Ultrasound Imaging Data Research Articles

Differences between CEUS LI-RADS and CECT LI-RADS in the diagnosis of focal liver lesions in patients at risk for HCC

ObjectivesTo compare the inter-modality consistency and diagnostic performances of the contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS) and contrast-enhanced computed tomography (CECT) LI-RADS in patients at risk for hepatocellular carcinoma (HCC), so as to help clinicians to select a more appropriate modality to follow the focal liver lesions (FLLs).MethodsThis retrospective study included untreated 277 FLLs from 247 patients who underwent both CEUS and CECT within 1 month. The ultrasound contrast medium used was SonoVue. FLL categories were independently assigned by two ultrasound physicians and two radiologists using CEUS LI-RADS v2017 and CECT LI-RADS v2018, respectively. The diagnostic performances of CEUS and CECT LI-RADS were evaluated using sensitivity, specificity, positive predictive value (PPV), and negative predictive value. Cohen’s Kappa was employed to evaluate the concordance of the LI-RADS category.ResultsThe inter-modality consistency for CEUS and CECT LI-RADS was 0.31 (p < 0.001). HCC was more frequently observed in CECT LR-3 and LR-4 hepatic lesions than in CEUS (7.3% vs. 19.5%, p < 0.001). The specificity and PPV of CEUS and CECT LR-5 for the diagnosis of HCC were 89.5%, 95.0%, and 82.5%, 94.4%, respectively. The sensitivity of CEUS LR-5 + LR-M for the diagnosis of hepatic malignancies was higher than that of CECT (93.7% vs. 82.7%, p < 0.001). The specificity and PPV of CEUS LR-M for the diagnosis of non-HCC malignancies were lower than those of CECT (59.7% vs. 95.5%, p < 0.001; 23.4% vs. 70.3%, p < 0.001).ConclusionsThe inter-modality consistency between the CEUS and CECT LI-RADS categories is fair. CEUS LI-RADS was more sensitive than CECT LI-RADS in terms of identifying hepatic malignancies, but weaker in terms of separating HCC from non-HCC malignancies.

Human in vivo medial gastrocnemius gear during active and passive muscle lengthening: effect of inconsistent methods and nomenclature on data interpretation.

'Muscle gear' is calculated as the ratio of fascicle-to-muscle length change, strain, or velocity. Inconsistencies in nomenclature and definitions of gear exist across disciplines partly due to differences in fascicle [curved (Lf) versus linear (Lf,straight)] and muscle [whole-muscle belly (Lb) versus belly segment (Lb,segment)] length calculation methods. We tested whether these differences affect gear magnitude during passive and active muscle lengthening of human medial gastrocnemius of young men (n=13, 26.3±5.0 years) using an isokinetic dynamometer. Lb, Lb,segment, Lf and Lf,straight were measured from motion analysis and ultrasound imaging data. Downshifts in belly gear but not belly segment gear occurred with muscle lengthening only during active lengthening. Muscle gear was unaffected by fascicle length measurement method (P=0.18) but differed when calculated as changes in Lb or Lb,segment (P<0.01) in a length-dependent manner. Caution is therefore advised for the use and interpretation of different muscle gear calculation methods and nomenclatures in animal and human comparative physiology.

Ultrasound Probe Calibration Method of Single-Wire Phantom Using Levenberg-Marquardt Algorithm

A freehand three-dimensional (3D) ultrasound system is a method of acquiring images using a 3D ultrasound probe or conventional two-dimensional (2D) ultrasound probe to give a 3D visualization of an object inside the body. Ultrasounds are used extensively in clinical applications since they are advantageous in that they do not bring dangerous radiation effects and have a low cost. However, a probe calibration method is needed to transform the coordinate position into a 3D visualization display, especially for image-guided intervention. The current ultrasound probe calibration system usually uses the numerical regression method for the N-wire phantom, which has problems in accuracy and reliability due to nonlinear point scattered ultrasound image data. Hence, a method for ultrasound probe positional calibration of single-wire phantom using the Levenberg-Marquardt algorithm (LMA) was proposed to overcome this weakness. This experiment consisted of an optical tracking system setup, a 2D ultrasound probe with marker, an ultrasound machine, and a single-wire object in a water container equipped with a marker. The position and orientation of the marker in a 2D ultrasound probe and the marker in the water container were tracked using the optical tracking system. A 2D ultrasound probe was equipped with a marker connected wirelessly using an optical tracking system to capture the single-wire object. The resulting sequences of 2D ultrasound images were reconstructed and visualized into 3D ultrasound images using three transformations, ultrasound beam to ultrasound probe’s marker, single-wire phantom position to container’s marker, and the 3D visualization transformation. The LMA was used to determine the best optimization parameters for determining the exact position and representing that 3D visualization. The experiment result showed that the lowest mean square error (MSE), rotation error, and translation error were 0.45 mm, 0.25°, and 0.3828 mm, respectively.

Midline suprapineal pseudocyst in brain of fetuses with open spina bifida.

Recently, it was noted that fetuses with open spina bifida (OSB) may have a midline cystic structure evident on ultrasound. Our aims were to determine the prevalence of this cystic structure, shed light on its pathophysiology and investigate the association between its presence and other characteristic brain findings in fetuses with OSB. This was a single-center retrospective study of all fetuses with OSB and available cineloop images in the axial plane referred to the Ontario Fetal Centre, Toronto, Canada, between June 2017 and May 2022. Ultrasound and magnetic resonance imaging (MRI) data obtained between 18 + 0 and 25 + 6 weeks were reviewed in search of a midline cystic structure. Pregnancy and lesion characteristics were collected. Transcerebellar diameter (TCD), clivus-supraocciput angle (CSA) and additional brain abnormalities (abnormal cavum septi pellucidi (CSP), abnormal corpus callosum (CC) and periventricular nodular heterotopia (PNH)) were assessed. In cases of in-utero repair, imaging findings were reviewed postoperatively. In cases of termination, neuropathological findings were reviewed, if available. Of 76 fetuses with OSB, 56 (73.7%) had a suprapineal cystic structure on ultrasound. The percentage of agreement between ultrasound and MRI detection was 91.5% (Cohen's kappa coefficient, 0.78 (95% CI, 0.57-0.98)). Brain autopsy in terminated cases revealed a dilatation of the posterior third ventricle, with redundant tela choroidea and arachnoid forming the membranous roof of the third ventricle, anterior and superior to the pineal gland. A cyst wall could not be identified, indicating that the structure was a pseudocyst. The presence of the pseudocyst was associated with a smaller CSA (pseudocyst absent, 62.11 ± 9.60° vs pseudocyst present, 52.71 ± 8.22°; P = 0.04). When the pseudocyst was present, its area was correlated inversely with TCD (r, -0.28 (95% CI, -0.51 to -0.02); P = 0.04). Fetal surgery did not have any impact on the growth rate of the pseudocyst (fetal surgery, 5.07 ± 3.29 mm2 /week vs expectant management, 4.35 ± 3.17 mm2 /week; P = 0.58). The presence of the pseudocyst was not associated with abnormal CSP, CC or presence of PNH. None of the cases with available postnatal follow-up required surgical procedure related to the pseudocyst. Approximately 75% of all OSB cases have a suprapineal pseudocyst. Its presence is associated with the degree of hindbrain herniation but not with abnormalities of the CSP and CC or presence of PNH. Thus, it should not be regarded as additional brain pathology and should not preclude fetuses from undergoing fetal surgery for OSB. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Multimodality deep learning radiomics nomogram for preoperative prediction of malignancy of breast cancer: a multicenter study

Background. Breast cancer is the most prevalent cancer diagnosed in women worldwide. Accurately and efficiently stratifying the risk is an essential step in achieving precision medicine prior to treatment. This study aimed to construct and validate a nomogram based on radiomics and deep learning for preoperative prediction of the malignancy of breast cancer (MBC). Methods. The clinical and ultrasound imaging data, including brightness mode (B-mode) and color Doppler flow imaging, of 611 breast cancer patients from multiple hospitals in China were retrospectively analyzed. Patients were divided into one primary cohort (PC), one validation cohort (VC) and two test cohorts (TC1 and TC2). A multimodality deep learning radiomics nomogram (DLRN) was constructed for predicting the MBC. The performance of the proposed DLRN was comprehensively assessed and compared with three unimodal models via the calibration curve, the area under the curve (AUC) of receiver operating characteristics and the decision curve analysis. Results. The DLRN discriminated well between the MBC in all cohorts [overall AUC (95% confidence interval): 0.983 (0.973–0.993), 0.972 (0.952–0.993), 0.897 (0.823–0.971), and 0.993 (0.977–1.000) on the PC, VC, test cohorts1 (TC1) and test cohorts2 TC2 respectively]. In addition, the DLRN performed significantly better than three unimodal models and had good clinical utility. Conclusion. The DLRN demonstrates good discriminatory ability in the preoperative prediction of MBC, can better reveal the potential associations between clinical characteristics, ultrasound imaging features and disease pathology, and can facilitate the development of computer-aided diagnosis systems for breast cancer patients. Our code is available publicly in the repository at https://github.com/wupeiyan/MDLRN.

Applying deep learning to recognize the properties of vitreous opacity in ophthalmic ultrasound images.

To explore the feasibility of artificial intelligence technology based on deep learning to automatically recognize the properties of vitreous opacities in ophthalmic ultrasound images. A total of 2000 greyscale Doppler ultrasound images containing non-pathological eye and three typical vitreous opacities confirmed as physiological vitreous opacity (VO), asteroid hyalosis (AH), and vitreous haemorrhage (VH) were selected and labelled for each lesion type. Five residual networks (ResNet) and two GoogLeNet models were trained to recognize vitreous lesions. Seventy-five percent of the images were randomly selected as the training set, and the remaining 25% were selected as the test set. The accuracy and parameters were recorded and compared among these seven different deep learning (DL) models. The precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC) values for recognizing vitreous lesions were calculated for the most accurate DL model. These seven DL models had significant differences in terms of their accuracy and parameters. GoogLeNet Inception V1 achieved the highest accuracy (95.5%) and minor parameters (10315580) in vitreous lesion recognition. GoogLeNet Inception V1 achieved precision values of 0.94, 0.94, 0.96, and 0.96, recall values of 0.94, 0.93, 0.97 and 0.98, and F1 scores of 0.94, 0.93, 0.96 and 0.97 for normal, VO, AH, and VH recognition, respectively. The AUC values for these four vitreous lesion types were 0.99, 1.0, 0.99, and 0.99, respectively. GoogLeNet Inception V1 has shown promising results in ophthalmic ultrasound image recognition. With increasing ultrasound image data, a wide variety of confidential information on eye diseases can be detected automatically by artificial intelligence technology based on deep learning.

Feeding artery: a valuable feature for differentiation of regenerative nodule, dysplastic nodules and small hepatocellular carcinoma in CEUS LI-RADS.

To investigate whether the feeding artery (FA) feature can aid in discriminating small hepatocellular carcinoma (HCC) using the contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS) from precancerous lesions. Between June 2017 and May 2021, a total of 347 patients with 351 precancerous liver lesions or small HCCs who underwent CEUS were enrolled. Two independent radiologists assigned LI-RADS categories to all lesions and assessed the presence of the FA feature, which was used as an ancillary feature to either upgrade or downgrade the LI-RADS category. The diagnostic performance of CEUS LI-RADS, both with and without the FA feature, was evaluated based on accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. The FA feature was found to be more prevalent in HCC (85.54%, p < 0.001) than in regenerative nodules (RNs, 29.73%), low-grade dysplastic nodules (LGDNs, 33.33%), and high-grade dysplastic nodules (HGDNs, 55.26%). Furthermore, the presence of arterial phase hyperenhancement (APHE), washout (WO), and FA in liver nodules was associated with a higher expression of GPC-3 and Ki-67 compared to the group without these features (p < 0.001). After adjusting, the sensitivity and accuracy of LR-5 for HCC improved from 68.67% (95%CI: 62.46%, 74.30%) to 77.51% (95%CI: 71.72%, 82.44%) and from 69.23% (95%CI: 64.11%, 74.02%) to 73.79% (95%CI: 68.86%, 78.31%), respectively. The FA feature is a valuable feature for distinguishing small HCC and precancerous lesions and could be added as a possible ancillary feature in CEUS LI-RADS which was backed up by biomarkers. The presence of a feeding artery is a valuable imaging feature in the differentiation of HCC and precancerous lesions. Incorporating this characteristic in the CEUS LI-RADS can enhance the diagnostic ability. • Feeding artery is more frequent in HCC than in regenerative nodules, low-grade dysplastic nodules, and high-grade dysplastic nodules. • Feeding artery feature is a valuable ancillary feature for CEUS LI-RADS to differentiate regenerative nodules, low-grade dysplastic nodules, high-grade dysplastic nodules, and HCC. • The existence of feeding artery, arterial phase hyperenhancement, and washout is associated with more GPC-3 positive expression and higher Ki-67 expression than the group without these features.

Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity

Lesion segmentation of ultrasound medical images based on deep learning techniques is a widely used method for diagnosing diseases. Although there is a large amount of ultrasound image data in medical centers and other places, labeled ultrasound datasets are a scarce resource, and it is likely that no datasets are available for new tissues/organs. Transfer learning provides the possibility to solve this problem, but there are too many features in natural images that are not related to the target domain. As a source domain, redundant features that are not conducive to the task will be extracted. Migration between ultrasound images can avoid this problem, but there are few types of public datasets, and it is difficult to find sufficiently similar source domains. Compared with natural images, ultrasound images have less information, and there are fewer transferable features between different ultrasound images, which may cause negative transfer. To this end, a multi-source adversarial transfer learning network for ultrasound image segmentation is proposed. Specifically, to address the lack of annotations, the idea of adversarial transfer learning is used to adaptively extract common features between a certain pair of source and target domains, which provides the possibility to utilize unlabeled ultrasound data. To alleviate the lack of knowledge in a single source domain, multi-source transfer learning is adopted to fuse knowledge from multiple source domains. In order to ensure the effectiveness of the fusion and maximize the use of precious data, a multi-source domain independent strategy is also proposed to improve the estimation of the target domain data distribution, which further increases the learning ability of the multi-source adversarial migration learning network in multiple domains. The effectiveness of multi-source adversarial transfer learning is demonstrated through experiments on three datasets of ultrasound image datasets.

Factors affecting the primary patency of native arteriovenous fistulas after ultrasound-guided percutaneous transluminal angioplasty

Objective By analyzing the clinical history, laboratory test indexes, and intraoperative ultrasound imaging data of patients receiving ultrasound-guided percutaneous transluminal angioplasty (UG-PTA) for the first time, the application value of UG-PTA in the treatment of peripheral stenosis of autogenous arteriovenous fistula (AVF) and the related factors affecting postoperative patency were investigated. Methods A total of 381 patients with dysfunction of radio-cephalic AVF were treated with UG-PTA from June 2017 to September 2019. According to the inclusion and exclusion criteria, 199 patients were included in this study. Baseline characteristics of patients, including demographic, clinical, and laboratory data, were collected. Kaplan–Meier’s survival curve was used to demonstrate the cumulative primary patency rate of UG-PTA. Univariate and multivariate Cox regression analysis was performed on clinical, anatomic, biochemical, and medication variables to identify the predictors of postintervention primary patency. Results The early technical success rate of UG-PTA was 98.4% (375/381). One hundred and ninety-nine patients, with an average age of 52.9 years, were analyzed, 97 of whom were males (48.7%). The median follow-up duration was 21 months. No major complication was observed. Postintervention primary patency rates were 87.7%, 75.8%, and 60.0% at 6, 12, and 24 months, respectively. A previously failed AVF (HR, 1.935, 95% CI 1.071–3.494; p = .029) and an increased level of parathyroid hormone (HR per 100 pg/mL increase, 1.105; 95% CI 1.014–1.203; p = .004) were identified as independent negative predictors of primary patency of UG-PTA. Conclusions UG-PTA is a safe and effective method for the treatment of peripheral stenosis of AVF. Previously failed AVF and elevated parathyroid hormone levels are associated with lower primary patency rate.

A machine learning approach to predict cerebral perfusion status based on internal carotid artery blood flow

Background and objectiveCerebral blood flow (CBF), or perfusion, is a prerequisite for maintaining brain metabolism and normal physiological functions. Diagnosing and evaluating cerebral perfusion status is crucial to managing brain disease. However, cerebral perfusion imaging devices are complicated to operate, should be controlled by specialized technicians, are often large, and are usually installed in fixed places such as hospitals. It is significantly difficult for clinicians to obtain the cerebral perfusion status in time. Considering that CBF is mainly supplied by the internal carotid artery (ICA), this study proposes a cerebral perfusion status prediction model that can automatically quantify the level of cerebral perfusion in patients by modeling the association between ICA blood flow and cerebral perfusion. Materials and methodsForty-eight participants were enrolled in the study after screening. We collected participants’ ICA ultrasound and brain magnetic resonance imaging (MRI) data before and after dobutamine injection based on a rigorous experimental paradigm and built an ICA-cerebral perfusion datasetdd. Support vector machine (SVM), k-nearest neighbor (KNN), decision tree (DT), random forest (RF), gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBOOST) were used for early prediction of cerebral perfusion status. The SHAP analysis was adopted to reveal the impact of interpretable predictions for each feature. ResultsThe XGBOOST model demonstrated the best overall classification performance with an accuracy of 78.01%, sensitivity of 96.67%, specificity of 98.23%, F1 score of 74.57%, Matthews correlation coefficient (MCC) of 62.17%, and area under the receiver operating characteristic curve (AUC) of 87.08%. Accelerated speed, peak systolic flow velocity, and resistance index of ICA blood flow are important factors for cerebral perfusion prediction. ConclusionsThe proposed method paves a new avenue for the study of predicting cerebral perfusion status automatically and providesv a noninvasive, real-time, and low-cost alternative to brain perfusion imaging. Moreover, this analysis identifies highly predictive features for the cerebral perfusion status and gives clinicians an intuitive understanding of the influence of key features. The prediction models can serve as an early warning tool that offers sufficient time for clinicians to take early intervention measures.

In Vivo Validation of Modulated Acoustic Radiation Force-Based Imaging in Murine Model of Abdominal Aortic Aneurysm Using VEGFR-2-Targeted Microbubbles.

The objective of this study is to validate the modulated acoustic radiation force (mARF)-based imaging method in the detection of abdominal aortic aneurysm (AAA) in murine models using vascular endothelial growth factor receptor 2 (VEGFR-2)-targeted microbubbles (MBs). The mouse AAA model was prepared using the subcutaneous angiotensin II (Ang II) infusion combined with the β-aminopropionitrile monofumarate solution dissolved in drinking water. The ultrasound imaging session was performed at 7 days, 14 days, 21 days, and 28 days after the osmotic pump implantation. For each imaging session, 10 C57BL/6 mice were implanted with Ang II-filled osmotic pumps, and 5 C57BL/6 mice received saline infusion only as the control group. Biotinylated lipid MBs conjugated to either anti-mouse VEGFR-2 antibody (targeted MBs) or isotype control antibody (control MBs) were prepared before each imaging session and were injected into mice via tail vein catheter. Two separate transducers were colocalized to image the AAA and apply ARF to translate MBs simultaneously. After each imaging session, tissue was harvested and the aortas were used for VEGFR-2 immunostaining analysis. From the collected ultrasound image data, the signal magnitude response of the adherent targeted MBs was analyzed, and a parameter, residual-to-saturation ratio ( Rres - sat ), was defined to measure the enhancement in the adherent targeted MBs signal after the cessation of ARF compared with the initial signal intensity. Statistical analysis was performed with the Welch t test and analysis of variance test. The Rres - sat of abdominal aortic segments from Ang II-challenged mice was significantly higher compared with that in the saline-infused control group ( P < 0.001) at all 4 time points after osmotic pump implantation (1 week to 4 weeks). In control mice, the Rres - sat values were 2.13%, 1.85%, 3.26%, and 4.85% at 1, 2, 3, and 4 weeks postimplantation, respectively. In stark contrast, the Rres - sat values for the mice with Ang II-induced AAA lesions were 9.20%, 20.6%, 22.7%, and 31.8%, respectively. It is worth noting that there was a significant difference between the Rres - sat for Ang II-infused mice at all 4 time points ( P < 0.005), a finding not present in the saline-infused mice. Immunostaining results revealed the VEGFR-2 expression was increased in the abdominal aortic segments of Ang II-infused mice compared with the control group. The mARF-based imaging technique was validated in vivo using a murine model of AAA and VEGFR-2-targeted MBs. Results in this study indicated that the mARF-based imaging technique has the ability to detect and assess AAA growth at early stages based on the signal intensity of adherent targeted MBs, which is correlated with the expression level of the desired molecular biomarker. The results may suggest, in very long term, a pathway toward eventual clinical implementation for an ultrasound molecular imaging-based approach to AAA risk assessment in asymptomatic patients.

Comparison of machine learning models and CEUS LI-RADS in differentiation of hepatic carcinoma and liver metastases in patients at risk of both hepatitis and extrahepatic malignancy

BackgroundCEUS LI-RADS (Contrast Enhanced Ultrasound Liver Imaging Reporting and Data System) has good diagnostic efficacy for differentiating hepatic carcinoma (HCC) from solid malignant tumors. However, it can be problematic in patients with both chronic hepatitis B and extrahepatic primary malignancy. We explored the diagnostic performance of LI-RADS criteria and CEUS-based machine learning (ML) models in such patients.MethodsConsecutive patients with hepatitis and HCC or liver metastasis (LM) who were included in a multicenter liver cancer database between July 2017 and January 2022 were enrolled in this study. LI-RADS and enhancement features were assessed in a training cohort, and ML models were constructed using gradient boosting, random forest, and generalized linear models. The diagnostic performance of the ML models was compared with LI-RADS in a validation cohort of patients with both chronic hepatitis and extrahepatic malignancy.ResultsThe mild washout time was adjusted to 54 s from 60 s, increasing accuracy from 76.8 to 79.4%. Through feature screening, washout type II, rim enhancement and unclear border were identified as the top three predictor variables. Using LI-RADS to differentiate HCC from LM, the sensitivity, specificity, and AUC were 68.2%, 88.6%, and 0.784, respectively. In comparison, the random forest and generalized linear model both showed significantly higher sensitivity and accuracy than LI-RADS (0.83 vs. 0.784; all P < 0.001).ConclusionsCompared with LI-RADS, the random forest and generalized linear model had higher accuracy for differentiating HCC from LM in patients with chronic hepatitis B and extrahepatic malignancy.

FBN: Weakly Supervised Thyroid Nodule Segmentation Optimized by Online Foreground and Background

The main objective of the work described here was to train a semantic segmentation model using classification data for thyroid nodule ultrasound images to reduce the pressure of obtaining pixel-level labeled data sets. Furthermore, we improved the segmentation performance of the model by mining the image information to narrow the gap between weakly supervised semantic segmentation (WSSS) and fully supervised semantic segmentation. Most WSSS methods use a class activation map (CAM) to generate segmentation results. However, the lack of supervision information makes it difficult for a CAM to highlight the object region completely. Therefore, we here propose a novel foreground and background pair (FB-Pair) representation method, which consists of high- and low-response regions highlighted by the original CAM-generated online in the original image. During training, the original CAM is revised using the CAM generated by the FB-Pair. In addition, we design a self-supervised learning pretext task based on FB-Pair, which requires the model to predict whether the pixels in FB-Pair are from the original image during training. After this task, the model will accurately distinguish between different categories of objects. Experiments on the thyroid nodule ultrasound image (TUI) data set revealed that our proposed method outperformed existing methods, with a 5.7% improvement in the mean intersection-over-union (mIoU) performance of segmentation compared with the second-best method and a reduction to 2.9% in the difference between the performance of benign and malignant nodules. Our method trains a well-performing segmentation model on ultrasound images of thyroid nodules using only classification data. In addition, we determined that CAM can take full advantage of the information in the images to highlight the target regions more accurately and thus improve the segmentation performance.

A Prospective Comparison of Transrectal Standard, Cognitive, Transperineal Fusion, and Mapping Prostate Biopsy for Cancer Detection.

Purpose: The aim of this research was to compare the clinically significant prostate cancer (csPCa) detection rate (International Society of Urological Pathology [ISUP] ≥2) for the four biopsy methods: transrectal ultrasound-guided biopsy (TRUS-GB), cognitive transrectal biopsy (COG-TB), fusion transperineal biopsy (FUS-TB), and transperineal template mapping biopsy (TPMB). Materials and Methods: The inclusion criteria were as follows: prostate-specific antigen (PSA) >2 ng/mL, and/or positive digital rectal examination (DRE), and/or suspicious lesion on transrectal ultrasound (TRUS) and Prostate Imaging Reporting and Data System (Pi-RADS) v2.1 ≥ 3 score. In total, 102 patients were enrolled in the study. Biopsies were performed by two urologists. In a single procedure, the first urologist performed a FUS-TB and TPMB followed by second urologist who performed TRUS-GB and COG-TB. All specimens were obtained within a single procedure. Results: The csPCa detection rate and overall cancer detection rate (CDR) per patient were comparable among the respective biopsy methods (p > 0.05). Compared with other biopsy methods, a lower clinically insignificant prostate cancer (cisPCa) was detected using COG-TB (p = 0.004). The positive cores percentage ratio (p < 0.001) as well as positive cores containing csPCa percentage ratio (p < 0.001) significantly increased for the targeted biopsy methods. The median maximum cancer core length (MCCL; p = 0.52) as well the median for the MCCL of csPCa (p = 0.47) did not differ significantly among the respective biopsy methods. Concordance of the Gleason scores between biopsy and postprostatectomy pathology did not differ significantly among biopsy methods (p = 0.87). For TRUS-GB, FUS-TB, and TPMB, the common predictive factors for csPCa were positive DRE, suspicious lesion on ultrasound and Pi-RADS 5. As for COG-TB, the only predictor was Pi-RADS 5. Conclusion: The targeted methods did not show an increase in detection of csPCa and overall CDR over systematic ones in patients with Pi-RADS ≥3. A lower cisPCa was detected using COG-TB in comparison with the other methods. The sampling efficiency increased for the targeted biopsy methods, which used only a proportion of positive cores and cores containing csPCa. There was no statistical difference in histology concordance among the biopsies. One common predictive factor of increased csPCa detection for all biopsy methods was Pi-RADS 5.

Comparison of the Feasibility and Diagnostic Performance of ACR CEUS LI-RADS and a Modified CEUS LI-RADS for HCC in Examinations Using Sonazoid.

The present study aimed to determine the feasibility of the American College of Radiology's (ACR) contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS) (version 2017) in examinations using Sonazoid and compare its diagnostic performance with that of modified LI-RADS in patients at high risk of hepatocellular carcinoma (HCC). This retrospective study's sample population consisted of 137 participants with a total of 140 nodules who underwent CEUS with Sonazoid and pathological confirmation via surgery or biopsy from January 2020 to February 2022. The lesions were evaluated and classified based on the reference standards (ie, ACR CEUS LI-RADS and modified LI-RADS). The overall diagnostic capabilities of the two systems were evaluated in terms of accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with 95% confidence intervals (CIs). The participants had a median age of 51 years and an interquartile range of 43-58 years. Regarding LR-5 as a predictor of HCC, the accuracy results of the ACR LI-RADS and modified LI-RADS algorithms were 72.9 and 71.4%, respectively (P = .50). The sensitivity of both systems was the same (69.7%; 95% CI: 60.7-77.8%). Regarding LR-M as a predictor of non-HCC malignancy, the diagnostic performance of the algorithms was the same, with accuracy and sensitivity results of 76.4 and 73.3%, respectively (95% CI: 44.9-92.2%). The findings indicate that modified LI-RADS had a moderate level of diagnostic performance for HCC in examinations using Sonazoid, which was comparable to ACR LI-RADS.

Comparative accuracy of sonography, mammography and the BI-RADS characterization of breast masses among adult women at Mulago Hospital, Uganda

Background Breast cancer is common among Ugandan women and mortality rate is significantly high. Uganda, like many low-income countries, has no national regular mammography screening programme, a gold standard in breast cancer imaging. Breast ultrasound and Breast Imaging Reporting and Data System (BI-RADS) classification is thus being promoted as a supplemental evaluation tool for breast masses. However, studies on the comparative accuracy of breast sonography, mammography and BI-RADS from low-income settings are limited. This study aimed to determine the accuracy of breast ultrasound, mammography and BI-RADS classification against histology in the evaluation of breast masses among adult women. Methods This was a cross-sectional study conducted at Mulago National Referral Hospital involving women with breast masses. The women underwent breast ultrasound, mammography and needle biopsy for histological analysis. The breast lesions were also evaluated against the BI-RADS characterization criteria. Results Overall, 212 breast masses were evaluated and included in the analysis. Of these, 50% (106) were benign and 50% (106) were malignant. The sensitivity for ultrasound and mammography separately was 68.5% and 72.5% respectively. The sensitivity for ultrasound and mammography combined was 85%. BI-RADS 5 category had the highest sensitivity at 59.9% while the highest specificity was noted among BI-RADS 3 and 5 at 100%. The highest accuracy was noted in the BI-RADS 5 category at 79.9%. Conclusions Findings from this study demonstrate that combining ultrasound and mammography could have a higher sensitivity and diagnostic accuracy than when these imaging modalities are used independently. In addition, the BI-RADS reporting classification has an optimum positive predictive value and should be promoted to standardize breast imaging reporting.

A deep learning model for the differential diagnosis of benign and malignant salivary gland tumors based on ultrasound imaging and clinical data.

The preoperative differentiation between benign parotid gland tumors (BPGTs) and malignant parotid gland tumors (MPGTs) is of great significance for therapeutic decision-making. Deep learning (DL), an artificial intelligence algorithm based on neural networks, can help overcome inconsistencies in conventional ultrasonic (CUS) examination outcomes. Therefore, as an auxiliary diagnostic tool, DL can support accurate diagnosis using massive ultrasonic (US) images. This current study developed and validated a DL-based US diagnosis for the preoperative differentiation of BPGT from MPGT. A total of 266 patients, including 178 patients with BPGT and 88 patients with MPGT, were consecutively identified from a pathology database and enrolled in this study. Ultimately, considering the limitations of the DL model, 173 patients were selected from the 266 patients and divided into 2 groups: a training set, and a testing set. US images of the 173 patients were used to construct the training set (including 66 benign and 66 malignant PGTs) and testing set (consisting of 21 benign and 20 malignant PGTs). These were then preprocessed by normalizing the grayscale of each image and reducing noise. Processed images were imported into the DL model, which was then trained to predict the images from the testing set and evaluated for performance. Based on the training and validation datasets, the diagnostic performance of the 3 models was assessed and verified using receiver operating characteristic (ROC) curves. Ultimately, before and after combining the clinical data, we compared the area under the curve (AUC) and diagnostic accuracy of the DL model with the opinions of trained radiologists to evaluate the application value of the DL model in US diagnosis. The DL model showed a significantly higher AUC value compared to doctor 1 + clinical data, doctor 2 + clinical data, and doctor 3 + clinical data (AUC =0.9583 vs. 0.6250, 0.7250, and 0.8025 respectively; all P<0.05). In addition, the sensitivity of the DL model was higher than the sensitivities of the doctors combined with clinical data (97.2% vs. 65%, 80%, and 90% for doctor 1 + clinical data, doctor 2 + clinical data, and doctor 3 + clinical data, respectively; all P<0.05). The DL-based US imaging diagnostic model has excellent performance in differentiating BPGT from MPGT, supporting its value as a diagnostic tool for the clinical decision-making process.

Letter to the Editor Regarding the Article "Contrast-Enhanced Ultrasound Liver Imaging Reporting and Data System in Diagnosing Hepatocellular Carcinoma: Diagnostic Performance and Interobserver Agreement" by Zhou and Collaborators.

N/A.

Response to Letter to the Editor Regarding the Article "Contrast-Enhanced Ultrasound Liver Imaging Reporting and Data System in Diagnosing Hepatocellular Carcinoma: Diagnostic Performance and Interobserver Agreement" by Zhou and Collaborators.

Thanks Stefanini and your colleagues for positive comments on our recent study of applying CEUS LI-RADS in eastern countries with emphasis on diagnostic performance and interobserver agreement [1]. We agree that the specificity of CEUS LR-5 is high enough (range:92.7–100.0 % in cirrhotic patients in our study) to rule out non-hepatocellular carcinoma(HCC) lesions. And we also agree that inconsistency of interpreting objective CEUS features, especially ancillary features, significantly hinder the general application of CEUS LI-RADS in targeted high-risk population. Even after years of CEUS LI-RADS learning and training, ancillary features are still deemed as failure to make additional value in final decision. Therefore, we fully approve removing current ancillary features (mosaic and nodule-in-nodule pattern) from CEUS LI-RADS workup as Stefanini demonstrated.

Comparison of preoperative ultrasound and MRI in the diagnosis of microvascular invasion in hepatocellular carcinoma.

Ultrasound has few reports on its application in prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC). The purpose of this study was to explore the diagnostic efficacies of preoperative ultrasound and magnetic resonance imaging (MRI) for HCC MVI and compare these two imaging methods for the diagnosis of this condition. The clinical and preoperative ultrasound and MR imaging data of 26 patients with newly diagnosed HCC were collected between October 2020 and October 2021. According to the gold standard (postoperative pathology), the patients were divided into MVI-positive and MVI-negative groups, and the efficacies of ultrasound and MRI in diagnosing HCC MVI and the consistency between the two imaging modalities were analyzed. For the preoperative diagnosis of MVI using ultrasound, the sensitivity was 93.33%, the specificity was 81.82%, and the accuracy was 88.46%. For preoperative MRI, the sensitivity was 66.67%, the specificity was 100%, and the accuracy was 80.77%. In diagnosing MVI, the two methods had significantly different efficacy (P = 0.031). Ultrasound and MRI have high diagnostic efficiency for MVI, but the accuracy of preoperative MRI was lower than that of preoperative ultrasound. These results indicate that ultrasound has a certain guiding significance in the diagnosis of HCC MVI.