Development of a machine learning-based model to predict prognosis of alpha-fetoprotein-positive hepatocellular carcinoma.

BACKGROUND: Patients with alpha-fetoprotein (AFP)-positive hepatocellular carcinoma (HCC) have aggressive biological behavior and poor prognosis. Therefore, survival time is one of the greatest concerns for patients with AFP-positive HCC. This study aimed to demonstrate the utilization of six machine learning (ML)-based prognostic models to predict overall survival of patients with AFP-positive HCC. METHODS: Data on patients with AFP-positive HCC were extracted from the Surveillance, Epidemiology, and End Results database. Six ML algorithms (extreme gradient boosting [XGBoost], logistic regression [LR], support vector machine [SVM], random forest [RF], K-nearest neighbor [KNN], and decision tree [ID3]) were used to develop the prognostic models of patients with AFP-positive HCC at one year, three years, and five years. Area under the receiver operating characteristic curve (AUC), confusion matrix, calibration curves, and decision curve analysis (DCA) were used to evaluate the model. RESULTS: A total of 2,038 patients with AFP-positive HCC were included for analysis. The 1-, 3-, and 5-year overall survival rates were 60.7%, 28.9%, and 14.3%, respectively. Seventeen features regarding demographics and clinicopathology were included in six ML algorithms to generate a prognostic model. The XGBoost model showed the best performance in predicting survival at 1-year (train set: AUC = 0.771; test set: AUC = 0.782), 3-year (train set: AUC = 0.763; test set: AUC = 0.749) and 5-year (train set: AUC = 0.807; test set: AUC = 0.740). Furthermore, for 1-, 3-, and 5-year survival prediction, the accuracy in the training and test sets was 0.709 and 0.726, 0.721 and 0.726, and 0.778 and 0.784 for the XGBoost model, respectively. Calibration curves and DCA exhibited good predictive performance as well. CONCLUSIONS: The XGBoost model exhibited good predictive performance, which may provide physicians with an effective tool for early medical intervention and improve the survival of patients.

Machine learning model for non-alcoholic steatohepatitis diagnosis based on ultrasound radiomics.

BACKGROUND: Non-Alcoholic Steatohepatitis (NASH) is a crucial stage in the progression of Non-Alcoholic Fatty Liver Disease(NAFLD). The purpose of this study is to explore the clinical value of ultrasound features and radiological analysis in predicting the diagnosis of Non-Alcoholic Steatohepatitis. METHOD: An SD rat model of hepatic steatosis was established through a high-fat diet and subcutaneous injection of CCl4. Liver ultrasound images and elastography were acquired, along with serum data and histopathological results of rat livers.The Pyradiomics software was used to extract radiomic features from 2D ultrasound images of rat livers. The rats were then randomly divided into a training set and a validation set, and feature selection was performed through dimensionality reduction. Various machine learning (ML) algorithms were employed to build clinical diagnostic models, radiomic models, and combined diagnostic models. The efficiency of each diagnostic model for diagnosing NASH was evaluated using Receiver Operating Characteristic (ROC) curves, Clinical Decision Curve Analysis (DCA), and calibration curves. RESULTS: In the machine learning radiomic model for predicting the diagnosis of NASH, the Area Under the Curve (AUC) of ROC curve for the clinical radiomic model in the training set and validation set were 0.989 and 0.885, respectively. The Decision Curve Analysis revealed that the clinical radiomic model had the highest net benefit within the probability threshold range of > 65%. The calibration curve in the validation set demonstrated that the clinical combined radiomic model is the optimal method for diagnosing Non-Alcoholic Steatohepatitis. CONCLUSION: The combined diagnostic model constructed using machine learning algorithms based on ultrasound image radiomics has a high clinical predictive performance in diagnosing Non-Alcoholic Steatohepatitis.

Enhancing malignancy prediction in thyroid nodules: A multimodal ultrasound radiomics approach in TI-RADS category 4 lesions.

PURPOSE: To explore the diagnostic value of intralesional and perilesional radiomics based on multimodal ultrasound (US) images in predicting the malignant ACR TIRADS 4 thyroid nodules (TNs). METHODS: A total of 297 cases of TNs in patients who underwent preoperative thyroid grayscale US and shear wave elastography (STE) were enrolled (training cohort: n = 150, internal validation cohort: n = 77, external validation cohort: n = 70). Regions of interests (ROIs) were delineated on grayscale US images and STE images, and then an isotropic expansion of 1.0, 1.5, 2.0, 2.5, and 3.0 mm was applied. Predictive models were established using recursive feature elimination-support vector machines (RFE-SVM) based on radiomics features calculated by random forest. RESULTS: The perilesional ROI1.5mm expansion achieved the highest area under curve (AUC) (AUC: 0.753 for grayscale US, 0.728 for STE; 95% confidence interval (CI): 0.664-0.743, 0.684-0.739, respectively). The joint model had the highest AUC values of 0.936 in the training dataset, 0.926 in internal dataset, and 0.893 in external dataset. The calibration curve showed good consistency and the decision curve indicated a greater clinical net benefit of the joint model. CONCLUSION: Joint model containing perilesional radiomics (1.5 mm) had significant value in predicting the malignant ACR TIRADS 4 TNs.

Performance of two-dimensional shear wave elastography for detecting advanced liver fibrosis and cirrhosis in patients with biliary atresia: a systematic review and meta-analysis.

BACKGROUND: Two-dimensional shear wave elastography (2D-SWE) has been proposed for detecting liver fibrosis in biliary atresia. OBJECTIVES: To assess the performance of 2D-SWE for detecting advanced liver fibrosis and cirrhosis in patients with biliary atresia. MATERIALS AND METHODS: Five electronic databases were searched to identify studies investigating the performance of 2D-SWE for diagnosing liver fibrosis in biliary atresia in children. We constructed the summary receiver operating characteristic (SROC) curves of 2D-SWE for detecting advanced liver fibrosis and cirrhosis, and then calculated the area under the SROC curves (AUROCs). RESULTS: Six studies with 470 patients (ages 55 days to 6.6 years) were included. The median correlation coefficient of 2D-SWE with pathological liver fibrosis stages was 0.779 (range: 0.443‒0.813). The summary AUROCs for advanced liver fibrosis and cirrhosis were 0.929 and 0.883, respectively. The summary sensitivity and specificity of 2D-SWE for advanced liver fibrosis were 88% (95% confidence interval [CI]: 80‒94%) and 85% (95% CI: 77‒91%) with I values of 0% and 45.6%, respectively, and for cirrhosis were 80% (95% CI: 72‒87%) and 82% (95% CI: 77‒86%) with I values of 12.9% and 0%, respectively. The diagnostic odds ratio (DOR) of 2D-SWE for advanced liver fibrosis and cirrhosis were 40.3 (95% CI: 18.2‒89.4) and 18.9 (95% CI: 11.2‒31.7), respectively. For preoperative detection of cirrhosis, the pooled AUROC, sensitivity, specificity, and DOR based on the four 2D-SWE studies were 0.877, 79% (95% CI: 71‒86%), 82% (95% CI: 77‒86%), and 17.58 (95% CI: 10.35‒29.85), respectively. CONCLUSIONS: Results show that 2D-SWE has potential as a non-invasive tool for detecting advanced liver fibrosis and cirrhosis in patients with biliary atresia.

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.

A sonogram radiomics model for differentiating granulomatous lobular mastitis from invasive breast cancer: a multicenter study.

PURPOSE: To construct a nomogram based on sonogram features and radiomics features to differentiate granulomatous lobular mastitis (GLM) from invasive breast cancer (IBC). MATERIALS AND METHODS: A retrospective collection of 213 GLMs and 472 IBCs from three centers was divided into a training set, an internal validation set, and an external validation set. A radiomics model was built based on radiomics features, and the RAD score of the lesion was calculated. The sonogram radiomics model was constructed using ultrasound features and RAD scores. Finally, the diagnostic efficacy of the three sonographers with different levels of experience before and after combining the RAD score was assessed in the external validation set. RESULTS: The RAD score, lesion diameter, orientation, echogenicity, and tubular extension showed significant differences in GLM and IBC (p < 0.05). The sonogram radiomics model based on these factors achieved optimal performance, and its area under the curve (AUC) was 0.907, 0.872, and 0.888 in the training, internal, and external validation sets, respectively. The AUCs before and after combining the RAD scores were 0.714, 0.750, and 0.830 and 0.834, 0.853, and 0.878, respectively, for sonographers with different levels of experience. The diagnostic efficacy was comparable for all sonographers when combined with the RAD score (p > 0.05). CONCLUSION: Radiomics features effectively enhance the ability of sonographers to discriminate between GLM and IBC and reduce interobserver variation. The nomogram combining ultrasound features and radiomics features show promising diagnostic efficacy and can be used to identify GLM and IBC in a noninvasive approach.

Clinical value of hemodynamic changes in diagnosis of hepatic encephalopathy after transjugular intrahepatic portosystemic shunt.

OBJECTIVE: This paper aims to investigate clinical value of intrahepatic and intra-stent hemodynamic changes after transjugular intrahepatic portosystemic shunt (TIPS), by using color Doppler ultrasound during the diagnosis of hepatic encephalopathy (HE) in the patients with hepatitis B cirrhosis. METHODS: A retrospective analysis of the patients with hepatitis B cirrhotic portal hypertension, who underwent TIPS in The First Affiliated Hospital of Anhui Medical University from January 2018 to January 2021, was conducted. 22 patients who developed HE within 3 months after TIPS comprised the observation group (HE group), and 51 patients who did not develop HE were randomly selected as the control group (non-HE group). The porto systemic gradient (PSG), as well as intrahepatic and intra-stent hemodynamic changes of patients in both the HE group and the non-HE group after TIPS were investigated. RESULTS: The intra-stent blood flow, PSG difference, and PSG decrease percentage in the HE group were higher than those in the non-HE group, and the intra-stent flow had a weak positive correlation with PSG difference and with the PSG decrease percentage (r = 0.420, 0.258, respectively). The areas under the ROC curves of HE based on the PSG difference, the PSG decrease percentage, and the intra-stent flow were 0.762, 0.753, and 0.693, respectively. CONCLUSION: The more obvious decrease in PSG, the larger the intra-stent blood flow, and the larger the possibility of HE occurrence were observed. Routine ultrasound measurement of hemodynamic changes has certain clinical significance for predicting HE occurrence.

Potential added value of computed tomography radiomics to multimodal prediction models for benign and malignant breast tumors.

Background: Early diagnosis is crucial to the treatment of breast cancer, but conventional imaging detection is challenging. Radiomics has the potential to improve early diagnostic efficacy in a noninvasive manner. This study examined whether integrating computed tomography (CT) radiomics information based on ultrasound (US) models can improve the efficacy of breast cancer prediction. Methods: We retrospectively analyzed 420 patients with pathologically confirmed benign or malignant breast tumors. Clinical data and examination images were collected, and the population was divided into training (n=294) and validation (n=126) groups at a ratio of 7:3. The region of interest (ROI) was manually segmented along the tumor boundary using MaZda software, and the features of each ROI was extracted. After dimension reduction and screening, the best features were retained. Subsequently, random forest (RF), support vector machines, and K-nearest neighbor classifiers were used to establish prediction models in an US and combined-methods group. Results: Finally, 8 of the 379 features were retained in the US group. Random forest was found to be the best model, and the area under the curve (AUC) of the training and validation groups was 0.90 [95% confidence interval (CI): 0.852-0.942] and 0.85 (95% CI: 0.775-0.930), respectively. Meanwhile, 12 of the 750 features were retained in the combined group. In this regard, random forest proved to be the best model, and the AUC of the training and validation group was 0.95 (95% CI: 0.918-0.981) and 0.92 (95% CI: 0.866-0.969), respectively. The calibration curve showed a good fit of the model. The decision curve showed that the clinical net benefit of the combined group was far greater than that of any single examination, and the prediction model of the combined group exhibited a degree of practical clinical value. Conclusions: The combined model based on US and CT images has potential application value in the prognostic prediction of benign and malignant breast diseases.

The Value of Follow-Up Liver Stiffness Changes Measured by Virtual Touch Quantification Elastography for Predicting Recurrence of Gastroesophageal Varices after Endoscopic Injection Sclerotherapy on Cirrhotic Patients.

Background and Aims: Recurrence of gastroesophageal varices (GEVs) after sclerotherapy is a public health problem. However, mass screening of recurrence of GEVs through gastroscopy is a high-cost procedure. We aim to evaluate the changes in liver stiffness (LS) over time after endoscopic injection sclerotherapy (EIS) and determine its value in predicting the recurrence of GEVs. Methods: One hundred and thirty-five patients with GEVs who underwent EIS treatment were included in this study. The patients were divided into two groups, namely, the nonrecurrence and recurrence groups, based on endoscopic findings at 6 months after discharge. LS measurements were obtained on five occasions. Repeated measure analysis of variance was employed to assess LS differences at different time points and compare them between the two groups. Results: The LS values during the 6-month postdischarge period were consistently higher than the baseline value (measured on the day of hospitalization). The recurrence group demonstrated sustained elevated LS levels throughout the 6-month follow-up period, while the nonrecurrence group showed a gradual decline in LS. The difference in LS trend between the two groups was statistically significant (P = 0.04). The area under the curve (AUC) values for LS differences were 0.806, with a corresponding 95% confidence interval (CI) of 0.640-0.918 and a cut-off value of 0.556, indicating their potential utility in predicting GEV recurrence. Conclusions: Longitudinal assessment of LS values in post-EIS patients can provide valuable information for predicting the recurrence of GEVs.

Ultrasound-Based Deep Learning Radiomics Nomogram for the Assessment of Lymphovascular Invasion in Invasive Breast Cancer: A Multicenter Study.

RATIONALE AND OBJECTIVES: The aim of this study was to develop a deep learning radiomics nomogram (DLRN) based on B-mode ultrasound (BMUS) and color doppler flow imaging (CDFI) images for preoperative assessment of lymphovascular invasion (LVI) status in invasive breast cancer (IBC). MATERIALS AND METHODS: In this multicenter, retrospective study, 832 pathologically confirmed IBC patients were recruited from eight hospitals. The samples were divided into training, internal test, and external test sets. Deep learning and handcrafted radiomics features reflecting tumor phenotypes on BMUS and CDFI images were extracted. The BMUS score and CDFI score were calculated after radiomics feature selection. Subsequently, a DLRN was developed based on the scores and independent clinic-ultrasonic risk variables. The performance of the DLRN was evaluated for calibration, discrimination, and clinical usefulness. RESULTS: The DLRN predicted the LVI with accuracy, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI 0.90-0.95), 0.91 (95% CI 0.87-0.95), and 0.91 (95% CI 0.86-0.94) in the training, internal test, and external test sets, respectively, with good calibration. The DLRN demonstrated superior performance compared to the clinical model and single scores across all three sets (p < 0.05). Decision curve analysis and clinical impact curve confirmed the clinical utility of the model. Furthermore, significant enhancements in net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indicated that the two scores could serve as highly valuable biomarkers for assessing LVI. CONCLUSION: The DLRN exhibited strong predictive value for LVI in IBC, providing valuable information for individualized treatment decisions.

Diagnostic accuracy of contrast-enhanced ultrasound for detecting clinically significant portal hypertension and severe portal hypertension in chronic liver disease: a meta-analysis.

BACKGROUND: Contrast-enhanced ultrasound (CEUS) has been proposed for detecting clinically significant portal hypertension (CSPH) and severe portal hypertension (SPH) in patients with chronic liver diseases (CLD). RESEARCH DESIGN & METHODS: Studies were selected that investigated the diagnostic performance of CEUS in patients with CLD up to 10 October 2022. The summary area under the receiver operating characteristic curve (AUROC), the summary diagnostic odds ratios, and the summary sensitivities and specificities were used to assess the performance of CEUS for detecting CSPH and SPH. RESULTS: A total of 7 studies were included in this meta-analysis. The summary sensitivity and specificity of this method for CSPH were 92% (95% confidence interval (CI), 76%-97%) and 78% (95% CI, 67%-86%), respectively, and the summary AUROC was 0.89 (95% CI, 0.86-0.92). Those for SPH were 81% (95% CI, 60%-93%), 82% (95% CI, 76%-86%), and 0.82 (95% CI, 0.79-0.85), respectively. A subgroup analysis of 3 subharmonic aided pressure estimation (SHAPE) studies revealed similar diagnostic performance (sensitivity: 95%; specificity: 74%; AUROC: 0.93) for detecting CSPH. CONCLUSIONS: CEUS shows good performance in diagnosing CSPH as well as SPH. SHAPE technique may play a more important role in evaluating CSPH in the future. REGISTRATION: The meta-analysis was not registered.

Radiomics Analysis of Breast Lesions in Combination with Coronal Plane of ABVS and Strain Elastography.

Background: Breast cancer is the most common tumor globally. Automated Breast Volume Scanner (ABVS) and strain elastography (SE) can provide more useful breast information. The use of radiomics combined with ABVS and SE images to predict breast cancer has become a new focus. Therefore, this study developed and validated a radiomics analysis of breast lesions in combination with coronal plane of ABVS and SE to improve the differential diagnosis of benign and malignant breast diseases. Patients and Methods: 620 pathologically confirmed breast lesions from January 2017 to August 2021 were retrospectively analyzed and randomly divided into a training set (n=434) and a validation set (n=186). Radiomic features of the lesions were extracted from ABVS, B-ultrasound, and strain elastography (SE) images, respectively. These were then filtered by Gradient Boosted Decision Tree (GBDT) and multiple logistic regression. The ABVS model is based on coronal plane features for the breast, B+SE model is based on features of B-ultrasound and SE, and the multimodal model is based on features of three examinations. The evaluation of the predicted performance of the three models used the receiver operating characteristic (ROC) and decision curve analysis (DCA). Results: The area under the curve, accuracy, specificity, and sensitivity of the multimodal model in the training set are 0.975 (95% CI:0.959-0.991),93.78%, 92.02%, and 96.49%, respectively, and 0.946 (95% CI:0.913 -0.978), 87.63%, 83.93%, and 93.24% in the validation set, respectively. The multimodal model outperformed the ABVS model and B+SE model in both the training (P < 0.001, P = 0.002, respectively) and validation sets (P < 0.001, P = 0.034, respectively). Conclusion: Radiomics from the coronal plane of the breast lesion provide valuable information for identification. A multimodal model combination with radiomics from ABVS, B-ultrasound, and SE could improve the diagnostic efficacy of breast masses.

An overview of ultrasound-derived radiomics and deep learning in liver.

Over the past few years, developments in artificial intelligence (AI), especially in radiomics and deep learning, have enabled the extraction of pathophysiology-related information from varied medical imaging and are progressively transforming medical practice. AI applications are extending into domains previously thought to be accessible only to human experts. Recent research has demonstrated that ultrasound-derived radiomics and deep learning represent an enticing opportunity to benefit preoperative evaluation and prognostic monitoring of diffuse and focal liver disease. This review summarizes the application of radiomics and deep learning in ultrasound liver imaging, including identifying focal liver lesions and staging of liver fibrosis, as well as the evaluation of pathobiological properties of malignant tumors and the assessment of recurrence and prognosis. Besides, we identify important hurdles that must be overcome while also discussing the challenges and opportunities of radiomics and deep learning in clinical applications.