Characterisation of CT detected ovarian masses is challenging with overlapping imaging features, unreliable biomarker or clinical presentation. We proposed a two-staged CT-based radiomics model to identify early-stage ovarian carcinoma (ES-OC) and sub-classify different types of benign ovarian masses (BOM). Patients with histologically confirmed BOM or ES-OC (FIGO I-II) were retrospectively recruited from 5 centres. Radiomics features were derived from CT images using PyRadiomics (v3.0.1), which intrinsically resampled volumes to isotropic 1 mm³ voxels. To reduce feature redundancy, features with high correlation (Spearman’s ρ ≥ 0.85) were excluded. Two-staged feature selection was applied. First, elastic-net regression with repeated 5-fold stratified cross-validation (100 iterations) was performed to identify highly repeatable features, followed by Mann-Whitney U testing for statistical significance. Second, Boruta algorithm with Random Forest (RF) estimator was employed over 500 iterations to robustly select features by comparing their importance to randomized shadow features. Several machine learning (ML) classifiers were evaluated using stratified 10‑fold GridSearch cross-validation with area under the curve (AUC) as tuning metric. The optimal model from each stage with highest cross-validated AUC was then evaluated on the respective test set. The AUC, calibration plot, and decision curve analysis (DCA) were employed to assess the performance and clinical utility of models. The study enrolled 483 patients with 529 lesions (ES-OC: 192 patients, 192 lesions; BOM: 291 patients, 337 lesions). In the first-stage, logistic regression (LR) algorithm was selected with high sensitivity (0.870), moderate specificity (0.719) and high AUC (0.859) in the test set. In the second-stage, support vector machines (SVM) had high diagnostic accuracy with sensitivity 0.750, specificity 0.839 and AUC 0.918. DCA identified the highest benefit at 0.20 risk threshold probability in determining ES-OC. The two-staged CT-based radiomics model incorporating LR and SVM algorithms had high diagnostic efficiency in characterising ES-OC and BOM, potentially in triaging disease and personalising care.

Purpose To develop and validate a structured CT-based grading system for imaging-identified extranodal extension (iENE) and assess its diagnostic accuracy and prognostic significance in esophageal squamous cell carcinoma. Materials and Methods In this retrospective multicenter study, preoperative CT examinations in patients with esophageal squamous cell carcinoma treated at four tertiary hospitals between January 2017 and December 2023 were reviewed. CT features evaluated included indistinct nodal margins, coalescent nodal mass, invasive encasement, halo sign, and black ring sign. Radiologic-pathologic node-by-node correlation was performed in the development cohort to assess diagnostic performance. The validation cohort consisted of an independent, multicenter patient population and was used to evaluate the prognostic value of iENE at the patient level. Logistic regression and receiver operating characteristic analyses were used to assess diagnostic performance, while overall survival was evaluated using Kaplan-Meier and Cox regression analyses. Results A total of 912 patients with esophageal squamous cell carcinoma were included, with 95 patients (mean age, 62 years ± 8; 75 male patients) in the development cohort and 817 patients (mean age, 62 years ± 9; 619 male patients) in the validation cohort. Coalescent nodal mass, invasive encasement, and black ring sign at CT demonstrated 100% specificity for pathologic ENE. An iENE score of 2 or higher achieved optimal diagnostic performance (sensitivity, 82% [36 of 44]; specificity, 90% [250 of 279]; accuracy, 89% [286 of 323]). Patients with high-risk iENE (score ≥2) had worse overall survival than those with low-risk disease in both the development cohort (hazard ratio, 8.83; 95% CI: 3.30, 23.64; P < .001) and validation cohort (hazard ratio range, 26.02-39.48; all P < .001). On multivariable analysis, iENE remained an independent prognostic factor (adjusted hazard ratio, 8.72; 95% CI: 6.88, 11.05; P < .001). Conclusion The CT-based iENE grading system demonstrated high diagnostic performance and provided independent prognostic stratification in esophageal squamous cell carcinoma.

Introduction: An accurate and reliable prognostic model for Nasal Extranodal Natural Killer/T-cell Lymphoma (ENKTL) is critical for survival outcomes and personalized therapy. Currently, there is no Magnetic Resonance Imaging (MRI)- based radiomics analysis in the prognosis model for nasal ENKTL patients. Objective: We aim to explore the value of MRI-based radiomics signature in the prognosis of patients with nasal ENKTL. Methods: A total of 159 nasal ENKTL patients were enrolled and divided into a training cohort (n=81) and a validation cohort (n=78) randomly. Radiomics features from pretreatment MRI examination were extracted, respectively. Then two-sample t-test and Least Absolute Shrinkage and Selection Operator (LASSO) regression were used to select the radiomics signatures and establish the Rad-score. Univariate and multivariate Cox proportional hazards regression models were used to investigate the prognostic value of baseline clinical features and establish clinical models. A radiomics nomogram based on the Rad-score and clinical features was constructed to predict Overall Survival (OS). The predictive efficacy of the three models was evaluated in two cohorts. Results: A total of 1,345 features were extracted from T2-weighted (T2-w) and Contrast-enhanced T1-weighted (CET1-w) images, respectively, and 1,037 features with Intraclass Correlation Coefficient (ICC) >0.7 were selected. Ultimately, 20 features were chosen to construct the Rad-score, which showed a significant association with OS. The C-indexes of the Rad-score were 0.733 (95% confidence interval [CI]: 0.645 to 0.816) and 0.824 (95% CI: 0.766-0.882), respectively, in training and validation cohorts. Through the univariate and multivariate analyses, three independent risk factors for OS were identified: Rad-score (HR: 10.962, 95% CI: 3.417-35.167, P <0.001), lactate dehydrogenase (LDH) level (HR: 3.009, 95% CI: 1.128-8.510, P = 0.028) and distant lymph-node involvement (HR: 2.966, 95% CI: 1.015-8.664, P = 0.047). Patients with distal lymph node involvement and LDH level before treatment were included in the clinical model, which achieved a C-index of 0.707 (95% CI: 0.600–0.814) in the training cohort and 0.635 (95% CI: 0.527–0.743) in the validation cohort. We integrated the Rad-score and clinical variables to establish a radiomics nomogram, which exhibited a satisfactory prediction performance with the C-indexes of 0.849(95% CI: 0.781-0.917) and 0.931(95% CI: 0.882-0.980) in two cohorts, respectively. The radiomics nomogram was more accurate in predicting OS in patients with nasal ENKTL than the other two models. Based on the radiomics nomogram, patients were categorized into low-risk and high-risk groups in two cohorts (P all < 0.05). The high-risk group defined by this nomogram exhibited a shorter OS. Conclusion: The Rad-score was significantly correlated with OS for nasal ENKTL patients. Moreover, the MRI-based radiomics nomogram could be used for risk stratification and might guide individual treatment decisions.

Platinum resistance carries poor prognosis in epithelial ovarian carcinoma (EOC). This study aimed to assess the value of radiomics model based on contrast-enhanced CT (ceCT) in predicting response to platinum-based chemotherapy in EOC. Patients with histologically confirmed EOC and pre-treatment ceCT were retrospectively recruited from 5 centres. All patients underwent standard platinum-based chemotherapy and optimal cytoreduction. Platinum sensitivity was determined by whether it recurred within six months after platinum-based chemotherapy. The whole tumour volume was manually segmented on the baseline ceCT. Radiomics features were extracted using the open-source package PyRadiomics (version 3.0.1). Patients from centres A-C were randomly divided into training and internal validation sets in 4:1 ratio. Patients from the centres D and E were assigned as independent external validation sets. Spearman’s rank correlation followed by 5-fold stratified cross validation (SCV) elastic net repeated for 100 times, and Mann-Whitney U test were deployed for feature reduction and selection. Adaptive synthetic sampling was applied to minimize class biases. Extra Trees classifier across 10-fold SCV was used for model building. The area under curve (AUC), calibration curve assessment, and decision curve analysis (DCA) were deployed to evaluate model performance and translational clinical utility. Seven hundred and three EOC patients (51.6 ± 9.3 years) were recruited. The training data (n = 608) yielded the following classification metrics: AUC (0.917), sensitivity (83.9

PURPOSE:Patients with residual nasopharyngeal carcinoma after receiving standard-of-care treatment have poor prognoses. In this trial, we aimed to assess the efficacy and safety of capecitabine maintenance therapy in patients with residual nasopharyngeal carcinoma. PATIENTS AND METHODS:This open-label, single-arm, phase II trial was conducted at Sun Yat-sen University Cancer Center. We recruited patients of 18 to 70 years of age with an Eastern Cooperative Oncology Group performance status score of 0 to 1, histopathologically or cytologically confirmed nasopharyngeal carcinoma (without distant metastasis), who had residual disease after receiving definitive treatment. Patients received 1 year of capecitabine maintenance therapy. The primary endpoint was 2-year progression-free survival. RESULTS:Between January 1, 2019, and December 30, 2022, 111 patients were recruited and commenced capecitabine maintenance therapy for 1 year. After a median follow-up duration of 34.8 months (IQR = 30.5-45.2), progression-free survival was 92% at 1 year, 86% at 2 years, and 81% at 3 years. Adverse events were reported in 97.3% of patients. Hand-foot syndrome was the most common adverse event (59.5%). In addition, 28.7% of patients experienced grade 3 treatment-related adverse events, the most common of which was hand-foot syndrome (7.2%); no grade 4 or 5 adverse events were recorded. A total of 72.1% of patients received the full dosage of capecitabine, and 76.6% of patients completed the 1-year capecitabine maintenance therapy. CONCLUSIONS:The antitumor efficacy of capecitabine maintenance therapy is promising, and the safety profile is manageable in patients with residual nasopharyngeal carcinoma after receiving standard-of-care treatment.

Supplementary Table 8. Compliance to treatment.

Rationale and Objectives: Accurate prediction of local recurrence or distant metastasis is critical for developing individualized therapies for locally advanced rectal cancer (LARC) patients after standard therapy. This study aims to develop and validate a multiparameter MRI-based radiomics signature (RS) for prognostic prediction in LARC patients receiving neoadjuvant chemoradiotherapy (nCRT) and total mesorectal excision (TME) and to explore the ability of RS for personalized survival risk stratification. Materials and Methods: In this multi-center study, 454 patients who received nCRT and TME and completed 3 years of follow-up participated. RS was constructed for prognostic prediction based on features extracted from pretreatment multiparameter MRI in a training cohort (TC; n = 298), which was tested in an internal validation cohort (IVC; n = 75) and further validated in an independent external validation cohort (EVC; n = 81). Furthermore, the ability of RS for personalized survival risk stratification was explored using the Kaplan-Meier survival curves. Results: The RS model showed satisfactory accuracy for prognostic prediction with AUCs of 0.83, 0.81 and 0.82 in the TC, IVC and EVC, respectively. In addition, RS helped to refine risk stratification for LARC patients on the basis of significantly different 3-year disease-free survival rates, independent of their pathological stage, pre-surgery CEA, and even treatment modality. Conclusions: The proposed RS can be used not only to predict local recurrence or distant metastasis but also to serve as an effective postoperative survival risk stratification tool for clinicians to facilitate decision-making for LARC patients receiving standard treatment.

Background:To develop and validate an innovative predictive model that integrates multisequence magnetic resonance (MR) radiomics, deep learning features, and clinical indicators to accurately predict the recurrence of hepatocellular carcinoma (HCC) after thermal ablation. Methods:This retrospective multicenter cohort study enrolled patients who were diagnosed with HCC and treated via thermal ablation. We extracted radiomic features from multisequence 3T MR images, analyzed these images using a 3D convolutional neural network (3D CNN), and incorporated clinical data into the model. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Results:The study included 535 patients from three hospitals, comprising 462 males and 43 females. The RDC model, which stands for the Radiomics-Deep Learning-Clinical data model, demonstrated high predictive accuracy, achieving AUCs of 0.794 in the training set, 0.777 in the validation set, and 0.787 in the test set. Statistical analysis confirmed the model's robustness and the significant contribution of the integrated features to its predictive capabilities. Conclusion:The RDC model effectively predicts HCC recurrence after thermal ablation by synergistically combining advanced imaging analysis and clinical parameters. This study highlights the potential of such integrative approaches to enhance prognostic assessments in HCC patients and offers a promising tool for clinical decision-making.

Patients with residual nasopharyngeal carcinoma after receiving definitive treatment have poor prognoses. Although immune checkpoint therapies have achieved breakthroughs for treating recurrent and metastatic nasopharyngeal carcinoma, none of these strategies have been assessed for treating residual nasopharyngeal carcinoma. In this single-arm, phase 2 trial, we aimed to evaluate the antitumor efficacy and safety of toripalimab (anti-PD1 antibody) plus capecitabine in patients with residual nasopharyngeal carcinoma after definitive treatment (ChiCTR1900023710). Primary endpoint of this trial was the objective response rate assessed according to RECIST (version 1.1). Secondary endpoints included complete response rate, disease control rate, duration of response, progression-free survival, safety profile, and treatment compliance. Between June 1, 2020, and May 31, 2021, 23 patients were recruited and received six cycles of toripalimab plus capecitabine every 3 weeks. In efficacy analyses, 13 patients (56.5%) had complete response, and 9 patients (39.1%) had partial response, with an objective response rate of 95.7% (95% CI 78.1-99.9). The trial met its prespecified primary endpoint. In safety analyses, 21 of (91.3%) 23 patients had treatment-related adverse events. The most frequently reported adverse event was hand-foot syndrome (11 patients [47.8%]). The most common grade 3 adverse event was hand-foot syndrome (two patients [8.7%]). No grades 4-5 treatment-related adverse events were recorded. This phase 2 trial shows that combining toripalimab with capecitabine has promising antitumour activity and a manageable safety profile for patients with residual nasopharyngeal carcinoma.

Radiomic and deep learning studies based on magnetic resonance imaging (MRI) of liver tumor are gradually increasing. Manual segmentation of normal hepatic tissue and tumor exhibits limitations. 105 patients diagnosed with hepatocellular carcinoma were retrospectively studied between Jan 2015 and Dec 2020. The patients were divided into three sets: training (n = 83), validation (n = 11), and internal testing (n = 11). Additionally, 9 cases were included from the Cancer Imaging Archive as the external test set. Using the arterial phase and T2WI sequences, expert radiologists manually delineated all images. Using deep learning, liver tumors and liver segments were automatically segmented. A preliminary liver segmentation was performed using the UNet + + network, and the segmented liver mask was re-input as the input end into the UNet + + network to segment liver tumors. The false positivity rate was reduced using a threshold value in the liver tumor segmentation. To evaluate the segmentation results, we calculated the Dice similarity coefficient (DSC), average false positivity rate (AFPR), and delineation time. The average DSC of the liver in the validation and internal testing sets was 0.91 and 0.92, respectively. In the validation set, manual and automatic delineation took 182.9 and 2.2 s, respectively. On an average, manual and automatic delineation took 169.8 and 1.7 s, respectively. The average DSC of liver tumors was 0.612 and 0.687 in the validation and internal testing sets, respectively. The average time for manual and automatic delineation and AFPR in the internal testing set were 47.4 s, 2.9 s, and 1.4, respectively, and those in the external test set were 29.5 s, 4.2 s, and 1.6, respectively. UNet + + can automatically segment normal hepatic tissue and liver tumors based on MR images. It provides a methodological basis for the automated segmentation of liver tumors, improves the delineation efficiency, and meets the requirement of extraction set analysis of further radiomics and deep learning.

Background:Radiomics analysis could provide complementary tissue characterization in ovarian cancer (OC). However, OC segmentation required in radiomics analysis is time-consuming and labour-intensive. In this study, we aim to evaluate the performance of deep learning-based segmentation of OC on contrast-enhanced CT images and the stability of radiomics features extracted from the automated segmentation.Methods:Staging abdominopelvic CT images of 367 patients with OC were retrospectively recruited. The training and cross-validation sets came from center A (n=283), and testing set (n=84) came from centers B and C. The tumours were manually delineated by a board-certified radiologist. Four model architectures provided by no-new-Net (nnU-Net) method were tested in this task. The segmentation performance evaluated by Dice score, Jaccard score, sensitivity and precision were compared among 4 architectures. The Pearson correlation coefficient (ρ), concordance correlation coefficient (ρc) and Bland-Altman plots were used to evaluate the volumetric assessment of OC between manual and automated segmentations. The stability of extracted radiomics features was evaluated by intraclass correlation coefficient (ICC).Results:The 3D U-Net cascade architecture achieved highest median Dice score, Jaccard score, sensitivity and precision for OC segmentation in the testing set, 0.941, 0.890, 0.973 and 0.925, respectively. Tumour volumes of manual and automated segmentations were highly correlated (ρ=0.944 and ρc =0.933). 85.0% of radiomics features had high correlation with ICC >0.8.Conclusions:The presented deep-learning segmentation could provide highly accurate automated segmentation of OC on CT images with high stability of the extracted radiomics features, showing the potential as a batch-processing segmentation tool.

Purpose: To explore whether texture features based on magnetic resonance can distinguish diseases combined hepatocellular-cholangiocarcinoma (cHCC-CC) from hepatocellular carcinoma (HCC) before operation.Methods: The clinical baseline data and MRI information of 342 patients with pathologically diagnosed cHCC-CC and HCC in two medical centers were collected. The data were divided into the training set and the test set at a ratio of 7:3. MRI images of tumors were segmented with ITK-SNAP software, and python open-source platform was used for texture analysis. Logistic regression as the base model, mutual information (MI) and Least Absolute Shrinkage and Selection Operator (LASSO) regression were used to select the most favorable features. The clinical, radiomics, and clinic-radiomics model were constructed based on logistic regression. The model's effectiveness was comprehensively evaluated by the receiver operating characteristic (ROC) curve, area under the curve (AUC), sensitivity, specificity, and Youden index which is the main, and the model results were exported by SHapley Additive exPlanations (SHAP).Results: A total of 23 features were included. Among all models, the arterial phase-based clinic-radiomics model showed the best performance in differentiating cHCC-CC from HCC before an operation, with the AUC of the test set being 0.863 (95% CI: 0.782 to 0.923), the specificity and sensitivity being 0.918 (95% CI: 0.819 to 0.973) and 0.738 (95% CI: 0.580 to 0.861), respectively. SHAP value results showed that the RMS was the most important feature affecting the model.Conclusion: Clinic-radiomics model based on DCE-MRI may be useful to distinguish cHCC-CC from HCC in a preoperative setting, especially in the arterial phase, and RMS has the greatest impact.

Abstract Purpose There is still currently a lack of magnetic resonance imaging (MRI) based radiomics analysis in the prognosis model for patients with nasal extranodal natural killer/T-cell lymphoma (ENKTL). We aim to investigate the value of MRI-based radiomics signature in the prognosis for patients with nasal ENKTL. Methods 159 nasal ENKTL patients were enrolled and divided into a training cohort (n = 81) and a validation cohort (n = 78) randomly. Radiomics features from pretreatment MRI examination were extracted respectively. Then two sample t-test and least absolute shrinkage and selection operator (LASSO) regression were used to select the radiomics signatures and establish the Rad-score. A radiomics nomogram based on the Rad-score and clinical features was constructed to predict overall survival (OS). Results The radiomics model that integrated Rad-score and clinical risk factors exhibited a satisfactory prediction performance compared with the Rad-score and clinical models in terms of OS in the training cohort (C-index: 0.849 vs. 0.733 vs. 0.707, AUC: 0.896 vs. 0.767 vs.0.798). For validation, the C-index of the three models was 0.931 vs. 0.824 vs. 0.635 respectively. Moreover, the AUC was 0.839 vs. 0.827 vs. 0.583 respectively. The calibration curves also suggested that the net benefit of radiomics models was higher than that of the Rad-score and clinical models. Conclusions The Rad-score was significantly correlated with OS for nasal ENKTL patients. Moreover, the MRI-based radiomics nomogram could be used for risk stratification and provide personalized treatment plans for patients.

Background To develop and validate radiomics models for prediction of tumor response to neoadjuvant therapy (NAT) in patients with locally advanced rectal cancer (LARC) using both pre-NAT and post-NAT multiparameter magnetic resonance imaging (mpMRI). Methods In this multicenter study, a total of 563 patients were included from two independent centers. 453 patients from center 1 were split into training and testing cohorts, the remaining 110 from center 2 served as an external validation cohort. Pre-NAT and post-NAT mpMRI was collected for feature extraction. The radiomics models were constructed using machine learning from a training cohort. The accuracy of the models was verified in a testing cohort and an independent external validation cohort. Model performance was evaluated using area under the curve (AUC), sensitivity, specificity, positive predictive value, and negative predictive value. Results The model constructed with pre-NAT mpMRI had favorable accuracy for prediction of non-response to NAT in the training cohort (AUC = 0.84), testing cohort (AUC = 0.81), and external validation cohort (AUC = 0.79). The model constructed with both pre-NAT and post-NAT mpMRI had powerful diagnostic value for pathologic complete response in the training cohort (AUC = 0.86), testing cohort (AUC = 0.87), and external validation cohort (AUC = 0.87). Conclusions Models constructed with multiphase and multiparameter MRI were able to predict tumor response to NAT with high accuracy and robustness, which may assist in individualized management of LARC.

ImportanceEpithelial ovarian carcinoma is heterogeneous and classified according to the World Health Organization Tumour Classification, which is based on histologic features and molecular alterations. Preoperative prediction of the histologic subtypes could aid in clinical management and disease prognostication.ObjectiveTo assess the value of radiomics based on contrast-enhanced computed tomography (CT) in differentiating histologic subtypes of epithelial ovarian carcinoma in multicenter data sets.Design, Setting, and ParticipantsIn this diagnostic study, 665 patients with histologically confirmed epithelial ovarian carcinoma were retrospectively recruited from 4 centers (Hong Kong, Guangdong Province of China, and Seoul, South Korea) between January 1, 2012, and February 28, 2022. The patients were randomly divided into a training cohort (n = 532) and a testing cohort (n = 133) with a ratio of 8:2. This process was repeated 100 times. Tumor segmentation was manually delineated on each section of contrast-enhanced CT images to encompass the entire tumor. The Mann-Whitney U test and voted least absolute shrinkage and selection operator were performed for feature reduction and selection. Selected features were used to build the logistic regression model for differentiating high-grade serous carcinoma and non–high-grade serous carcinoma.ExposuresContrast-enhanced CT-based radiomics.Main Outcomes and MeasuresIntraobserver and interobserver reproducibility of tumor segmentation were measured by Dice similarity coefficients. The diagnostic efficiency of the model was assessed by receiver operating characteristic curve and area under the curve.ResultsIn this study, 665 female patients (mean [SD] age, 53.6 [10.9] years) with epithelial ovarian carcinoma were enrolled and analyzed. The Dice similarity coefficients of intraobserver and interobserver were all greater than 0.80. Twenty radiomic features were selected for modeling. The areas under the curve of the logistic regression model in differentiating high-grade serous carcinoma and non–high-grade serous carcinoma were 0.837 (95% CI, 0.835-0.838) for the training cohort and 0.836 (95% CI, 0.833-0.840) for the testing cohort.Conclusions and RelevanceIn this diagnostic study, radiomic features extracted from contrast-enhanced CT were useful in the classification of histologic subtypes in epithelial ovarian carcinoma. Intraobserver and interobserver reproducibility of tumor segmentation was excellent. The proposed logistic regression model offered excellent discriminative ability among histologic subtypes.

BACKGROUND:Lymph node status is vital for prognosis and treatment decisions for esophageal squamous cell carcinoma (ESCC). This study aimed to construct and evaluate an optimal radiomics-based method for a more accurate evaluation of individual regional lymph node status in ESCC and to compare it with traditional size-based measurements.METHODS:The study consecutively collected 3225 regional lymph nodes from 530 ESCC patients receiving upfront surgery from January 2011 to October 2015. Computed tomography (CT) scans for individual lymph nodes were analyzed. The study evaluated the predictive performance of machine-learning models trained on features extracted from two-dimensional (2D) and three-dimensional (3D) radiomics by different contouring methods. Robust and important radiomics features were selected, and classification models were further established and validated.RESULTS:The lymph node metastasis rate was 13.2% (427/3225). The average short-axis diameter was 6.4 mm for benign lymph nodes and 7.9 mm for metastatic lymph nodes. The division of lymph node stations into five regions according to anatomic lymph node drainage (cervical, upper mediastinal, middle mediastinal, lower mediastinal, and abdominal regions) improved the predictive performance. The 2D radiomics method showed optimal diagnostic results, with more efficient segmentation of nodal lesions. In the test set, this optimal model achieved an area under the receiver operating characteristic curve of 0.841-0.891, an accuracy of 84.2-94.7%, a sensitivity of 65.7-83.3%, and a specificity of 84.4-96.7%.CONCLUSIONS:The 2D radiomics-based models noninvasively predicted the metastatic status of an individual lymph node in ESCC and outperformed the conventional size-based measurement. The 2D radiomics-based model could be incorporated into the current clinical workflow to enable better decision-making for treatment strategies.

Objective This study aims to develop and externally validate a contrast-enhanced magnetic resonance imaging (CE-MRI) radiomics-based model for preoperative differentiation between fat-poor angiomyolipoma (fp-AML) and hepatocellular carcinoma (HCC) in patients with noncirrhotic livers and to compare the diagnostic performance with that of two radiologists. Methods This retrospective study was performed with 165 patients with noncirrhotic livers from three medical centers. The dataset was divided into a training cohort (n = 99), a time-independent internal validation cohort (n = 24) from one center, and an external validation cohort (n = 42) from the remaining two centers. The volumes of interest were contoured on the arterial phase (AP) images and then registered to the venous phase (VP) and delayed phase (DP), and a total of 3,396 radiomics features were extracted from the three phases. After the joint mutual information maximization feature selection procedure, four radiomics logistic regression classifiers, including the AP model, VP model, DP model, and combined model, were built. The area under the receiver operating characteristic curve (AUC), diagnostic accuracy, sensitivity, and specificity of each radiomics model and those of two radiologists were evaluated and compared. Results The AUCs of the combined model reached 0.789 (95%CI, 0.579–0.999) in the internal validation cohort and 0.730 (95%CI, 0.563–0.896) in the external validation cohort, higher than the AP model (AUCs, 0.711 and 0.638) and significantly higher than the VP model (AUCs, 0.594 and 0.610) and the DP model (AUCs, 0.547 and 0.538). The diagnostic accuracy, sensitivity, and specificity of the combined model were 0.708, 0.625, and 0.750 in the internal validation cohort and 0.619, 0.786, and 0.536 in the external validation cohort, respectively. The AUCs for the two radiologists were 0.656 and 0.594 in the internal validation cohort and 0.643 and 0.500 in the external validation cohort. The AUCs of the combined model surpassed those of the two radiologists and were significantly higher than that of the junior one in both validation cohorts. Conclusions The proposed radiomics model based on triple-phase CE-MRI images was proven to be useful for differentiating between fp-AML and HCC and yielded comparable or better performance than two radiologists in different centers, with different scanners and different scanning parameters.

目的 探讨及复习颅锁骨发育不全综合征(CCD)的发病机制、临床表现、影像特征及治疗方法,以提高对本病的全面认识及影像诊断.方法 回顾性分析我院已确诊的1例CCD典型病例的临床表现及影像动态观察,结合文献对该病的临床及影像表现、治疗方案进行归纳分析.结果 本例患者有典型的颅骨、锁骨、牙齿发育不全表现.结论 CCD具有典型的临床及影像表现,有助于临床明确诊断,当同时有锁骨、颅骨及牙齿发育异常时,应想到本病的可能.