ObjectiveTo investigate the feasibility of a CAD system S-detect on a database from a single Chinese medical center.Materials and methodsAn experienced radiologist performed breast US examinations and made assessments of 266 consecutive breast lesions in 227 patients. S-detect classified the lesions automatically in a dichotomous form. An in-training resident who was blind to both the US diagnostic results and histological results reviewed the images afterward. The final histological results were considered as the diagnostic gold standard. The diagnostic performances and interrater agreements were analyzed.ResultsA total of 266 focal breast lesions (161 benign lesions and 105 malignant lesions) were assessed in this study. S-detect had a lower sensitivity (87.07%) and a higher specificity (72.27%) compared with the experienced radiologist (sensitivity 98.1% and specificity 65.43%). The sensitivity and specificity of S-detect were better than that of the resident (sensitivity 82.86% and specificity 68.94%). The AUC value of S-detect (0.807) showed no significant difference with the experienced radiologist (0.817) and was higher than that of the resident (0.758). S-detect had moderate agreement with the experienced radiologist.ConclusionIn this single-center study, a high level of diagnostic performance of S-detect on 266 breast lesions of Chinese women was observed. S-detect had almost equal diagnostic capacity with an experienced radiologist and performed better than a novice reader. S-detect was also distinguished for its high specificity. These results supported the feasibility of S-detect in aiding the diagnosis of breast lesions on an independent database.
ObjectiveThe aim of the study is to explore the potential value of S-Detect for residents-in-training, a computer-assisted diagnosis system based on deep learning (DL) algorithm.MethodsThe study was designed as a cross-sectional study. Routine breast ultrasound examinations were conducted by an experienced radiologist. The ultrasonic images of the lesions were retrospectively assessed by five residents-in-training according to the Breast Imaging Report and Data System (BI-RADS) lexicon, and a dichotomic classification of the lesions was provided by S-Detect. The diagnostic performances of S-Detect and the five residents were measured and compared using the pathological results as the gold standard. The category 4a lesions assessed by the residents were downgraded to possibly benign as classified by S-Detect. The diagnostic performance of the integrated results was compared with the original results of the residents.ParticipantsA total of 195 focal breast lesions were consecutively enrolled, including 82 malignant lesions and 113 benign lesions.ResultsS-Detect presented higher specificity (77.88%) and area under the curve (AUC) (0.82) than the residents (specificity: 19.47%–48.67%, AUC: 0.62–0.74). A total of 24, 31, 38, 32 and 42 identified as BI-RADS 4a lesions by residents 1, 2, 3, 4 and 5 were downgraded to possibly benign lesions by S-Detect, respectively. Among these downgraded lesions, 24, 28, 35, 30 and 40 lesions were proven to be pathologically benign, respectively. After combining the residents' results with the results of the software in category 4a lesions, the specificity and AUC of the five residents significantly improved (specificity: 46.02%–76.11%, AUC: 0.71–0.85, p<0.001). The intraclass correlation coefficient of the five residents also increased after integration (from 0.480 to 0.643).ConclusionsWith the help of the DL software, the specificity, overall diagnostic performance and interobserver agreement of the residents greatly improved. The software can be used as adjunctive tool for residents-in-training, downgrading 4a lesions to possibly benign and reducing unnecessary biopsies.
Objective:Contrast-enhanced ultrasound (CEUS) is a well-established imaging modality which has been put into clinical use in recent years with the development of second-generation contrast agent and imaging devices, and its applications in the assessment of inflammatory arthritis, such as rheumatoid arthritis, psoriatic arthritis, and ankylosing spondylitis, have provoked abundant discussion and researches among radiologists and rheumatologists. To summarize the achievements of clinical studies on CEUS in the application of arthritis, and to keep up with the latest progresses of the imaging technique, we reviewed the literature in recent years, hoping to establish the role of CEUS in joint diseases.Data Sources:PubMed and EMBASE.Study Selection:We searched the database with the conditions “contrast-enhanced ultrasound AND arthritis” with the time limitation of recent 10 years. Clinical studies applying CEUS in inflammatory arthritis and review articles about development of CEUS in joint diseases in English were selected.Results:As it is proved by most studies in recent years, by delineating microvasculature within the inflamed joints, CEUS can indicate early arthritis with high sensitivity and specificity. Moreover, the imaging of CEUS has been proved to be consistent with histopathological changes of inflammatory arthritis. Quantitative analysis of CEUS permits further evaluation of disease activity. CEUS also plays a significant role in the therapeutic monitoring of the disease, which has been backed up by a number of studies.Conclusions:CEUS may be a new choice for the rheumatologists to evaluate inflammatory arthritis, because of its low price, ability to provide dynamic pictures, and high sensitivity to angiogenesis. It can also be applied in disease classification and therapeutic monitoring. More studies about CEUS need to be done to set up the diagnostic standards.
Objective: To develop a nomogram for predicting axillary lymph node (ALN) metastases using the breast imaging reporting and data system (BI-RADS) ultrasound lexicon. Methods: A total of 703 patients from July 2015 to January 2018 were included in this study as a primary cohort for model construction. Moreover, 109 patients including 51 pathologically confirmed N1 patients (TNM staging) and 58 non-metastatic patients were recruited as an external validation cohort from March 2018 to August 2019. Ultrasound images and clinical information of these patients were retrospectively reviewed. The ultrasonic features based on the BI-RADS lexicon were extracted by two radiologists. The features extracted from the primary cohort were used to develop a nomogram using multivariate analysis. Internal and external validations were performed to evaluate the predictive efficacy of the nomogram. Results: The nomogram was based on two features (size, lesion boundary) and showed an area under the curve of 0.75 (95% confidence interval [CI], 0.70-0.79) in the primary cohort and 0.91 (95% CI, 0.84-0.97) in the external validation cohort; it achieved an 88% sensitivity in N1 patients. Conclusion: The nomogram based on BI-RADS ultrasonic features can predict breast cancer ALN status with relatively high accuracy. It has potential clinical value in improving the sensitivity and accuracy of the preoperative diagnosis of ALN metastases, especially for N1 patients.
Background: Deep learning-based computer-aided diagnosis (CAD) is an important method in aiding diagnosis for radiologists. We investigated the accuracy of a deep learning-based CAD in classifying breast lesions with different histological types. Methods: A total of 448 breast lesions were detected on ultrasound (US) and classified by an experienced radiologist, a resident and deep learning-based CAD respectively. The pathological results of the lesions were chosen as the golden standard. The diagnostic performances of the three raters in different pathological types were analyzed. Results: For the overall diagnostic performance, deep learning-based CAD presented a significantly higher specificity (76.96%) compared with the two radiologists. The area under ROC of CAD was almost equal with the experienced radiologist (0.81 vs. 0.81), while significantly higher than the resident (0.81 vs. 0.70, P<0.0001). In the benign lesions, deep learning-based CAD had a higher accuracy than both the two radiologists, which correctly classified as benign lesions in 119/135 of fibroadenomas (88.1%), 25/35 of adenosis (71.4%), 14/27 of intraductal papillary tumors (51.9%), 5/10 of inflammation (50%), and 4/8 of sclerosing adenosis (50%). But only the differences between CAD and the two radiologists in fibroadenomas had statistical significance (P=0.0011 and P=0.0313), and the differences between CAD and the resident in adenosis had statistical significance (P=0.012). In the malignant lesions, 151/168 of invasive ductal carcinomas (89.9%), 21/29 of ductal carcinoma in situ (DCIS) (72.4%) and 6/7 of invasive lobular carcinomas (85.7%) were diagnosed as malignancies by deep learning-based CAD, with no significant differences between CAD and the two radiologists. Conclusions: In the diagnosis of these common types of breast lesions, deep learning-based CAD had a satisfying performance. Deep learning-based CAD had a better performance in the breast benign lesions, especially in fibroadenomas and adenosis. Therefore, deep learning-based CAD is a promising supplemental tool to US to increase the specificity and avoid unnecessary benign biopsies.
Objectives We aimed to assess the clinical value of multimodal photoacoustic/ultrasound (PA/US) articular imaging scores, a novel imaging method which can reflect the micro-vessels and oxygenation level of inflamed joints of rheumatoid arthritis (RA). Methods Seven small joints were examined by the PA/US imaging system. A 0–3 scoring system was used to semi-quantify the PA and power-Doppler (PD) signals, and the sums of PA and PD scores (PA-sum and PD-sum scores) of the seven joints were calculated. The relative oxygen saturation (SO2) values of the inflamed joints were measured and classified into 3 PA+SO2 patterns. The correlations between the PA/US imaging scores and the disease activity scores were assessed. Results Thirty-one patients of RA and a total of 217 joints were examined using the PA/US system. The PA-sum had high positive correlations with the standard clinical scores of RA (DAS28 [ESR] ρ = 0.754, DAS28 [CRP] ρ = 0.796, SDAI ρ = 0.836, CDAI ρ = 0.837, p < 0.001), which were superior to the PD-sum (DAS28 [ESR] ρ = 0.651, DAS28 [CRP] ρ = 0.676, SDAI ρ = 0.716, CDAI ρ = 0.709, p < 0.001). For the patients with high PA-sum scores, significant differences between hypoxia and hyperoxia were identified in pain visual analog score (p = 0.020) and patient’s global assessment (p = 0.026). The PA+SO2 patterns presented moderate and high correlation with PGA (ρ = 0.477, p = 0.0077) and VAS pain score (ρ = 0.717, p < 0.001). Conclusion The PA scores have significant correlations with standard clinical scores for RA, and the PA+SO2 patterns are also related with clinical scores that reflect pain severity. PA may have clinical potential in evaluating RA. Key Points • Multimodal photoacoustic/ultrasound imaging is a novel method to assess micro-vessels and oxygenation of local lesions. • Significant correlations between multimodal imaging parameters and clinical scores of RA patients were verified. • The multimodal PA/US system can provide objective imaging parameters, including PA scores of micro-vessels and relative SO2value, as a supplementary to disease activity evaluation.
Owing to the heavy health burdens from rheumatoid arthritis, a sensitive and objective imaging method is needed for early diagnosis and accurate evaluation of the disease. We aimed to fabricate vascular epithelial growth factor (VEGF)Àtargeted microbubbles (MBs) to evaluate the expression levels of VEGF within the inflammatory lesions of rats with adjuvant-induced arthritis (AIA) using a multimodal photoacoustic (PA)/ ultrasound (US) imaging system. Fluorescein isothiocyanateÀbiotin double-labeled vascular endothelial growth factor receptor 2 antibodies and Cy5.5Àbiotin double-labeled VEGF2 antibodies were added to the avidinlabeled MBs to synthesize VEGF-targeted MBs. The antibodies could specifically bind to the MBs according to the flow cytometry and fluorescence imaging. In vitro experiments on the cellular uptake of the target MBs also validated the interaction of the VEGF antibodies and the MBs. Multimodal contrast-enhanced US (CEUS)/PA imaging was performed in sequence on the inflamed paws of the AIA rats with a single PA/US imaging system after the injection of the targeted MBs. The CEUS and PA signals were then quantified and verified by the pathologic results. A CEUS pattern of fast wash in and slow washout was observed in the AIA rats after injection of targeted MBs. Compared with AIA rats injected with unconnected VEGF antibodies and naked MBs, AIA rats injected with targeted MBs presented a higher peak intensity (p = 0.0079 and 0.0079 respectively) and a longer time to peak (p = 0.0117 and 0.0117, respectively). The PA signals were also significantly enhanced after injection of targeted MBs (p = 0.0112 and 0.0119, respectively), which was in accordance with the pathologic and immunohistochemical results. In conclusion, VEGF-targeted MBs can be used as agents for multimodal CEUS/PA imaging and to detect VEGF expression in the inflammatory lesions of AIA rats in vivo. This strategy may be useful in imaging evaluation of arthritis by identifying inflammation-related molecules in different imaging modes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.