Data System Category Research Articles

TECRR: a benchmark dataset of radiological reports for BI-RADS classification with machine learning, deep learning, and large language model baselines

BackgroundRecently, machine learning (ML), deep learning (DL), and natural language processing (NLP) have provided promising results in the free-form radiological reports’ classification in the respective medical domain. In order to classify radiological reports properly, a high-quality annotated and curated dataset is required. Currently, no publicly available breast imaging-based radiological dataset exists for the classification of Breast Imaging Reporting and Data System (BI-RADS) categories and breast density scores, as characterized by the American College of Radiology (ACR). To tackle this problem, we construct and annotate a breast imaging-based radiological reports dataset and its benchmark results. The dataset was originally in Spanish. Board-certified radiologists collected and annotated it according to the BI-RADS lexicon and categories at the Breast Radiology department, TecSalud Hospitals Monterrey, Mexico. Initially, it was translated into English language using Google Translate. Afterwards, it was preprocessed by removing duplicates and missing values. After preprocessing, the final dataset consists of 5046 unique reports from 5046 patients with an average age of 53 years and 100% women. Furthermore, we used word-level NLP-based embedding techniques, term frequency-inverse document frequency (TF-IDF) and word2vec to extract semantic and syntactic information. We also compared the performance of ML, DL and large language models (LLMs) classifiers for BI-RADS category classification.ResultsThe final breast imaging-based radiological reports dataset contains 5046 unique reports. We compared K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient-Boosting (GB), Extreme Gradient Boosting (XGB), Long Short-Term Memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT) and Biomedical Generative Pre-trained Transformer (BioGPT) classifiers. It is observed that the BioGPT classifier with preprocessed data performed 6% better with a mean sensitivity of 0.60 (95% confidence interval (CI), 0.391-0.812) compared to the second best performing classifier BERT, which achieved mean sensitivity of 0.54 (95% CI, 0.477-0.607).ConclusionIn this work, we propose a curated and annotated benchmark dataset that can be used for BI-RADS and breast density category classification. We also provide baseline results of most ML, DL and LLMs models for BI-RADS classification that can be used as a starting point for future investigation. The main objective of this investigation is to provide a repository for the investigators who wish to enter the field to push the boundaries further.

Optimization of Extended Pelvic Lymph Node Dissection Side for Prostate Cancer.

This study aimed to show the association between tumor location and laterality of positive lymph nodes by evaluating biopsy and magnetic resonance imaging (MRI) findings, and to optimize the extended pelvic lymph node dissection (ePLND) side for prostate cancer. The study enrolled patients who underwent robot-assisted radical prostatectomy with ePLND. Tumor locations were determined according to International Society of Urological Pathology grade group 4/5 in biopsies and Prostate Imaging-Reporting and Data System category 4/5 in MRI results. The concordance of tumor location lobe and positive lymph node side with the performance of tumor location-guided ePLND for positive lymph node detection was evaluated. For 301 patients who underwent ePLND at Kyushu University Hospital, tumor locations determined by biopsy and MRI findings showed no lesion in 8 (2.7%) patients, unilateral lobe in 223 (74.1%) patients, and bilateral lobe in 70 (23.3%) patients. The accuracies for detection of any and all positive lymph nodes by tumor location-guided unilateral ePLND were 99.6% and 97.3%, respectively. Among the patients at St. Luke's International Hospital, the accuracies for detection of any and all positive lymph nodes by tumor location-guided unilateral ePLND were estimated to be 99.0% and 97.3%, respectively. This study proposed tumor location-guided ePLND according to biopsy and MRI findings. This novel strategy is expected to reduce the burden of bilateral ePLND at the cost of acceptable risk of failing to detect positive lymph nodes.

Evaluating text and visual diagnostic capabilities of large language models on questions related to the Breast Imaging Reporting and Data System Atlas 5th edition.

This study aimed to evaluate the performance of large language models (LLMs) and multimodal LLMs in interpreting the Breast Imaging Reporting and Data System (BI-RADS) categories and providing clinical management recommendations for breast radiology in text-based and visual questions. This cross-sectional observational study involved two steps. In the first step, we compared ten LLMs (namely ChatGPT 4o, ChatGPT 4, ChatGPT 3.5, Google Gemini 1.5 Pro, Google Gemini 1.0, Microsoft Copilot, Perplexity, Claude 3.5 Sonnet, Claude 3 Opus, and Claude 3 Opus 200K), general radiologists, and a breast radiologist using 100 text-based multiple-choice questions (MCQs) related to the BI-RADS Atlas 5th edition. In the second step, we assessed the performance of five multimodal LLMs (ChatGPT 4o, ChatGPT 4V, Claude 3.5 Sonnet, Claude 3 Opus, and Google Gemini 1.5 Pro) in assigning BI-RADS categories and providing clinical management recommendations on 100 breast ultrasound images. The comparison of correct answers and accuracy by question types was analyzed using McNemar's and chi-squared tests. Management scores were analyzed using the Kruskal- Wallis and Wilcoxon tests. Claude 3.5 Sonnet achieved the highest accuracy in text-based MCQs (90%), followed by ChatGPT 4o (89%), outperforming all other LLMs and general radiologists (78% and 76%) (P < 0.05), except for the Claude 3 Opus models and the breast radiologist (82%) (P > 0.05). Lower-performing LLMs included Google Gemini 1.0 (61%) and ChatGPT 3.5 (60%). Performance across different categories of showed no significant variation among LLMs or radiologists (P > 0.05). For breast ultrasound images, Claude 3.5 Sonnet achieved 59% accuracy, significantly higher than other multimodal LLMs (P < 0.05). Management recommendations were evaluated using a 3-point Likert scale, with Claude 3.5 Sonnet scoring the highest (mean: 2.12 ± 0.97) (P < 0.05). Accuracy varied significantly across BI-RADS categories, except Claude 3 Opus (P < 0.05). Gemini 1.5 Pro failed to answer any BI-RADS 5 questions correctly. Similarly, ChatGPT 4V failed to answer any BI-RADS 1 questions correctly, making them the least accurate in these categories (P < 0.05). Although LLMs such as Claude 3.5 Sonnet and ChatGPT 4o show promise in text-based BI-RADS assessments, their limitations in visual diagnostics suggest they should be used cautiously and under radiologists' supervision to avoid misdiagnoses. This study demonstrates that while LLMs exhibit strong capabilities in text-based BI-RADS assessments, their visual diagnostic abilities are currently limited, necessitating further development and cautious application in clinical practice.

Preliminary experiments on interpretable ChatGPT-assisted diagnosis for breast ultrasound radiologists.

Ultrasound is essential for detecting breast lesions. The American College of Radiology's Breast Imaging Reporting and Data System (BI-RADS) classification system is widely used, but its subjectivity can lead to inconsistency in diagnostic outcomes. Artificial intelligence (AI) models, such as ChatGPT-3.5, may potentially enhance diagnostic accuracy and efficiency in medical settings. This study aimed to assess the utility of the ChatGPT-3.5 model in generating BI-RADS classifications for breast ultrasound reports and its ability to replicate the "chain of thought" (CoT) in clinical decision-making to improve model interpretability. Breast ultrasound reports were collected, and ChatGPT-3.5 was used to generate diagnoses and treatment plans. We evaluated GPT-4's performance by comparing its generated reports to those from doctors with various levels of experience. We also conducted a Turing test and a consistency analysis. To enhance the interpretability of the model, we applied the CoT method to deconstruct the decision-making chain of the GPT model. A total of 131 patients were evaluated, with 57 doctors participating in the experiment. ChatGPT-3.5 showed promising performance in structure and organization (S&O), professional terminology and expression (PTE), treatment recommendations (TR), and clarity and comprehensibility (C&C). However, improvements are needed in BI-RADS classification, malignancy diagnosis (MD), likelihood of being written by a physician (LWBP), and ultrasound doctor artificial intelligence acceptance (UDAIA). Turing test results indicated that AI-generated reports convincingly resembled human-authored reports. Reproducibility experiments displayed consistent performance. Erroneous report analysis revealed issues related to incorrect diagnosis, inconsistencies, and overdiagnosis. The CoT investigation supports the potential of ChatGPT to replicate the clinical decision-making process and offers insights into AI interpretability. The ChatGPT-3.5 model holds potential as a valuable tool for assisting in the efficient determination of BI-RADS classifications and enhancing diagnostic performance.

Enhancing Breast Cancer Detection through Advanced AI-Driven Ultrasound Technology: A Comprehensive Evaluation of Vis-BUS.

This study aims to enhance breast cancer detection accuracy through an AI-driven ultrasound tool, Vis-BUS, developed by Barreleye Inc., Seoul, South Korea. Vis-BUS incorporates Lesion Detection AI (LD-AI) and Lesion Analysis AI (LA-AI), along with a Cancer Probability Score (CPS), to differentiate between benign and malignant breast lesions. A retrospective analysis was conducted on 258 breast ultrasound examinations to evaluate Vis-BUS's performance. The primary methods included the application of LD-AI and LA-AI to b-mode ultrasound images and the generation of CPS for each lesion. Diagnostic accuracy was assessed using metrics such as the Area Under the Receiver Operating Characteristic curve (AUROC) and the Area Under the Precision-Recall curve (AUPRC). The study found that Vis-BUS achieved high diagnostic accuracy, with an AUROC of 0.964 and an AUPRC of 0.967, indicating its effectiveness in distinguishing between benign and malignant lesions. Logistic regression analysis identified that 'Fatty' lesion density had an extremely high odds ratio (OR) of 27.7781, suggesting potential convergence issues. The 'Unknown' density category had an OR of 0.3185, indicating a lower likelihood of correct classification. Medium and large lesion sizes were associated with lower likelihoods of correct classification, with ORs of 0.7891 and 0.8014, respectively. The presence of microcalcifications showed an OR of 1.360. Among Breast Imaging-Reporting and Data System categories, category C5 had a significantly higher OR of 10.173, reflecting a higher likelihood of correct classification. Vis-BUS significantly improves diagnostic precision and supports clinical decision-making in breast cancer screening. However, further refinement is needed in areas like lesion density characterization and calcification detection to optimize its performance.

Evaluation of combined hepatocellular-cholangiocarcinoma using CEUS LI-RADS: correlation with pathological characteristics.

To explore the factors that influence the contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS) classification of combined hepatocellular-cholangiocarcinoma (cHCC-ICC). Between September 2014 to July 2020, the CEUS features of 58 patients with pathologically confirmed cHCC-ICC were retrospectively evaluated and assigned according to the CEUS LI-RADS (version 2017). The pathological characteristics of nodules categorizing as different CEUS LI-RADS categories were compared. Multivariate logistic regression analysis was conducted to explore potential factors that may influence the CEUS LI-RADS classification of cHCC-ICC. According to CEUS LI-RADS, 32.8% (19/58), 63.8% (37/58), and 3.4% (2/58) were categorized as LR-5, LR-M, and LR-TIV, respectively. There was significant difference between the LR-M and LR-5 groups with regard to the pathological grade, nodule size, and HCC/ICC-component ratio of cHCC-ICC. Multivariate logistic regression analysis identified tumor size and the relative proportions of hepatocellular carcinomas (HCC) and intrahepatic cholangiocarcinomas (ICC) components as the independent influencing factors. Tumor size and the relative proportion of HCC and ICC components within the nodule had a significant impact on the CEUS LI-RADS classification of cHCC-ICC.

Histopathological Grading based on Tumor Margin according to BI-RADS Mammography in Breast Cancer

Highlights: The highest distribution of breast cancer patients’ age based on the 5-year age interval was 45- 49 years old. There was no significant difference between tumor margin and age of breast cancer patients. There was no significant difference between tumor margin and histopathological grade. Abstract Introduction: Mammography is an X-ray technique used to take images of the breast. It is the primary diagnostic method for breast tumors. Breast imaging reporting and data system (BI-RADS) classification is needed to determine benign or malignant masses by accessing the mass's shape, margin, density, and other features. However, the tumor margin is the most helpful one. This study aimed to know the difference in the distribution of tumor margin types in each histopathological grading in breast cancer patients. Methods: This was an observational analytic study with a comparative approach using secondary data from medical records of patients with breast cancer at the radio diagnostic and anatomical pathology installation of Dr. Soetomo General Acadamic Hospital, Surabaya, from January 2017 to December 2021. All statistical data were performed using the International Business Machines Corporation (IBM) Statistical Package for Social Sciences (SPSS) version 27. Results: Out of 235 cases, the highest distribution of breast cancer patients’ age interval was 45-49 years old (20.9%), the primary tumor margin type was spiculated (64.3%), and the highest distribution of histopathological grading was grade 3 (53.2%). There was no significant difference between tumor margin and age of breast cancer patients (p = 0.815), with spiculated tumor margin as the most common type in all age intervals. There was no significant difference (p = 0.163) in the distribution of tumor margin types in each histopathological grading, with spiculated tumor margin as the most common type in every grade. Conclusion: There was no significant difference between tumor margin and age of breast cancer patients, and there was no significant difference between tumor margin and histopathological grading.

Diagnostic efficacy of the contrast-enhanced ultrasound thyroid imaging reporting and data system classification for benign and malignant thyroid nodules.

The contrasted-enhanced ultrasound thyroid imaging reporting and data system (CEUS TI-RADS) is the first international risk stratification system for thyroid nodules based on conventional ultrasound (US) and CEUS. This study aimed to evaluate the diagnostic efficacy of CEUS TI-RADS for benign and malignant thyroid nodules and to assess the related interobserver agreement. The study recruited 433 patients who underwent thyroid US and CEUS between January 2019 and June 2023 at the Affiliated Hospital of Guangdong Medical University. A retrospective analysis of 467 thyroid nodules confirmed by fine-needle aspiration (FNA) and/or surgery was performed. Further, a CEUS TI-RADS classification was assigned to each thyroid nodule based on the CEUS TI-RADS scoring criteria for the US and CEUS features of the nodule. The nodules were grouped based on their sizes as follows: size ≤1 cm, group A; size >1 and ≤4 cm, group B; and size >4 cm, group C. Multivariate logistic regression was used to analyze independent risk factors for malignant thyroid nodules. Pathological assessment was the reference standard for establishing the sensitivity (SEN), specificity (SPE), accuracy (ACC), positive predictive value (PPV), and negative predictive value (NPV) of CEUS TI-RADS in diagnosing malignant thyroid nodules. The area under the curve (AUC) in the receiver operating characteristic (ROC) curve analysis was used to compare the diagnostic efficacy of the scoring system in predicting malignancy in three groups of nodules. The intragroup correlation coefficient (ICC) was adopted to assess the interobserver agreement of the CEUS TI-RADS score. Out of the 467 thyroid nodules, 262 were malignant and 205 were benign. Logistic regression analysis revealed that the independent risk factors for malignant thyroid nodules included punctate echogenic foci (P<0.001), taller-than-wide shape (P=0.015), extrathyroidal invasion (P=0.020), irregular margins/lobulation (P=0.036), hypoechoicity on US (P=0.038), and hypoenhancement on CEUS (P<0.001). The AUC for the CEUS TI-RADS in diagnosing malignant thyroid nodules was 0.898 for all nodules, 0.795 for group A, 0.949 for group B, and 0.801 for group C, with the optimal cutoff values of the CEUS TI-RADS being 5 points, 6 points, 5 points, and 5 points, respectively. Among these groups of nodules, group B had the highest AUC, with the SEN, SPE, ACC, PPV, and NPV for diagnosing malignant nodules being 95.9%, 88.1%, 92.8%, 92.6%, and 93.2%, respectively. The ICC of the CEUS TI-RADS classification between senior and junior physicians was 0.862 (P<0.001). In summary, CEUS TI-RADS demonstrated significant efficacy in distinguishing thyroid nodules. Nonetheless, there were variations in its capacity to detect malignant nodules across diverse sizes, and it demonstrate optimal performance in 1- to 4-cm nodules. These findings may serve as important insights for clinical diagnoses.

Non-genetic factors and breast cancer: an umbrella review of meta-analyses

BackgroundPrevious research has found associations between various non-genetic factors and breast cancer (BrCa) risk. This study summarises and appraises the credibility of the available evidence on the association between non-genetic factors and BrCa risk.MethodsWe conducted an umbrella review of meta-analyses. Medline, Scopus, and the Cochrane databases were systematically searched for meta-analyses examining non-genetic factors and BrCa incidence or mortality. The strength of the evidence was graded in four categories (i.e., weak, suggestive, highly suggestive, convincing).ResultsA total of 781 meta-analyses from 280 publications were evaluated and graded. We included exposures related to anthropometric measurements, biomarkers, breast characteristics and diseases, diet and supplements, environment, exogenous hormones, lifestyle and social factors, medical history, medication, reproductive history, and pregnancy. The largest number of examined associations was found for the category of diet and supplements and for exposures such as aspirin use and active smoking. The statistically significant (P-value < 0.05) meta-analyses were 382 (49%), of which 204 (53.4%) reported factors associated with increased BrCa risk. Most of the statistically significant evidence (n = 224, 58.6%) was graded as weak. Convincing harmful associations with heightened BrCa risk were found for increased body mass index (BMI), BMI and weight gain in postmenopausal women, oral contraceptive use in premenopausal women, increased androstenedione, estradiol, estrone, and testosterone concentrations, high Breast Imaging Reporting and Data System (BIRADS) classification, and increased breast density. Convincing protective factors associated with lower BrCa risk included high fiber intake and high sex hormone binding globulin (SHBG) levels while highly suggestive protective factors included high 25 hydroxy vitamin D [25(OH)D] levels, adherence to healthy lifestyle, and moderate-vigorous physical activity.ConclusionsOur findings suggest some highly modifiable factors that protect from BrCa. Interestingly, while diet was the most studied exposure category, the related associations failed to reach higher levels of evidence, indicating the methodological limitations in the field. To improve the validity of these associations, future research should utilise more robust study designs and better exposure assessment techniques. Overall, our study provides knowledge that supports the development of evidence-based BrCa prevention recommendations and guidance, both at an individual level and for public health initiatives.Trial registrationPROSPERO CRD42022370675.

Clinical Validation of a Deep Learning Algorithm for Automated Coronary Artery Disease Detection and Classification Using a Heterogeneous Multivendor Coronary Computed Tomography Angiography Data Set.

We sought to clinically validate a fully automated deep learning (DL) algorithm for coronary artery disease (CAD) detection and classification in a heterogeneous multivendor cardiac computed tomography angiography data set. In this single-centre retrospective study, we included patients who underwent cardiac computed tomography angiography scans between 2010 and 2020 with scanners from 4 vendors (Siemens Healthineers, Philips, General Electrics, and Canon). Coronary Artery Disease-Reporting and Data System (CAD-RADS) classification was performed by a DL algorithm and by an expert reader (reader 1, R1), the gold standard. Variability analysis was performed with a second reader (reader 2, R2) and the radiologic reports on a subset of cases. Statistical analysis was performed stratifying patients according to the presence of CAD (CAD-RADS >0) and obstructive CAD (CAD-RADS ≥3). Two hundred ninety-six patients (average age: 53.66 ± 13.65, 169 males) were enrolled. For the detection of CAD only, the DL algorithm showed sensitivity, specificity, accuracy, and area under the curve of 95.3%, 79.7%, 87.5%, and 87.5%, respectively. For the detection of obstructive CAD, the DL algorithm showed sensitivity, specificity, accuracy, and area under the curve of 89.4%, 92.8%, 92.2%, and 91.1%, respectively. The variability analysis for the detection of obstructive CAD showed an accuracy of 92.5% comparing the DL algorithm with R1, and 96.2% comparing R1 with R2 and radiology reports. The time of analysis was lower using the DL algorithm compared with R1 (P < 0.001). The DL algorithm demonstrated robust performance and excellent agreement with the expert readers' analysis for the evaluation of CAD, which also corresponded with significantly reduced image analysis time.

Intraindividual comparison of CT and MRI for predicting vessels encapsulating tumor clusters in hepatocellular carcinoma.

To establish and validate scoring models for predicting vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC) using computed tomography (CT) and magnetic resonance imaging (MRI), and to intra-individually compare the predictive performance between the two modalities. We retrospectively included 324 patients with surgically confirmed HCC who underwent preoperative dynamic CT and MRI with extracellular contrast agent between June 2019 and August 2020. These patients were then divided into a discovery cohort (n = 227) and a validation cohort (n = 97). Imaging features and Liver Imaging Reporting and Data System (LI-RADS) categories of VETC-positive HCCs were evaluated. Logistic regression analyses were conducted on the discovery cohort to identify clinical and imaging predictors associated with VETC-positive cases. Subsequently, separate CT-based and MRI-based scoring models were developed, and their diagnostic performance was compared using generalized estimating equations. On both CT and MRI, VETC-positive HCCs exhibited a higher frequency of size > 5.0 cm, necrosis or severe ischemia, non-smooth tumor margin, targetoid appearance, intratumor artery, and heterogeneous enhancement with septations or irregular ring-like structure compared to VETC-negative HCCs (all p < 0.05). Regarding LI-RADS categories, VETC-positive HCCs were more frequently categorized as LR-M than VETC-negative cases (all p < 0.05). In the validation cohort, the CT-based model showed similar sensitivity (76.7% vs. 86.7%, p = 0.375), specificity (83.6% vs. 74.6%, p = 0.180), and area under the curve value (0.80 vs. 0.81, p = 0.910) to the MRI-based model in predicting VETC-positive HCCs. Preoperative CT and MRI demonstrated comparable performance in the identification of VETC-positive HCCs, thus displaying promising predictive capabilities. Both computed tomography and magnetic resonance imaging demonstrated promise in preoperatively identifying the vessel-encapsulating tumor cluster pattern in hepatocellular carcinoma, with no statistically significant difference between the two modalities, potentially adding additional prognostic value. Computed tomography (CT) and magnetic resonance imaging (MRI) show promise in the preoperative identification of vessels encapsulating tumor clusters-positive hepatocellular carcinoma (HCC). HCC with vessels encapsulating tumor cluster patterns were more frequently LR-M compared to those without. These CT and MRI models showed comparable ability in identifying vessels encapsulating tumor clusters-positive HCC.

Clinical-imaging metrics for the diagnosis of prostate cancer in PI-RADS 3 lesions

ObjectiveTo explore the feasibility and efficacy of clinical-imaging metrics in the diagnosis of prostate cancer (PCa) and clinically significant prostate cancer (csPCa) in prostate imaging-reporting and data system (PI-RADS) category 3 lesions. MethodsA retrospective analysis was conducted on lesions diagnosed as PI-RADS 3. They were categorized into benign, non-csPCa and csPCa groups. Apparent diffusion coefficient (ADC), T2-weighted imaging signal intensity (T2WISI), coefficient of variation of ADC and T2WISI, prostate-specific antigen density (PSAD), ADC density (ADCD), prostate-specific antigen lesion volume density (PSAVD) and ADC lesion volume density (ADCVD) were measured and calculated. Univariate and multivariate analyses were used to identify risk factors associated with PCa and csPCa. Receiver operating characteristic curve (ROC) and decision curves were utilized to assess the efficacy and net benefit of independent risk factors. ResultsAmong 202 patients, 133 had benign prostate disease, 25 non-csPCa and 44 csPCa. Age, PSA and lesion location showed no significant differences (P > 0.05) among the groups. T2WISI and coefficient of variation of ADC (ADCcv) were independent risk factors for PCa in PI-RADS 3 lesions, yielding an area under the curve (AUC) of 0.68. ADC was an independent risk factor for csPCa in PI-RADS 3 lesions, yielding an AUC of 0.65. Decision curve analysis showed net benefit for patients at certain probability thresholds. ConclusionsT2WISI and ADCcv, along with ADC, respectively showed considerable promise in enhancing the diagnosis of PCa and csPCa in PI-RADS 3 lesions.

Ovarian _ Reporting and Data System (O_RADS) Classification of Ovarian Lesions on Ultrasound Basis

Abstract Background Ovarian lesions present a special diagnostic challenge when imaging findings cannot be categorized into benign or malignant pathology. Ultrasonography (US), Computed Tomography (CT), and Magnetic Resonance Imaging (MRI) are currently used to evaluate ovarian tumors. Aim of the Work The aim of this work is to determine the efficacy of the classification of ovarian lesions on an ultrasound basis. Patients and Methods This was a prospective observational study conducted on 30 females with ovarian lesions at the Radiology Department of Ain Shams University Hospitals for 6 months from February to august 2022. Results The benign lesions of O-RADS 1, O-RADS 2, O-RADS 3, O-RADS 4, and O-RADS 5 represented 5.3%, 63.2%, 15.8%, 10.5% and 5.3% respectively. The malignant lesions of O-RADS 5, O- RADS 4 represented 81.8%, and 18.2%, respectively. There was a highly statistically significant difference between benign and malignant lesions in terms of the O-RADS score (P &amp;lt; 0.001). In order to assess the diagnostic performance of the O-RADS score to discriminate malignant from benign lesions, a ROC curve analysis was performed. O-RADS score (AUC of 0.959) showed a sensitivity of 100%, a specificity of 84.21%, PPV of 78.6%, and NPV of 100%, with the optimal cutoff value for predicting malignancy was &amp;gt;O-RADS 3. Conclusion The current study concluded the following: Ultrasonography is definitely an important non- invasive tool and is helpful in diagnosing most cases of ovarian lesions. O-RADS system has good sensitivity and moderate specificity for classifying ovarian lesions.

Diagnostic value of contrast-enhanced ultrasound and shear-wave elastography for small breast nodules.

The study aims to evaluate the diagnostic efficacy of contrast-enhanced ultrasound (CEUS) and shear-wave elastography (SWE) in detecting small malignant breast nodules in an effort to inform further refinements of the Breast Imaging Reporting and Data System (BI-RADS) classification system. This study retrospectively analyzed patients with breast nodules who underwent conventional ultrasound, CEUS, and SWE at Gongli Hospital from November 2015 to December 2019. The inclusion criteria were nodules ≤ 2 cm in diameter with pathological outcomes determined by biopsy, no prior treatments, and solid or predominantly solid nodules. The exclusion criteria included pregnancy or lactation and low-quality images. Imaging features were detailed and classified per BI-RADS. Diagnostic accuracy was assessed using receiver operating characteristic curves. The study included 302 patients with 305 breast nodules, 113 of which were malignant. The diagnostic accuracy was significantly improved by combining the BI-RADS classification with CEUS and SWE. The combined approach yielded a sensitivity of 88.5%, specificity of 87.0%, positive predictive value of 80.0%, negative predictive value of 92.8%, and accuracy of 87.5% with an area under the curve of 0.877. Notably, 55.8% of BI-RADS 4A nodules were downgraded to BI-RADS 3 and confirmed as benign after pathological examination, suggesting the potential to avoid unnecessary biopsies. The integrated use of the BI-RADS classification, CEUS, and SWE enhances the accuracy of differentiating benign and malignant small breast nodule, potentially reducing the need for unnecessary biopsies.

The Concordance between the Thyroid Imaging Reporting and Data System and Thy Cytological Classification

The Concordance between the Thyroid Imaging Reporting and Data System and Thy Cytological Classification

Preoperative prediction of central lymph node metastasis in follicular variant of papillary thyroid carcinoma using clinical and ultrasound features.

The most common metastatic site of follicular variant of papillary thyroid carcinoma (FVPTC) is the central lymph nodes, which may be associated with the prognosis and survival of patients. In the present study, we establish a combined model based on preoperative clinical and ultrasound (US) features of FVPTC to predict the risk of central lymph node metastasis (CLNM). From January 2013 to December 2022, 315 patients with FVPTC were enrolled and randomly divided into the training and validation cohorts in a ratio of 7:3. The independent risk factors for CLNM in FVPTC were analysed using univariate and multivariate logistic regression analyses. Then, three different models were established based on clinical and US data. Subsequently, a nomogram was constructed to predict CLNM. Its predictive effect was evaluated via receiver operating characteristic and calibration curve analyses. Backward multivariate regression analysis revealed that age (P=0.001), thyroid peroxidase antibody (TPOAb) (P=0.11), diameter (P=0.047), irregular/lobulated margin (P=0.15), extrathyroidal extension (P=0.001), nodules with macrocalcifications (P=0.009), nodules with microcalcification (P=0.003) and Thyroid Imaging Reporting and Data System (ACR-TI-RADS) category 5 (P=0.33) were independent risk factors for CLNM in FVPTC. The areas under the curve of the matching nomogram in the training (N=221) and validation cohorts (N=94) were 0.841 [95% confidence interval (CI): 0.788-0.895] and 0.735 (95% CI: 0.621-0.872), respectively. Preoperative thyroid US provides useful features for prediction of CLNM. The nomogram constructed based on combining US and clinical features can better predict the risk of CLNM and may facilitate decision-making in clinical settings.

Comparison of Mammography, Ultrasonography, and both Combined in the Interpretation of Palpable Breast Mass

Background: Breast cancer is the most common female malignancy in worldwide and the second leading cause of female cancer death in the United States (1, 14). On average, every two minutes a woman is diagnosed with breast cancer and one woman will die of breast cancer every thirteen minutes(13) In Libyan breast cancer is most common cancer in female (17 ) Although the majority of palpable lumps are benign, a new palpable breast mass is a common presenting sign of breast cancer. the aim of the study to reveal the role of USS and MG and both in evaluating palpable breast mass because both are available and more accurate in evaluated palpable breast mass depend on the aging and breast density .Materials and methods: prospective study between January 2018 and march 2019 In Department of Radiology in Benghazi medical center (BMC); used the Breast Imaging Reporting and Data System (BI-RADS) classification on fifty palpable breast masses in two models (USS and MG ) and described each masses by selecting a single term from the Bl-RADS lexicon for description mass margin and shape. Kappa values were calculated to assess the agreement between BIRADS assessment category and agreement between descriptions of masses margin and shape .Additionally, another reader used same USS Bl-RADS lexicon for description mass margin to assessed lnter-observer variability. Result :Regarding BIRADS assessment category, agreement between the MG and combined (USS and MG ) interpretations were moderate (K=0.4);agreement between USS and combined (USS and MG ) was very good (k=0.84); agreement between BIRADs category of USS and MG in descriptive shape of palpable breast mass was moderate (k=0.50) while for margin fair agreement (k=0.26).poor lnter-observer variability(k=0.19) in USS Bl-RADS lexicon for description mass margin. Conclusion: USS better than MG in detected palpable breast mass so can be use as diagnostic tool for characterized palpable breast mass.

Clinical risk factors and cancer risk of thyroid imaging reporting and data system category 4 A thyroid nodules

PurposeBeyond the Thyroid Imaging Reporting and Data System (TIRADS) classification of thyroid nodules, additional factors must be weighed in the decision to perform fine needle aspiration (FNA). In this study, we aimed to identify risk factors for malignancy in patients with ultrasound-classified Chinese-TIRADS (C-TIRADS) 4 A nodules.MethodsPatients who underwent thyroid FNA at our institution between May 2021 and September 2022 were enrolled. We collected demographic data, including age, sex, previous radiation exposure, and family history. An in-person questionnaire was used to collect lifestyle data, such as smoking habits and alcohol consumption. Body mass index (BMI) was calculated. The serum levels of thyroid stimulating hormone (TSH), thyroid peroxidase antibody (TPOAb), and thyroglobulin antibody (TGAb) were measured. Prior to FNA, ultrasonic inspection reports were reviewed. The cytologic diagnoses for FNA of thyroid nodules followed the Bethesda System for Reporting Thyroid Cytopathology (2017).ResultsAmong the 252 C-TIRADS 4 A nodules, 103 were malignant. Compared to those in the benign group, the patients in the malignant group had a younger age (42.2 ± 13.6 vs. 51.5 ± 14.0 years, P < 0.001). Logistic regression showed that advanced age was associated with a lower risk of malignancy in C-TIRADS 4 A nodules (OR = 0.95, 95% CI 0.93 ~ 0.97, P < 0.001). We demonstrated a decreased risk of malignancy in patients with 48.5 years or older.ConclusionAdvanced age was associated with a decreased risk of malignancy in patients with C-TIRADS 4 A nodules. This study indicated that in addition to sonographic characteristics, patient age should be considered when assessing the risk of malignancy.

Nodule-in-nodule architecture of hepatocellular carcinomas: enhancement patterns in the hepatobiliary phase and pathological features.

This study aimed to evaluate the enhancement patterns in the hepatobiliary phase (HBP) and pathological features of nodule-in-nodule-type hepatocellular carcinoma (NIN-HCC) patients. In this single-institution retrospective study, 27 consecutive cirrhosis patients with 29 histologically confirmed NIN-HCCs who underwent preoperative examination via Gd-EOB-DTPA-enhanced MRI were enrolled from January 2016 to September 2023. Two blinded radiologists assessed the imaging features of both the inner and outer nodules in NIN-HCCs to reach a consensus on the Liver Imaging Reporting & Data System (LI-RADS) categories of the lesions. Based on the different enhancement patterns of the inner and outer nodules in the HBP, NIN-HCCs were classified into different groups and further divided into different types. Imaging features and LI-RADS categories were subsequently compared among the groups. Pathological findings for NIN-HCCs were also evaluated. Among 29 NIN-HCCs, all inner nodules showed hypervascularity, with a maximum diameter of 13.2 ± 5.5mm; 51.7% (15/29) showed "wash-in with washout" enhancement; and 48.3% (14/29) showed "wash-in without washout" enhancement. All outer nodules showed hypovascularity, with a maximum diameter of 25.6 ± 7.3mm, and 51.9% (14/29) showed a washout appearance on PVP. Among all the lesions, the maximum diameter was 27.5 ± 6.8mm; 12 (41.4%) lesions were LR-4, and 17 (58.6%) lesions were LR-5. NIN-HCCs were classified into hypointense (62.1%, 18/29) and isointense (37.9%, 11/29) groups based on the signal intensity of the outer nodules in the HBP. In the hypointense group, 2 (6.9%) of the inner nodules were hypointense (type A), 11 (37.9%) were isointense (type B), and 5 (17.2%) were hyperintense (type C) compared to the background hypointense outer nodules. In the isointense group, 9 (31.0%) of the inner nodules were hypointense (type D), 2 (6.9%) were isointense (type E), and no (0%) was hyperintense (type F) compared to the background isointense outer nodules. There were no significant differences in the diameter, dynamic enhancement patterns of the inner or outer nodules, or LI-RADS scores of the lesions between the hypointense group and the isointense group (all P > 0.05). Histologically, the inner nodules of NIN-HCCs were mainly composed of moderately differentiated HCC (75.9% 22/29), whereas the outer nodules consisted of either well-differentiated HCC or high-grade dysplastic nodules (HGDNs). NIN-HCCs exhibit specific MRI findings closely associated with their pathological features. The spectrum of HBP enhancement patterns provides valuable insights into the underlying cell biological mechanisms of these lesions. NIN-HCC subtypes may be used as a morphologic marker in the early stage of multistep hepatocarcinogenesis.

Molecular Breast Imaging Biopsy with a Dual-Detector System.

Purpose To develop a molecular breast imaging (MBI)-guided biopsy system using dual-detector MBI and to perform initial testing in participants. Materials and Methods The Stereo Navigator MBI Accessory biopsy system comprises a lower detector, upper fenestrated compression paddle, and upper detector. The upper detector retracts, allowing craniocaudal, oblique, or medial or lateral biopsy approaches. The compression paddle allows insertion of a needle guide and needle. Lesion depth is calculated by triangulation of lesion location on the upper detector at 0° and 15° and relative lesion activity on upper and lower detectors. In a prospective study (July 2022-June 2023), participants with Breast Imaging Reporting and Data System category 2, 3, 4, or 5 breast lesions underwent MBI-guided biopsy. After injection of 740 MBq technetium 99m sestamibi, craniocaudal and mediolateral oblique MBI (2-minute acquisition per view) confirmed lesion visualization. A region of interest over the lesion permitted depth calculation in the system software. Upper detector retraction allowed biopsy device placement. Specimen images were obtained on the retracted upper detector, confirming sampling of the target. Results Of 21 participants enrolled (mean age, 50.6 years ± 10.1 [SD]; 21 [100%] women), 17 underwent MBI-guided biopsy with concordant pathology. No lesion was observed at the time of biopsy in four participants. Average lesion size was 17 mm (range, 6-38 mm). Average procedure time, including preprocedure imaging, was 55 minutes ± 13 (range, 38-90 minutes). Pathology results included invasive ductal carcinoma (n = 1), fibroadenoma (n = 4), pseudoangiomatous stromal hyperplasia (n = 6), and fibrocystic changes (n = 6). Conclusion MBI-guided biopsy using a dual-head system with retractable upper detector head was feasible, well tolerated, and efficient. Keywords: Breast Biopsy, Molecular Breast Imaging, Image-guided Biopsy, Molecular Breast Imaging-guided Biopsy, Breast Cancer Clinical trial registration no. NCT06058650 © RSNA, 2024.