Radiologists In Ultrasound Research Articles

Standardized IETA criteria enhance accuracy of junior and intermediate ultrasound radiologists in diagnosing malignant endometrial and intrauterine lesions.

To transform the standardized descriptions of the ultrasound characteristics of endometrial and intrauterine lesions devised by the International Endometrial Tumor Analysis (IETA) group into a practical scoring method and to investigate whether application of this method enhances the diagnostic accuracy of ultrasound radiologists with different levels of experience in detecting malignancy compared with subjective assessment. This was a retrospective study of 855 patients with endometrial and/or intrauterine lesions, who were divided into a training (n = 600) and a validation (n = 255) set. Ultrasound radiologists with varying levels of experience (expert, intermediate and junior) evaluated all lesions by subjective assessment and according to IETA rules. Using IETA rules, the experts identified signs of malignancy in the training set, assigned scores for each indicator and validated the scoring method in the validation set. The intermediate-level and junior ultrasound radiologists reassessed the malignancy of the lesions using the IETA scoring method and compared their classifications with those made previously by subjective assessment. Postsurgical pathological evaluation was used as the reference standard. Using subjective assessment, the experts demonstrated the highest level of diagnostic accuracy, with a sensitivity of 85.0%, specificity of 94.3% and an area under the receiver-operating-characteristics curve (AUC) of 0.897. Applying the IETA scoring method (comprising eight ultrasound characteristics that contributed to the total score) with a threshold of > 25 points for the diagnosis of malignancy achieved a sensitivity of 84.7%, specificity of 94.7% and AUC of 0.9533 in the training set, with similar performance in the validation set, when performed by experts. Using the IETA scoring method, both junior and intermediate ultrasound radiologists showed improvement in sensitivity (from 55.5% to 74.8% and from 70.2% to 77.1%, respectively), specificity (from 88.4% to 91.5% and from 87.4% to 92.2%, respectively) and AUC (from 0.704 to 0.827 and from 0.793 to 0.841, respectively) for diagnosing malignant lesions. The IETA scoring method exhibits high diagnostic efficacy for malignant endometrial and intrauterine lesions. This method compensates for the lack of experience among junior and intermediate-level ultrasound radiologists, enhancing their diagnostic skill to a level nearing that of experienced senior ultrasound radiologists. Further research is essential to validate the practicality of implementing this method and to confirm its clinical value. © 2024 International Society of Ultrasound in Obstetrics and Gynecology.

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.

Developing a Word Lexicon from Electronic Health Records for Natural Language Processing Analysis of Free-Text Reports for Patients with Venous Thromboembolism.

Patients with gliomas, particularly glioblastomas (GBM) have a higher risk of developing venous thromboembolism (VTE), including both pulmonary embolism (PE) or deep vein thrombosis (DVT), both correlating with overall survival (OS) and potential biological signaling relevance for analysis of the tumor state in conjunction with evolving biomarkers. Artificial intelligence (AI) approaches thar employ VTE as a clinical feature in brain tumor patients is understudied due to the difficulty in analyzing unstructured clinical data in electronic health records (EHR). Data expansion by creating a word lexicon for natural language processing (NLP) of free-text clinical reports will allow exposure of VTE for classification of large-scale data sets, NLP and AI. Patients with a pathologic diagnosis of GBM (2005-2021) were extracted from EHR and screened for the development of VTE based on radiology free-text reports - ultrasound (US) of extremities and Computed Topography-pulmonary angiogram (CT). Language data were collected manually and verified computationally using radiology report text filtration. Common phrases and words employed were collected to generate a lexicon for future computational analysis. Kaplan-Meier survival analyses were generated for VTE in relation OS and progression-free survival (PFS). A total of 163 patients (mean age = 56.1 ± 12.1, 65% male) were included, 48 (29.4%) were screened for VTE following clinical suspicion on history or physical exam, and 15 (9.2%) were found to have a VTE. Screening methods were US 83.3% (40) or CT 13.9% (6), or both 4.6% (2). 28.6% (12) of US and 37.5% (3) of CT resulted in a positive VTE diagnosis. Terms that were only detected in patients with VTE were for US: "complete" 44%, "thrombosis detected" (8.3%), "occlusive" (16%), "partial" (16%), "critical" (25%), "residual" (8.3%) and for CT: "critical" (67%) and "pulmonary emboli" (33%). Words used in free-text reports showed a high degree of inter-reporter variability. The words "partial", "residual", "complete", "critical" or "clotted" when used as an "or" Boolean statement applied to US and CT radiology reports identified ∼93% of the patients with VTE. Patients with VTE had worse OS (median 14 vs. 19 months, p = .0189) and PFS (median 6 vs. 9 months, p = .0239) compared to patients without VTE indicating underlying pathology associated with both prevalence of VTE and tumor burden and the need to incorporate VTE as a clinical feature in large scale data analyses. US and CT yield a similar percentage of positive VTE findings while employing different terms to characterize VTE. We confirm that patients with VTE have poorer outcomes and present a word combination that identifies patients with VTE in large-scale radiology report data. Further research will focus on validation in other datasets, NLP approaches to optimize and data aggregation with laboratory data and large-scale omics panels to expose thrombosis as a clinical feature for biomarker analysis.

Use of cine images in standard ultrasound imaging: a survey of sonologists.

The aim of this study was to explore how sonologists utilize cine images in their routine practice. A 10-question, multiple choice survey was distributed to members of the Society of Radiologists in Ultrasound. The survey queried respondent's routine inclusion of cines for ultrasound examinations in normal and abnormal studies in addition to questions related to respondent's practice type, geographic location, number of radiologists interpreting ultrasound examinations, and ultrasound imaging workflow. Sixty-five percent of respondents are in academic practice. Geographic location of practice, number of radiologists in the practice who interpret ultrasound, and whether the sonologist was on site where the examinations were performed was variable. Of respondents, 97% of used both static and cine images for abnormal/positive examinations and 82% used both for normal/negative studies. Nearly all respondents, who are mostly in academic practice, report using both static and cine images for all ultrasound examinations in their practice.

CLRM-04 DEVELOPING A WORD LEXICON FOR VENOUS THROMBOEMBOLISM DATA ANNOTATION USING RADIOLOGY REPORTS IN GLIOBLASTOMA PATIENTS - LINKING LARGE-SCALE DATA SETS TO EXPAND CLINICAL FEATURES FOR AI

Abstract Patients with gliomas, particularly glioblastomas (GBM), have a higher risk of developing venous thromboembolism (VTE), correlating with overall survival (OS). Artificial intelligence (AI) approaches that employ VTE as a clinical feature in brain tumor patients is understudied due to the difficulty in analyzing electronic health records (EHR). Data expansion by creating a word lexicon for natural language processing (NLP) of free-text clinical reports will allow exposure of VTE for the classification of large-scale data sets, NLP, and AI. Patients with a pathologic diagnosis of GBM (2005-2021) were screened for the development of VTE based on radiology free-text reports (ultrasound (US) of extremities and Computed Topography-pulmonary angiogram (CT)). Kaplan-Meier survival analyses about overall survival (OS) and progression-free survival (PFS) were generated for VTE. 163 patients (mean age = 56.1 ± 12.1, 65% male) were included, 48 (29.4%) were screened for VTE following clinical suspicion on history or physical exam, and 15 (9.2%) were found to have a VTE. Screening methods were ultrasound 83.3% (40) or CT 13.9% (6), or both 4.6% (2). 28.6% (12) of US and 37.5% (3) of CT resulted in a positive VTE diagnosis. The words “partial”, “residual”, “complete”, “critical” or “clotted” when used as an “or” boolean statement applied to US and CT radiology reports identified ~93% of the patients with VTE. Patients with VTE had worse OS (median 14 vs. 19 months, p = .0189) and PFS (median 6 vs. 9 months, p = .0239) than patients without VTE, indicating underlying pathology associated with both prevalence of VTE and tumor burden. US and CT yield a similar percentage of positive VTE findings while employing different terms to characterize VTE. We confirm that patients with VTE have poorer outcomes and present a word combination that identifies patients with VTE in large-scale radiology report data.

"Truffle sign". A suspicious malignant pattern of lymphadenopathies in children observed on ultrasound. Preliminary study.

The differential diagnosis of lymphadenopathies in children including benign and malignant conditions is often difficult to identify by ultrasound (US). The lymphadenopathies in children are frequent and mostly benign, therefore it is essential to decide what patients should undergo further studies. To describe the potential usefulness of a new suspicious ultrasound sign on pediatric lymphadenopathies that can orient the diagnosis of malignancy. We retrospectively reviewed all pediatric cases with lymphadenopathy suspicious of lymphoma or lymphoproliferative syndrome on soft tissue ultrasound from 2014 to 2021. Two expert ultrasound radiologists reviewed ultrasound images of these patients, associating the internal structure of infiltrated adenopathy with the internal structure of the truffles. On ultrasound, twelve cases presented enlarged lymphadenopathy with loss of internal structure, without hilum; mostly hypoechoic parenchyma, with some fine echogenic serpiginous linear surrounding hypoechoic pseudo nodular images, resembling the inner structure of black truffles. This US pattern looked suspicious and histological study was recommended. In 9 cases a lymphomatous infiltrated adenopathy was confirmed on biopsy. The truffle sign is a new potential suspicious ultrasound sign, that can suggest malignant lymphadenopathy in children. This ultrasound pattern can have some probable usefulness to the radiologist in order to recommend further studies, including histological study, that need to be validated by a larger sample. It is important to recognize easily and early the lymphomatous compromise in a lymph node.

Value of deep learning models based on ultrasonic dynamic videos for distinguishing thyroid nodules.

This study was designed to distinguish benign and malignant thyroid nodules by using deep learning(DL) models based on ultrasound dynamic videos. Ultrasound dynamic videos of 1018 thyroid nodules were retrospectively collected from 657 patients in Zhejiang Cancer Hospital from January 2020 to December 2020 for the tests with 5 DL models. In the internal test set, the area under the receiver operating characteristic curve (AUROC) was 0.929(95% CI: 0.888,0.970) for the best-performing model LSTM Two radiologists interpreted the dynamic video with AUROC values of 0.760 (95% CI: 0.653, 0.867) and 0.815 (95% CI: 0.778, 0.853). In the external test set, the best-performing DL model had AUROC values of 0.896(95% CI: 0.847,0.945), and two ultrasound radiologist had AUROC values of 0.754 (95% CI: 0.649,0.850) and 0.833 (95% CI: 0.797,0.869). This study demonstrates that the DL model based on ultrasound dynamic videos performs better than the ultrasound radiologists in distinguishing thyroid nodules.

Impact of the coronavirus disease 2019 pandemic on ultrasound screening of developmental dysplasia of the hip and follow-up imaging: a report from southeastern Turkey.

To investigate the effect of coronavirus disease 2019 restrictions on ultrasound (US) screening of developmental dysplasia of the hip (DDH) in a children's hospital. The records of US screening of DDH were retrospectively evaluated in the pandemic period (April 2020 to July 2021) and the pre-pandemic period (January 2019 to February 2020). The monthly US number, sex, radiologist number, and age at the initial examination were recorded. A total of 6107 US scans were performed during the pre-pandemic period, which significantly decreased to 3340 during the pandemic. The number of monthly US scans performed did not change between the pre-pandemic (142.7/month) and pandemic (128.2/month) periods. The number of delayed examinations in the total population did not significantly change between the two periods. However, the number of delayed examinations in patients with abnormal hips was significantly increased during the pandemic compared with that in the pre-pandemic period. Coronavirus disease 2019 restrictions decreased the US screening rate of DDH by almost half, but the number of US scans performed by each radiologist was unchanged. The compliance with follow-up recommendations was reduced by half, which may lead to an increase in the incidence of delayed and untreated DDH cases.

The use of additional imaging studies after biliary point-of-care ultrasound in the emergency department.

We sought to determine the test characteristics of biliary point-of-care ultrasound (POCUS) and to assess the usefulness of obtaining radiology ultrasound (RUS) or cholescintigraphy (HIDA) after biliary POCUS. We conducted a retrospective review of emergency department patients who underwent biliary POCUS between May 4, 2018 and November 28, 2021. To be included, patients had to have at least one of the following confirmatory evaluations (considered in this order): surgery, HIDA, RUS, or abdominal CT scan. When a discrepancy existed between the POCUS and the RUS or HIDA, they were compared to a higher criterion standard (if available). Using 348 patients who had a confirmatory evaluation after biliary POCUS, we found the sensitivity and specificity of biliary POCUS for gallstones to be 97.0% (95% CI 92.6 to 99.2%) and 99.5% (95% CI 97.3 to 100%), respectively. For cholecystitis, the sensitivity and specificity were 83.8% (95% CI 72.9 to 91.6%) and 98.6% (95% CI 96.4 to 99.6%), respectively. RUS and POCUS were concordant in 72 (81.8%) of 88 cases in which the patient had both studies while HIDA and POCUS were concordant in 24 (70.6%) of 34 cases. POCUS was deemed correct in at least 50% of discrepant cases with RUS and at least 30% of discrepant cases with HIDA. Biliary POCUS has excellent sensitivity and specificity for cholelithiasis; it has lower sensitivity for cholecystitis, but the specificity remains high. Performing a confirmatory RUS or cholescintigraphy after a positive biliary POCUS adds little value, but additional imaging may be useful when POCUS is negative for cholecystitis.

66 The Use of Additional Imaging Studies after Abnormal Biliary Point-of-Care Ultrasound in the Emergency Department

Emergency-physician-performed point-of-care ultrasound (POCUS) of the gallbladder has been shown to achieve sensitivity and specificity for cholelithiasis and cholecystitis that are similar to that of radiology ultrasound (RUS). However, in our experience, additional diagnostic imaging studies (such as RUS or cholescintigraphy) are often performed after abnormal biliary POCUS to confirm the results. The utility of this strategy is uncertain. We thus sought to determine the test characteristics of biliary POCUS for cholelithiasis and cholecystitis in our hospital system, and to assess the usefulness of obtaining additional imaging after an abnormal biliary POCUS.

Survey Study on the Experience, Practice Patterns, and Preferences of the Fellows of the Society of Radiologists in Ultrasound for Evaluation and Management of Gallbladder Polyps Detected With Ultrasound.

Gallbladder polyps (GPs) are a common incidental finding on ultrasound; however, important differences in recommended management exist among professional society guidelines.An electronic survey was sent to 189 fellows of the Society of Radiologists in Ultrasound. Main outcomes included preferences and current practice patterns for evaluation, management, and surveillance of GPs as well as personal lifetime experience with gallbladder sonography and GPs.A total of 64 subjects (34%) with experience in gallbladder sonography completed the study. The estimated combined total number of gallbladder scans seen by the responders was 3,071,880. None of fellows had ever seen a pedunculated GP <1 cm detected on ultrasound that was proven to be malignant at the time of detection or during subsequent follow-up. All of the fellows used size as a feature to stratify recommendations. The median size threshold currently used by Society of Radiologists in Ultrasound fellows for recommending ultrasound follow-up was 6 mm, and their preferred threshold was 7 mm. The median size threshold for recommending surgical consultation was 10 mm, and the preferred threshold was 10 mm. Wall thickening and shape were considered important factors by 76% and 67% of respondents, respectively.Society of Radiologists in Ultrasound fellows tend to provide recommendations most similar to the American College of Radiology and Canadian Association of Radiology guidelines for management of GPs. Many would prefer guidelines that result in fewer recommendations for follow-up and surgical consultation. Despite a substantial combined experience, this survey did not uncover any case of a small GP that was malignant.

RADIOMICS BASED ON TWO-DIMENSIONAL AND THREE-DIMENSIONAL ULTRASOUND FOR EXTRATHYROIDAL EXTENSION FEATURE PREDICTION IN PAPILLARY THYROID CARCINOMA.

To evaluate the diagnostic performance of radiomics features of two-dimensional (2D) and three-dimensional (3D) ultrasound (US) in predicting extrathyroidal extension (ETE) status in papillary thyroid carcinoma (PTC). 2D and 3D thyroid ultrasound images of 72 PTC patients confirmed by pathology were retrospectively analyzed. The patients were assigned to ETE and non-ETE. The regions of interest (ROIs) were obtained manually. From these images, a larger number of radiomic features were automatically extracted. Lastly, the diagnostic abilities of the radiomics models and a radiologist were evaluated using receiver operating characteristic (ROC) analysis. We extracted 1693 texture features firstly. The area under the ROC curve (AUC) of the radiologist was 0.65. For 2D US, the mean AUC of the three classifiers separately were: 0.744 for logistic regression (LR), 0.694 for multilayer perceptron (MLP), 0.733 for support vector machines (SVM). For 3D US they were 0.876 for LR, 0.825 for MLP, 0.867 for SVM. The diagnostic efficiency of the radiomics was better than radiologist. The LR model had favorable discriminate performance with higher area under the curve. Radiomics based on US image had the potential to preoperatively predict ETE. Radiomics based on 3D US images presented more advantages over radiomics based on 2D US images and radiologist.

Impact of point-of-care ultrasound on treatment time for ectopic pregnancy.

Point-of-care ultrasound (POCUS) is useful in the evaluation of early pregnancy by confirming intrauterine pregnancy and recognizing hemorrhage from ectopic pregnancy. We sought to determine whether transabdominal POCUS by itself or in conjunction with consultative radiology ultrasound (RADUS), reduces Emergency Department (ED) treatment time for patients with ectopic pregnancy requiring operative care, when compared to RADUS alone. A secondary objective was to determine whether the incorporation of POCUS reduces time to operative care for patients with ruptured ectopic pregnancy specifically, when compared to RADUS alone. We performed a retrospective review of patients admitted for operative management of ectopic pregnancy. We excluded patients with known ectopic pregnancy and/or imaging prior to arriving to the treatment area, found not to have an ectopic pregnancy, or did not undergo operative care. Descriptive statistics, classical and nonparametric statistical analysis, and linear regression were performed. There were 220 patients admitted with ectopic pregnancy, 111 met exclusion criteria, yielding 109 for analysis. Of 109, 36 received POCUS (23/36 also had RADUS), while 73 received RADUS only. Among the POCUS group 31/36 (86%) were classified as ruptured versus 47/73 (64%) in the RADUS group. The average ED treatment time in the POCUS group for all admitted ectopic pregnancies was 157.9 min (standard deviation [SD] 101.3) versus 206.3 min (SD 76.6) in the RADUS group (p = 0.0141). The median time to operating room (OR) for ruptured ectopic pregnancies was 203.0 min (interquartile range [IQR] 159.0) in the POCUS group versus 293.0 min (IQR 139.0) in the RADUS group (p = 0.0002). Regression analysis of the primary outcome was limited by multiple interactions and sample size. When controlling for race, positive shock index and ED visit time, POCUS was found to be associated with a significantly shorter time to OR among ruptured ectopic pregnancies compared to RADUS (p = 0.0052). Compared to RADUS alone, incorporation of POCUS was associated with significantly faster ED treatment time for all ectopic pregnancies and significantly faster time to OR for ruptured ectopic pregnancies, even when combined with RADUS. When controlling for clinical differences, time to OR was still faster for patients who underwent POCUS. The integration of POCUS should be considered to expedite care for patients with ectopic pregnancy requiring operative care.

Exploring the Performance of Ultrasound Risk Stratification Systems in Thyroid Nodules of Pediatric Patients.

Simple SummaryAlthough pediatric thyroid nodules are uncommon, they need high clinical expertise and alert since they carry a greater risk of malignancy compared with those presenting in adults. Since there are no specific ultrasound (US)-based risk stratification systems (RSSs) for pediatric thyroid nodules, the application of adult-based RSSs in the pediatric population could represent a step forward in the care of children and adolescents with thyroid nodules. We compared the diagnostic performance of the main US-based RSSs *i.e., the American College of Radiology (ACR), European (EU), Korean (K) Thyroid Imaging Reporting and Data Systems (TI-RADSs) and ATA US RSS criteria) for detecting malignant thyroid lesions in pediatric patients. For ACR TI-RADS and EU-TIRADS, we found a sensitivity of 41.7%, and, for K-TIRADS and ATA US RSS, we found a sensitivity of 50%. The four US-based RSSs (i.e., ACR-TIRADS, EU-TIRADS, K-TIRADS, and ATA US RSS) have suboptimal performance in managing pediatric patients with thyroid nodules, with one-half of cancers without indication for FNA according to their recommendations. All thyroidologists, as well as the panelists of next TIRADSs, should be aware of these findings.Neck ultrasound (nUS) is the cornerstone of clinical management of thyroid nodules in pediatric patients, as well as adults. The current study was carried out to explore and compare the diagnostic performance of the main US-based risk stratification systems (RSSs) (i.e., the American College of Radiology (ACR), European (EU), Korean (K) TI-RADSs and ATA US RSS criteria) for detecting malignant thyroid lesions in pediatric patients. We conducted a retrospective analysis of consecutive children and adolescents who received a diagnosis of thyroid nodule. We included subjects with age <19 years having thyroid nodules with benign cytology/histology or final histological diagnosis. We excluded subjects with (a) a previous malignancy, (b) a history of radiation exposure, (c) cancer genetic susceptibility syndromes, (d) lymph nodes suspicious for metastases of thyroid cancer at nUS, (e) a family history of thyroid cancer, or (f) cytologically indeterminate nodules without histology and nodules with inadequate cytology. We included 41 nodules in 36 patients with median age 15 years (11–17 years). Of the 41 thyroid nodules, 29 (70.7%) were benign and 12 (29.3%) were malignant. For both ACR TI-RADS and EU-TIRADS, we found a sensitivity of 41.7%. Instead, for both K-TIRADS and ATA US RSS, we found a sensitivity of 50%. The missed malignancy rate for ACR-TIRADS and EU-TIRADS was 58.3%, while that for K-TIRADS and ATA US RSS was 50%. The unnecessary FNA prevalence for ACR TI-RADS and EU-TIRADS was 58.3%, while that for K-TIRADS and ATA US RSS was 76%. Our findings suggest that the four US-based RSSs (i.e., ACR-TIRADS, EU-TIRADS, K-TIRADS, and ATA US RSS) have suboptimal performance in managing pediatric patients with thyroid nodules, with one-half of cancers without indication for FNA according to their recommendations.

Improved diagnosis of thyroid cancer aided with deep learning applied to sonographic text reports: a retrospective, multi-cohort, diagnostic study.

Objective:Large volume radiological text data have been accumulated since the incorporation of electronic health record (EHR) systems in clinical practice. We aimed to determine whether deep natural language processing algorithms could aid radiologists in improving thyroid cancer diagnosis.Methods:Sonographic EHR data were obtained from the EHR database. Pathological reports were used as the gold standard for diagnosing thyroid cancer. We developed thyroid cancer diagnosis based on natural language processing (THCaDxNLP) to interpret unstructured sonographic text reports for thyroid cancer diagnosis. We used the area under the receiver operating characteristic curve (AUROC) as the primary metric to measure the performance of the THCaDxNLP. We compared the performance of thyroid ultrasound radiologists aided with THCaDxNLP vs. those without THCaDxNLP using 5 independent test sets.Results:We obtained a total number of 788,129 sonographic radiological reports. The number of thyroid sonographic data points was 132,277, 18,400 of which were thyroid cancer patients. Among the 5 test sets, the numbers of patients per set were 439, 186, 82, 343, and 171. THCaDxNLP achieved high performance in identifying thyroid cancer patients (the AUROC ranged from 0.857–0.932). Thyroid ultrasound radiologists aided with THCaDxNLP achieved significantly higher performances than those without THCaDxNLP in terms of accuracy (93.8% vs. 87.2%; one-sided t-test, adjusted P = 0.003), precision (92.5% vs. 86.0%; P = 0.018), and F1 metric (94.2% vs. 86.4%; P = 0.007).Conclusions:THCaDxNLP achieved a high AUROC for the identification of thyroid cancer, and improved the accuracy, sensitivity, and precision of thyroid ultrasound radiologists. This warrants further investigation of THCaDxNLP in prospective clinical trials.

Overview of the Ultrasound Classification Systems in the Field of Thyroid Cytology.

Simple SummaryUltrasound (US) is the preferred imaging modality for thyroid nodule evaluation. Accurate US assessment of thyroid lesions can help decrease unwarranted FNA procedures of benign nodules. Several thyroid nodule risk classification systems that focus on US features have been published. Some of them highlight simple US patterns, while others rely on the presence of multiple US features to categorize thyroid nodules. The current review offers an evaluation of different US system, combining them with the use of fine needle aspiration and the cytological classification systems.The increasing application of ultrasound (US) in recent years has led to a greater number of thyroid nodule diagnoses. Consequently, the number of fine needle aspirations performed to evaluate these lesions has increased. Although the majority of thyroid nodules are benign, identifying methods to define specific lesions and tailor risk of malignancy has become vital. Some of the tools employed to stratify thyroid nodule risk include clinical factors, thyroid US findings, and reporting systems for thyroid cytopathology. Establishing high concordance between US features and cytologic diagnoses might help reduce healthcare costs by diminishing unnecessary thyroid procedures and treatment. This review aims to review radiology US classification systems that influence the practice of thyroid cytology.

AIUM Practice Parameter for the Performance of Sonohysterography and Hysterosalpingo-Contrast Sonography.

AIUM Practice Parameter for the Performance of Sonohysterography and Hysterosalpingo-Contrast Sonography.

Lung CT Image Segmentation Using Reinforcement Learning

Nowadays, lung disease is a major global problem in the world. Many of the lung diseases are untreatable and reduce the life span of the individual. Initial diagnosis of these diseases can help to completely cure the illness and reduce disease progression. Diagnosis of lung disease is often made based on CT scan images of the lungs. But the diagnosis of lung disease in CT images is a complicated and challenging task. Such a challenge is due to the noise of imaging, the lack of transparency of the image, the intensity of the lighting of some components, and so on. Eliminating these issues makes it easy to diagnose the disease for specialized physicians as well as existing automated diagnostic systems. In this paper, we propose a novel approach for lung CT image segmentation that solves some of these challenges. Also, correct accurate segmentation of these images can help to automatically detect lung diseases. The correct segmentation means a precise determination of the intensity of each area’s brightness, the exact location of the pixels in each area and the preservation of the original image. We employed a reinforcement-based approach for our image segmentation. The proposed method produces the image without noise, and the image components are split with the best accuracy. To evaluate our approach, we manually generated 200 labelled lung CT images. After that, the proposed method, along with two recently published approaches is evaluated against our generated dataset. This comparative evaluation is conducted in two qualitative and quantitative ways. For the qualitative comparison, we employed the consultation of two ultrasound radiologists for evaluating the results of our approach. We also used a similarity measurement to quantitatively evaluate the performance of our proposed segmentation method. In both evaluation approaches, the proposed algorithm provides better performance compared to the other methods. The proposed method provides an accuracy of more than 90% for lung image segmentation, which shows around 5% increase in the accuracy comparing to the state of the art. The high accuracy of this method is due to its fitness to the application.

Special Report of the Society for Maternal-Fetal Medicine Placenta Accreta Spectrum Ultrasound Marker Task Force: Consensus on definition of markers and approach to the ultrasound examination in pregnancies at risk for placenta accreta spectrum

Placenta accreta spectrum includes the full range of abnormal placental attachment to the uterus or other structures, encompassing placenta accreta, placenta increta, placenta percreta, morbidly adherent placenta, and invasive placentation. The incidence of placenta accreta spectrum has increased in recent years, largely driven by increasing rates of cesarean delivery. Prenatal detection of placenta accreta spectrum is primarily made by ultrasound and is important to reduce maternal morbidity associated with the condition. Despite a large body of research on various placenta accreta spectrum ultrasound markers and their screening performance, inconsistencies in the literature persist. In response to the need for standardizing the definitions of placenta accreta spectrum markers and the approach to the ultrasound examination, the Society for Maternal-Fetal Medicine convened a task force with representatives from the American Institute of Ultrasound in Medicine, the American College of Obstetricians and Gynecologists, the American College of Radiology, the International Society of Ultrasound in Obstetrics and Gynecology, the Society for Radiologists in Ultrasound, the American Registry for Diagnostic Medical Sonography, and the Gottesfeld-Hohler Memorial Ultrasound Foundation. The goals of the task force were to assess placenta accreta spectrum sonographic markers on the basis of available data and expert consensus, provide a standardized approach to the prenatal ultrasound evaluation of the uterus and placenta in pregnancies at risk of placenta accreta spectrum, and identify research gaps in the field. This manuscript provides information on the Placenta Accreta Spectrum Task Force process and findings.

Impact of radiomics on the breast ultrasound radiologist’s clinical practice: From lumpologist to data wrangler

ObjectiveThe study aims to assess the impact of radiomics in the clinical practice of breast ultrasound, to determine which lesions are undetermined by the software, and to discuss the future of the radiologist’s role. MethodsConsecutive analyses of 207 ultrasound masses from January 2018 to April 2019 referred for percutaneous breast biopsy. Breast masses were classified using dedicated ultrasound software (AI). The AI software automatically classified the masses on a scale of 0–100, where 100 is the most suspicious. We adopt the histology results as the gold standard. The cut-off point of malignancy by radiomics was determined, with ±10 % of margin error according to the Youden’s index. We considered these lesions as undetermined masses. The performance of the AI software and the radiologist classification was compared using the area under roc curves (AUROC). We also discuss the impact of radiologist validation of AI results, especially in undetermined lesions. ResultsOf the 207 evaluated masses, 143 were benign, and 64 were malignant. The Youden’s index was 0.516, including undetermined masses with a varied range of 10 % (0.464−0.567). Twenty-one (14.58 %) benign and twelve (19.05 %) malignant masses were in this range. The best accuracy performance to classify masses was the combination of the reader and AI (0.829). The most common undetermined masses in AI were fibroadenoma, followed by phyllodes tumor, steatonecrosis as benign. Whereas, low-grade, and high-grade invasive ductal carcinoma represents the malignant lesions. ConclusionsArtificial Intelligence has a reliable performance in ultrasound breast masses classification. Radiologist validation is critical to determine the final BI-RADS assessment, especially in undetermined masses to obtain the best classification performance