Ultrasound in Medicine and Biology最新文献

{"title":"Ischemia/Reperfusion Injury Enhances Accumulation of Perfluoropropane Droplets","authors":"Cheng Chen ,&nbsp;Shouqiang Li ,&nbsp;Terry O. Matsunaga ,&nbsp;John J. Pacella ,&nbsp;E. Carr Everbach ,&nbsp;Feng Xie ,&nbsp;Thomas R. Porter ,&nbsp;Flordeliza S. Villanueva ,&nbsp;Xucai Chen","doi":"10.1016/j.ultrasmedbio.2024.10.012","DOIUrl":"10.1016/j.ultrasmedbio.2024.10.012","url":null,"abstract":"<div><h3>Objective</h3><div>Perfluoropropane droplets (PD) are nanometer-sized particles that can be formulated from commercially available contrast agents. The preferential retention of PDs in diseased microvascular beds can be detected by ultrasound imaging techniques after acoustic activation and offers an opportunity for the detection of such processes as scar formation or inflammation. We hypothesized that in the presence of ischemia/reperfusion (I/R) injury, retention of intravenously injected PDs would be enhanced.</div></div><div><h3>Methods</h3><div>Using an established intravital microscopy model of rat cremaster microcirculation, we determined the retention and subsequent acoustic activation behavior of PDs in exteriorized rat cremaster tissue. DiI-labeled droplets (200 µL) were administered intravenously. Acoustic activation was achieved with a clinical ultrasound system at two ultrasound frequencies (1.5 and 7 MHz).</div></div><div><h3>Results</h3><div>Fluorescent microbubbles could be detected in the microvasculature after intravenous injection of PDs and subsequent acoustic activation. Increased retention of PDs was observed in the I/R group compared with control group with both ultrasound frequencies (<em>p</em> &lt; 0.05). Using higher-resolution microscopy, we found evidence that some droplets extravasate to the outside of the endothelial border or are potentially engulfed by leukocytes.</div></div><div><h3>Conclusion</h3><div>Our data indicate that targeted imaging of the developing scar zones might be possible with ultrasound activation of intravenously injected PDs, and a method of targeting therapies to these same regions could be developed.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 2","pages":"Pages 336-340"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11744877/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142631399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a Nomogram-Integrated Model Incorporating Intra-tumoral and Peri-tumoral Ultrasound Radiomics Alongside Clinical Parameters for the Prediction of Histological Grading in Invasive Breast Cancer","authors":"Wenjia Wan ,&nbsp;Kai Zhu ,&nbsp;Zhicheng Ran ,&nbsp;Xinyu Zhu ,&nbsp;Dongmo Wang","doi":"10.1016/j.ultrasmedbio.2024.09.025","DOIUrl":"10.1016/j.ultrasmedbio.2024.09.025","url":null,"abstract":"<div><h3>Objective</h3><div>To develop a comprehensive nomogram to predict the histological grading of breast cancer and further examine its clinical significance by integrating both intra-tumoral and peri-tumoral ultrasound radiomics features.</div></div><div><h3>Methods</h3><div>In a retrospective study 468 female breast cancer patients were analyzed from 2017 to 2020 at the Second Affiliated Hospital of Harbin Medical University. Patients were grouped into high-grade (n = 215) and low-grade (n = 253) categories based on pathological evaluation. Tumor regions of interest were defined and expanded automatically to peri-tumor regions of interest. Ultrasound radiomics features were extracted independently. To ensure rigor, cases were randomly divided into 80% training and 20% test sets. Optimal features were selected using statistical and machine learning methods. Intra-tumor, peri-tumor, and combined radiomics models were constructed. To determine the best predictors of breast cancer histological grading, we screened the features using single- and multi-factor logistic regression analyses. Finally, a nomogram was developed and evaluated for its predictive value in this context.</div></div><div><h3>Results</h3><div>By applying logistic regression, we integrated ultrasound, clinicopathologic, and radiomics features to generate a nomogram. The combined model outperformed others, achieving areas under the curve of 0.934 and 0.812 in training and test sets. Calibration curves also showed high accuracy and reliability.</div></div><div><h3>Conclusion</h3><div>A nomogram constructed through the integration of combined intra-tumor–peri-tumor ultrasound radiomics features along with clinicopathologic characteristics exhibited remarkable performance in distinguishing the histologic grades of invasive breast cancer.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 2","pages":"Pages 262-272"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142548554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of Different Low-Intensity Pulsed Ultrasound Intensities and Durations on a Post-Traumatic Knee Joint Contracture Model in Rats","authors":"Ryo Nakahara ,&nbsp;Akira Ito ,&nbsp;Momoko Nagai-Tanima ,&nbsp;Chia Tai ,&nbsp;Zixi Zhao ,&nbsp;Shixuan Xu ,&nbsp;Fumika Miyamoto ,&nbsp;Sachiko Abiko ,&nbsp;Tomoki Aoyama ,&nbsp;Hiroshi Kuroki","doi":"10.1016/j.ultrasmedbio.2024.11.012","DOIUrl":"10.1016/j.ultrasmedbio.2024.11.012","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to investigate the low-intensity pulsed ultrasound (LIPUS) therapeutic effects on knee joint dysfunction after immobilization following trauma and to identify the optimum LIPUS intensity and duration.</div></div><div><h3>Methods</h3><div>A knee post-traumatic joint contracture (PTJC) model was established in male Wistar rats divided into three groups: front irradiation (n = 4), medial irradiation (n = 3), and sham (n = 3). LIPUS irradiation was performed for 20 min/day (30 mW/cm² [spatial average temporal average] SATA, 1 MHz, duty cycle of 20%, 5 times/week, for 2 weeks). PTJC model rats were also divided into LIPUS and sham groups with LIPUS performed at different intensities (30 or 120 mW/cm² SATA) and durations (5 or 20 min). The range of motion (ROM) of the knee joint with skin and muscles (knee ROM) and without (knee joint intrinsic ROM) and the length of the posterior joint capsule and the intra-articular adhesion of the knee joint were evaluated.</div></div><div><h3>Results</h3><div>Knee ROM and knee joint intrinsic ROM were significantly larger in the front LIPUS group (<em>p</em> &lt; 0.01). The length of the posterior capsule was significantly higher in the LIPUS groups (<em>p</em> &lt; 0.01), but no significant differences between the LIPUS groups were observed. The intra-articular adhesion length was significantly lower in the 120 mW/cm²–20 min group than those in the 30 mW/cm²–5 min group (<em>p</em> &lt; 0.01). The effects on LIPUS intensity and duration to intra-articular adhesion were not synergistic but additive.</div></div><div><h3>Conclusion</h3><div>LIPUS therapy may be a rehabilitation approach for preventing knee joint dysfunction after trauma or surgical invasion.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 2","pages":"Pages 396-401"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142741189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Value of Necrotic Area Features in Contrast-Enhanced Ultrasound for Distinguishing Between Benign and Malignant Subpleural Pulmonary Lesions","authors":"Yang Cong,&nbsp;Jiawei Yi,&nbsp;Ke Bi,&nbsp;Yi Zhang,&nbsp;Mengjun Shen,&nbsp;HuiMing Zhu,&nbsp;Yin Wang","doi":"10.1016/j.ultrasmedbio.2024.11.008","DOIUrl":"10.1016/j.ultrasmedbio.2024.11.008","url":null,"abstract":"<div><h3>Objective</h3><div>To analyze Necrotic Area Features of subpleural pulmonary lesions (SPLs) demonstrated by contrast-enhanced ultrasound (CEUS) and investigate their value in differentiating between malignant and benign SPLs.</div></div><div><h3>Methods</h3><div>Patients with SPLs who underwent CEUS at our hospital from January to May 2021. The following patient information was recorded: (i) age, (ii) sex, (iii) lesion size, (iv) lesion location, (v) size of necrotic areas and (vi) necrotic area morphology, including sieve-like necrosis, necrotic area with septal enhancement, necrotic area with annular enhancement margins, and necrotic area with burr-like enhancement margins. These parameters were analyzed using univariate and multivariate logistic regression. Subgroup analyses based on lesion size were further conducted using the collected data.</div></div><div><h3>Results</h3><div>A total of 212 patients with 212 SPLs were enrolled, comprising 99 benign and 113 malignant cases. Significant differences were observed between malignant and benign groups in terms of age, sex, lesion size and necrotic area morphology (all, <em>p</em> &lt; 0.05).</div></div><div><h3>Conclusion</h3><div>Necrotic area's features observed on CEUS were valuable for distinguishing between benign and malignant SPLs. Age, sex, lesion size and the presence of burr-like enhancement margins are identified as independent predictors of malignant lesions.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 2","pages":"Pages 381-386"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142695816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficacy and Safety of Focused Ultrasound Treatment for High-risk Human Papillomavirus Infection-related Cervical Intraepithelial Neoplasia Grade 2 in Nulligravidae Women: A Retrospective Study","authors":"Miao Zhang ,&nbsp;Hao Jiang ,&nbsp;Liming Chen ,&nbsp;Jiaojiao Ren ,&nbsp;Chengzhi Li ,&nbsp;Yujuan Liu ,&nbsp;Honggui Zhou ,&nbsp;Qiuling Shi","doi":"10.1016/j.ultrasmedbio.2024.10.013","DOIUrl":"10.1016/j.ultrasmedbio.2024.10.013","url":null,"abstract":"<div><h3>Objective</h3><div>This retrospective study aimed to investigate the efficacy and safety of focused ultrasound (FU) treatment for high-risk human papillomavirus (HR-HPV) infection-related cervical intraepithelial neoplasia grade 2 (CIN2) in nulligravidae under 35 y old, while also assessing pregnancy outcomes post-treatment.</div></div><div><h3>Methods</h3><div>Nulligravid patients aged 18–35 y with histologically confirmed CIN2 and HR-HPV infection were included in the study. We collected demographics, pertinent medical history, HPV genotypes and cervical length at baseline. Follow-up evaluations were conducted at 6- and 12-mo intervals post-treatment to assess histopathological response, HPV infection clearance and adverse events related to treatment.</div></div><div><h3>Results</h3><div>A total of 31 eligible patients were recruited and underwent FU treatment. At the 6-mo follow-up, complete pathologic response was observed in 22 out of 31 patients (70.96%), while partial response was seen in eight out of 31 patients (25.80%). The average duration from pathological diagnosis to achieving either a complete response or partial response after treatment was 214.36 ± 24.31 (186–270) d. The baseline remission rate for HPV was 35.48% at 6 mo, increasing to 71.49% at 12 mo. Moderate lower abdominal pain and increased vaginal discharge were the most frequent adverse events. Among the patients desiring pregnancy, the successful pregnancy rate was 57.14%, resulting in eight deliveries.</div></div><div><h3>Conclusion</h3><div>FU demonstrated a favorable safety profile and efficacy in nulliparous females under 35 y old with CIN2, and its benefits for fertility warrant further investigation.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 2","pages":"Pages 341-347"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142711673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Liver Nodule Visibility and Diagnostic Classification Using Ultrasound Local Attenuation Coefficient Slope Imaging","authors":"Iman Rafati ,&nbsp;François Destrempes ,&nbsp;Ladan Yazdani ,&nbsp;Maxime Barat ,&nbsp;Elige Karam ,&nbsp;Audrey Fohlen ,&nbsp;Bich N. Nguyen ,&nbsp;Hélène Castel ,&nbsp;An Tang ,&nbsp;Guy Cloutier","doi":"10.1016/j.ultrasmedbio.2025.01.007","DOIUrl":"10.1016/j.ultrasmedbio.2025.01.007","url":null,"abstract":"<div><h3>Objective</h3><div>B-mode ultrasound (US) presents challenges in accurately detecting and distinguishing between benign and malignant liver nodules. This study utilized quantitative US local attenuation coefficient slope (LACS) imaging to address these limitations.</div></div><div><h3>Materials and Methods</h3><div>This is a prospective, cross-sectional study in adult patients with definable solid liver nodules at US conducted from March 2021 to December 2023. The composite reference standard included histopathology when available or magnetic resonance imaging. LACS images were obtained using a phantom-free method. Nodule visibility was assessed by computing the contrast-to-noise ratio (CNR). Classification accuracy for differentiating benign and malignant lesions was assessed with the area under the receiver operating characteristic curve (AUC), along with sensitivity and specificity.</div></div><div><h3>Results</h3><div>The study enrolled 97 patients (age: 62 y ± 13 [standard deviation]), with 57.0% malignant and 43.0% benign observations (size: 26.3 ± 18.9 mm). LACS images demonstrated higher CNR (12.3 dB) compared to B-mode (<em>p</em> &lt; 0.0001). The AUC for differentiating nodules and liver parenchyma was 0.85 (95% confidence interval [CI]: 0.79–0.90), with higher values for malignant (0.93, CI: 0.88–0.97) than benign nodules (0.76, CI: 0.66–0.87). A LACS threshold of 0.94 dB/cm/MHz provided a sensitivity of 0.83 (CI: 0.74–0.89) and a specificity of 0.82 (CI: 0.73–0.88). LACS mean values were higher (<em>p</em> &lt; 0.0001) in malignant (1.28 ± 0.27 dB/cm/MHz) than benign nodules (0.98 ± 0.19 dB/cm/MHz).</div></div><div><h3>Conclusion</h3><div>LACS imaging improves nodule visibility and provides better differentiation between benign and malignant liver nodules, showing promise as a diagnostic tool.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 5","pages":"Pages 807-814"},"PeriodicalIF":2.4,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143076148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and Validation of an Ultrasound-Based Clinical Radiomics Nomogram for Diagnosing Gouty Arthritis","authors":"Minghang Lin ,&nbsp;Lei Yan ,&nbsp;Mei He ,&nbsp;Shuqiang Chen","doi":"10.1016/j.ultrasmedbio.2024.12.009","DOIUrl":"10.1016/j.ultrasmedbio.2024.12.009","url":null,"abstract":"<div><h3>Objective</h3><div>This study aimed to develop and validate a diagnostic model for gouty arthritis by integrating ultrasonographic radiomic features with clinical parameters.</div></div><div><h3>Methods</h3><div>A total of 604 patients suspected of having gouty arthritis were enrolled and randomly divided into a training set (n = 483) and a validation set (n = 121) in a 4:1 ratio. Univariate and multivariate analyses were conducted on the clinical data to identify statistically significant clinical features for constructing an initial diagnostic model. Key radiomic features were identified in the training set using least absolute shrinkage and selection operator (LASSO) regression analysis to establish a radiomic model. A composite clinicoradiomic nomogram was then developed by combining clinical (such as C-reactive protein, erythrocyte sedimentation rate and uric acid level) and radiomic features through logistic regression. The predictive performance of the clinical model, radiomic model and clinicoradiomic nomogram was evaluated in the validation set using receiver operating characteristic curves, calibration curves and decision curve analysis.</div></div><div><h3>Results</h3><div>The clinicoradiomic nomogram, which integrated imaging features and clinical characteristics via logistic regression, demonstrated superior predictive performance in the validation set, with an area under the curve (AUC) of 0.936 (95% CI: 0.885–0.986), surpassing both clinical (AUC = 0.924; 95% CI: 0.873–0.976) and radiomic models (AUC = 0.828; 95% CI: 0.738–0.918) alone. Decision curve analysis further confirmed the clinical utility of this model, particularly in differentiating between gouty and non-gouty arthritis.</div></div><div><h3>Conclusion</h3><div>Compared with standalone clinical or radiomic models, the ultrasonography-based clinicoradiomic model exhibited enhanced predictive accuracy for diagnosing gouty arthritis, presenting a novel and promising approach for the early diagnosis and management of gouty arthritis.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 4","pages":"Pages 650-660"},"PeriodicalIF":2.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143069146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Response to the Letter From Prof. Fosberg et al.","authors":"Li Zhang ,&nbsp;Yao Chen ,&nbsp;Jian-chu Li","doi":"10.1016/j.ultrasmedbio.2024.12.005","DOIUrl":"10.1016/j.ultrasmedbio.2024.12.005","url":null,"abstract":"","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 4","pages":"Pages 723-724"},"PeriodicalIF":2.4,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143061054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterization of LIPUS Parameters Suitable for Hip Bone Fracture","authors":"Poornima Palanisamy ,&nbsp;Shuai Li ,&nbsp;Queenie Tsung-Kwan Shea ,&nbsp;Michelle Meng-Chen Li ,&nbsp;Wing-Hoi Cheung ,&nbsp;Ling Qin ,&nbsp;Simon Kwoon-Ho Chow ,&nbsp;Yong-Ping Zheng","doi":"10.1016/j.ultrasmedbio.2025.01.001","DOIUrl":"10.1016/j.ultrasmedbio.2025.01.001","url":null,"abstract":"<div><h3>Objective</h3><div>To investigate the effects of ultrasound treatment on the healing of hip bone fractures using frequencies of 0.5 MHz and 1.5 MHz with constant intensity (30 mW/cm²) at the fractured site.</div></div><div><h3>Methods</h3><div>For the <em>ex vivo</em> experiments, acoustic attenuations of 0.5 MHz and 1.5 MHz ultrasound were measured and compared using different thicknesses of human cadaver and porcine tissues in a hydrophone system. For the <em>in vivo</em> experiments, 20 hip-fractured rabbits were divided into four groups, namely: control, 1.5 MHz with unchangeable intensity (positive control), 0.5 MHz with changeable intensity, and 1.5 MHz with changeable intensity. For the 0.5 and 1.5 MHz groups with changeable intensity, a constant intensity of 30 mW/cm² at the fracture site was achieved using a compensation method for power transmission with reference to the acoustic attenuation.</div></div><div><h3>Results</h3><div>The effective intensity measured using a hydrophone was substantially reduced to 6.16 mW/cm² from 30 mW/cm² in the positive control device after propagating soft tissues with a thickness of 5.0 cm, with an attenuation of approximately 6.0 dB. Meanwhile, for the 0.5 and 1.5 MHz groups, the ultrasound intensity was consistently controlled at 30 mW/cm² after passing through tissues with different thicknesses using the compensation method. In the <em>in vivo</em> study using a newly established hip fracture rabbit model, the best results in bone histomorphometry, mechanical properties, and histological evaluation were consistently found in the 0.5 MHz group, while the 1.5 MHz group exhibited relatively better bone healing than the positive control group.</div></div><div><h3>Conclusion</h3><div>The results suggest a LIPUS frequency of 0.5 MHz together with the consistent intensity of 30 mW/cm² at the fracture site for more effective treatment of hip bone fractures.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 4","pages":"Pages 695-706"},"PeriodicalIF":2.4,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143061047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Regional Image Quality Scoring for 2-D Echocardiography Using Deep Learning","authors":"Gilles Van De Vyver ,&nbsp;Svein-Erik Måsøy ,&nbsp;Håvard Dalen ,&nbsp;Bjørnar Leangen Grenne ,&nbsp;Espen Holte ,&nbsp;Sindre Hellum Olaisen ,&nbsp;John Nyberg ,&nbsp;Andreas Østvik ,&nbsp;Lasse Løvstakken ,&nbsp;Erik Smistad","doi":"10.1016/j.ultrasmedbio.2024.12.008","DOIUrl":"10.1016/j.ultrasmedbio.2024.12.008","url":null,"abstract":"<div><h3>Objective</h3><div>To develop and compare methods to automatically estimate regional ultrasound image quality for echocardiography separate from view correctness.</div></div><div><h3>Methods</h3><div>Three methods for estimating image quality were developed: (i) classic pixel-based metric: the generalized contrast-to-noise ratio (gCNR), computed on myocardial segments (region of interest) and left ventricle lumen (background), extracted by a U-Net segmentation model; (ii) local image coherence: the average local coherence as predicted by a U-Net model that predicts image coherence from B-mode ultrasound images at the pixel level; (iii) deep convolutional network: an end-to-end deep-learning model that predicts the quality of each region in the image directly. These methods were evaluated against manual regional quality annotations provided by three experienced cardiologists.</div></div><div><h3>Results</h3><div>The results indicated poor performance of the gCNR metric, with Spearman correlation to annotations of <em>ρ</em> = 0.24. The end-to-end learning model obtained the best result, <em>ρ</em> = 0.69, comparable to the inter-observer correlation, <em>ρ</em> = 0.63. Finally, the coherence-based method, with <em>ρ</em> = 0.58, out-performed the classical metrics and was more generic than the end-to-end approach.</div></div><div><h3>Conclusion</h3><div>The deep convolutional network provided the most accurate regional quality prediction, while the coherence-based method offered a more generalizable solution. gCNR showed limited effectiveness in this study. The image quality prediction tool is available as an open-source Python library at <span><span>https://github.com/GillesVanDeVyver/arqee</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49399,"journal":{"name":"Ultrasound in Medicine and Biology","volume":"51 4","pages":"Pages 638-649"},"PeriodicalIF":2.4,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143048169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}