Quantitative Imaging in Medicine and Surgery最新文献

{"title":"Novel fat suppression technique for ultrashort echo time MRI using single-point Dixon phase modeling.","authors":"Nathan Newbury, Sam Sedaghat, Jiyo S Athertya, Soo Hyun Shin, Yajun Ma, Saeed Jerban, Michael Carl, Melissa Lou Silva, Eric Y Chang, Jiang Du, Hyungseok Jang","doi":"10.21037/qims-24-1998","DOIUrl":"10.21037/qims-24-1998","url":null,"abstract":"<p><strong>Background: </strong>Fat suppression plays a vital role in numerous magnetic resonance imaging (MRI) examinations, particularly in the musculoskeletal (MSK) system. However, current fat suppression methods are not fully optimized for ultrashort echo time (UTE) imaging, despite being essential for many advanced UTE-based imaging applications. This study aimed to investigate a novel fat suppression technique for UTE MRI using a single-point Dixon (1p-Dixon) approach through phase modeling.</p><p><strong>Methods: </strong>In this study, four cadaveric human knee joints, and six healthy volunteers were included. A 1p-Dixon-based fat suppression method was developed, which utilizes intrinsic information from complex UTE signals. Additionally, a data-driven approach based on the phase distribution was used for the decomposition of water and fat signals in short T2 tissues. The feasibility of the proposed method was evaluated in a fat-water phantom first and validated in <i>ex vivo</i> and <i>in vivo</i> human knee joints. The patella tendon, cartilage, posterior cruciate ligament (PCL), anterior cruciate ligament (ACL), and meniscus were evaluated in each knee.</p><p><strong>Results: </strong>In the phantom experiment, there was a significant correlation between the estimated fat fraction and the actual fat fraction (R>0.98; P<0.05). The <i>ex vivo</i> experiment revealed a significant difference in contrast-to-noise ratios (CNRs) measured from the two images without and with 1p-Dixon (P<0.001). The CNR values ranged from 3.4±0.5 to 9.6±5.0 and 1.8±1.6 to 4.1±0.8 for measurement with and without 1p-Dixon, respectively. The 1p-Dixon significantly improved the contrast in the <i>in vivo</i> experiment (P<0.0001). The CNR values ranged from 5.1±6.0 to 41.0±9.7 and 2.7±1.2 to 15.4±3.3 for measurement with and without 1p-Dixon, respectively in the <i>in vivo</i> experiment.</p><p><strong>Conclusions: </strong>Our novel fat suppression technique has been shown to provide a fast, time-saving, and robust fat suppression for UTE imaging without the need for additional scans.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"4580-4591"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12082590/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative susceptibility mapping for Alzheimer's disease, mild cognitive impairment, and normal aging: evaluation of corpus callosum.","authors":"Sittaya Buathong, Siriwan Piyapitayanan, Tanyaluck Thientunyakit, Chakmeedaj Sethanandha, Weerasak Muangpaisan, Panida Charnchaowanish, Kingkarn Aphiwatthanasumet, Orasa Chawalparit, Chanon Ngamsombat","doi":"10.21037/qims-24-319","DOIUrl":"10.21037/qims-24-319","url":null,"abstract":"<p><strong>Background: </strong>Abnormal iron metabolism and accumulation in the brain have been proposed as pathological changes in Alzheimer's disease (AD). These changes can be detected using quantitative susceptibility mapping (QSM). The corpus callosum (CC), an essential white matter structure in the brain, is thought to undergo volume and microstructural changes in Alzheimer's patients, with specific regional atrophy related to cognitive impairment and dementia severity. This study aimed to measure <i>in vivo</i> susceptibility in each part of the CC in AD, mild cognitive impairment (MCI), and healthy control (HC), and assess their associations with neurocognitive scores and QSM value changes in follow-up imaging.</p><p><strong>Methods: </strong>A retrospective study was conducted with 34 patients with AD, 32 patients with MCI, and 29 cases with HC. A subset of these participants had available follow-up magnetic resonance imaging (MRI) data, including 13 AD patients, 14 MCI patients, and 14 HC cases. Structural MRI data were processed using FreeSurfer software version 6.0 to segment the CC into five parts. QSM processing was performed using STISuite 3.0, and the results were registered and analyzed for susceptibilities in each CC segment using the FSL (FMRIB Software Library, version 5.0.7). Correlations between susceptibility levels and diagnosis were evaluated using the Kruskal-Wallis test, while associations between susceptibility and cognitive function [Thai Mental State Examination (TMSE) and Clinical Dementia Rating (CDR)] were assessed using Spearman's rank correlation coefficient. Changes after follow-up were assessed using paired samples <i>t</i>-tests and one-way analysis of variance (ANOVA).</p><p><strong>Results: </strong>Significantly increased susceptibility was observed in the mid-anterior and central parts of the CC for AD patients compared to normal controls (0.051 and 0.103 ppm in AD and -0.014 and 0.003 ppm in HC; P value =0.014 and 0.009). Susceptibility in the mid-anterior, central regions, showed weakly positive correlations with CDR-global scores (r=0.296, P=0.006 and r=0.287, P=0.005). After a 2-year follow-up, susceptibility significantly increased across groups. In the HC group, significant increases were observed in the mid-anterior region (mean difference =0.074 ppm; P value =0.021). For the MCI group, a significant increase in the mid-posterior region (mean difference =0.081 ppm; P value =0.039) was found. For the AD group, a significant increase was found in the mid-posterior and posterior regions (mean difference =0.021 and 0.086 ppm; P value =0.013 and 0.005).</p><p><strong>Conclusions: </strong>The study findings suggest that increased susceptibilities in the mid-anterior and central parts of the CC can serve as a potential biomarker for the diagnosis of MCI and AD and assess cognitive function in these diseases.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"4566-4579"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12084761/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AttmNet: a hybrid Transformer integrating self-attention, Mamba, and multi-layer convolution for enhanced lesion segmentation.","authors":"Hancan Zhu, Yibing Huang, Kelin Yao, Jinxiang Shang, Keli Hu, Zhong Li, Guanghua He","doi":"10.21037/qims-2024-2561","DOIUrl":"10.21037/qims-2024-2561","url":null,"abstract":"<p><strong>Background: </strong>Accurate lesion segmentation is critical for cancer diagnosis and treatment. Convolutional neural networks (CNNs) are widely used for medical image segmentation but struggle to capture long-range dependencies. Transformers mitigate this limitation but come with high computational costs. Mamba, a state-space model (SSM), efficiently models long-range dependencies but lacks precision in fine details. To address these challenges, this study aimed to develop a novel segmentation approach that combines the strengths of CNNs, Transformers, and Mamba, enhancing both global context understanding and local feature extraction in medical image segmentation.</p><p><strong>Methods: </strong>We propose AttmNet, a U-shaped network designed for medical image segmentation, which incorporates a novel structure called MAM (Multiscale-Convolution, Self-Attention, and Mamba). The MAM block integrates multi-layer convolution for multi-scale feature learning with an Att-Mamba component that combines self-attention and Mamba to effectively capture global context while preserving fine details. We evaluated AttmNet on four public datasets for breast, skin, and lung lesion segmentation.</p><p><strong>Results: </strong>AttmNet outperformed state-of-the-art methods in terms of intersection over union (IoU) and Dice similarity coefficients. On the breast ultrasound (BUS) dataset, AttmNet achieved a 3.38% improvement in IoU and a 4.54% increase in Dice over the next best method. On the breast ultrasound images (BUSI) dataset, AttmNet's IoU and Dice coefficients were 1.17% and 3.21% higher than the closest competitor, respectively. In the PH2 Dermoscopy Image dataset, AttmNet surpassed the next best model by 0.25% in both IoU and Dice. On the larger coronavirus disease 2019 (COVID-19) Lung dataset, AttmNet maintained strong performance, achieving higher IoU and Dice scores than the next best models, SegMamba and TransUNet.</p><p><strong>Conclusions: </strong>AttmNet is a powerful and efficient tool for medical image segmentation, addressing the limitations of existing methods through its advanced design. The MAM block significantly enhances segmentation accuracy while maintaining computational efficiency, making AttmNet highly suitable for clinical applications. The code is available at https://github.com/hyb2840/AttmNet.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"4296-4310"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12084717/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Value of deep learning model for predicting Breast Imaging Reporting and Data System 3 and 4A lesions on mammography.","authors":"Xiaohui Lin, Tingting Liao, Yuting Yang, Rushan Ouyang, Yunshu Zhou, Xiaohui Lai, Jie Ma","doi":"10.21037/qims-24-1523","DOIUrl":"10.21037/qims-24-1523","url":null,"abstract":"<p><strong>Background: </strong>The diagnostic categorization of a lesion as Breast Imaging Reporting and Data System (BI-RADS) category 3 or 4A determines whether a patient needs a biopsy; however, interobserver variability exists among radiologists in mammographic interpretation. This variability may lead to underdiagnoses of BI-RADS 3 lesions and unnecessary biopsies of benign BI-RADS 4A lesions. Therefore, we assessed the diagnostic value of a mammography-based deep learning (DL) model for differentiating BI-RADS 3 and 4A lesions and its impact on radiologists' decision-making.</p><p><strong>Methods: </strong>This retrospective multicenter study analyzed 846 mammographically detected breast lesions (BI-RADS 3 and 4A) from 824 patients at Shenzhen People's Hospital and Shenzhen Luohu People's Hospital between January and December 2020. Six breast imaging specialists (three junior and three senior) independently reviewed all mammograms with and without DL model assistance. The follow-up or biopsy results were used as the reference standard. Diagnostic performance was evaluated using receiver operating characteristic (ROC) curves and the area under the curve (AUC), with the DeLong test being used to compare AUCs.</p><p><strong>Results: </strong>The DL model yielded an AUC of 0.74 for distinguishing BI-RADS 3 and 4A lesions, outperforming junior radiologists' standalone performance (AUC =0.57, AUC =0.55, and AUC =0.58) but remaining inferior to senior radiologists (AUC =0.78, AUC =0.77, and AUC =0.76). With DL model assistance, all six radiologists had higher AUCs for diagnosing BI-RADS 3 and 4A lesions as compared to their unassisted performance. Importantly, DL integration significantly increased junior radiologists' AUCs to 0.74-0.77 (P<0.001), whereas the increase in the AUCs of the senior radiologists (to 0.79, 0.78, and 0.78) was not significant (P>0.05).</p><p><strong>Conclusions: </strong>The mammography-based DL model significantly improved the diagnostic performance of junior radiologists for BI-RADS 3 and 4A lesions, effectively reducing missed diagnoses and unnecessary biopsies.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"4047-4058"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12084680/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 a nomogram based on conventional and contrast-enhanced ultrasound for differentiating malignant from benign thyroid nodules.","authors":"Qi-Guo Wang, Mei Li, Guang-Xiu Deng, Hai-Qing Huang, Qin Qiu, Jian-Jun Lin","doi":"10.21037/qims-24-1796","DOIUrl":"10.21037/qims-24-1796","url":null,"abstract":"<p><strong>Background: </strong>Conventional ultrasound (US) has been routinely used for differential diagnosis of thyroid nodules, but its discriminatory performance remains unsatisfactory. This study aimed to develop and validate a prediction nomogram model based on conventional US and contrast-enhanced ultrasound (CEUS) features for differentiating malignant from benign thyroid nodules.</p><p><strong>Methods: </strong>A total of 815 thyroid nodules with surgical pathology results and complete conventional US and CEUS data were retrospectively collected from the First People's Hospital of Qinzhou between January 2019 and July 2023. The nodules were grouped into a training cohort (n=571) and a validation cohort (n=244) at a 7:3 ratio. Independent risk factors of malignancy were selected by stepwise multivariate logistic regression analysis, and a prediction nomogram model was subsequently constructed. The diagnostic performance of the model was evaluated by the area under the receiver operating characteristic curve (AUC) in both the training and validation cohorts. The unnecessary fine-needle aspiration biopsy (FNAB) rate was calculated.</p><p><strong>Results: </strong>Multivariate logistic regression analysis identified irregular margin, aspect ratio >1, and microcalcification from conventional US images, as well as hypo-enhancement intensity and ring enhancement from CEUS images, as independent predictors for malignancy. The AUC, sensitivity, specificity, and accuracy of the prediction nomogram model were 0.947 [95% confidence interval (CI): 0.928-0.966], 90.4%, 88.8%, and 89.8% in the training cohort, and 0.957 (95% CI: 0.928-0.986), 94.5%, 86.4%, and 91.8% in the validation cohort, respectively. Using the prediction model, the unnecessary FNAB rates reduced from 29.6% to 6.1% in the training cohort and from 29.3% to 6.7% in the validation cohort compared to the Chinese Thyroid Imaging Reporting and Data System. Decision curve analysis demonstrated good clinical utility of the nomogram model.</p><p><strong>Conclusions: </strong>The prediction nomogram model incorporating conventional US and CEUS features could effectively distinguish between malignant and benign thyroid nodules and reduce unnecessary FNAB rates.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"4641-4654"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12082573/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lightweight attention network for guidewire segmentation and localization in clinical fluoroscopic images of vascular interventional surgery.","authors":"Haoyun Wang, Ziyang Mei, Kanqi Wang, Jingsong Mao, Lianxin Wang, Gang Liu, Yang Zhao","doi":"10.21037/qims-2024-2926","DOIUrl":"10.21037/qims-2024-2926","url":null,"abstract":"<p><strong>Background: </strong>During transcatheter arterial chemoembolization (TACE), the delivery of a guidewire to the lesion site is a critical step, making the analysis and positioning of guidewire morphology crucial for both robotic systems and physicians in interventional surgeries. Current research on guidewires often faces challenges such as a low image signal-to-noise ratio and severe class imbalance. To overcome these issues and enhance the practical delivery of guidewires in clinical settings, this study introduces a comprehensive dataset for guidewire delivery during TACE and develops a specialized deep learning model for segmenting guidewire morphology in X-ray fluoroscopic images.</p><p><strong>Methods: </strong>We retrospectively collected 2,839 X-ray images acquired under real-time guidance from 38 subjects and manually annotated the guidewires. We proposed a deep learning-based guidewire segmentation method, which integrated two effective modules designed in this study: a bilateral feature fusion (BGA) module and a lightweight gated attention (SDA) module, achieving precise segmentation of guidewires in intraoperative images.</p><p><strong>Results: </strong>Quantitative and qualitative assessments were performed on 903 clinical images from 27 X-ray fluoroscopy videos. The segmentation network proposed in this paper demonstrated superior performance, achieving an area under the curve (AUC) of 91.64%, a Macro-F1 score of 85.63%, and a Dice coefficient of 71.29%.</p><p><strong>Conclusions: </strong>This study introduces a novel guidewire segmentation method specifically designed for clinical TACE. It not only assists physicians during interventional procedures but is also expected to be integrated into the intelligent systems of vascular interventional surgical robots, enabling robotic assistance in the future interventional surgeries.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"4689-4707"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12082592/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative assessment of biomechanical changes in oral lesions at different cancerous stages using optical coherence elastography.","authors":"Yuhao Yang, Mengzhen Tang, Wangge Xiong, Hao Luo, Zekun Li, Xinyu Yang, Weihua Chen, Xiaojing Hu, Xingdao He, Jian Yang","doi":"10.21037/qims-24-2359","DOIUrl":"10.21037/qims-24-2359","url":null,"abstract":"<p><strong>Background: </strong>Oral cancer is the sixth most common cancer worldwide. The detection, prevention, and control of oral potentially malignant disorders (OPMDs) at early stages is imperative to reduce the incidence of oral cancer. This study analyzed ultrastructural and biomechanical tissue properties during tongue cancer development in Sprague-Dawley (SD) rats using optical coherence elastography (OCE). Our investigation examined the changes associated with oral cancer pathogenesis and explored the feasibility of OCE as an early diagnostic tool for oral cancer.</p><p><strong>Methods: </strong>In this study, 4-nitroquinoline-1-oxide (4NQO) was used to induce oral carcinogenesis in SD rats. In total, 10 normal tissues, five hyperplastic lesions, eight low-grade dysplasias (LGDs), eight moderate-high-grade dysplasias (M-HGDs), seven carcinomas in situ (CISs), and seven squamous cell carcinomas (SCCs) were examined. The oral stroma changes were sequentially imaged by <i>in vivo</i> shaker-based OCE (shaker-OCE). The changes in the oral stroma from normal to hyperplasia, atypical hyperplasia, CIS, and cancer were determined using OCE, and histological findings such as extracellular matrix (ECM) components (including collagen and elastic fibers) and the expression of cancer-associated fibroblasts (CAFs) were compared at different stages of tongue cancer development.</p><p><strong>Results: </strong>The findings showed that OCE imaging could be used to accurately distinguish between normal, hyperplasia, atypical hyperplasia, CIS, and oral cancer. Additionally, there were significant differences in the tongue tissue biomechanics across the different lesion levels (P<0.05). Further, as the malignancy of the tongue cancer progressed in the SD rats, the level of collagen fibers gradually increased, showing a positive correlation (r=0.353, P<0.05), while the level of elastic fiber expression gradually decreased, showing a negative correlation (r=-0.776, P<0.05). The alpha-smooth muscle actin (α-SMA) scores of CIS and SCC were statistically significantly higher than those of normal, simple hyperplasia, mild atypical hyperplasia, and moderate-high atypical hyperplasia (P<0.05).</p><p><strong>Conclusions: </strong>The ability of the shaker-OCE system to obtain the structural and biomechanical characteristics of tongue tissues in a non-invasive, real-time manner was confirmed by this study. It also showed notable benefits in terms of early diagnosis and the dynamic monitoring of tongue cancer. The systematic validation of the physiopathological model revealed a strong correlation between the elastic properties of cancerous tissues and pathological evolution, which provides a theoretical basis and experimental evidence for the clinical application of OCE technology.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"4592-4607"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12082576/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the regrowth of residual uterine fibroids after high-intensity focused ultrasound treatment: an interpretable magnetic resonance imaging radiomics model.","authors":"Yang Liu, Zhibo Xiao, Fajin Lv, Yuanli Luo, Chengwei Li, Bin Yu","doi":"10.21037/qims-24-1844","DOIUrl":"10.21037/qims-24-1844","url":null,"abstract":"<p><strong>Background: </strong>The evaluation of residual uterine fibroids (RFs) after magnetic resonance imaging (MRI)-based radiomics is complex, making it challenging to accurately predict and interpret the regrowth of RFs following high-intensity focused ultrasound (HIFU) treatment. Therefore, the aim of this research was to establish a robust multiparametric radiomics model which functions to predict the regrowth of RFs following HIFU treatment. Moreover, SHapley Additive exPlanations (SHAP) was adopted to clarify the internal prediction process of the model.</p><p><strong>Methods: </strong>In this retrospective investigation, 116 patients diagnosed with uterine fibroids who underwent HIFU treatment were enrolled, and underwent follow-up imaging approximately one-year post-treatment. Patients were categorized into RF regrowth and non-regrowth groups based on the occurrence of residual fibroid regrowth 1 year after treatment. The cohort was divided into a training set (N=92) and a test set (N=24). A total of 218 radiomic features were acquired from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI) scans. Subsequent to the implementation of preprocessing and feature selection steps, logistic regression (LR) models were developed using radiomic features from T2WI and CE-T1WI, as well as a feature-level fusion of both. Finally, the SHAP approach was applied to interpret the underlying predictive mechanisms.</p><p><strong>Results: </strong>The LR models achieved areas under the curve (AUCs) of 0.926 [95% confidence interval (CI): 0.817-1.000] for the T2WI model, 0.879 (95% CI: 0.731-1.000) for the CE-T1WI model, and 0.946 (95% CI: 0.897-0.995) for the fusion model. The SHAP technology was employed to facilitate clinicians' comprehension of the influence exerted by radiomic features on the model's predictions from both global and individual perspectives.</p><p><strong>Conclusions: </strong>The multiparametric radiomics model demonstrated robustness in predicting the regrowth of RFs post-HIFU treatment. Radiomic features may serve as potential biomarkers for preoperative evaluation for HIFU treatment and enhance the mechanism of RF regrowth after HIFU.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"3950-3963"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12084746/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting cardiac resynchronization therapy response: development and validation of a single photon emission computed tomography-based nomogram.","authors":"Zhongwei Jiang, Zhongqiang Zhao, Zhuo He, Qiushi Chen, Ju Bu, Chunxiang Li, Dianfu Li, Chang Cui, Weihua Zhou, Huiyuan Qin, Cheng Wang","doi":"10.21037/qims-2024-2700","DOIUrl":"10.21037/qims-2024-2700","url":null,"abstract":"<p><strong>Background: </strong>Cardiac resynchronization therapy (CRT) is an effective treatment for patients with drug-refractory heart failure. However, more than thirty percent of patients do not benefit from CRT. This study aimed to develop and validate a novel model based on single photon emission computed tomography (SPECT) phase analysis features to predict CRT response.</p><p><strong>Methods: </strong>We identified 163 CRT patients who received gated resting SPECT myocardial perfusion imaging (MPI) between 2010 and 2020 at The First Affiliated Hospital of Nanjing Medical University. All variables were first processed by univariate logistic regression, and those with a P value <0.05 were retained. The selected variables were subsequently used in the least absolute shrinkage and selection operator (LASSO) regression to construct a predictive model, which was then represented as a nomogram. Nomogram performance was assessed via receiver operating characteristic (ROC) curves, calibration curves, and decision curve analyses (DCAs). Internal validation was performed by bootstrapping with 1,000 replicates.</p><p><strong>Results: </strong>Of the 163 patients, 93 (57.1%) responded to CRT during follow-up. Responders had a wider QRS complex duration (QRSd) (164.80 <i>vs</i>. 154.51 ms, P=0.003), fewer premature ventricular contractions (PVCs) (1,392.98 <i>vs</i>. 2,283.60, P=0.003), lower prevalence of non-sustained ventricular tachycardia (NS-VT) (45.2% <i>vs</i>. 77.1%, P<0.001), and better cardiac function [based on N-terminal pro-B-type natriuretic peptide (NT-proBNP), New York Heart Association (NYHA), and left ventricle (LV) parameters] compared to non-responders. Univariate logistic regression revealed 14 variables significantly associated with CRT response (all P<0.05). The area under the ROC curve (AUC) value for the nomogram was 0.845 [95% confidence interval (CI): 0.785-0.906; sensitivity: 0.771; specificity: 0.849]. Internal validation yielded a mean AUC of 0.814 (95% CI: 0.777-0.836). The calibration curve demonstrated strong consistency between the predicted and observed outcomes. DCA revealed that the nomogram consistently provides a net benefit over the baseline, demonstrating its high practical value in clinical decision-making. A web-based dynamic nomogram (https://jzw20000624.shinyapps.io/CRTpredictionmodel/) was developed for clinical application.</p><p><strong>Conclusions: </strong>We developed and validated a SPECT-based prediction model for predicting CRT response, which can assist clinicians in optimizing CRT candidacy preoperatively. Pacing at the latest contraction and relaxation segments, while avoiding scarred regions and optimizing preoperative status, is anticipated to improve CRT response.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"4247-4261"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12084738/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Whole-cerebrum three-dimensional pseudo-continuous arterial spin labeling at 5T: reproducibility and preliminary application in moyamoya.","authors":"Xiaoyuan Fan, Zhonghui Li, Guangsong Han, Gan Sun, Hualu Han, Yuehui Hong, Shuo Chen, Hui You, Jun Ni, Guobin Li, Mingli Li, Feng Feng","doi":"10.21037/qims-24-2274","DOIUrl":"10.21037/qims-24-2274","url":null,"abstract":"<p><strong>Background: </strong>Pseudo-continuous arterial spin labeling (PCASL) at 7T benefits from increased signal-to-noise ratio (SNR) and prolonged T1, but suffers from field inhomogeneities and increased specific absorption rate (SAR). We proposed that 5T magnetic resonance imaging (MRI) system may be a balanced choice for PCASL imaging. The aim of this study was to achieve whole-cerebrum PCASL imaging at ultra-high field 5T MRI system, assess the reproducibility and preliminarily explore its clinical application in moyamoya disease/syndrome.</p><p><strong>Methods: </strong>Twenty healthy volunteers were prospectively recruited for the reproducibility analysis. Both single-delay and multi-delay PCASL sequences were scanned twice on the 5T MRI scanner separated by a 10-minute period. Uncorrected cerebral blood flow (uCBF) from single-delay arterial spin labeling (ASL), corrected cerebral blood flow (cCBF) and arterial transit time (ATT) from multi-delay ASL were computed. The reproducibility of uCBF, cCBF and ATT were evaluated by calculating intraclass correlation coefficient (ICC), within-subject coefficient of variation (wsCV) and Pearson correlation coefficients between twice scans in grey matter regions and white matter (WM). Also, 26 patients diagnosed with moyamoya disease/syndrome were included and underwent multi-delay PCASL. The severity of intracranial arteries was graded as magnetic resonance angiography (MRA) score using time-of-flight (TOF) MRA. The relationship between MRA score and cCBF/ATT were assessed by one-way analysis of variance and Pearson correlation analysis.</p><p><strong>Results: </strong>uCBF, cCBF and ATT showed excellent reliability in all regions with ICCs ranging from 0.856 to 0.962, wsCVs ranging from 2.39% to 6.76% and Pearson correlation coefficients ranging from 0.865 to 0.966. Multi-delay ASL demonstrated superior reproducibility of CBF quantification compared to single-delay ASL in regions with heterogeneous transit time, including WM, occipital lobe, limbic system and subcortical region. In patients with moyamoya disease/syndrome, those with higher anterior cerebral artery (ACA) or middle cerebral artery (MCA) scores exhibited lower cCBF (P<0.05). Correlation analysis showed that MRA score was negatively associated with cCBF (r=-0.540, P<0.001) and positively associated with ATT (r=0.515, P<0.001).</p><p><strong>Conclusions: </strong>Whole-cerebrum PCASL imaging at 5T ultra-high field was achieved with good reproducibility and applied well in patients with moyamoya disease/syndrome, which offers a promising tool in the assessment of hemodynamic conditions in cerebrovascular diseases.</p>","PeriodicalId":54267,"journal":{"name":"Quantitative Imaging in Medicine and Surgery","volume":"15 5","pages":"3824-3838"},"PeriodicalIF":2.9,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12084759/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144095687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}