Junhui Huang , Yongsheng Ao , Lan Mu , Jierui Zhao , Hongliang Chen , Long Yang , Bingyu Yao , Shuheng Zhang , Shimin Yang , Greta S.P. Mok , Ke Zhang , Zhanli Hu , Ye Li , Dong Liang , Xin Liu , Hairong Zheng , Lihua Qiu , Na Zhang
{"title":"超快速DCE-MRI鉴别乳腺良恶性病变的可行性","authors":"Junhui Huang , Yongsheng Ao , Lan Mu , Jierui Zhao , Hongliang Chen , Long Yang , Bingyu Yao , Shuheng Zhang , Shimin Yang , Greta S.P. Mok , Ke Zhang , Zhanli Hu , Ye Li , Dong Liang , Xin Liu , Hairong Zheng , Lihua Qiu , Na Zhang","doi":"10.1016/j.compmedimag.2025.102561","DOIUrl":null,"url":null,"abstract":"<div><h3>Objectives</h3><div>This study investigates whether the use of ultrafast DCE-MRI immediately after contrast injection is an alternative to conventional DCE-MRI for diagnosing benign and malignant breast lesions.</div></div><div><h3>Methods</h3><div>A total of 86 female patients were included in this prospective study. Each patient underwent both ultrafast DCE-MRI and conventional DCE-MRI before surgery. The Mann-Whitney U test was used to analyze whether there were significant differences in DCE-MRI parameters between benign and malignant breast lesions (p < 0.05) for both conventional and ultrafast methods. The AUC value of the ROC curve was used to assess the diagnostic performance for each parameter and to determine their critical values, sensitivity, and specificity using the maximum Youden index. Delong test and support vector machine (SVM) were also used to evaluate the performance of conventional DCE-MRI and ultrafast DCE-MRI in identifying benign and malignant breast lesions.</div></div><div><h3>Results</h3><div>A total of 99 lesion areas (21 benign and 78 malignant lesions) were found in the 86 patients. Conventional DCE-MRI has only two semiquantitative parameters that can identify benign and malignant (Wash-out and SER, p < 0.05), whereas ultrafast DCE-MRI is the one that can identify benign and malignant for all semiquantitative parameters except clearance, and there are more semiquantitative parameters that can be used to identify benign and malignant by ultrafast DCE-MRI than by conventional DCE-MRI. The ultrafast DCE-MRI parameters (AUC=0.8626) had a greater AUC than the conventional DCE-MRI parameters (AUC=0.7552) for distinguishing between benign and malignant breast lesions.</div></div><div><h3>Conclusions</h3><div>Ultrafast DCE-MRI is effective in identifying benign and malignant breast lesions at the early stage of contrast injection; therefore, it is feasible to use Ultrafast DCE-MRI instead of conventional DCE-MRI to diagnose benign and malignant breast tumor lesions.</div></div><div><h3>Advances in knowledge</h3><div>We evaluated ultrafast DCE-MRI's quantitative parameters in distinguishing benign from malignant breast lesions. SVM was used to assess the performance of conventional and ultrafast DCE-MRI in breast malignancy discrimination.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"123 ","pages":"Article 102561"},"PeriodicalIF":5.4000,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Feasibility of ultrafast DCE-MRI for identifying benign and malignant breast lesions\",\"authors\":\"Junhui Huang , Yongsheng Ao , Lan Mu , Jierui Zhao , Hongliang Chen , Long Yang , Bingyu Yao , Shuheng Zhang , Shimin Yang , Greta S.P. Mok , Ke Zhang , Zhanli Hu , Ye Li , Dong Liang , Xin Liu , Hairong Zheng , Lihua Qiu , Na Zhang\",\"doi\":\"10.1016/j.compmedimag.2025.102561\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Objectives</h3><div>This study investigates whether the use of ultrafast DCE-MRI immediately after contrast injection is an alternative to conventional DCE-MRI for diagnosing benign and malignant breast lesions.</div></div><div><h3>Methods</h3><div>A total of 86 female patients were included in this prospective study. Each patient underwent both ultrafast DCE-MRI and conventional DCE-MRI before surgery. The Mann-Whitney U test was used to analyze whether there were significant differences in DCE-MRI parameters between benign and malignant breast lesions (p < 0.05) for both conventional and ultrafast methods. The AUC value of the ROC curve was used to assess the diagnostic performance for each parameter and to determine their critical values, sensitivity, and specificity using the maximum Youden index. Delong test and support vector machine (SVM) were also used to evaluate the performance of conventional DCE-MRI and ultrafast DCE-MRI in identifying benign and malignant breast lesions.</div></div><div><h3>Results</h3><div>A total of 99 lesion areas (21 benign and 78 malignant lesions) were found in the 86 patients. Conventional DCE-MRI has only two semiquantitative parameters that can identify benign and malignant (Wash-out and SER, p < 0.05), whereas ultrafast DCE-MRI is the one that can identify benign and malignant for all semiquantitative parameters except clearance, and there are more semiquantitative parameters that can be used to identify benign and malignant by ultrafast DCE-MRI than by conventional DCE-MRI. The ultrafast DCE-MRI parameters (AUC=0.8626) had a greater AUC than the conventional DCE-MRI parameters (AUC=0.7552) for distinguishing between benign and malignant breast lesions.</div></div><div><h3>Conclusions</h3><div>Ultrafast DCE-MRI is effective in identifying benign and malignant breast lesions at the early stage of contrast injection; therefore, it is feasible to use Ultrafast DCE-MRI instead of conventional DCE-MRI to diagnose benign and malignant breast tumor lesions.</div></div><div><h3>Advances in knowledge</h3><div>We evaluated ultrafast DCE-MRI's quantitative parameters in distinguishing benign from malignant breast lesions. SVM was used to assess the performance of conventional and ultrafast DCE-MRI in breast malignancy discrimination.</div></div>\",\"PeriodicalId\":50631,\"journal\":{\"name\":\"Computerized Medical Imaging and Graphics\",\"volume\":\"123 \",\"pages\":\"Article 102561\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2025-04-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computerized Medical Imaging and Graphics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0895611125000709\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computerized Medical Imaging and Graphics","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0895611125000709","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0
摘要
目的本研究探讨注射造影剂后立即使用超快速DCE-MRI是否可以替代常规DCE-MRI诊断乳腺良恶性病变。方法86例女性患者纳入前瞻性研究。每位患者术前均行超快DCE-MRI和常规DCE-MRI检查。采用Mann-Whitney U检验分析乳腺良恶性病变DCE-MRI参数在常规方法和超快方法下是否存在显著差异(p <; 0.05)。ROC曲线的AUC值用于评估各参数的诊断性能,并使用最大约登指数确定其临界值、敏感性和特异性。采用德隆测试和支持向量机(SVM)评价常规DCE-MRI和超快速DCE-MRI对乳腺良恶性病变的识别能力。结果86例患者共发现99个病变区,其中良性21个,恶性78个。常规DCE-MRI只有两个半定量参数能识别良恶性(washout和SER, p <; 0.05),而超快DCE-MRI是除清除率外所有半定量参数都能识别良恶性的,超快DCE-MRI比常规DCE-MRI有更多的半定量参数可用于良恶性识别。超快DCE-MRI参数(AUC=0.8626)鉴别乳腺良恶性病变的AUC高于常规DCE-MRI参数(AUC=0.7552)。结论超声快速DCE-MRI在注射造影剂早期鉴别乳腺良恶性病变有较好的疗效;因此,使用超快DCE-MRI代替常规DCE-MRI诊断乳腺良恶性肿瘤病变是可行的。我们评估了超快速DCE-MRI在区分乳腺良恶性病变中的定量参数。采用支持向量机评价常规和超快DCE-MRI对乳腺恶性肿瘤的鉴别效果。
Feasibility of ultrafast DCE-MRI for identifying benign and malignant breast lesions
Objectives
This study investigates whether the use of ultrafast DCE-MRI immediately after contrast injection is an alternative to conventional DCE-MRI for diagnosing benign and malignant breast lesions.
Methods
A total of 86 female patients were included in this prospective study. Each patient underwent both ultrafast DCE-MRI and conventional DCE-MRI before surgery. The Mann-Whitney U test was used to analyze whether there were significant differences in DCE-MRI parameters between benign and malignant breast lesions (p < 0.05) for both conventional and ultrafast methods. The AUC value of the ROC curve was used to assess the diagnostic performance for each parameter and to determine their critical values, sensitivity, and specificity using the maximum Youden index. Delong test and support vector machine (SVM) were also used to evaluate the performance of conventional DCE-MRI and ultrafast DCE-MRI in identifying benign and malignant breast lesions.
Results
A total of 99 lesion areas (21 benign and 78 malignant lesions) were found in the 86 patients. Conventional DCE-MRI has only two semiquantitative parameters that can identify benign and malignant (Wash-out and SER, p < 0.05), whereas ultrafast DCE-MRI is the one that can identify benign and malignant for all semiquantitative parameters except clearance, and there are more semiquantitative parameters that can be used to identify benign and malignant by ultrafast DCE-MRI than by conventional DCE-MRI. The ultrafast DCE-MRI parameters (AUC=0.8626) had a greater AUC than the conventional DCE-MRI parameters (AUC=0.7552) for distinguishing between benign and malignant breast lesions.
Conclusions
Ultrafast DCE-MRI is effective in identifying benign and malignant breast lesions at the early stage of contrast injection; therefore, it is feasible to use Ultrafast DCE-MRI instead of conventional DCE-MRI to diagnose benign and malignant breast tumor lesions.
Advances in knowledge
We evaluated ultrafast DCE-MRI's quantitative parameters in distinguishing benign from malignant breast lesions. SVM was used to assess the performance of conventional and ultrafast DCE-MRI in breast malignancy discrimination.
期刊介绍:
The purpose of the journal Computerized Medical Imaging and Graphics is to act as a source for the exchange of research results concerning algorithmic advances, development, and application of digital imaging in disease detection, diagnosis, intervention, prevention, precision medicine, and population health. Included in the journal will be articles on novel computerized imaging or visualization techniques, including artificial intelligence and machine learning, augmented reality for surgical planning and guidance, big biomedical data visualization, computer-aided diagnosis, computerized-robotic surgery, image-guided therapy, imaging scanning and reconstruction, mobile and tele-imaging, radiomics, and imaging integration and modeling with other information relevant to digital health. The types of biomedical imaging include: magnetic resonance, computed tomography, ultrasound, nuclear medicine, X-ray, microwave, optical and multi-photon microscopy, video and sensory imaging, and the convergence of biomedical images with other non-imaging datasets.