomic features. The radiological label established using these six features had a satisfactory prediction performance. The C-index was 0.716 (95% CI: 0.645-0.787) in the training group and 0.718 (95% CI: 0.612-0.825) in the validation group. The radiomics nomogram, which included the radiological label and clinical risk factors, achieved a better prediction than the radiological label alone. The C-index was 0.742 (95% CI: 0.674-0.810) in the training group and 0.715 (95% CI: 0.609-0.820) in the validation group. The results of the calibration curve and decision curve analyses indicated that the radiomics nomogram was superior in predicting LRFS of oesophageal carcinoma after radiotherapy.

CONCLUSIONS

A radiological label was successfully established to predict the LRFS of oesophageal squamous cell carcinoma after radiotherapy. The radiomics nomogram was complementary to the clinical prognostic features and could improve the prediction of the LRFS after radiotherapy for oesophageal cancer.