Diagnosis of Ovarian Neoplasms Using Nomogram in Combination With Ultrasound Image-Based Radiomics Signature and Clinical Factors

Performance of radiomics analysis in ultrasound imaging for differentiating benign from malignant adnexal masses: A systematic review and meta-analysis

INTRODUCTION

We present the state of the art of ultrasound-based machine learning (ML) radiomics models in the context of ovarian masses and analyze their accuracy in differentiating between benign and malignant adnexal masses.

MATERIAL AND METHODS

Web of Science, PubMed, and Scopus databases were searched. All studies were imported into RAYYAN QCRI software. All studies that developed and internally or externally validated ML models using only radiomics features extracted from ultrasound images were included. The overall quality of the included studies was assessed using the QUADAS-AI tool. Summary sensitivity and specificity analyses with corresponding 95% confidence intervals (CIs) were reported.

RESULTS

12 studies developed ML models including only radiomics features extracted from ultrasound images, and six of them were included in the meta-analysis. The overall sensitivity and specificity for differentiating benign from malignant adnexal masses were 0.80 (95% CI 0.74-0.87) and 0.86 (95% CI 0.80-0.90), respectively, in the validation set. All studies demonstrated a high risk of bias in subject selection (e.g., lack of details on image sources or scanner models; absence of image preprocessing), and the majority also showed a high risk in the index test (e.g., models were not validated on external datasets) domain. In contrast, the risk of bias was generally low for the reference standard (i.e., most studies used a reference that accurately identified the target condition) and the testing workflow (i.e., the time interval between the index test and reference standard was appropriate) domains.

CONCLUSIONS

The good performance of ultrasound-based radiomics models in the validation set supports that radiomics is worth exploring to improve the diagnosis of adnexal masses. So far, the studies have a high risk of bias due to the small sample size, single-setting design, and no external validation included.

Radiomics analysis of ultrasound images to discriminate between benign and malignant adnexal masses with solid morphology on ultrasound

OBJECTIVE

The primary aim was to identify radiomics ultrasound features that can distinguish between benign and malignant adnexal masses with solid ultrasound morphology, and between primary malignant (including borderline and primary invasive) and metastatic solid ovarian masses, and to develop ultrasound-based machine learning models that include radiomics features to discriminate between benign and malignant solid adnexal masses. The secondary aim was to compare the discrimination performance of our newly developed radiomics models with that of the Assessment of Different NEoplasias in the adneXa (ADNEX) model and that of subjective assessment by an experienced ultrasound examiner.

METHODS

This was a retrospective, observational single-center study conducted at Fondazione Policlinico Universitario A. Gemelli IRCC, in Rome, Italy. Included were patients with a histological diagnosis of an adnexal tumor with solid morphology according to International Ovarian Tumor Analysis (IOTA) terminology at preoperative ultrasound examination performed in 2014-2020, who were managed with surgery. The patient cohort was split randomly into training and validation sets at a ratio of 70:30 and with the same proportion of benign and malignant tumors in the two subsets, with malignant tumors including borderline, primary invasive and metastatic tumors. We extracted 68 radiomics features, belonging to two different families: intensity-based statistical features and textural features. Models to predict malignancy were built based on a random forest classifier, fine-tuned using 5-fold cross-validation over the training set, and tested on the held-out validation set. The variables used in model-building were patient age and radiomics features that were statistically significantly different between benign and malignant adnexal masses and assessed as not redundant based on the Pearson correlation coefficient. We evaluated the discriminative ability of the models and compared it to that of the ADNEX model and that of subjective assessment by an experienced ultrasound examiner using the area under the receiver-operating-characteristics curve (AUC) and classification performance by calculating sensitivity and specificity.

RESULTS

In total, 326 patients were included and 775 preoperative ultrasound images were analyzed. Of the 68 radiomics features extracted, 52 differed statistically significantly between benign and malignant tumors in the training set, and 18 uncorrelated features were selected for inclusion in model-building. The same 52 radiomics features differed significantly between benign, primary malignant and metastatic tumors. However, the values of the features manifested overlapped between primary malignant and metastatic tumors and did not differ significantly between them. In the validation set, 25/98 (25.5%) tumors were benign and 73/98 (74.5%) were malignant (6 borderline, 57 primary invasive, 10 metastatic). In the validation set, a model including only radiomics features had an AUC of 0.80, sensitivity of 0.78 and specificity of 0.76 at an optimal cut-off for risk of malignancy of 68%, based on Youden's index. The corresponding results for a model including age and radiomics features were AUC of 0.79, sensitivity of 0.86 and specificity of 0.56 (cut-off 60%, based on Youden's index), while those of the ADNEX model were AUC of 0.88, sensitivity of 0.99 and specificity of 0.64 (at a 20% risk-of-malignancy cut-off). Subjective assessment had a sensitivity of 0.99 and specificity of 0.72.

CONCLUSIONS

Our radiomics model had moderate discriminative ability on internal validation and the addition of age to this model did not improve its performance. Even though our radiomics models had discriminative ability inferior to that of the ADNEX model, our results are sufficiently promising to justify continued development of radiomics analysis of ultrasound images of adnexal masses. © 2024 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Integrating plasma exosomal miRNAs, ultrasound radiomics and tPSA for the diagnosis and prediction of early prostate cancer: a multi-center study

INTRODUCTION

This multi-center study aims to explore the roles of plasma exosomal microRNAs (miRNAs), ultrasound (US) radiomics, and total prostate-specific antigen (tPSA) levels in early prostate cancer detection.

METHODS

We analyzed the publicly available dataset GSE112264 to identify the differentially expressed miRNAs associated with prostate cancer. Then, PyRadiomics was used to extract image features, and least absolute shrinkage and selection operator (LASSO) was used to screen the data. Subsequently, according to strict inclusion and exclusion criteria, the internal dataset (n = 199) was used to construct a diagnostic model, and the receiver operating characteristic (ROC) curve, calibration curve, decision curve analysis (DCA), and DeLong test were used to evaluate its diagnostic performance. Finally, we used an external dataset (n = 158) for further validation.

RESULTS

The number of features extracted by PyRadiomics was 851, and the number of features screened by LASSO was 23. We combined the hsa-miR-320c, hsa-miR-944, radiomics, and tPSA features to construct a joint model. The area under the ROC curve of the combined model was 0.935. In the internal validation, the area under the curve (AUC) of the training set was 0.943, and the AUC of the test set was 0.946. The AUC of the external data set was 0.910. The calibration curve and decision curve were consistent with the performance of the combined model. There was a significant difference in the prediction ability between the combined prediction model and the single index prediction model, indicating the high credibility and accuracy of the combined model in predicting PCa.

CONCLUSIONS

The combined prediction model, consisting of plasma exosomal miRNAs (hsa-miR-320c and hsa-miR-944), US radiomics, and clinical tPSA, can be utilized for the early diagnosis of prostate cancer.

Radiomics and radiogenomics: extracting more information from medical images for the diagnosis and prognostic prediction of ovarian cancer

Ovarian cancer (OC) remains one of the most lethal gynecological malignancies globally. Despite the implementation of various medical imaging approaches for OC screening, achieving accurate differential diagnosis of ovarian tumors continues to pose significant challenges due to variability in image performance, resulting in a lack of objectivity that relies heavily on the expertise of medical professionals. This challenge can be addressed through the emergence and advancement of radiomics, which enables high-throughput extraction of valuable information from conventional medical images. Furthermore, radiomics can integrate with genomics, a novel approach termed radiogenomics, which allows for a more comprehensive, precise, and personalized assessment of tumor biological features. In this review, we present an extensive overview of the application of radiomics and radiogenomics in diagnosing and predicting ovarian tumors. The findings indicate that artificial intelligence methods based on imaging can accurately differentiate between benign and malignant ovarian tumors, as well as classify their subtypes. Moreover, these methods are effective in forecasting survival rates, treatment outcomes, metastasis risk, and recurrence for patients with OC. It is anticipated that these advancements will function as decision-support tools for managing OC while contributing to the advancement of precision medicine.

Role of artificial intelligence applied to ultrasound in gynecology oncology: A systematic review

The aim of this paper was to explore the role of artificial intelligence (AI) applied to ultrasound imaging in gynecology oncology. Web of Science, PubMed, and Scopus databases were searched. All studies were imported to RAYYAN QCRI software. The overall quality of the included studies was assessed using QUADAS-AI tool. Fifty studies were included, of these 37/50 (74.0%) on ovarian masses or ovarian cancer, 5/50 (10.0%) on endometrial cancer, 5/50 (10.0%) on cervical cancer, and 3/50 (6.0%) on other malignancies. Most studies were at high risk of bias for subject selection (i.e., sample size, source, or scanner model were not specified; data were not derived from open-source datasets; imaging preprocessing was not performed) and index test (AI models was not externally validated) and at low risk of bias for reference standard (i.e., the reference standard correctly classified the target condition) and workflow (i.e., the time between index test and reference standard was reasonable). Most studies presented machine learning models (33/50, 66.0%) for the diagnosis and histopathological correlation of ovarian masses, while others focused on automatic segmentation, reproducibility of radiomics features, improvement of image quality, prediction of therapy resistance, progression-free survival, and genetic mutation. The current evidence supports the role of AI as a complementary clinical and research tool in diagnosis, patient stratification, and prediction of histopathological correlation in gynecological malignancies. For example, the high performance of AI models to discriminate between benign and malignant ovarian masses or to predict their specific histology can improve the diagnostic accuracy of imaging methods.

Accuracy of machine learning in the preoperative identification of ovarian borderline tumors: a meta-analysis

AIM

The objective of this study is to explore the diagnostic value of machine learning (ML) in borderline ovarian tumors through meta-analysis.

METHODS

Pubmed, Embase, Web of Science, and Cochrane Library databases were comprehensively retrieved from database inception untill February 16, 2023. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was adopted to evaluate the risk of bias in the original studies. Sub-group analyses of ML were conducted according to clinical features and radiomics features. We separately discussed the discriminative value of ML for borderline vs benign and borderline vs malignant tumors.

RESULTS

Eighteen studies involving 12,778 subjects were included in our analysis. The modeling variables mainly consisted of radiomics features (n=13) and a small number of clinical features (n=5). When distinguishing between borderline and benign tumors, the ML model based on radiomic features achieved a c-index of 0.782 (95% CI: 0.732-0.831), sensitivity of 0.75 (95% CI: 0.67-0.82), and specificity of 0.75 (95% CI: 0.67-0.81) in the validation set. When distinguishing between borderline and malignant tumors, the ML model based on radiomic features achieved a c-index of 0.916 (95% CI: 0.891-0.940), sensitivity of 0.86 (95% CI: 0.78-0.91), and specificity of 0.88 (95% CI: 0.82-0.92) in the validation set. In addition, we analyzed the discriminatory ability of radiologists and found that their sensitivity was 0.26 (95% CI: 0.12-0.46) and specificity was 0.94 (95% CI: 0.90-0.97).

CONCLUSIONS

ML has tremendous potential in the preoperative diagnosis and differentiation of borderline ovarian tumors and may be more accurate than radiologists in diagnosing and differentiating borderline ovarian tumors.

Ultrasound-based deep learning radiomics model for differentiating benign, borderline, and malignant ovarian tumours: a multi-class classification exploratory study

BACKGROUND

Accurate preoperative identification of ovarian tumour subtypes is imperative for patients as it enables physicians to custom-tailor precise and individualized management strategies. So, we have developed an ultrasound (US)-based multiclass prediction algorithm for differentiating between benign, borderline, and malignant ovarian tumours.

METHODS

We randomised data from 849 patients with ovarian tumours into training and testing sets in a ratio of 8:2. The regions of interest on the US images were segmented and handcrafted radiomics features were extracted and screened. We applied the one-versus-rest method in multiclass classification. We inputted the best features into machine learning (ML) models and constructed a radiomic signature (Rad_Sig). US images of the maximum trimmed ovarian tumour sections were inputted into a pre-trained convolutional neural network (CNN) model. After internal enhancement and complex algorithms, each sample's predicted probability, known as the deep transfer learning signature (DTL_Sig), was generated. Clinical baseline data were analysed. Statistically significant clinical parameters and US semantic features in the training set were used to construct clinical signatures (Clinic_Sig). The prediction results of Rad_Sig, DTL_Sig, and Clinic_Sig for each sample were fused as new feature sets, to build the combined model, namely, the deep learning radiomic signature (DLR_Sig). We used the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) to estimate the performance of the multiclass classification model.

RESULTS

The training set included 440 benign, 44 borderline, and 196 malignant ovarian tumours. The testing set included 109 benign, 11 borderline, and 49 malignant ovarian tumours. DLR_Sig three-class prediction model had the best overall and class-specific classification performance, with micro- and macro-average AUC of 0.90 and 0.84, respectively, on the testing set. Categories of identification AUC were 0.84, 0.85, and 0.83 for benign, borderline, and malignant ovarian tumours, respectively. In the confusion matrix, the classifier models of Clinic_Sig and Rad_Sig could not recognise borderline ovarian tumours. However, the proportions of borderline and malignant ovarian tumours identified by DLR_Sig were the highest at 54.55% and 63.27%, respectively.

CONCLUSIONS

The three-class prediction model of US-based DLR_Sig can discriminate between benign, borderline, and malignant ovarian tumours. Therefore, it may guide clinicians in determining the differential management of patients with ovarian tumours.

Machine learning and radiomics for segmentation and classification of adnexal masses on ultrasound

Ultrasound-based models exist to support the classification of adnexal masses but are subjective and rely upon ultrasound expertise. We aimed to develop an end-to-end machine learning (ML) model capable of automating the classification of adnexal masses. In this retrospective study, transvaginal ultrasound scan images with linked diagnoses (ultrasound subjective assessment or histology) were extracted and segmented from Imperial College Healthcare, UK (ICH development dataset; n = 577 masses; 1444 images) and Morgagni-Pierantoni Hospital, Italy (MPH external dataset; n = 184 masses; 476 images). A segmentation and classification model was developed using convolutional neural networks and traditional radiomics features. Dice surface coefficient (DICE) was used to measure segmentation performance and area under the ROC curve (AUC), F1-score and recall for classification performance. The ICH and MPH datasets had a median age of 45 (IQR 35-60) and 48 (IQR 38-57) years old and consisted of 23.1% and 31.5% malignant cases, respectively. The best segmentation model achieved a DICE score of 0.85 ± 0.01, 0.88 ± 0.01 and 0.85 ± 0.01 in the ICH training, ICH validation and MPH test sets. The best classification model achieved a recall of 1.00 and F1-score of 0.88 (AUC:0.93), 0.94 (AUC:0.89) and 0.83 (AUC:0.90) in the ICH training, ICH validation and MPH test sets, respectively. We have developed an end-to-end radiomics-based model capable of adnexal mass segmentation and classification, with a comparable predictive performance (AUC 0.90) to the published performance of expert subjective assessment (gold standard), and current risk models. Further prospective evaluation of the classification performance of this ML model against existing methods is required.

Diagnostic value of a CT-based radiomics nomogram for discrimination of benign and early stage malignant ovarian tumors

BACKGROUND

This study aimed to identify the diagnostic value of models constructed using computed tomography-based radiomics features for discrimination of benign and early stage malignant ovarian tumors.

METHODS

The imaging and clinicopathological data of 197 cases of benign and early stage malignant ovarian tumors (FIGO stage I/II), were retrospectively analyzed. The patients were randomly assigned into training data set and validation data set. Radiomics features were extracted from images of plain computed tomography scan and contrast-enhanced computed tomography scan, were then screened in the training data set, and a radiomics model was constructed. Multivariate logistic regression analysis was used to construct a radiomic nomogram, containing the traditional diagnostic model and the radiomics model. Moreover, the decision curve analysis was used to assess the clinical application value of the radiomics nomogram.

RESULTS

Six textural features with the greatest diagnostic efficiency were finally screened. The value of the area under the receiver operating characteristic curve showed that the radiomics nomogram was superior to the traditional diagnostic model and the radiomics model (P < 0.05) in the training data set. In the validation data set, the radiomics nomogram was superior to the traditional diagnostic model (P < 0.05), but there was no statistically significant difference compared to the radiomics model (P > 0.05). The calibration curve and the Hosmer-Lemeshow test revealed that the three models all had a great degree of fit (All P > 0.05). The results of decision curve analysis indicated that utilization of the radiomics nomogram to distinguish benign and early stage malignant ovarian tumors had a greater clinical application value when the risk threshold was 0.4-1.0.

CONCLUSIONS

The computed tomography-based radiomics nomogram could be a non-invasive and reliable imaging method to discriminate benign and early stage malignant ovarian tumors.

Ovarian cancer beyond imaging: integration of AI and multiomics biomarkers

High-grade serous ovarian cancer is the most lethal gynaecological malignancy. Detailed molecular studies have revealed marked intra-patient heterogeneity at the tumour microenvironment level, likely contributing to poor prognosis. Despite large quantities of clinical, molecular and imaging data on ovarian cancer being accumulated worldwide and the rise of high-throughput computing, data frequently remain siloed and are thus inaccessible for integrated analyses. Only a minority of studies on ovarian cancer have set out to harness artificial intelligence (AI) for the integration of multiomics data and for developing powerful algorithms that capture the characteristics of ovarian cancer at multiple scales and levels. Clinical data, serum markers, and imaging data were most frequently used, followed by genomics and transcriptomics. The current literature proves that integrative multiomics approaches outperform models based on single data types and indicates that imaging can be used for the longitudinal tracking of tumour heterogeneity in space and potentially over time. This review presents an overview of studies that integrated two or more data types to develop AI-based classifiers or prediction models.Relevance statement Integrative multiomics models for ovarian cancer outperform models using single data types for classification, prognostication, and predictive tasks.Key points• This review presents studies using multiomics and artificial intelligence in ovarian cancer.• Current literature proves that integrative multiomics outperform models using single data types.• Around 60% of studies used a combination of imaging with clinical data.• The combination of genomics and transcriptomics with imaging data was infrequently used.

Ultrasound-based radiomic analysis of the peripheral nerves for differentiation between CIDP and POEMS syndrome

BACKGROUND

Demyelinating peripheral neuropathy is characteristic of both polyneuropathy, organomegaly, endocrinopathy, M-protein, and skin changes (POEMS) syndrome and chronic inflammatory demyelinating polyneuropathy (CIDP). We hypothesized that the different pathogeneses underlying these entities would affect the sonographic imaging features.

PURPOSE

To investigate whether ultrasound (US)-based radiomic analysis could extract features to describe the differences between CIDP and POEMS syndrome.

MATERIAL AND METHODS

In this retrospective study, we evaluated nerve US images from 26 with typical CIDP and 34 patients with POEMS syndrome. Cross-sectional area (CSA) and echogenicity of the median and ulnar nerves were evaluated in each US image of the wrist, forearm, elbow, and mid-arm. Radiomic analysis was performed on these US images. All radiomic features were examined using receiver operating characteristic analysis. Optimal features were selected using a three-step feature selection method and were inputted into XGBoost to build predictive machine-learning models.

RESULTS

The CSAs were more enlarged in patients with CIDP than in those with POEMS syndrome without significant differences, except for that of the ulnar nerve at the wrist. Nerve echogenicity was significantly more heterogeneous in patients with CIDP than in those with POEMS syndrome. The radiomic analysis yielded four features with the highest area under the curve (AUC) value of 0.83. The machine-learning model showed an AUC of 0.90.

CONCLUSION

US-based radiomic analysis has high AUC values in differentiating POEM syndrome from CIDP. Machine-learning algorithms further improved the discriminative ability.

A CT-based radiomics nomogram for differentiating ovarian cystadenomas and endometriotic cysts

AIM

To construct and validate a computed tomography (CT)-based radiomics nomogram integrating radiomics signature and clinical factors to distinguish ovarian cystadenomas and endometriotic cysts.

MATERIALS AND METHODS

A total of 287 patients with ovarian cystadenomas (n=196) or endometriotic cysts (n=91) were divided randomly into a training cohort (n=200) and a validation cohort (n=87). Radiomics features based on the portal venous phase of CT images were extracted by PyRadiomics. The least absolute shrinkage and selection operation regression was applied to select the significant features and develop the radiomics signature. A radiomics score (rad-score) was calculated. The clinical model was built by the significant clinical factors. Multivariate logistic regression analysis was employed to construct the radiomics nomogram based on significant clinical factors and rad-score. The diagnostic performances of the radiomics nomogram, radiomics signature, and clinical model were evaluated and compared in the training and validation cohorts. Diagnostic confusion matrices of these models were calculated for the validation cohort and compared with those of the radiologists.

RESULTS

Seventeen radiomics features from CT images were used to build the radiomics signature. The radiomics nomogram incorporating cancer antigen 125 (CA-125) level and rad-score showed the best performance in both the training and validation cohorts with AUCs of 0.925 (95% confidence interval [CI]: 0.885-0.965), and 0.942 (95% CI: 0.891-0.993), respectively. The accuracy of radiomics nomogram in the confusion matrix outperformed the radiologists.

CONCLUSIONS

The radiomics nomogram performed well for differentiating ovarian cystadenomas and endometriotic cysts, and may help in clinical decision-making process.

Clinicomics-guided distant metastasis prediction in breast cancer via artificial intelligence

BACKGROUND

Breast cancer has become the most common malignant tumour worldwide. Distant metastasis is one of the leading causes of breast cancer-related death. To verify the performance of clinicomics-guided distant metastasis risk prediction for breast cancer via artificial intelligence and to investigate the accuracy of the created prediction models for metachronous distant metastasis, bone metastasis and visceral metastasis.

METHODS

We retrospectively enrolled 6703 breast cancer patients from 2011 to 2016 in our hospital. The figures of magnetic resonance imaging scanning and ultrasound were collected, and the figures features of distant metastasis in breast cancer were detected. Clinicomics-guided nomogram was proven to be with significant better ability on distant metastasis prediction than the nomogram constructed by only clinical or radiographic data.

RESULTS

Three clinicomics-guided prediction nomograms on distant metastasis, bone metastasis and visceral metastasis were created and validated. These models can potentially guide metachronous distant metastasis screening and lead to the implementation of individualized prophylactic therapy for breast cancer patients.

CONCLUSION

Our study is the first study to make cliniomics a reality. Such cliniomics strategy possesses the development potential in artificial intelligence medicine.

Analysis of computer-aided diagnostics in the preoperative diagnosis of ovarian cancer: a systematic review

OBJECTIVES

Different noninvasive imaging methods to predict the chance of malignancy of ovarian tumors are available. However, their predictive value is limited due to subjectivity of the reviewer. Therefore, more objective prediction models are needed. Computer-aided diagnostics (CAD) could be such a model, since it lacks bias that comes with currently used models. In this study, we evaluated the available data on CAD in predicting the chance of malignancy of ovarian tumors.

METHODS

We searched for all published studies investigating diagnostic accuracy of CAD based on ultrasound, CT and MRI in pre-surgical patients with an ovarian tumor compared to reference standards.

RESULTS

In thirty-one included studies, extracted features from three different imaging techniques were used in different mathematical models. All studies assessed CAD based on machine learning on ultrasound, CT scan and MRI scan images. Per imaging method, subsequently ultrasound, CT and MRI, sensitivities ranged from 40.3 to 100%; 84.6-100% and 66.7-100% and specificities ranged from 76.3-100%; 69-100% and 77.8-100%. Results could not be pooled, due to broad heterogeneity. Although the majority of studies report high performances, they are at considerable risk of overfitting due to the absence of an independent test set.

CONCLUSION

Based on this literature review, different CAD for ultrasound, CT scans and MRI scans seem promising to aid physicians in assessing ovarian tumors through their objective and potentially cost-effective character. However, performance should be evaluated per imaging technique. Prospective and larger datasets with external validation are desired to make their results generalizable.

Ultrasound Radiomics Nomogram to Diagnose Sub-Centimeter Thyroid Nodules Based on ACR TI-RADS

The aim of the present study was to develop a radiomics nomogram to assess whether thyroid nodules (TNs) < 1 cm are benign or malignant. From March 2021 to March 2022, 156 patients were admitted to the Affiliated Hospital of Nantong University, and from September 2017 to March 2022, 116 patients were retrospectively collected from the Jiangsu Provincial Hospital of Integrated Traditional Chinese and Western Medicine. These patients were divided into a training group and an external test group. A radiomics nomogram was established using multivariate logistics regression analysis using the radiomics score and clinical data, including the ultrasound feature scoring terms from the thyroid imaging reporting and data system (TI-RADS). The radiomics nomogram incorporated the correlated predictors, and compared with the clinical model (training set AUC: 0.795; test set AUC: 0.783) and radiomics model (training set AUC: 0.774; test set AUC: 0.740), had better discrimination performance and correction effects in both the training set (AUC: 0.866) and the test set (AUC: 0.866). Both the decision curve analysis and clinical impact curve showed that the nomogram had a high clinical application value. The nomogram constructed based on TI-RADS and radiomics features had good results in predicting and distinguishing benign and malignant TNs < 1 cm.

Machine-learning-based contrast-enhanced computed tomography radiomic analysis for categorization of ovarian tumors

Objectives

This study aims to evaluate the diagnostic performance of machine-learning-based contrast-enhanced CT radiomic analysis for categorizing benign and malignant ovarian tumors.

Methods

A total of 1,329 patients with ovarian tumors were randomly divided into a training cohort (N=930) and a validation cohort (N=399). All tumors were resected, and pathological findings were confirmed. Radiomic features were extracted from the portal venous phase images of contrast-enhanced CT. The clinical predictors included age, CA-125, HE-4, ascites, and margin of tumor. Both radiomics model (including selected radiomic features) and mixed model (incorporating selected radiomic features and clinical predictors) were constructed respectively. Six classifiers [k-nearest neighbor (KNN), support vector machines (SVM), random forest (RF), logistic regression (LR), multi-layer perceptron (MLP), and eXtreme Gradient Boosting (XGBoost)] were used for each model. The mean relative standard deviation (RSD) and area under the receiver operating characteristic curve (AUC) were applied to evaluate and select the best classifiers. Then, the performances of the two models with selected classifiers were assessed in the validation cohort.

Results

The MLP classifier with the least RSD (1.21 and 0.53, respectively) was selected as the best classifier in both radiomics and mixed models. The two models with MLP classifier performed well in the validation cohort, with the AUCs of 0.91 and 0.96 and with accuracies (ACCs) of 0.83 and 0.87, respectively. The Delong test showed that the AUC of mixed model was statistically different from that of radiomics model (p&lt;0.001).

Conclusions

Machine-learning-based CT radiomic analysis could categorize ovarian tumors with good performance preoperatively. The mixed model with MLP classifier may be a potential tool in clinical applications.

Discriminating Between Benign and Malignant Solid Ovarian Tumors Based on Clinical and Radiomic Features of MRI

RATIONALE AND OBJECTIVES

To develop and validate a combined model integrating clinical and radiomic features to non-invasive discriminate between the benign and malignant solid ovarian tumors.

MATERIALS AND METHODS

A total of 148 patients with 156 solid ovarian tumors (86 benign and 70 malignant tumors) were included in this study. The dataset was split into the training and the test set with a ratio of 8:2 using stratified random sampling. 12 clinical features and 1612 radiomic features were extracted from each tumor. These features were selected by least absolute shrinkage and selection operator (Lasso). Three classification models were built using extreme gradient boosting (XGB) algorithm: clinical model, radiomic model, combined model. The area under the receiver operating characteristic curve (AUC), accuracy, precision and sensitivity were analyzed to evaluate the performance of these models.

RESULTS

All of the three models obtained good performances in differentiating benign with malignant solid ovarian tumors in both training and test sets. The AUC, accuracy, precision, sensitivity of clinical model and radiomic model in test set were 0.847 (95% confidence interval (CI), 0.707-0.986, p <0.01), 0.774, 0.769, 0.714, and 0.807 (95%CI, 0.652-0.961, p <0.05), 0.677, 0.643, 0.643, respectively. Combined model had the best prediction results, the AUC, accuracy, precision and sensitivity were 0.954 (95%CI, 0.862-1.0, p <0.01), 0.839, 0.909 and 0.714 in test set.

CONCLUSION

Radiomics based on machine learning can be helpful for radiologists in differentiating the benign and malignant solid ovarian tumors.

An Ultrasonic-Based Radiomics Nomogram for Distinguishing Between Benign and Malignant Solid Renal Masses

Objectives

This study was conducted in order to develop and validate an ultrasonic-based radiomics nomogram for diagnosing solid renal masses.

Methods

Six hundred renal solid masses with benign renal lesions (n = 204) and malignant renal tumors (n = 396) were divided into a training set (n = 480) and a validation set (n = 120). Radiomics features were extracted from ultrasound (US) images preoperatively and then a radiomics score (RadScore) was calculated. By integrating the RadScore and independent clinical factors, a radiomics nomogram was constructed. The diagnostic performance of junior physician, senior physician, RadScore, and radiomics nomogram in identifying benign from malignant solid renal masses was evaluated based on the area under the receiver operating characteristic curve (ROC) in both the training and validation sets. The clinical usefulness of the nomogram was assessed using decision curve analysis (DCA).

Results

The radiomics signature model showed satisfactory discrimination in the training set [area under the ROC (AUC), 0.887; 95% confidence interval (CI), 0.860–0.915] and the validation set (AUC, 0.874; 95% CI, 0.816–0.932). The radiomics nomogram also demonstrated good calibration and discrimination in the training set (AUC, 0.911; 95% CI, 0.886–0.936) and the validation set (AUC, 0.861; 95% CI, 0.802–0.921). In addition, the radiomics nomogram model showed higher accuracy in discriminating benign and malignant renal masses compared with the evaluations by junior physician (DeLong p = 0.004), and the model also showed significantly higher specificity than the senior and junior physicians (0.93 vs. 0.57 vs. 0.46).

Conclusions

The ultrasonic-based radiomics nomogram shows favorable predictive efficacy in differentiating solid renal masses.

Ultrasound Radiomics Nomogram Integrating Three-Dimensional Features Based on Carotid Plaques to Evaluate Coronary Artery Disease

This study aimed to explore the feasibility of ultrasound radiomics analysis before invasive coronary angiography (ICA) for evaluating the severity of coronary artery disease (CAD) quantified by the SYNTAX score (SS). This study included 105 carotid plaques from 105 patients (64 low-SS patients, 41 intermediate-high-SS patients). The clinical characteristics and three-dimensional ultrasound (3D-US) features before ICA were assessed. Ultrasound images of carotid plaques were used for radiomics analysis. Least absolute shrinkage and selection operator (LASSO) regression, which generated several nonzero coefficients, was used to select features that could predict intermediate-high SS. Based on those coefficients, the radiomics score (Rad-score) was calculated. The selected clinical characteristics, 3D-US features, and Rad-score were finally integrated into a radiomics nomogram. Among the clinical characteristics and 3D-US features, high-density lipoprotein (HDL), apolipoprotein B (Apo B), and plaque volume were identified as predictors for distinguishing between low SS and intermediate-high SS. During the radiomics process, 8 optimal radiomics features most capable of identifying intermediate-high SS were selected from 851 candidate radiomics features. The differences in Rad-score between the training and the validation set were significant (p = 0.016 and 0.006). The radiomics nomogram integrating HDL, Apo B, plaque volume, and Rad-score showed excellent results in the training set (AUC, 0.741 (95% confidence interval (CI): 0.646–0.835)) and validation set (AUC, 0.939 (95% CI: 0.860–1.000)), with good calibration (mean absolute errors of 0.028 and 0.059 in training and validation sets, respectively). Decision curve analysis showed that the radiomics nomogram could identify patients who could obtain the most benefit. We concluded that the radiomics nomogram based on carotid plaque ultrasound has favorable value for the noninvasive prediction of intermediate-high SS. This radiomics nomogram has potential value for the risk stratification of CAD before ICA and provides clinicians with a noninvasive diagnostic tool.