With the rapid development of new technologies, including artificial intelligence and genome sequencing, radiogenomics has emerged as a state-of-the-art science in the field of individualized medicine. Radiogenomics combines a large volume of quantitative data extracted from medical images with individual genomic phenotypes and constructs a prediction model through deep learning to stratify patients, guide therapeutic strategies, and evaluate clinical outcomes. Recent studies of various types of tumors demonstrate the predictive value of radiogenomics. And some of the issues in the radiogenomic analysis and the solutions from prior works are presented. Although the workflow criteria and international agreed guidelines for statistical methods need to be confirmed, radiogenomics represents a repeatable and cost-effective approach for the detection of continuous changes and is a promising surrogate for invasive interventions. Therefore, radiogenomics could facilitate computer-aided diagnosis, treatment, and prediction of the prognosis in patients with tumors in the routine clinical setting. Here, we summarize the integrated process of radiogenomics and introduce the crucial strategies and statistical algorithms involved in current studies.

Purpose: While there are no clear indications of whether central lymph node dissection is necessary in patients with T1-T2, non-invasive, clinically uninvolved central neck lymph nodes papillary thyroid carcinoma (PTC), this study seeks to develop and validate models for predicting the risk of central lymph node metastasis (CLNM) in these patients based on machine learning algorithms.Methods: This is a retrospective study comprising 1,271 patients with T1-T2 stage, non-invasive, and clinically node negative (cN0) PTC who underwent surgery at the Department of Endocrine and Breast Surgery of The First Affiliated Hospital of Chongqing Medical University from February 1, 2016, to December 31, 2018. We applied six machine learning (ML) algorithms, including Logistic Regression (LR), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Decision Tree (DT), and Neural Network (NNET), coupled with preoperative clinical characteristics and intraoperative information to develop prediction models for CLNM. Among all the samples, 70% were randomly selected to train the models while the remaining 30% were used for validation. Indices like the area under the receiver operating characteristic (AUROC), sensitivity, specificity, and accuracy were calculated to test the models' performance.Results: The results showed that ~51.3% (652 out of 1,271) of the patients had pN1 disease. In multivariate logistic regression analyses, gender, tumor size and location, multifocality, age, and Delphian lymph node status were all independent predictors of CLNM. In predicting CLNM, six ML algorithms posted AUROC of 0.70–0.75, with the extreme gradient boosting (XGBoost) model standing out, registering 0.75. Thus, we employed the best-performing ML algorithm model and uploaded the results to a self-made online risk calculator to estimate an individual's probability of CLNM (https://jin63.shinyapps.io/ML_CLNM/).Conclusions: With the incorporation of preoperative and intraoperative risk factors, ML algorithms can achieve acceptable prediction of CLNM with Xgboost model performing the best. Our online risk calculator based on ML algorithm may help determine the optimal extent of initial surgical treatment for patients with T1-T2 stage, non-invasive, and clinically node negative PTC.

BackgroundMutations of BRAFV600E and TERT promoters are associated with thyroid cancer development. This study further investigated association of these mutations with clinicopathological characteristics from patients with papillary thyroid carcinoma (PTC).MethodsTumor tissues from 342 PTC patients were obtained for DNA extraction and polymerase chain reaction amplification to detect the BRAFV600E mutation using amplification-refractory mutation system-polymerase chain reaction. TERT promoter mutations were assessed using Sanger DNA sequencing. The association of these gene mutations with clinicopathological characteristics was then statistically analyzed.ResultsTwo hundred and seventy of 342 (78.9%) PTC patients harbored the BRAFV600E mutation, which was associated with older age male patients. Moreover, TERT promoter mutations occurred in 12 of 342 (3.5 %) PTC patients, all of whom also had the BRAF mutation. One hundred thirty-three patients with papillary thyroid microcarcinoma (PTMC) had no TERT mutations. Statistically, the coexistence of BRAF and TERT promoter mutations were significantly associated with older age, larger tumor size, extrathyroidal extension, and advanced tumor stage, but not with central lymph node metastasis, lateral lymph node metastasis, numbers of lymph node metastasis >5, and numbers of involved/harvested lymph nodes (No. of LNs involved or harvested). The multivariate analyses showed older age (odds ratio [OR], 2.194; 95% CI: 1.117–4.311; p=0.023), larger tumor size (OR, 4.100; 95% CI: 2.257–7.450; p<0.001), and multiplicity (OR, 2.240; 95% CI: 1.309–3.831; p=0.003) were all independent predictors for high prevalence of extrathyroidal extension. However, there was no statistical association with any clinicopathological characteristics except for Hashimoto thyroiditis in PTMC.ConclusionThe current study demonstrated that the coexistence of BRAF and TERT promoter mutations were associated with the PTC aggressiveness, although these mutations were not associated with PTC lymph node metastasis or with PTMC.

BackgroundCervical lymph node metastasis of papillary thyroid carcinoma (PTC) is common. However, whether undergoing prophylactic central lymph node (CLN) dissection or lateral lymph node (LLN) dissections to prevent metastasis is still controversial. This study aimed to retrospectively investigate the risk factors of LLN metastasis in clinical lymph node-negative (cN0) PTC patients.MethodsWe retrospectively studied 783 lymph node-negative (cN0) PTC patients who underwent total thyroidectomy plus CLN dissection and LLN dissection.ResultsThe rates of CLN and LLN metastases were 68.2 and 47.4%, respectively. Large tumor size (> 20 mm) had a fourfold higher risk of LLN metastasis compared with small tumor size (≤ 20 mm; OR = 4.082, 95% CI 2.646–6.289; P = 0.001). Patients with tumor in the upper lobe had ~ 3-fold higher risk of LLN metastasis compared with patients with tumor in other locations (OR = 2.874, 95% CI 1.916–4.310; P = 0.001). Multifocality and extrathyroidal extension indicated a twofold higher risk of LLN metastasis. Having ≥ 2 CLN metastases dramatically increased the risk of LLN metastasis, compared with those with < 2 CLN metastases (OR = 6.536, 95% CI 4.630–9.259; P = 0.001).ConclusionsLarge tumor size (> 20 mm), tumor located in the upper lobe, multifocality, extrathyroidal extension, and ≥ 2 CLN metastases may increase the risk of LLN metastasis in cN0 PTC patients.