Preoperative Discrimination Research Articles

Performance of International Ovarian Tumor Analysis (IOTA) predictive models in preoperative discrimination between benign and malignant adnexal lesions: preliminary outcomes in a Tertiary Care Hospital in Greece.

To apply the International Ovarian Tumor Analysis (IOTA) predictive models, the logistic regression model 2 (LR2) and the IOTA Assessment of Different NEoplasias in the adneXa (ADNEX), in patients with ovarian masses and to compare their performance in preoperative discrimination between benign and malignant adnexal lesions. This was a retrospective diagnostic accuracy study with prospectively collected data, performed between January 2019 and December 2022, in a single tertiary gynecologic oncology center in Greece. The study included women with an adnexal lesion which underwent surgery within 6months after of using the LR2 and ADNEX protocol to assess the risk of malignancy. Correlation of the ultrasound findings with the postoperative histopathological analysis was performed. Receiver-operating characteristics (ROC) curve analysis was used to determine the diagnostic accuracy of the models to classify tumors; sensitivity and specificity were determined for each model and their performance was compared. Of the136 participants, 117 (86%) had benign ovarian masses and 19 (14%) had malignant tumors. The area under the ROC curve (AUC) of the LR2 model was 0.84 (95% CI 0.74-0.93), which was significantly higher than the AUC for ADNEX model: 0.78 (95% CI 0.67-0.89). At a cut off > 10%, the LR2 model had the highest sensitivity 89.5% (95% CI 66.9-98.7) and specificity 85.1% (95% CI 76.9-91.2) compared to ADNEX model [sensitivity 84.2% (95% CI 60.4-96.6) and specificity 71.8% (95% CI 62.7-79.7)]. IOTA LR2 had the highest accuracy in differentiating between benign and malignant ovarian masses. IOTA LR2 and ADNEX models were both useful tools in discriminating between benign and malignant ovarian masses.

Clinical Utility and Diagnostic Accuracy of ROMA, RMI, ADNEX, HE4, and CA125 in the Prediction of Malignancy in Adnexal Masses.

We aimed to compare the clinical utility and diagnostic accuracy of the ADNEX model, ROMA score, RMI I, and RMI IV, as well as two serum markers (CA125 and HE4) in preoperative discrimination between benign and malignant adnexal masses (AMs). We conducted a retrospective study extracting all consecutive patients with AMs seen at our Institution between January 2015 and December 2020. Accuracy metrics included sensitivity (SE), specificity (SP), and area under the receiver operating characteristic curve (AUC), and their 95% confidence intervals (CI) were calculated for basic discrimination between AMs. Model performance was evaluated in terms of discrimination ability and clinical utility (net benefit, NB). A total of 581 women were included; 481 (82.8%) had a benign ovarian tumor and 100 (17.2%) had a malignant tumor. The SE and SP of CA125, HE4, ROMA score, RMI I, RMI IV, and ADNEX model were 0.60 (0.54-0.66) and 0.80 (0.76-0.83); 0.39 (0.30-0.49) and 0.96 (0.94-0.98); 0.59 (0.50-0.68) and 0.92 (0.88-0.95); 0.56 (0.46-0.65) and 0.98 (0.96-0.99); 0.54 (0.44-0.63) and 0.96 (0.94-0.98); 0.82 (0.73-0.88) and 0.91 (0.89-0.94), respectively. The overall AUC was 0.76 (0.74-0.79) for CA125, 0.81 (0.78-0.83) for HE4, 0.82 (0.80-0.85) for ROMA, 0.86 (0.84-0.88) for RMI I, 0.83 (0.81-0.86) for RMI IV, and 0.92 (0.90-0.94) for ADNEX. The NB for ADNEX was higher than other biomarkers and models across all decision thresholds between 5% and 50%. The ADNEX model showed a better discrimination ability and clinical utility when differentiating malignant from benign Ams, compared to CA125, HE4, ROMA score, RMI I, and RMI IV.

Mid-level data fusion strategy based on urinary nucleosides SERS spectra and blood CEA levels for enhanced preoperative detection of lymph node metastasis in colorectal cancer

BackgroundPreoperative prediction of lymph node metastasis (LNM) plays a crucial role in the treatment and prognosis of colorectal cancer (CRC). The traditional histopathological examination is invasive and time-consuming, providing pathological features only postoperatively. Preoperative serum carcinoembryonic antigen (CEA) is strongly correlated with postoperative LN status. However, the detection accuracy of LNM based on a single preoperative CEA level is low. Therefore, developing a more powerful and sensitive diagnostic tool would be of great clinical value for improving the accurate preoperative prediction of LNM in CRC patients. ResultsThis study aimed to develop a mid-level fusion approach using urinary nucleosides Raman spectra and blood CEA data to enhance the preoperative discrimination of CRC patients with and without LNM. Surface-enhanced Raman scattering (SERS) spectra of urinary modified nucleosides, isolated by affinity chromatography, were first acquired from 48 patients with LNM and 49 patients without LNM. The principal component analysis (PCA) scores obtained from the SERS spectra were then combined with preoperative blood CEA values to create a fused data array. The discriminant accuracy based on either dataset alone or the fused data was evaluated using three machine learning algorithms: linear discriminant analysis, k-nearest neighbors, and support vector machine. Results showed that the fused data could discriminate between the two groups with an accuracy of up to 91 %, outperforming SERS alone (86 %) and CEA alone (69 %). SignificanceTo our knowledge, this is the first report of mid-level data fusion of urinary nucleosides SERS spectra with blood CEA levels for the preoperative prediction of LNM in CRC. This work demonstrates that the mid-level data fusion strategy aided by SVM algorithm can greatly improve the preoperative prediction accuracy of LNM. This is crucial for therapeutic decision-making and prognostic assessment in CRC.

Preoperative discrimination of invasive and non-invasive breast cancer using machine learning based on automated breast volume scanning (ABVS) radiomics and virtual touch quantification (VTQ)

PurposeEvaluating the efficacy of machine learning for preoperative differentiation between invasive and non-invasive breast cancer through integrated automated breast volume scanning (ABVS) radiomics and virtual touch quantification (VTQ) techniques.MethodsWe conducted an extensive retrospective analysis on a cohort of 171 breast cancer patients, differentiating them into 124 invasive and 47 non-invasive cases. The data was meticulously divided into a training set (n = 119) and a validation set (n = 52), maintaining a 70:30 ratio. Several machine learning models were developed and tested, including Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM). Their performance was evaluated using the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC), and visualized the feature contributions of the optimal model using Shapley Additive Explanations (SHAP).ResultsThrough both univariate and multivariate logistic regression analyses, we identified key independent predictors in differentiating between invasive and non-invasive breast cancer types: coronal plane features, Shear Wave Velocity (SWV), and Radscore. The AUC scores for our machine learning models varied, ranging from 0.625 to 0.880, with the DT model demonstrating a notably high AUC of 0.874 in the validation set.ConclusionOur findings indicate that machine learning models, which integrate ABVS radiomics and VTQ, are significantly effective in preoperatively distinguishing between invasive and non-invasive breast cancer. Particularly, the DT model stood out in the validation set, establishing it as the primary model in our study. This highlights its potential utility in enhancing clinical decision-making processes.

Machine learning-assisted diagnosis of parotid tumor by using contrast-enhanced CT imaging features

PurposeThis study aims to develop a machine learning diagnostic model for parotid gland tumors based on preoperative contrast-enhanced CT imaging features to assist in clinical decision-making. Materials and methodsClinical data and contrast-enhanced CT images of 144 patients with parotid gland tumors from the Peking University School of Stomatology Hospital, collected from January 2019 to December 2022, were gathered. The 3D slicer software was utilized to accurately annotate the tumor regions, followed by exploring the correlation between multiple preoperative contrast-enhanced CT imaging features and the benign or malignant nature of the tumor, as well as the type of benign tumor. A prediction model was constructed using the k-nearest neighbors (KNN) algorithm. ResultsThrough feature selection, four key features—morphology, adjacent structure invasion, boundary, and suspicious cervical lymph node metastasis—were identified as crucial in preoperative discrimination between benign and malignant tumors. The KNN prediction model achieved an accuracy rate of 94.44 %. Additionally, six features including arterial phase CT value, age, delayed phase CT value, pre-contrast CT value, venous phase CT value, and gender, were also significant in the classification of benign tumors, with a KNN prediction model accuracy of 95.24 %. ConclusionThe machine learning model based on preoperative contrast-enhanced CT imaging features can effectively discriminate between benign and malignant parotid gland tumors and classify benign tumors, providing valuable reference information for clinicians.

High-performance presurgical differentiation of glioblastoma and metastasis by means of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics

ObjectivesTo evaluate the performance of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics in distinguishing between glioblastoma (Gb) and solitary brain metastasis (SBM).Materials and methodsIn this retrospective study, NODDI images were curated from 109 patients with Gb (n = 57) or SBM (n = 52). Automatically segmented multiple volumes of interest (VOIs) encompassed the main tumor regions, including necrosis, solid tumor, and peritumoral edema. Radiomics features were extracted for each main tumor region, using three NODDI parameter maps. Radiomics models were developed based on these three NODDI parameter maps and their amalgamation to differentiate between Gb and SBM. Additionally, radiomics models were constructed based on morphological magnetic resonance imaging (MRI) and diffusion imaging (diffusion-weighted imaging [DWI]; diffusion tensor imaging [DTI]) for performance comparison.ResultsThe validation dataset results revealed that the performance of a single NODDI parameter map model was inferior to that of the combined NODDI model. In the necrotic regions, the combined NODDI radiomics model exhibited less than ideal discriminative capabilities (area under the receiver operating characteristic curve [AUC] = 0.701). For peritumoral edema regions, the combined NODDI radiomics model achieved a moderate level of discrimination (AUC = 0.820). Within the solid tumor regions, the combined NODDI radiomics model demonstrated superior performance (AUC = 0.904), surpassing the models of other VOIs. The comparison results demonstrated that the NODDI model was better than the DWI and DTI models, while those of the morphological MRI and NODDI models were similar.ConclusionThe NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM.Clinical relevance statementThe NODDI radiomics model showed promising performance for preoperative discrimination between Gb and SBM, and radiomics features can be incorporated into the multidimensional phenotypic features that describe tumor heterogeneity.Key Points• The neurite orientation dispersion and density imaging (NODDI) radiomics model showed promising performance for preoperative discrimination between glioblastoma and solitary brain metastasis.• Compared with other tumor volumes of interest, the NODDI radiomics model based on solid tumor regions performed best in distinguishing the two types of tumors.• The performance of the single-parameter NODDI model was inferior to that of the combined-parameter NODDI model.

Estimation of Foetal Weight by Ultrasonography and Neonate at Birth

Background: Ultrasonography intervention in delivery is highly sensitive and primary important for further tests of foetal well-being. Objective: The purpose of the present study was to observe the correlation of estimated foetal weight with neonatal birth weight. Methodology: This was a cross-sectional study on patients at the Labour Ward of Department of Obstetrics and Gynaecology at Sir Salimullah Medical College and Mitford Hospiptal, Dhaka, Bangladesh for six months. The women were selected who had normal pregnancy with early ultrasounographic examination for confirmation of gestational age, singleton live foetus, ultrasound examination for pregnancy profile done within 3 days before delivery. A sonographic foetal weight was estimated by using measurements of foetal body parts-biparietal diameter, abdominal circumference and femoral length. To measure the femur length, first a projection was made that shows a transverse section of one of the long bones, then scan at 900 to this to obtain a longitudinal section. Results: A total number of 100 patients were recruited for this study. The mean (±SD) sonographically estimated foetal weight was 3074±534gm with ranged from 2100 to 4100 gm. The mean (±SD) neonatal birth weight was 2978±466 gm with ranged from 2500 to 3800 gm (p<0.05). Sonographically estimated foetal weight less than 3000 g were correlated with neonatal birth weight. Out of the 100 cases 57(57.0%) cases had less than 3000 g estimated foetal weight and 43(43.0%) cases had 3000 g or more than 3000gm estimated foetal weight Sonographically. Among the 57 cases, which were less than 3000 g by Sonographically, 41 cases were less than 3000 g and 16 cases were found 3000 g or more than 3000 g in neonatal birth weight. Conclusion: Ultrasonography has definite value in the diagnosis of estimated foetal weight and can be regarded as a sensitive and specific imaging modality for pre-operative discrimination of the pregnant women. Journal of National Institute of Neurosciences Bangladesh, January 2023;9(1):42-47

Simple rules, O-RADS, ADNEX and SRR model: Single oncologic center validation of diagnostic predictive models alone and combined (two-step strategy) to estimate the risk of malignancy in adnexal masses and ovarian tumors

ObjectiveTo compare performance of Assessment of Different NEoplasias in the adneXa (ADNEX model), Ovarian-Adnexal Reporting and Data System (O-RADS), Simple Rules Risk (SRR) assessment and the two-step strategy based on the application of Simple Rules (SR) followed by SRR and SR followed by ADNEX in the pre-operative discrimination between benign and malignant adnexal masses (AMs). MethodsWe conducted a retrospective study from January-2018 to December-2021 in which consecutive patients with at AMs were recruited. Accuracy metrics included sensitivity (SE) and specificity (SP) with their 95% confidence intervals (CI) were calculated for ADNEX, O-RADS and SRR. When SR was inconclusive a “two-step strategy” was adopted applying SR + ADNEX model and SR + SRR assessment. ResultsA total of 514 women were included, 400 (77.8%) had a benign ovarian tumor and 114 (22.2%) had a malignant tumor. At a threshold malignancy risk of >10%, the SE and SP of ADNEX model, O-RADS and SRR were: 0.92 (95% CI, 0.86–0.96) and 0.88 (95% CI, 0.85–0.91); 0.93 (95% CI, 0.87–0.97) and 0.89 (95% CI, 0.96–0.92); 0.88 (95% CI, 0.80–0.93) and 0.84 (95% CI, 0.80–0.87), respectively. When we applied SR, 109 (21.2%) cases resulted inconclusive. The SE and SP of two-step strategy SR + SRR assessment and SR + ADNEX model were 0.88 (95% CI, 0.80–0.93) and 0.92 (95% CI, 0.89–0.94), SR + ADNEX model 0.90 (95% CI, 0.83–0.95) and 0.93 (95% CI, 0.90–0.96), respectively. ConclusionsO-RADS presented the highest SE, similar to ADNEX model and SR + ADNEX model. However, the SR + ADNEX model presented the higher performance accuracy with the higher SP and PPV. This two-step strategy, SR and ADNEX model applicated to inconclusive SR, is convenient for clinical evaluation.

Preoperative Discrimination of CDKN2A/B Homozygous Deletion Status in Isocitrate Dehydrogenase-Mutant Astrocytoma: A Deep Learning-Based Radiomics Model Using MRI.

Cyclin-dependent kinase inhibitor 2A/B (CDKN2A/B) homozygous deletion has been verified as an independent and critical biomarker of negative prognosis and short survival in isocitrate dehydrogenase (IDH)-mutant astrocytoma. Therefore, noninvasive and accurate discrimination of CDKN2A/B homozygous deletion status is essential for the clinical management of IDH-mutant astrocytoma patients. To develop a noninvasive, robust preoperative model based on MR imagefeatures for discriminating CDKN2A/B homozygous deletion status of IDH-mutant astrocytoma. Retrospective. Two hundred fifty-one patients: 107 patients with CDKN2A/B homozygous deletion and 144 patients without CDKN2A/B homozygous deletion. 3.0 T/1.5 T: Contrast-enhanced T1-weighted spin-echo inversion recovery sequence (CE-T1WI) and T2-weighted fluid-attenuation spin-echo inversion recovery sequence (T2FLAIR). A total of 1106 radiomics and 1000 deep learning features extracted from CE-T1WI and T2FLAIR were used to develop models to discriminate the CDKN2A/B homozygous deletion status. Radiomics models, deep learning-based radiomics (DLR) models and the final integrated model combining radiomics features with deep learning features were developed and compared their preoperative discrimination performance. Pearson chi-square test and Mann Whitney U test were used for assessing the statistical differences in patients' clinical characteristics. The Delong test compared the statistical differences of receiver operating characteristic (ROC) curves and area under the curve (AUC) of different models. The significance threshold is P < 0.05. The final combined model (training AUC = 0.966; validation AUC = 0.935; test group: AUC = 0.943) outperformed the optimal models based on only radiomics or DLR features (training: AUC = 0.916 and 0.952; validation: AUC = 0.886 and 0.912; test group: AUC = 0.862 and 0.902). Whether based on a single sequence or a combination of two sequences, radiomics and DLR models have achieved promising performance in assessing CDKN2A/B homozygous deletion status. However, the final model combining both deep learning and radiomics features from CE-T1WI and T2FLAIR outperformed the optimal radiomics or DLR model. 4 TECHNICAL EFFICACY: Stage 2.

The value of whole-volume apparent diffusion coefficient histogram analysis in preoperatively distinguishing intracranial solitary fibrous tumor and transitional meningioma.

To investigate the value of whole-volume apparent diffusion coefficient (ADC) histogram analysis in preoperatively distinguishing intracranial solitary fibrous tumors (SFT) from transitional meningiomas (TM), thereby assisting the establishment of the treatment protocol. Preoperative diffusion-weighted imaging datasets of 24 patients with SFT and 28 patients with TM were used to extract whole-volume ADC histogram parameters, including variance, skewness, kurtosis, and mean, as well as 1st (AP1), 10th (AP10), 50th (AP50), 90th (AP90), and 99th (AP99) percentiles of ADC using MaZda software. The independent t-test or Mann-Whitney U test was used to compare the differences between ADC histogram parameters of SFT and TM. Receiver operating characteristic (ROC) curves were generated to evaluate the performance of significant ADC histogram parameters. Spearman's correlation coefficients were calculated to evaluate correlations between these parameters and the Ki-67 expression levels. SFT exhibited significantly higher variance, and lower AP1 and AP10 (all P < 0.05) than TM. The best diagnostic performance was obtained by variance, with an area under the ROC curve of 0.848 (0.722-0.933). However, there was no significant difference in skewness, kurtosis, mean, or other percentiles of ADC between the two groups (all P > 0.05). Significant correlations were also observed between the Ki-67 proliferation index and variance (r = 0.519), AP1 (r = -0.425), and AP10 (r = -0.372) (all P < 0.05). Whole-volume ADC histogram analysis is a feasible tool for non-invasive preoperative discrimination between intracranial SFT and TM, with variance being the most promising prospective parameter.

A semiautomated radiomics model based on multimodal dual-layer spectral CT for preoperative discrimination of the invasiveness of pulmonary ground-glass nodules.

In recent years, spectral computed tomography (CT) has shown excellent performance in the diagnosis of ground-glass nodules (GGNs) invasiveness; however, no research has combined spectral multimodal data and radiomics analysis for comprehensive analysis and exploration. Therefore, this study goes a step further on the basis of the previous research: to investigate the value of dual-layer spectral CT-based multimodal radiomics in accessing the invasiveness of lung adenocarcinoma manifesting as GGNs. In this study, 125 GGNs with pathologically confirmed preinvasive adenocarcinoma (PIA) and lung adenocarcinoma were divided into a training set (n=87) and a test set (n=38). Each lesion was automatically detected and segmented by the pre-trained neural networks, and 63 multimodal radiomic features were extracted. The least absolute shrinkage and selection operator (LASSO) was used to select target features, and a rad-score was constructed in the training set. Logistic regression analysis was conducted to establish a joint model which combined age, gender, and the rad-score. The diagnostic performance of the two models was compared by the receiver operating characteristic (ROC) curve and precision-recall curve. The difference between the two models was compared by the ROC analysis. The test set was used to evaluate the predictive performance and calibrate the model. Five radiomic features were selected. In the training and test sets, the area under the curve (AUC) of the radiomics model was 0.896 (95% CI: 0.830-0.962) and 0.881 (95% CI: 0.777-0.985) respectively, and the AUC of the joint model was 0.932 (95% CI: 0.882-0.982) and 0.887 (95% CI: 0.786-0.988) respectively. There was no significant difference in AUC between the radiomics model and joint model in the training and test sets (0.896 vs. 0.932, P=0.088; 0.881 vs. 0.887, P=0.480). Multimodal radiomics based on dual-layer spectral CT showed good predictive performance in differentiating the invasiveness of GGNs, which could assist in the decision of clinical treatment strategies.

Deep Learning Radiomics Model of Dynamic Contrast‐Enhanced MRI for Evaluating Vessels Encapsulating Tumor Clusters and Prognosis in Hepatocellular Carcinoma

Vessels encapsulating tumor cluster (VETC) is a critical prognostic factor and therapeutic predictor of hepatocellular carcinoma (HCC). However, noninvasive evaluation of VETC remains challenging. To develop and validate a deep learning radiomic (DLR) model of dynamic contrast-enhanced MRI (DCE-MRI) for the preoperative discrimination of VETC and prognosis of HCC. Retrospective. A total of 221 patients with histologically confirmed HCC and stratified this cohort into training set (n = 154) and time-independent validation set (n = 67). A 1.5 T and 3.0 T; DCE imaging with T1-weighted three-dimensional fast spoiled gradient echo. Histological specimens were used to evaluate VETC status. VETC+ cases had a visible pattern (≥5% tumor area), while cases without any pattern were VETC-. The regions of intratumor and peritumor were segmented manually in the arterial, portal-venous and delayed phase (AP, PP, and DP, respectively) of DCE-MRI and reproducibility of segmentation was evaluated. Deep neural network and machine learning (ML) classifiers (logistic regression, decision tree, random forest, SVM, KNN, and Bayes) were used to develop nine DLR, 54 ML and clinical-radiological (CR) models based on AP, PP, and DP of DCE-MRI for evaluating VETC status and association with recurrence. The Fleiss kappa, intraclass correlation coefficient, receiver operating characteristic curve, area under the curve (AUC), Delong test and Kaplan-Meier survival analysis. P value <0.05 was considered as statistical significance. Pathological VETC+ were confirmed in 68 patients (training set: 46, validation set: 22). In the validation set, DLR model based on peritumor PP (peri-PP) phase had the best performance (AUC: 0.844) in comparison to CR (AUC: 0.591) and ML (AUC: 0.672) models. Significant differences in recurrence rates between peri-PP DLR model-predicted VETC+ and VETC- status were found. The DLR model provides a noninvasive method to discriminate VETC status and prognosis of HCC patients preoperatively. 4. Stage 2.

Performance of IOTA Simple Rules Risks, ADNEX Model, Subjective Assessment Compared to CA125 and HE4 with ROMA Algorithm in Discriminating between Benign, Borderline and Stage I Malignant Adnexal Lesions.

Borderline ovarian tumors (BOTs) and early clinical stage malignant adnexal masses can make sonographic diagnosis challenging, while the clinical utility of tumor markers, e.g., CA125 and HE4, or the ROMA algorithm, remains controversial in such cases. To compare the IOTA group Simple Rules Risk (SRR), the ADNEX model and the subjective assessment (SA) with serum CA125, HE4 and the ROMA algorithm in the preoperative discrimination between benign tumors, BOTs and stage I malignant ovarian lesions (MOLs). A multicenter retrospective study was conducted with lesions classified prospectively using subjective assessment and tumor markers with the ROMA. The SRR assessment and ADNEX risk estimation were applied retrospectively. The sensitivity, specificity, positive and negative likelihood ratios (LR+ and LR-) were calculated for all tests. In total, 108 patients (the median age: 48 yrs, 44 postmenopausal) with 62 (79.6%) benign masses, 26 (24.1%) BOTs and 20 (18.5%) stage I MOLs were included. When comparing benign masses with combined BOTs and stage I MOLs, SA correctly identified 76% of benign masses, 69% of BOTs and 80% of stage I MOLs. Significant differences were found for the presence and size of the largest solid component (p = 0.0006), the number of papillary projections (p = 0.01), papillation contour (p = 0.008) and IOTA color score (p = 0.0009). The SRR and ADNEX models were characterized by the highest sensitivity (80% and 70%, respectively), whereas the highest specificity was found for SA (94%). The corresponding likelihood ratios were as follows: LR+ = 3.59 and LR- = 0.43 for the ADNEX; LR+ = 6.40 and LR- = 0.63 for SA and LR+ = 1.85 with LR- = 0.35 for the SRR. The sensitivity and specificity of the ROMA test were 50% and 85%, respectively, with LR+ = 3.44 and LR- = 0.58. Of all the tests, the ADNEX model had the highest diagnostic accuracy of 76%. This study demonstrates the limited value of diagnostics based on CA125 and HE4 serum tumor markers and the ROMA algorithm as independent modalities for the detection of BOTs and early stage adnexal malignant tumors in women. SA and IOTA methods based on ultrasound examination may present superior value over tumor marker assessment.

Machine learning-based multiparametric magnetic resonance imaging radiomics model for distinguishing central neurocytoma from glioma of lateral ventricle.

To develop a machine learning-based radiomics model based on multiparametric magnetic resonance imaging (MRI) for preoperative discrimination between central neurocytomas (CNs) and gliomas of lateral ventricles. A total of 132 patients from two medical centers were enrolled in this retrospective study. Patients from the first medical center were divided into a training cohort (n = 74) and an internal validation cohort (n = 30). Patients from the second medical center were used as the external validation cohort (n = 28). Features were extracted from contrast-enhanced T1-weighted and T2-weighted images. A support vector machine was used for radiomics model investigation. Performance was evaluated using the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). The model's performance was also compared with those of three radiologists. The radiomics model achieved an AUC of 0.986 in the training cohort, 0.933 in the internal validation cohort, and 0.903 in the external validation cohort. In the three cohorts, the AUC values were 0.657, 0.786, and 0.708 for radiologist 1; 0.838, 0.799, and 0.790 for radiologist 2; and 0.827, 0.871, and 0.862 for radiologist 3. When assisted by the radiomics model, two radiologists improved their performance in the training cohort (p < 0.05) but not in the internal or external validation cohorts. The machine learning radiomics model based on multiparametric MRI showed better performance for distinguishing CNs from lateral ventricular gliomas than did experienced radiologists, and it showed the potential to improve radiologist performance. • The machine learning radiomics model shows excellent performance in distinguishing CNs from gliomas. • The radiomics model outweighs two experienced radiologists (area under the receiver operating characteristic curve, 0.90 vs 0.79 and 0.86, respectively). • The radiomics model has the potential to enhance radiologist performance.

Non-contrast and contrast enhanced computed tomography radiomics in preoperative discrimination of lung invasive and non-invasive adenocarcinoma.

This study aimed to assess the value of radiomics based on non-contrast computed tomography (NCCT) and contrast-enhanced computed tomography (CECT) images in the preoperative discrimination between lung invasive adenocarcinomas (IAC) and non-invasive adenocarcinomas (non-IAC). We enrolled 1,185 pulmonary nodules (478 non-IACs and 707 IACs) to build and validate radiomics models. An external testing set comprising 63 pulmonary nodules was collected to verify the generalization of the models. Radiomic features were extracted from both NCCT and CECT images. The predictive performance of radiomics models in the validation and external testing sets were evaluated and compared with radiologists' evaluations. The predictive performances of the radiomics models were also compared between three subgroups in the validation set (Group 1: solid nodules, Group 2: part-solid nodules, and Group 3: pure ground-glass nodules). The NCCT, CECT, and combined models showed good ability to discriminate between IAC and non-IAC [respective areas under the curve (AUCs): validation set = 0.91, 0.90, and 0.91; Group 1 = 0.82, 0.79, and 0.81; Group 2 = 0.93, 0.92, and 0.93; and Group 3 = 0.90, 0.90, and 0.89]. In the external testing set, the AUC of the three models were 0.89, 0.91, and 0.89, respectively. The accuracies of these three models were comparable to those of the senior radiologist and better those that of the junior radiologist. Radiomic models based on CT images showed good predictive performance in discriminating between lung IAC and non-IAC, especially in part solid nodule group. However, radiomics based on CECT images provided no additional value compared to NCCT images.

Differentiating between adrenocortical carcinoma and lipid-poor cortical adenoma: A novel cross-sectional imaging-based score

BackgroundDiscrimination between adrenocortical carcinoma and lipid-poor cortical adenoma preoperatively is frequently difficult as these two entities have overlapping imaging characteristics. Differentiation will allow for the selection of the most appropriate operative approach and may help prevent over-treatment. We aimed to identify imaging features that could preoperatively differentiate adrenocortical carcinoma from lipid-poor cortical adenoma and use them in a novel imaging-based score. MethodsWe conducted a retrospective analysis of patients with pathologically proven adrenocortical carcinoma and lipid-poor cortical adenoma who underwent resection in a single tertiary referral center between March 1998 and August 2020. The inclusion criteria were diameter >1 cm, attenuation >10 Hounsfield units on nonenhanced computed tomography, and histopathologic diagnosis. Patients with metastatic or locally advanced adrenocortical carcinoma adenoma (stages 3–4) were excluded. We developed a score using binary logistic multivariate regression model in 5-fold derivation (∼70%) cohorts with stepwise backward conditional regression as feature selection. Standardized mean regression weight was used as variable score points. ResultsWe identified 232 adrenals resected across 211 patients. By comparing the imaging characteristics of adrenocortical carcinoma (n = 56) and lipid-poor cortical adenoma (n = 156), we revealed statistically significant differences between the groups in 9 parameters: size, attenuation, thin and thick rim enhancement patterns, heterogeneity, calcification, necrosis, fat infiltration, and lymph node prominence. The score mean performance was 100% sensitivity for the exclusion of adrenocortical carcinoma, 80% specificity (95% confidence interval, 68.3–91.5), 66% positive predictive value (95% confidence interval, 52.3–78.7), and 100% negative predictive value with area under the curve of 0.974. ConclusionWe defined and evaluated a novel 9-variable, imaging-based score. This score outperformed any single variable and could facilitate safe preoperative discrimination of adrenocortical carcinoma and lipid-poor cortical adenoma.

Clinical utility of vesical imaging-reporting and data system (VI-RADS) in non-muscle invasive bladder cancer (NMIBC) patients candidate for en-bloc transurethral resection: A prospective study.

To assess accuracy of vesical imaging-reporting and data system (VI-RADS) 5-point score in detection of muscle invasive bladder cancer and avoiding second look transurethral resection of the tumors (TURBT). Additionally, to assess safety and efficacy of bipolar en-block transurethral urethral resection of bladder tumor. Patients with bladder mass up to 5 cm were included in the study. VI-RADS 5-point score was done preoperative for all cases and postoperatively before second look TURBT. Patients were followed up for 12 months. In all, 80 cases were eligible for the study. Preoperative VI-RADS score at cutoff of 3 had sensitivity of 89.3 %, specificity 83.3 %, postive predective value (PPV) 92.6 %, negative predictive value (NPV) 76.9 %, accuracy of 87.5 %, while at cutoff 2 sensitivity was 82.1%, specificity 91.7%, PPV 95.8%, NPV 68.8%, accuracy of 85.0%. Operative time 28.8 ± 9.4 minutes, hemoglobin drop 0.3 ± 0.05 g/dl, catheterization time 2.8 ± 0.8 days, hospital stay 1.4 ± 0.4 days. No complications occurred. Recurrence in field of resection 3.75%. Detrusor muscle was available in 76 cases (95%). Postoperative VI-RADS score at cutoff of 3 had sensitivity of 78.6%, specificity 77.8%, PPV 84.6%, NPV 70.0%, accuracy of 78.3%. At cutoff 2 VI-RADS score sensitivity was 71.4%, specificity 77.8%, PPV 83.3%, NPV 63.6%, accuracy of 73.9%. VI-RADS 5-point score showed high sensitivity and specificity in preoperative discrimination of non-muscle invasive bladder cancer (NMIBC) from muscle invasive bladder cancer cases and in avoiding unnecessary second look TURBT. Bipolar en-block TURBT technique is both safe and efficacious in resecting NMIBC cases with low recurrence rate.

Analysis of outcomes for communication mode in cochlear implant in prelingually deafened adults

ObjectiveRecent studies have suggested that speech perception outcomes after cochlear implantation (CI) in prelingually deafened adults have improved with advances in CI technology and speech processing strategies. However, the outcomes vary from case to case. Communication mode has been reported in many studies as the factor that related to the post CI outcomes. This study aimed at investigating the post CI outcomes and the progress during 2 years for each communication mode. Material and MethodsThe subjects were 17 prelingually deafened adults undergoing CI at our hospital between April 2013 and March 2019. We investigated preoperative factors affecting post CI outcomes. Also we analyzed post CI outcomes for each communication mode and compared preoperative factors for each communication mode. ResultsCommunication mode and preoperative discrimination score were the factor affecting on postoperative discrimination score. The speech perception score after CI improved significantly in the oral and lip-reading group and total communication group. The speech perception scores in postlingually deafened adults improved significantly during the first six months and became to plateau after CI. On the other hand, the scores of prelingually deafened adults tended to improve gradually after six months postoperatively. Furthermore, the degree of improvement and progress differed by each communication mode. ConclusionThe communication mode is important factors in predicting outcomes in prelingually deafened adults after CI. Long-term auditory training is important for prelingually deafened adults who use visual information as their preoperative method of communication.

Performance of IOTA Simple Rules, Simple Rules risk assessment, ADNEX model and O-RADS in differentiating between benign and malignant adnexal lesions in North American women.

To apply the International Ovarian Tumor Analysis (IOTA) Simple Rules (SR), the IOTA Simple Rules risk assessment (SRR), the IOTA Assessment of Different NEoplasias in the adneXa (ADNEX) model and the Ovarian-Adnexal Reporting and Data System (O-RADS) in the same cohort of North American patients and to compare their performance in preoperative discrimination between benign and malignant adnexal lesions. This was a single-center diagnostic accuracy study, performed between March 2018 and February 2021, which included 150 women with an adnexal lesion. Using the ADNEX model, lesions were classified prospectively, whereas the SR, SRR assessment and O-RADS were applied retrospectively. Surgery with histological analysis was performed within 6 months of the ultrasound exam. Sensitivity and specificity were determined for each testing modality and the performance of the different modalities was compared. Of the 150 women, 110 (73.3%) had a benign ovarian tumor and 40 (26.7%) had a malignant tumor. The mean risk of malignancy generated by the ADNEX model without CA 125 was significantly higher in malignant vs benign lesions (63.3% vs 11.8%) and the area under the receiver-operating-characteristics curve (AUC) of the ADNEX model for differentiating between benign and malignant adnexal masses at the time of ultrasound examination was 0.937. The mean risk of malignancy generated by SRR assessment was also significantly higher in malignant vs benign lesions (74.1% vs 15.9%) and the AUC was 0.941. To compare the ADNEX model, SRR assessment and O-RADS, the malignancy risk threshold was set at ≥ 10%. This cut-off differentiates O-RADS low-risk categories (Category ≤ 3) from intermediate-to-high-risk categories (Categories 4 and 5). At this cut-off, the sensitivity of the ADNEX model was 97.5% (95% CI, 85.3%-99.9%) and the specificity was 63.6% (95% CI, 53.9%-72.4%), and, for the SRR model, the sensitivity was 100% (95% CI, 89.1%-100%) and the specificity was 51.8% (95% CI, 42.1%-61.4%). In the 113 cases to which the SR could be applied, the sensitivity was 100% (95% CI, 81.5%-100%) andthe specificity was 95.6% (95% CI, 88.5%-98.6%). If the remaining 37 cases, which were inconclusive under SR, were designated 'malignant', the sensitivity remained at 100% but the specificity was reduced to 79.1% (95% CI, 70.1%-86.0%). The 150 cases fell into the following O-RADS categories: 17 (11.3%) lesions in Category 2, 34 (22.7%) in Category 3, 66 (44.0%) in Category 4 and 33 (22.0%) in Category 5. There were no histologically proven malignant lesions in Category 2 or 3. There were 14 malignant lesions in Category 4 and 26 in Category 5. The sensitivity of O-RADS using a malignancy risk threshold of ≥ 10% was 100% (95% CI, 89.1%-100.0%) and the specificity was 46.4% (95% CI, 36.9%-56.1%). When IOTA terms and techniques are used, the performance of IOTA models in a North American patient population is in line with published IOTA results in other populations. The IOTA SR, SRR assessment and ADNEX model and O-RADS have similar sensitivity in the preoperative discrimination of malignant from benign pelvic tumors; however, the IOTA models have higher specificity and the algorithm does not require the use of magnetic resonance imaging. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.

Machine Learning-Based Radiological Features and Diagnostic Predictive Model of Xanthogranulomatous Cholecystitis

BackgroundXanthogranulomatous cholecystitis (XGC) is a rare benign chronic inflammatory disease of the gallbladder that is sometimes indistinguishable from gallbladder cancer (GBC), thereby affecting the decision of the choice of treatment. Thus, this study aimed to analyse the radiological characteristics of XGC and GBC to establish a diagnostic prediction model for differential diagnosis and clinical decision-making.MethodsWe investigated radiological characteristics confirmed by the RandomForest and Logistic regression to establish computed tomography (CT), magnetic resonance imaging (MRI), CT/MRI models and diagnostic prediction model, and performed receiver operating characteristic curve (ROC) analysis to prove the effectiveness of the diagnostic prediction model.ResultsBased on the optimal features confirmed by the RandomForest method, the mean area under the curve (AUC) of the ROC of the CT and MRI models was 0.817 (mean accuracy = 0.837) and 0.839 (mean accuracy = 0.842), respectively, whereas the CT/MRI model had a considerable predictive performance with the mean AUC of 0.897 (mean accuracy = 0.906). The diagnostic prediction model established for the convenience of clinical application was similar to the CT/MRI model with the mean AUC and accuracy of 0.888 and 0.898, respectively, indicating a preferable diagnostic efficiency in distinguishing XGC from GBC.ConclusionsThe diagnostic prediction model showed good diagnostic accuracy for the preoperative discrimination of XGC and GBC, which might aid in clinical decision-making.