首页 > 最新文献

Journal of Magnetic Resonance Imaging最新文献

英文 中文
Associations of Postencephalitic Epilepsy Using Multi-Contrast Whole Brain MRI: A Large Self-Supervised Vision Foundation Model Strategy.
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-02-03 DOI: 10.1002/jmri.29734
Ronghui Gao, Anjiao Peng, Yifei Duan, Mengyao Chen, Tao Zheng, Meng Zhang, Lei Chen, Huaiqiang Sun
<p><strong>Background: </strong>Postencephalitic epilepsy (PEE) is a severe neurological complication following encephalitis. Early identification of individuals at high risk for PEE is important for timely intervention.</p><p><strong>Purpose: </strong>To develop a large self-supervised vision foundation model using a big dataset of multi-contrast head MRI scans, followed by fine-tuning with MRI data and follow-up outcomes from patients with PEE to develop a PEE association model.</p><p><strong>Study type: </strong>Retrospective.</p><p><strong>Population: </strong>Fifty-seven thousand six hundred twenty-one contrast-enhanced head MRI scans from 34,871 patients for foundation model construction, and head MRI scans from 144 patients with encephalitis (64 PEE, 80 N-PEE) for the PEE association model.</p><p><strong>Field strength/sequence: </strong>1.5-T, 3-T, T1-weighted imaging, T2-weighted imaging, fluid attenuated inversion recovery, T1-weighted contrast-enhanced imaging.</p><p><strong>Assessment: </strong>The foundation model was developed using self-supervised learning and cross-contrast context recovery. Patients with encephalitis were monitored for a median of 3.7 years (range 0.7-7.5 years), with epilepsy diagnosed according to International League Against Epilepsy. Occlusion sensitivity mapping highlighted brain regions involved in PEE classifications. Model performance was compared with DenseNet without pre-trained weights.</p><p><strong>Statistical tests: </strong>Performance was assessed via confusion matrices, accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver operating characteristic curve (AUC). The DeLong test evaluated AUC between the two models (P < 0.05 for statistical significance).</p><p><strong>Results: </strong>The PEE association model achieved accuracy, sensitivity, specificity, precision, F1 score, and AUC of 79.3% (95% CI: 0.71-0.92), 92.3% (95% CI: 0.80-1.00), 68.8% (95% CI: 0.55-0.87), 70.6% (95% CI: 0.61-0.90), 80.0% (95% CI: 0.71-0.93), and 81.0% (95% CI: 0.68-0.92), respectively. A significant AUC improvement was found compared to DenseNet (Delong test, P = 0.03). The association model focused on brain regions affected by encephalitis.</p><p><strong>Data conclusion: </strong>Using extensive unlabeled data via self-supervised learning addressed the limitations of supervised tasks with limited data. The fine-tuned foundation model outperformed DenseNet, which was trained exclusively on task data.</p><p><strong>Plain language summary: </strong>This research develops a model to assess the occurrence epilepsy after encephalitis, a severe brain inflammation condition. By using over 57,000 brain scans, the study trains a computer program to recognize patterns in brain images. The model analyzes whole-brain scans to identify areas commonly affected by the disease, such as the temporal and frontal lobes. It was tested on data from patients with encephalitis and showed better performance than o
{"title":"Associations of Postencephalitic Epilepsy Using Multi-Contrast Whole Brain MRI: A Large Self-Supervised Vision Foundation Model Strategy.","authors":"Ronghui Gao, Anjiao Peng, Yifei Duan, Mengyao Chen, Tao Zheng, Meng Zhang, Lei Chen, Huaiqiang Sun","doi":"10.1002/jmri.29734","DOIUrl":"https://doi.org/10.1002/jmri.29734","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Postencephalitic epilepsy (PEE) is a severe neurological complication following encephalitis. Early identification of individuals at high risk for PEE is important for timely intervention.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;To develop a large self-supervised vision foundation model using a big dataset of multi-contrast head MRI scans, followed by fine-tuning with MRI data and follow-up outcomes from patients with PEE to develop a PEE association model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Study type: &lt;/strong&gt;Retrospective.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Population: &lt;/strong&gt;Fifty-seven thousand six hundred twenty-one contrast-enhanced head MRI scans from 34,871 patients for foundation model construction, and head MRI scans from 144 patients with encephalitis (64 PEE, 80 N-PEE) for the PEE association model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Field strength/sequence: &lt;/strong&gt;1.5-T, 3-T, T1-weighted imaging, T2-weighted imaging, fluid attenuated inversion recovery, T1-weighted contrast-enhanced imaging.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Assessment: &lt;/strong&gt;The foundation model was developed using self-supervised learning and cross-contrast context recovery. Patients with encephalitis were monitored for a median of 3.7 years (range 0.7-7.5 years), with epilepsy diagnosed according to International League Against Epilepsy. Occlusion sensitivity mapping highlighted brain regions involved in PEE classifications. Model performance was compared with DenseNet without pre-trained weights.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Statistical tests: &lt;/strong&gt;Performance was assessed via confusion matrices, accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver operating characteristic curve (AUC). The DeLong test evaluated AUC between the two models (P &lt; 0.05 for statistical significance).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The PEE association model achieved accuracy, sensitivity, specificity, precision, F1 score, and AUC of 79.3% (95% CI: 0.71-0.92), 92.3% (95% CI: 0.80-1.00), 68.8% (95% CI: 0.55-0.87), 70.6% (95% CI: 0.61-0.90), 80.0% (95% CI: 0.71-0.93), and 81.0% (95% CI: 0.68-0.92), respectively. A significant AUC improvement was found compared to DenseNet (Delong test, P = 0.03). The association model focused on brain regions affected by encephalitis.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Data conclusion: &lt;/strong&gt;Using extensive unlabeled data via self-supervised learning addressed the limitations of supervised tasks with limited data. The fine-tuned foundation model outperformed DenseNet, which was trained exclusively on task data.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Plain language summary: &lt;/strong&gt;This research develops a model to assess the occurrence epilepsy after encephalitis, a severe brain inflammation condition. By using over 57,000 brain scans, the study trains a computer program to recognize patterns in brain images. The model analyzes whole-brain scans to identify areas commonly affected by the disease, such as the temporal and frontal lobes. It was tested on data from patients with encephalitis and showed better performance than o","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143080140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Influence of Multiband Technique on Temporal Diffusion Spectroscopy and Its Diagnostic Value in Breast Tumors.
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-31 DOI: 10.1002/jmri.29715
Jie Ding, Zhen Zhang, Hongyan Xiao, Lijia Zhi, Xiuzheng Yue, Dazhi Chen, Rongrong Zhu, Lili Yang, Chao You, Yajia Gu
<p><strong>Background: </strong>Temporal diffusion spectroscopy (TDS) is a noninvasive diffusion imaging technique used to characterizing cellular microstructures. The influence of multiband (MB) on TDS, particularly in breast tumor imaging remain unknown.</p><p><strong>Purpose: </strong>To investigate the influence of MB on TDS in terms of scanning time, image quality, and quantitative parameters and to assess the diagnostic value of TDS with MB in breast tumors.</p><p><strong>Study type: </strong>Prospective.</p><p><strong>Population: </strong>Seventy-one women with 71 confirmed lesions.</p><p><strong>Field strength/sequence: </strong>3.0 T; oscillating gradient spin-echo (OGSE), OGSE with MB, and pulsed gradient spin-echo, and routine magnetic resonance imaging squences.</p><p><strong>Assessment: </strong>TDS with MB was used to assess diagnostic efficacy in differentiating benign and malignant tumors. A comparison of scanning time and image quality was performed in 17 patients. Imaging parameters were analyzed using limited spectrally edited diffusion (IMPULSED) and apparent diffusion coefficient (ADC) values were compared between MB and non-MB protocols. The cell diameter from TDS was compared with histopathological measurements in 21 patients.</p><p><strong>Statistical tests: </strong>Bland-Altman plot, paired t test, Mann-Whitney U test, kappa test, DeLong's test, intraclass correlation coefficient agreement, receiver operating characteristic curve, area under the curve (AUC), and simple linear regression, with statistical significance set at P < 0.05.</p><p><strong>Results: </strong>The TDS with MB protocol had a shorter average scanning time than that without MB protocol (7 minutes 22 seconds vs. 12 minutes 28 seconds); image quality was improved by reducing image artifacts. Most IMPULSED parameters and ADC values did not significantly differ between the MB and non-MB protocols (P = 0.23, P = 0.17). The IMPULSED parameters of cellularity and intracellular volume fraction achieved the highest AUC values for distinguishing breast tumors (0.865 and 0.821, respectively), surpassing the diagnostic efficiency of conventional ADC-1000 (0.776). The correlation between IMPULSED parameters and microscopic cell size was strong (r = 0.842).</p><p><strong>Data conclusion: </strong>The MB technique improved the TDS protocol's efficiency and reduced the image artifacts. TDS parameters correlated with pathological findings and showed good performance in differentiating benign from malignant breast tumors.</p><p><strong>Plain language summary: </strong>We explored the impact of simultaneous multislice acquisition technology on temporal diffusion spectroscopy (TDS) and whether combining this method could help distinguish benign from malignant breast tumors. Our findings showed that simultaneous multislice acquisition technology shortened the scanning time and improved image quality by reducing motion-related issues. Additionally, measurements of cell size
{"title":"Influence of Multiband Technique on Temporal Diffusion Spectroscopy and Its Diagnostic Value in Breast Tumors.","authors":"Jie Ding, Zhen Zhang, Hongyan Xiao, Lijia Zhi, Xiuzheng Yue, Dazhi Chen, Rongrong Zhu, Lili Yang, Chao You, Yajia Gu","doi":"10.1002/jmri.29715","DOIUrl":"https://doi.org/10.1002/jmri.29715","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Temporal diffusion spectroscopy (TDS) is a noninvasive diffusion imaging technique used to characterizing cellular microstructures. The influence of multiband (MB) on TDS, particularly in breast tumor imaging remain unknown.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;To investigate the influence of MB on TDS in terms of scanning time, image quality, and quantitative parameters and to assess the diagnostic value of TDS with MB in breast tumors.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Study type: &lt;/strong&gt;Prospective.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Population: &lt;/strong&gt;Seventy-one women with 71 confirmed lesions.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Field strength/sequence: &lt;/strong&gt;3.0 T; oscillating gradient spin-echo (OGSE), OGSE with MB, and pulsed gradient spin-echo, and routine magnetic resonance imaging squences.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Assessment: &lt;/strong&gt;TDS with MB was used to assess diagnostic efficacy in differentiating benign and malignant tumors. A comparison of scanning time and image quality was performed in 17 patients. Imaging parameters were analyzed using limited spectrally edited diffusion (IMPULSED) and apparent diffusion coefficient (ADC) values were compared between MB and non-MB protocols. The cell diameter from TDS was compared with histopathological measurements in 21 patients.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Statistical tests: &lt;/strong&gt;Bland-Altman plot, paired t test, Mann-Whitney U test, kappa test, DeLong's test, intraclass correlation coefficient agreement, receiver operating characteristic curve, area under the curve (AUC), and simple linear regression, with statistical significance set at P &lt; 0.05.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The TDS with MB protocol had a shorter average scanning time than that without MB protocol (7 minutes 22 seconds vs. 12 minutes 28 seconds); image quality was improved by reducing image artifacts. Most IMPULSED parameters and ADC values did not significantly differ between the MB and non-MB protocols (P = 0.23, P = 0.17). The IMPULSED parameters of cellularity and intracellular volume fraction achieved the highest AUC values for distinguishing breast tumors (0.865 and 0.821, respectively), surpassing the diagnostic efficiency of conventional ADC-1000 (0.776). The correlation between IMPULSED parameters and microscopic cell size was strong (r = 0.842).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Data conclusion: &lt;/strong&gt;The MB technique improved the TDS protocol's efficiency and reduced the image artifacts. TDS parameters correlated with pathological findings and showed good performance in differentiating benign from malignant breast tumors.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Plain language summary: &lt;/strong&gt;We explored the impact of simultaneous multislice acquisition technology on temporal diffusion spectroscopy (TDS) and whether combining this method could help distinguish benign from malignant breast tumors. Our findings showed that simultaneous multislice acquisition technology shortened the scanning time and improved image quality by reducing motion-related issues. Additionally, measurements of cell size","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143074596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Editorial for "Identifying Primary Sites of Spinal Metastases: Expert-Derived Features vs. ResNet50 Model Using Non-Enhanced MRI".
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-29 DOI: 10.1002/jmri.29723
Grace McIlvain, Zhuoyu Shi
{"title":"Editorial for \"Identifying Primary Sites of Spinal Metastases: Expert-Derived Features vs. ResNet50 Model Using Non-Enhanced MRI\".","authors":"Grace McIlvain, Zhuoyu Shi","doi":"10.1002/jmri.29723","DOIUrl":"https://doi.org/10.1002/jmri.29723","url":null,"abstract":"","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143066038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Application of Anti-Motion Ultra-Fast Quantitative MRI in Neurological Disorder Imaging: Insights From Huntington's Disease.
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-29 DOI: 10.1002/jmri.29682
Fei Wu, Haiyang Luo, Xiao Wang, Qinqin Yang, Yuchuan Zhuang, Liangjie Lin, Yanbo Dong, Andrey Tulupov, Yong Zhang, Shuhui Cai, Zhong Chen, Congbo Cai, Jianfeng Bao, Jingliang Cheng
<p><strong>Background: </strong>Conventional quantitative MRI (qMRI) scan is time-consuming and highly sensitive to movements, posing great challenges for quantitative images of individuals with involuntary movements, such as Huntington's disease (HD).</p><p><strong>Purpose: </strong>To evaluate the potential of our developed ultra-fast qMRI technique, multiple overlapping-echo detachment (MOLED), in overcoming involuntary head motion and its capacity to quantitatively assess tissue changes in HD.</p><p><strong>Study type: </strong>Prospective.</p><p><strong>Phantom/subjects: </strong>A phantom comprising 13 tubes of MnCl<sub>2</sub> at varying concentrations, 5 healthy volunteers (male/female: 1/4), 22 HD patients (male/female: 14/8) and 27 healthy controls (male/female: 15/12).</p><p><strong>Field strength/sequence: </strong>3.0 T. MOLED-T2 sequence, MOLED-T2* sequence, T2-weighted spin-echo sequence, T1-weighted gradient echo sequence, and T2-dark-fluid sequence.</p><p><strong>Assessment: </strong>T1-weighted images were reconstructed into high-resolution images, followed by segmentation to delineate regions of interest (ROIs). Subsequently, the MOLED T2 and T2* maps were aligned with the high-resolution images, and the ROIs were transformed into the MOLED image space using the transformation matrix and warp field. Finally, T2 and T2* values were extracted from the MOLED relaxation maps.</p><p><strong>Statistical tests: </strong>Bland-Altman analysis, independent t test, Mann-Whitney U test, Pearson correlation analysis, and Spearman correlation analysis, P < 0.05 was considered statistically significant.</p><p><strong>Results: </strong>MOLED-T2 and MOLED-T2* sequences demonstrated good accuracy (Meandiff = - 0.20%, SDdiff = 1.05%, and Meandiff = -1.73%, SDdiff = 10.98%, respectively), and good repeatability (average intraclass correlation coefficient: 0.856 and 0.853, respectively). More important, MOLED T2 and T2* maps remained artifact-free across all HD patients, even in the presence of apparent head motions. Moreover, there were significant differences in T2 and T2* values across multiple ROIs between HD and controls.</p><p><strong>Data conclusion: </strong>The ultra-fast scanning capabilities of MOLED effectively mitigate the impact of head movements, offering a robust solution for quantitative imaging in HD. Moreover, T2 and T2* values derived from MOLED provide powerful capabilities for quantifying tissue changes.</p><p><strong>Plain language summary: </strong>Quantitative MRI scan is time-consuming and sensitive to movements. Consequently, obtaining quantitative images is challenging for patients with involuntary movements, such as those with Huntington's Disease (HD). In response, a newly developed MOLED technique has been introduced, promising to resist motion through ultra-fast scan. This technique has demonstrated excellent accuracy and reproducibility and importantly all HD patient's MOLED maps remained artifacts-free. Additional
{"title":"Application of Anti-Motion Ultra-Fast Quantitative MRI in Neurological Disorder Imaging: Insights From Huntington's Disease.","authors":"Fei Wu, Haiyang Luo, Xiao Wang, Qinqin Yang, Yuchuan Zhuang, Liangjie Lin, Yanbo Dong, Andrey Tulupov, Yong Zhang, Shuhui Cai, Zhong Chen, Congbo Cai, Jianfeng Bao, Jingliang Cheng","doi":"10.1002/jmri.29682","DOIUrl":"https://doi.org/10.1002/jmri.29682","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Conventional quantitative MRI (qMRI) scan is time-consuming and highly sensitive to movements, posing great challenges for quantitative images of individuals with involuntary movements, such as Huntington's disease (HD).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;To evaluate the potential of our developed ultra-fast qMRI technique, multiple overlapping-echo detachment (MOLED), in overcoming involuntary head motion and its capacity to quantitatively assess tissue changes in HD.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Study type: &lt;/strong&gt;Prospective.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Phantom/subjects: &lt;/strong&gt;A phantom comprising 13 tubes of MnCl&lt;sub&gt;2&lt;/sub&gt; at varying concentrations, 5 healthy volunteers (male/female: 1/4), 22 HD patients (male/female: 14/8) and 27 healthy controls (male/female: 15/12).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Field strength/sequence: &lt;/strong&gt;3.0 T. MOLED-T2 sequence, MOLED-T2* sequence, T2-weighted spin-echo sequence, T1-weighted gradient echo sequence, and T2-dark-fluid sequence.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Assessment: &lt;/strong&gt;T1-weighted images were reconstructed into high-resolution images, followed by segmentation to delineate regions of interest (ROIs). Subsequently, the MOLED T2 and T2* maps were aligned with the high-resolution images, and the ROIs were transformed into the MOLED image space using the transformation matrix and warp field. Finally, T2 and T2* values were extracted from the MOLED relaxation maps.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Statistical tests: &lt;/strong&gt;Bland-Altman analysis, independent t test, Mann-Whitney U test, Pearson correlation analysis, and Spearman correlation analysis, P &lt; 0.05 was considered statistically significant.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;MOLED-T2 and MOLED-T2* sequences demonstrated good accuracy (Meandiff = - 0.20%, SDdiff = 1.05%, and Meandiff = -1.73%, SDdiff = 10.98%, respectively), and good repeatability (average intraclass correlation coefficient: 0.856 and 0.853, respectively). More important, MOLED T2 and T2* maps remained artifact-free across all HD patients, even in the presence of apparent head motions. Moreover, there were significant differences in T2 and T2* values across multiple ROIs between HD and controls.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Data conclusion: &lt;/strong&gt;The ultra-fast scanning capabilities of MOLED effectively mitigate the impact of head movements, offering a robust solution for quantitative imaging in HD. Moreover, T2 and T2* values derived from MOLED provide powerful capabilities for quantifying tissue changes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Plain language summary: &lt;/strong&gt;Quantitative MRI scan is time-consuming and sensitive to movements. Consequently, obtaining quantitative images is challenging for patients with involuntary movements, such as those with Huntington's Disease (HD). In response, a newly developed MOLED technique has been introduced, promising to resist motion through ultra-fast scan. This technique has demonstrated excellent accuracy and reproducibility and importantly all HD patient's MOLED maps remained artifacts-free. Additional","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143066033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Effects of Static and Low-Frequency Magnetic Fields on Gene Expression.
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-29 DOI: 10.1002/jmri.29726
Vitalii Zablotskii, Oksana Gorobets, Svitlana Gorobets, Tatyana Polyakova

Substantial research over the past two decades has established that magnetic fields affect fundamental cellular processes, including gene expression. However, since biological cells and subcellular components exhibit diamagnetic behavior and are therefore subjected to very small magnetic forces that cannot directly compete with the viscoelastic and bioelectric intracellular forces responsible for cellular machinery functions, it becomes challenging to understand cell-magnetic field interactions and to reveal the mechanisms through which these interactions differentially influence gene expression in cells. The limited understanding of the molecular mechanisms underlying biomagnetic effects has hindered progress in developing effective therapeutic applications of magnetic fields. This review examines the expanding body of literature on genetic events during static and low-frequency magnetic field exposure, focusing particularly on how changes in gene expression interact with cellular machinery. To address this, we conducted a systematic review utilizing extensive search strategies across multiple databases. We explore the intracellular mechanisms through which transcription functions may be modified by a magnetic field in contexts where other cellular signaling pathways are also activated by the field. This review summarizes key findings in the field, outlines the connections between magnetic fields and gene expression changes, identifies critical gaps in current knowledge, and proposes directions for future research. LEVEL OF EVIDENCE: NA TECHNICAL EFFICACY: Stage 4.

{"title":"Effects of Static and Low-Frequency Magnetic Fields on Gene Expression.","authors":"Vitalii Zablotskii, Oksana Gorobets, Svitlana Gorobets, Tatyana Polyakova","doi":"10.1002/jmri.29726","DOIUrl":"https://doi.org/10.1002/jmri.29726","url":null,"abstract":"<p><p>Substantial research over the past two decades has established that magnetic fields affect fundamental cellular processes, including gene expression. However, since biological cells and subcellular components exhibit diamagnetic behavior and are therefore subjected to very small magnetic forces that cannot directly compete with the viscoelastic and bioelectric intracellular forces responsible for cellular machinery functions, it becomes challenging to understand cell-magnetic field interactions and to reveal the mechanisms through which these interactions differentially influence gene expression in cells. The limited understanding of the molecular mechanisms underlying biomagnetic effects has hindered progress in developing effective therapeutic applications of magnetic fields. This review examines the expanding body of literature on genetic events during static and low-frequency magnetic field exposure, focusing particularly on how changes in gene expression interact with cellular machinery. To address this, we conducted a systematic review utilizing extensive search strategies across multiple databases. We explore the intracellular mechanisms through which transcription functions may be modified by a magnetic field in contexts where other cellular signaling pathways are also activated by the field. This review summarizes key findings in the field, outlines the connections between magnetic fields and gene expression changes, identifies critical gaps in current knowledge, and proposes directions for future research. LEVEL OF EVIDENCE: NA TECHNICAL EFFICACY: Stage 4.</p>","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143066042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Editorial for "Combining Multifrequency Magnetic Resonance Elastography with Automatic Segmentation to Assess Renal Function in Patients With Chronic Kidney Disease".
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-28 DOI: 10.1002/jmri.29721
Ilkay S Idilman, Musturay Karcaaltincaba
{"title":"Editorial for \"Combining Multifrequency Magnetic Resonance Elastography with Automatic Segmentation to Assess Renal Function in Patients With Chronic Kidney Disease\".","authors":"Ilkay S Idilman, Musturay Karcaaltincaba","doi":"10.1002/jmri.29721","DOIUrl":"https://doi.org/10.1002/jmri.29721","url":null,"abstract":"","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143052736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Combining Multifrequency Magnetic Resonance Elastography With Automatic Segmentation to Assess Renal Function in Patients With Chronic Kidney Disease.
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-28 DOI: 10.1002/jmri.29719
Qiumei Liang, Haiwei Lin, Junfeng Li, Peiyin Luo, Ruirui Qi, Qiuyi Chen, Fanqi Meng, Haodong Qin, Feifei Qu, Youjia Zeng, Wenjing Wang, Jiandong Lu, Bingsheng Huang, Yueyao Chen
<p><strong>Background: </strong>Multifrequency MR elastography (mMRE) enables noninvasive quantification of renal stiffness in patients with chronic kidney disease (CKD). Manual segmentation of the kidneys on mMRE is time-consuming and prone to increased interobserver variability.</p><p><strong>Purpose: </strong>To evaluate the performance of mMRE combined with automatic segmentation in assessing CKD severity.</p><p><strong>Study type: </strong>Prospective.</p><p><strong>Participants: </strong>A total of 179 participants consisting of 95 healthy volunteers and 84 participants with CKD.</p><p><strong>Field strength/sequence: </strong>3 T, single shot spin echo planar imaging sequence.</p><p><strong>Assessment: </strong>Participants were randomly assigned into training (n = 58), validation (n = 15), and test (n = 106) sets. Test set included 47 healthy volunteers and 58 CKD participants with different stages (21 stage 1-2, 22 stage 3, and 16 stage 4-5) based on estimated glomerular filtration rate (eGFR). Shear wave speed (SWS) values from mMRE was measured using automatic segmentation constructed through the nnU-Net deep-learning network. Standard manual segmentation was created by a radiologist. In the test set, the automatically segmented renal SWS were compared between healthy volunteers and CKD subgroups, with age as a covariate. The association between SWS and eGFR was investigated in participants with CKD.</p><p><strong>Statistical tests: </strong>Dice similarity coefficient (DSC), analysis of covariance, Pearson and Spearman correlation analyses. P < 0.05 was considered statistically significant.</p><p><strong>Results: </strong>Mean DSCs between standard manual and automatic segmentation were 0.943, 0.901, and 0.970 for the renal cortex, medulla, and parenchyma, respectively. The automatically quantified cortical, medullary, and parenchymal SWS were significantly correlated with eGFR (r = 0.620, 0.605, and 0.640, respectively). Participants with CKD stage 1-2 exhibited significantly lower cortical SWS values compared to healthy volunteers (2.44 ± 0.16 m/second vs. 2.56 ± 0.17 m/second), after adjusting age.</p><p><strong>Conclusion: </strong>mMRE combined with automatic segmentation revealed abnormal renal stiffness in patients with CKD, even with mild renal impairment.</p><p><strong>Plain language summary: </strong>The renal stiffness of patients with chronic kidney disease varies according to the function and structure of the kidney. This study integrates multifrequency magnetic resonance elastography with automated segmentation technique to assess renal stiffness in patients with chronic kidney disease. The findings indicate that this method is capable of distinguishing between patients with chronic kidney disease, including those with mild renal impairment, while simultaneously reducing the subjectivity and time required for radiologists to analyze images. This research enhances the efficiency of image processing for radiologists and as
背景:多频磁共振弹性成像(mMRE)可对慢性肾脏病(CKD)患者的肾脏硬度进行无创量化。目的:评估多频磁共振弹性成像(mMRE)结合自动分段评估 CKD 严重程度的性能:研究类型:前瞻性:研究类型:前瞻性。参与者:共 179 人,包括 95 名健康志愿者和 84 名 CKD 患者:3 T,单次自旋回波平面成像序列:参与者被随机分配到训练组(58 人)、验证组(15 人)和测试组(106 人)。测试组包括 47 名健康志愿者和 58 名根据估计肾小球滤过率(eGFR)划分为不同阶段(1-2 期 21 人、3 期 22 人、4-5 期 16 人)的慢性肾脏病患者。mMRE 的剪切波速度(SWS)值是通过 nnU-Net 深度学习网络构建的自动分割测量的。标准手动分割由放射科医生创建。在测试集中,将自动分割的肾脏 SWS 在健康志愿者和 CKD 亚组之间进行比较,并将年龄作为协变量。在患有慢性肾脏病的参与者中,研究了 SWS 与 eGFR 之间的关联:骰子相似系数(DSC)、协方差分析、皮尔逊和斯皮尔曼相关分析。P 结果:肾皮质、髓质和实质的标准人工分割和自动分割的平均 DSC 分别为 0.943、0.901 和 0.970。自动量化的皮质、髓质和实质 SWS 与 eGFR 显著相关(r 分别为 0.620、0.605 和 0.640)。结论:mMRE 与自动分割相结合显示出慢性肾脏病患者肾脏僵硬度异常,即使是轻度肾功能损害。本研究将多频磁共振弹性成像技术与自动分割技术相结合,以评估慢性肾脏病患者的肾脏硬度。研究结果表明,这种方法能够区分慢性肾病患者,包括轻度肾功能损害患者,同时减少放射科医生分析图像的主观性和所需时间。这项研究提高了放射科医生处理图像的效率,并协助肾病专家检测慢性肾病患者的早期损伤。
{"title":"Combining Multifrequency Magnetic Resonance Elastography With Automatic Segmentation to Assess Renal Function in Patients With Chronic Kidney Disease.","authors":"Qiumei Liang, Haiwei Lin, Junfeng Li, Peiyin Luo, Ruirui Qi, Qiuyi Chen, Fanqi Meng, Haodong Qin, Feifei Qu, Youjia Zeng, Wenjing Wang, Jiandong Lu, Bingsheng Huang, Yueyao Chen","doi":"10.1002/jmri.29719","DOIUrl":"https://doi.org/10.1002/jmri.29719","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Multifrequency MR elastography (mMRE) enables noninvasive quantification of renal stiffness in patients with chronic kidney disease (CKD). Manual segmentation of the kidneys on mMRE is time-consuming and prone to increased interobserver variability.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;To evaluate the performance of mMRE combined with automatic segmentation in assessing CKD severity.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Study type: &lt;/strong&gt;Prospective.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Participants: &lt;/strong&gt;A total of 179 participants consisting of 95 healthy volunteers and 84 participants with CKD.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Field strength/sequence: &lt;/strong&gt;3 T, single shot spin echo planar imaging sequence.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Assessment: &lt;/strong&gt;Participants were randomly assigned into training (n = 58), validation (n = 15), and test (n = 106) sets. Test set included 47 healthy volunteers and 58 CKD participants with different stages (21 stage 1-2, 22 stage 3, and 16 stage 4-5) based on estimated glomerular filtration rate (eGFR). Shear wave speed (SWS) values from mMRE was measured using automatic segmentation constructed through the nnU-Net deep-learning network. Standard manual segmentation was created by a radiologist. In the test set, the automatically segmented renal SWS were compared between healthy volunteers and CKD subgroups, with age as a covariate. The association between SWS and eGFR was investigated in participants with CKD.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Statistical tests: &lt;/strong&gt;Dice similarity coefficient (DSC), analysis of covariance, Pearson and Spearman correlation analyses. P &lt; 0.05 was considered statistically significant.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Mean DSCs between standard manual and automatic segmentation were 0.943, 0.901, and 0.970 for the renal cortex, medulla, and parenchyma, respectively. The automatically quantified cortical, medullary, and parenchymal SWS were significantly correlated with eGFR (r = 0.620, 0.605, and 0.640, respectively). Participants with CKD stage 1-2 exhibited significantly lower cortical SWS values compared to healthy volunteers (2.44 ± 0.16 m/second vs. 2.56 ± 0.17 m/second), after adjusting age.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;mMRE combined with automatic segmentation revealed abnormal renal stiffness in patients with CKD, even with mild renal impairment.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Plain language summary: &lt;/strong&gt;The renal stiffness of patients with chronic kidney disease varies according to the function and structure of the kidney. This study integrates multifrequency magnetic resonance elastography with automated segmentation technique to assess renal stiffness in patients with chronic kidney disease. The findings indicate that this method is capable of distinguishing between patients with chronic kidney disease, including those with mild renal impairment, while simultaneously reducing the subjectivity and time required for radiologists to analyze images. This research enhances the efficiency of image processing for radiologists and as","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143052734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Evaluating the Potential of Quantitative Susceptibility Mapping for Detecting Iron Deposition of Renal Fibrosis in a Rabbit Model.
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-28 DOI: 10.1002/jmri.29722
Tingting Zha, Zhiping Zhang, Liang Pan, Lei Peng, Yanan Du, Peng Wu, Jie Chen, Wei Xing

Background: As ferroptosis is a key factor in renal fibrosis (RF), iron deposition monitoring may help evaluating RF. The capability of quantitative susceptibility mapping (QSM) for detecting iron deposition in RF remains uncertain.

Purpose: To investigate the potential of QSM to detect iron deposition in RF.

Study type: Animal model.

Animal model: Eighty New Zealand rabbits were randomly divided into control (N = 10) and RF (N = 70) groups, consisting of baseline, 7, 14, 21, and 28 days (N = 12 in each), and longitudinal (N = 10) subgroups. RF was induced via unilateral renal arteria stenosis.

Field strength/sequence: 3 T, QSM with gradient echo, arterial spin labeling with gradient spin echo.

Assessment: Bilateral kidney QSM values (χ) in the cortex (χCO) and outer medulla (χOM) were evaluated with histopathology.

Statistical tests: Analysis of variance, Kruskal-Wallis, Spearman's correlation, and the area under the receiver operating characteristic curve (AUC). P < 0.05 was significant.

Results: In fibrotic kidneys, χCO decreased at 7 days ([-6.69 ± 0.98] × 10-2 ppm) and increased during 14-28 days ([-1.85 ± 2.11], [0.14 ± 0.58], and [1.99 ± 0.60] × 10-2 ppm, respectively), while the χOM had the opposite trend. Both significantly correlated with histopathology (|r| = 0.674-0.849). AUC of QSM for distinguishing RF degrees was 0.692-0.993. In contralateral kidneys, the χCO initially decreased ([-6.67 ± 0.84] × 10-2 ppm) then recovered to baseline ([-4.81 ± 0.89] × 10-2 ppm), while the χOM at 7-28 days ([2.58 ± 1.40], [2.25 ± 1.83], [2.49 ± 2.11], [2.43 ± 1.32] × 10-2 ppm, respectively) were significantly higher than baseline ([0.54 ± 0.18] × 10-2 ppm).

Data conclusion: Different iron deposition patterns were observed in RF with QSM values, suggesting the potential of QSM for iron deposition monitoring in RF.

Plain language summary: Renal fibrosis (RF) is a common outcome in most kidney diseases, leading to scarring and loss of kidney function. Increasing evidence suggests that abnormal iron metabolism plays an important role in RF. This study used a technique called quantitative susceptibility mapping (QSM) to measure kidney iron levels in rabbits with RF. Specifically, rabbits with advanced RF exhibited higher kidney iron concentrations, and moderate to strong correlations between QSM values and histopathology demonstrated that QSM could accurately detect changes in iron levels and assess RF severity. Overall, QSM shows promise as a tool for monitoring iron deposition in RF progression.

Evidence level: 2 TECHNICAL EFFICACY: Stage 3.

{"title":"Evaluating the Potential of Quantitative Susceptibility Mapping for Detecting Iron Deposition of Renal Fibrosis in a Rabbit Model.","authors":"Tingting Zha, Zhiping Zhang, Liang Pan, Lei Peng, Yanan Du, Peng Wu, Jie Chen, Wei Xing","doi":"10.1002/jmri.29722","DOIUrl":"https://doi.org/10.1002/jmri.29722","url":null,"abstract":"<p><strong>Background: </strong>As ferroptosis is a key factor in renal fibrosis (RF), iron deposition monitoring may help evaluating RF. The capability of quantitative susceptibility mapping (QSM) for detecting iron deposition in RF remains uncertain.</p><p><strong>Purpose: </strong>To investigate the potential of QSM to detect iron deposition in RF.</p><p><strong>Study type: </strong>Animal model.</p><p><strong>Animal model: </strong>Eighty New Zealand rabbits were randomly divided into control (N = 10) and RF (N = 70) groups, consisting of baseline, 7, 14, 21, and 28 days (N = 12 in each), and longitudinal (N = 10) subgroups. RF was induced via unilateral renal arteria stenosis.</p><p><strong>Field strength/sequence: </strong>3 T, QSM with gradient echo, arterial spin labeling with gradient spin echo.</p><p><strong>Assessment: </strong>Bilateral kidney QSM values (χ) in the cortex (χ<sub>CO</sub>) and outer medulla (χ<sub>OM</sub>) were evaluated with histopathology.</p><p><strong>Statistical tests: </strong>Analysis of variance, Kruskal-Wallis, Spearman's correlation, and the area under the receiver operating characteristic curve (AUC). P < 0.05 was significant.</p><p><strong>Results: </strong>In fibrotic kidneys, χ<sub>CO</sub> decreased at 7 days ([-6.69 ± 0.98] × 10<sup>-2</sup> ppm) and increased during 14-28 days ([-1.85 ± 2.11], [0.14 ± 0.58], and [1.99 ± 0.60] × 10<sup>-2</sup> ppm, respectively), while the χ<sub>OM</sub> had the opposite trend. Both significantly correlated with histopathology (|r| = 0.674-0.849). AUC of QSM for distinguishing RF degrees was 0.692-0.993. In contralateral kidneys, the χ<sub>CO</sub> initially decreased ([-6.67 ± 0.84] × 10<sup>-2</sup> ppm) then recovered to baseline ([-4.81 ± 0.89] × 10<sup>-2</sup> ppm), while the χ<sub>OM</sub> at 7-28 days ([2.58 ± 1.40], [2.25 ± 1.83], [2.49 ± 2.11], [2.43 ± 1.32] × 10<sup>-2</sup> ppm, respectively) were significantly higher than baseline ([0.54 ± 0.18] × 10<sup>-2</sup> ppm).</p><p><strong>Data conclusion: </strong>Different iron deposition patterns were observed in RF with QSM values, suggesting the potential of QSM for iron deposition monitoring in RF.</p><p><strong>Plain language summary: </strong>Renal fibrosis (RF) is a common outcome in most kidney diseases, leading to scarring and loss of kidney function. Increasing evidence suggests that abnormal iron metabolism plays an important role in RF. This study used a technique called quantitative susceptibility mapping (QSM) to measure kidney iron levels in rabbits with RF. Specifically, rabbits with advanced RF exhibited higher kidney iron concentrations, and moderate to strong correlations between QSM values and histopathology demonstrated that QSM could accurately detect changes in iron levels and assess RF severity. Overall, QSM shows promise as a tool for monitoring iron deposition in RF progression.</p><p><strong>Evidence level: </strong>2 TECHNICAL EFFICACY: Stage 3.</p>","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143059366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Editorial for "Left Ventricular Hemodynamic Forces Changes in Fabry Disease: A Cardiac Magnetic Resonance Study".
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-28 DOI: 10.1002/jmri.29724
Scott D Flamm
{"title":"Editorial for \"Left Ventricular Hemodynamic Forces Changes in Fabry Disease: A Cardiac Magnetic Resonance Study\".","authors":"Scott D Flamm","doi":"10.1002/jmri.29724","DOIUrl":"https://doi.org/10.1002/jmri.29724","url":null,"abstract":"","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143052661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Identifying Primary Sites of Spinal Metastases: Expert-Derived Features vs. ResNet50 Model Using Nonenhanced MRI.
IF 3.3 2区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Pub Date : 2025-01-27 DOI: 10.1002/jmri.29720
Ke Liu, Jinlai Ning, Siyuan Qin, Jun Xu, Dapeng Hao, Ning Lang
<p><strong>Background: </strong>The spinal column is a frequent site for metastases, affecting over 30% of solid tumor patients. Identifying the primary tumor is essential for guiding clinical decisions but often requires resource-intensive diagnostics.</p><p><strong>Purpose: </strong>To develop and validate artificial intelligence (AI) models using noncontrast MRI to identify primary sites of spinal metastases, aiming to enhance diagnostic efficiency.</p><p><strong>Study type: </strong>Retrospective.</p><p><strong>Population: </strong>A total of 514 patients with pathologically confirmed spinal metastases (mean age, 59.3 ± 11.2 years; 294 males) were included, split into a development set (360) and a test set (154).</p><p><strong>Field strength/sequence: </strong>Noncontrast sagittal MRI sequences (T1-weighted, T2-weighted, and fat-suppressed T2) were acquired using 1.5 T and 3 T scanners.</p><p><strong>Assessment: </strong>Two models were evaluated for identifying primary sites of spinal metastases: the expert-derived features (EDF) model using radiologist-identified imaging features and a ResNet50-based deep learning (DL) model trained on noncontrast MRI. Performance was assessed using accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (ROC-AUC) for top-1, top-2, and top-3 indicators.</p><p><strong>Statistical tests: </strong>Statistical analyses included Shapiro-Wilk, t tests, Mann-Whitney U test, and chi-squared tests. ROC-AUCs were compared via DeLong tests, with 95% confidence intervals from 1000 bootstrap replications and significance at P < 0.05.</p><p><strong>Results: </strong>The EDF model outperformed the DL model in top-3 accuracy (0.88 vs. 0.69) and AUC (0.80 vs. 0.71). Subgroup analysis showed superior EDF performance for common sites like lung and kidney (e.g., kidney F1: 0.94 vs. 0.76), while the DL model had higher recall for rare sites like thyroid (0.80 vs. 0.20). SHapley Additive exPlanations (SHAP) analysis identified sex (SHAP: -0.57 to 0.68), age (-0.48 to 0.98), T1WI signal intensity (-0.29 to 0.72), and pathological fractures (-0.76 to 0.25) as key features.</p><p><strong>Data conclusion: </strong>AI techniques using noncontrast MRI improve diagnostic efficiency for spinal metastases. The EDF model outperformed the DL model, showing greater clinical potential.</p><p><strong>Plain language summary: </strong>Spinal metastases, or cancer spreading to the spine, are common in patients with advanced cancer, often requiring extensive tests to determine the original tumor site. Our study explored whether artificial intelligence could make this process faster and more accurate using noncontrast MRI scans. We tested two methods: one based on radiologists' expertise in identifying imaging features and another using a deep learning model trained to analyze MRI images. The expert-based method was more reliable, correctly identifying the tumor site in 88% of cases when considering th
{"title":"Identifying Primary Sites of Spinal Metastases: Expert-Derived Features vs. ResNet50 Model Using Nonenhanced MRI.","authors":"Ke Liu, Jinlai Ning, Siyuan Qin, Jun Xu, Dapeng Hao, Ning Lang","doi":"10.1002/jmri.29720","DOIUrl":"https://doi.org/10.1002/jmri.29720","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The spinal column is a frequent site for metastases, affecting over 30% of solid tumor patients. Identifying the primary tumor is essential for guiding clinical decisions but often requires resource-intensive diagnostics.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Purpose: &lt;/strong&gt;To develop and validate artificial intelligence (AI) models using noncontrast MRI to identify primary sites of spinal metastases, aiming to enhance diagnostic efficiency.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Study type: &lt;/strong&gt;Retrospective.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Population: &lt;/strong&gt;A total of 514 patients with pathologically confirmed spinal metastases (mean age, 59.3 ± 11.2 years; 294 males) were included, split into a development set (360) and a test set (154).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Field strength/sequence: &lt;/strong&gt;Noncontrast sagittal MRI sequences (T1-weighted, T2-weighted, and fat-suppressed T2) were acquired using 1.5 T and 3 T scanners.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Assessment: &lt;/strong&gt;Two models were evaluated for identifying primary sites of spinal metastases: the expert-derived features (EDF) model using radiologist-identified imaging features and a ResNet50-based deep learning (DL) model trained on noncontrast MRI. Performance was assessed using accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve (ROC-AUC) for top-1, top-2, and top-3 indicators.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Statistical tests: &lt;/strong&gt;Statistical analyses included Shapiro-Wilk, t tests, Mann-Whitney U test, and chi-squared tests. ROC-AUCs were compared via DeLong tests, with 95% confidence intervals from 1000 bootstrap replications and significance at P &lt; 0.05.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;The EDF model outperformed the DL model in top-3 accuracy (0.88 vs. 0.69) and AUC (0.80 vs. 0.71). Subgroup analysis showed superior EDF performance for common sites like lung and kidney (e.g., kidney F1: 0.94 vs. 0.76), while the DL model had higher recall for rare sites like thyroid (0.80 vs. 0.20). SHapley Additive exPlanations (SHAP) analysis identified sex (SHAP: -0.57 to 0.68), age (-0.48 to 0.98), T1WI signal intensity (-0.29 to 0.72), and pathological fractures (-0.76 to 0.25) as key features.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Data conclusion: &lt;/strong&gt;AI techniques using noncontrast MRI improve diagnostic efficiency for spinal metastases. The EDF model outperformed the DL model, showing greater clinical potential.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Plain language summary: &lt;/strong&gt;Spinal metastases, or cancer spreading to the spine, are common in patients with advanced cancer, often requiring extensive tests to determine the original tumor site. Our study explored whether artificial intelligence could make this process faster and more accurate using noncontrast MRI scans. We tested two methods: one based on radiologists' expertise in identifying imaging features and another using a deep learning model trained to analyze MRI images. The expert-based method was more reliable, correctly identifying the tumor site in 88% of cases when considering th","PeriodicalId":16140,"journal":{"name":"Journal of Magnetic Resonance Imaging","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143046937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Journal of Magnetic Resonance Imaging
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1