Menglin Wu, Fan Li, Yuhui Tao, Yuhan Zhang, Shanshan Wang, Pablo D. Burstein, Xuetao Mu, Jie Zhu
{"title":"MP-MRI中前列腺癌分割和PI-RADS分级的病变引导选择性多模态整合。","authors":"Menglin Wu, Fan Li, Yuhui Tao, Yuhan Zhang, Shanshan Wang, Pablo D. Burstein, Xuetao Mu, Jie Zhu","doi":"10.1002/mp.70019","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Prostate cancer (PCa) presents a significant global health challenge affecting men. Accurate segmentation and grading of PCa lesions in multiparametric Magnetic Resonance Imaging (mp-MRI) are essential for effective diagnosis and treatment planning.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>This study aimed to develop and validate an automated model for PCa lesion segmentation and Prostate Imaging Reporting and Data System (PI-RADS) grading in mp-MRI.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>The lesion's perceived characteristics are strongly related to both imaging modalities and lesion locations. Therefore, we propose a Lesion-guided Selective Multi-modal Integration (LeSMI) module. This module incorporates two advanced mechanisms—Dynamic Modality Weighting (DMW) and Localized Lesion Attention (LLA)—to dynamically integrate crucial information across and within imaging modalities. Specifically, DMW operates on the mp-MRI inputs (T2-weighted (T2w) images, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps) to dynamically assign weights to each modality, thereby integrating complementary information and enhancing feature identification across different contexts. LLA, on the other hand, maintains spatial structure information within each modality for precise lesion localization. Inspired by clinical workflows, our framework is employed through a two-stage Prostate Cancer Segmentation and Grading (PCaSG) strategy, leveraging knowledge from segmentation to improve PI-RADS grading performance. We validated our method using two publicly available datasets, namely, Prostate158 and PI-CAI Challenge, to assess its advantages over other methods. For the Prostate158 dataset, we used the officially reported partition with 119 cases for training, 20 for validation, and 19 for testing. In contrast, the PI-CAI Challenge dataset, which lacks predefined splits, was randomly divided into 180 for training, 20 for validation, and 20 for testing. In addition to these dataset partitions, 5-fold cross-validation was conducted on both the Prostate158 and PI-CAI Challenge datasets to provide a more robust and comprehensive statistical evaluation of the model's performance.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>Evaluated on the Prostate158 and PI-CAI Challenge datasets, our method demonstrated superior performance, achieving a Dice Similarity Coefficient (DSC) of 51.30% and a lesion-level quadratic-weighted kappa score (<span></span><math>\n <semantics>\n <mrow>\n <mi>Q</mi>\n <mi>W</mi>\n <msub>\n <mi>K</mi>\n <mi>l</mi>\n </msub>\n </mrow>\n <annotation>$QW{{K}_l}$</annotation>\n </semantics></math>) of 62.48% on Prostate158, and a DSC of 43.81% and a <span></span><math>\n <semantics>\n <mrow>\n <mi>Q</mi>\n <mi>W</mi>\n <msub>\n <mi>K</mi>\n <mi>l</mi>\n </msub>\n </mrow>\n <annotation>$QW{{K}_l}$</annotation>\n </semantics></math> of 42.98% on PI-CAI. These results represent improvements of up to 2% in DSC and 17% in <span></span><math>\n <semantics>\n <mrow>\n <mi>Q</mi>\n <mi>W</mi>\n <msub>\n <mi>K</mi>\n <mi>l</mi>\n </msub>\n </mrow>\n <annotation>$QW{{K}_l}$</annotation>\n </semantics></math> over current state-of-the-art models on Prostate158, and enhancements of 4% in DSC and 3% in <span></span><math>\n <semantics>\n <mrow>\n <mi>Q</mi>\n <mi>W</mi>\n <msub>\n <mi>K</mi>\n <mi>l</mi>\n </msub>\n </mrow>\n <annotation>$QW{{K}_l}$</annotation>\n </semantics></math> on PI-CAI.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>The proposed model's robustness in handling diverse lesion presentations, combined with its reliable assessments, underscores its significant clinical applicability. Our model offers substantial advancements in both segmentation accuracy and PI-RADS grading, addressing the challenges of inter-reader variability and the need for high expertise in conventional diagnostic practices. This technological innovation holds promise for enhancing early, accurate detection and risk assessment in prostate cancer management, ultimately improving patient outcomes.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 10","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Lesion-guided selective multi-modal integration for prostate cancer segmentation and PI-RADS grading in MP-MRI\",\"authors\":\"Menglin Wu, Fan Li, Yuhui Tao, Yuhan Zhang, Shanshan Wang, Pablo D. Burstein, Xuetao Mu, Jie Zhu\",\"doi\":\"10.1002/mp.70019\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n \\n <section>\\n \\n <h3> Background</h3>\\n \\n <p>Prostate cancer (PCa) presents a significant global health challenge affecting men. Accurate segmentation and grading of PCa lesions in multiparametric Magnetic Resonance Imaging (mp-MRI) are essential for effective diagnosis and treatment planning.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Purpose</h3>\\n \\n <p>This study aimed to develop and validate an automated model for PCa lesion segmentation and Prostate Imaging Reporting and Data System (PI-RADS) grading in mp-MRI.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Methods</h3>\\n \\n <p>The lesion's perceived characteristics are strongly related to both imaging modalities and lesion locations. Therefore, we propose a Lesion-guided Selective Multi-modal Integration (LeSMI) module. This module incorporates two advanced mechanisms—Dynamic Modality Weighting (DMW) and Localized Lesion Attention (LLA)—to dynamically integrate crucial information across and within imaging modalities. Specifically, DMW operates on the mp-MRI inputs (T2-weighted (T2w) images, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps) to dynamically assign weights to each modality, thereby integrating complementary information and enhancing feature identification across different contexts. LLA, on the other hand, maintains spatial structure information within each modality for precise lesion localization. Inspired by clinical workflows, our framework is employed through a two-stage Prostate Cancer Segmentation and Grading (PCaSG) strategy, leveraging knowledge from segmentation to improve PI-RADS grading performance. We validated our method using two publicly available datasets, namely, Prostate158 and PI-CAI Challenge, to assess its advantages over other methods. For the Prostate158 dataset, we used the officially reported partition with 119 cases for training, 20 for validation, and 19 for testing. In contrast, the PI-CAI Challenge dataset, which lacks predefined splits, was randomly divided into 180 for training, 20 for validation, and 20 for testing. In addition to these dataset partitions, 5-fold cross-validation was conducted on both the Prostate158 and PI-CAI Challenge datasets to provide a more robust and comprehensive statistical evaluation of the model's performance.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Results</h3>\\n \\n <p>Evaluated on the Prostate158 and PI-CAI Challenge datasets, our method demonstrated superior performance, achieving a Dice Similarity Coefficient (DSC) of 51.30% and a lesion-level quadratic-weighted kappa score (<span></span><math>\\n <semantics>\\n <mrow>\\n <mi>Q</mi>\\n <mi>W</mi>\\n <msub>\\n <mi>K</mi>\\n <mi>l</mi>\\n </msub>\\n </mrow>\\n <annotation>$QW{{K}_l}$</annotation>\\n </semantics></math>) of 62.48% on Prostate158, and a DSC of 43.81% and a <span></span><math>\\n <semantics>\\n <mrow>\\n <mi>Q</mi>\\n <mi>W</mi>\\n <msub>\\n <mi>K</mi>\\n <mi>l</mi>\\n </msub>\\n </mrow>\\n <annotation>$QW{{K}_l}$</annotation>\\n </semantics></math> of 42.98% on PI-CAI. These results represent improvements of up to 2% in DSC and 17% in <span></span><math>\\n <semantics>\\n <mrow>\\n <mi>Q</mi>\\n <mi>W</mi>\\n <msub>\\n <mi>K</mi>\\n <mi>l</mi>\\n </msub>\\n </mrow>\\n <annotation>$QW{{K}_l}$</annotation>\\n </semantics></math> over current state-of-the-art models on Prostate158, and enhancements of 4% in DSC and 3% in <span></span><math>\\n <semantics>\\n <mrow>\\n <mi>Q</mi>\\n <mi>W</mi>\\n <msub>\\n <mi>K</mi>\\n <mi>l</mi>\\n </msub>\\n </mrow>\\n <annotation>$QW{{K}_l}$</annotation>\\n </semantics></math> on PI-CAI.</p>\\n </section>\\n \\n <section>\\n \\n <h3> Conclusion</h3>\\n \\n <p>The proposed model's robustness in handling diverse lesion presentations, combined with its reliable assessments, underscores its significant clinical applicability. Our model offers substantial advancements in both segmentation accuracy and PI-RADS grading, addressing the challenges of inter-reader variability and the need for high expertise in conventional diagnostic practices. This technological innovation holds promise for enhancing early, accurate detection and risk assessment in prostate cancer management, ultimately improving patient outcomes.</p>\\n </section>\\n </div>\",\"PeriodicalId\":18384,\"journal\":{\"name\":\"Medical physics\",\"volume\":\"52 10\",\"pages\":\"\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-09-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Medical physics\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://aapm.onlinelibrary.wiley.com/doi/10.1002/mp.70019\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://aapm.onlinelibrary.wiley.com/doi/10.1002/mp.70019","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
摘要
背景:前列腺癌(PCa)是影响男性的重大全球健康挑战。多参数磁共振成像(mp-MRI)对前列腺癌病变的准确分割和分级对于有效的诊断和治疗计划至关重要。目的:本研究旨在开发和验证mp-MRI中前列腺癌病变分割和前列腺成像报告和数据系统(PI-RADS)分级的自动化模型。方法:病变的感知特征与成像方式和病变部位密切相关。因此,我们提出了一种病变引导的选择性多模态集成(LeSMI)模块。该模块结合了两种先进的机制-动态模态加权(DMW)和局部病变注意(LLA)-在成像模态之间和内部动态整合关键信息。具体来说,DMW对mp-MRI输入(t2加权(T2w)图像、扩散加权成像(DWI)和表观扩散系数(ADC)图)进行操作,动态地为每个模态分配权重,从而整合互补信息,增强不同背景下的特征识别。另一方面,LLA在每个模态中保持空间结构信息,以精确定位病变。受临床工作流程的启发,我们的框架通过两阶段前列腺癌分割和分级(PCaSG)策略来使用,利用分割的知识来提高PI-RADS分级性能。我们使用两个公开可用的数据集(即prostat158和PI-CAI Challenge)验证了我们的方法,以评估其相对于其他方法的优势。对于prostat158数据集,我们使用官方报告的分区,其中有119个案例用于训练,20个用于验证,19个用于测试。相比之下,PI-CAI Challenge数据集缺乏预定义的分割,随机分为180个用于训练,20个用于验证,20个用于测试。除了这些数据集分区之外,还对prostatest158和PI-CAI Challenge数据集进行了5倍交叉验证,以提供对模型性能更稳健和全面的统计评估。结果:在prostat158和PI-CAI Challenge数据集上,我们的方法表现出了优异的性能,在prostat158上实现了51.30%的骰子相似系数(DSC)和62.48%的病变水平二次加权kappa评分(QW K l $QW{{K}_l}$),在PI-CAI上实现了43.81%的DSC和42.98%的QW K l $QW{{K}_l}$。这些结果表明,在前列腺158上,与目前最先进的模型相比,DSC提高了2%,qwkl $QW{{K}_l}$提高了17%,PI-CAI上DSC提高了4%,qwkl $QW{{K}_l}$提高了3%。结论:所提出的模型在处理不同病变表现方面的稳健性,加上其可靠的评估,强调了其重要的临床适用性。我们的模型在分割准确性和PI-RADS分级方面提供了实质性的进步,解决了阅读器间可变性的挑战和传统诊断实践中对高专业知识的需求。这项技术创新有望在前列腺癌管理中加强早期、准确的检测和风险评估,最终改善患者的预后。
Lesion-guided selective multi-modal integration for prostate cancer segmentation and PI-RADS grading in MP-MRI
Background
Prostate cancer (PCa) presents a significant global health challenge affecting men. Accurate segmentation and grading of PCa lesions in multiparametric Magnetic Resonance Imaging (mp-MRI) are essential for effective diagnosis and treatment planning.
Purpose
This study aimed to develop and validate an automated model for PCa lesion segmentation and Prostate Imaging Reporting and Data System (PI-RADS) grading in mp-MRI.
Methods
The lesion's perceived characteristics are strongly related to both imaging modalities and lesion locations. Therefore, we propose a Lesion-guided Selective Multi-modal Integration (LeSMI) module. This module incorporates two advanced mechanisms—Dynamic Modality Weighting (DMW) and Localized Lesion Attention (LLA)—to dynamically integrate crucial information across and within imaging modalities. Specifically, DMW operates on the mp-MRI inputs (T2-weighted (T2w) images, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps) to dynamically assign weights to each modality, thereby integrating complementary information and enhancing feature identification across different contexts. LLA, on the other hand, maintains spatial structure information within each modality for precise lesion localization. Inspired by clinical workflows, our framework is employed through a two-stage Prostate Cancer Segmentation and Grading (PCaSG) strategy, leveraging knowledge from segmentation to improve PI-RADS grading performance. We validated our method using two publicly available datasets, namely, Prostate158 and PI-CAI Challenge, to assess its advantages over other methods. For the Prostate158 dataset, we used the officially reported partition with 119 cases for training, 20 for validation, and 19 for testing. In contrast, the PI-CAI Challenge dataset, which lacks predefined splits, was randomly divided into 180 for training, 20 for validation, and 20 for testing. In addition to these dataset partitions, 5-fold cross-validation was conducted on both the Prostate158 and PI-CAI Challenge datasets to provide a more robust and comprehensive statistical evaluation of the model's performance.
Results
Evaluated on the Prostate158 and PI-CAI Challenge datasets, our method demonstrated superior performance, achieving a Dice Similarity Coefficient (DSC) of 51.30% and a lesion-level quadratic-weighted kappa score () of 62.48% on Prostate158, and a DSC of 43.81% and a of 42.98% on PI-CAI. These results represent improvements of up to 2% in DSC and 17% in over current state-of-the-art models on Prostate158, and enhancements of 4% in DSC and 3% in on PI-CAI.
Conclusion
The proposed model's robustness in handling diverse lesion presentations, combined with its reliable assessments, underscores its significant clinical applicability. Our model offers substantial advancements in both segmentation accuracy and PI-RADS grading, addressing the challenges of inter-reader variability and the need for high expertise in conventional diagnostic practices. This technological innovation holds promise for enhancing early, accurate detection and risk assessment in prostate cancer management, ultimately improving patient outcomes.
期刊介绍:
Medical Physics publishes original, high impact physics, imaging science, and engineering research that advances patient diagnosis and therapy through contributions in 1) Basic science developments with high potential for clinical translation 2) Clinical applications of cutting edge engineering and physics innovations 3) Broadly applicable and innovative clinical physics developments
Medical Physics is a journal of global scope and reach. By publishing in Medical Physics your research will reach an international, multidisciplinary audience including practicing medical physicists as well as physics- and engineering based translational scientists. We work closely with authors of promising articles to improve their quality.