分享:
分享到微信朋友圈
X
综述
直肠癌淋巴结转移的临床与MRI研究进展
李帝良 万丽娟 张红梅

Cite this article as: LI D L, WAN L J, ZHANG H M. Advances in clinical and MRI research on lymph node metastasis in rectal cancer[J]. Chin J Magn Reson Imaging, 2025, 16(7): 185-191.本文引用格式:李帝良, 万丽娟, 张红梅. 直肠癌淋巴结转移的临床与MRI研究进展[J]. 磁共振成像, 2025, 16(7): 185-191. DOI:10.12015/issn.1674-8034.2025.07.030.


[摘要] 直肠癌是我国最常见的恶性肿瘤之一,其发病率和死亡率均呈逐年上升趋势。淋巴结转移(lymph node metastasis, LNM)作为直肠癌转移的主要方式之一,与患者的分期和预后密切相关,因此准确评估淋巴结状态对于患者的诊疗至关重要。目前美国国立综合癌症网络指南推荐直肠癌患者行MRI检查以评估淋巴结状态,但常规MRI形态学特征诊断LNM的准确性仍有待提高,尚不能满足临床对直肠癌精准诊疗的需求。功能性MRI技术及人工智能有望在直肠癌淋巴结评估方面展现较好的预测价值,然而尚缺乏全面总结二者新近研究的综述。因此,本文就直肠癌LNM的途径、常规形态及功能性MRI技术,以及人工智能在直肠癌淋巴结评估方面近年来的进展进行综述,以期帮助读者了解目前评估直肠癌淋巴结状态的现状以及未来发展方向。笔者认为,未来研究可聚焦于挖掘新的形态学特征,进一步优化功能性MRI技术和人工智能算法,规范化扫描参数和诊断模型,并在建立多中心、大样本的直肠癌MRI数据库后进行验证,促进各种诊断工具的临床转化,以辅助医生精准诊断直肠癌LNM与制订个体化治疗方案。
[Abstract] Rectal cancer is one of the most common malignant tumors in China, with both its incidence and mortality rates demonstrating a consistent upward trend in recent years. Lymph node metastasis (LNM), as one of the primary metastatic pathways in rectal cancer, is closely associated with disease staging and patient prognosis. Therefore, accurate assessment of lymph node status is critical for guiding clinical management. The current National Comprehensive Cancer Network guidelines recommend MRI for assessing lymph node status in patients with rectal cancer. However, the diagnostic accuracy of conventional MRI morphological features in identifying LNM remains suboptimal and insufficient to meet clinical demands for precision diagnosis and treatment of rectal cancer. Emerging functional MRI techniques and artificial intelligence demonstrate considerable potential in enhancing predictive capabilities for lymph node evaluation, yet a comprehensive review of recent advances in these fields is still lacking. This review systematically examines the metastatic pathways of lymph nodes, conventional and functional MRI techniques, and artificial intelligence applications in lymph node assessment in rectal cancer. It aims to provide readers with insights into current assessment approaches and future directions. We suggest that future studies should prioritize the discovery of novel morphological biomarkers, refinement of functional MRI techniques and artificial intelligence algorithms, standardization of imaging protocols and diagnostic models, and validation through multi-center studies with large-scale rectal cancer MRI databases. These advancements may accelerate the clinical translation of diagnostic tools, ultimately aiding clinicians in achieving precise diagnosis of LNM and tailoring personalized therapeutic strategies for rectal cancer patients.
[关键词] 直肠癌;淋巴结转移;磁共振成像;临床诊疗;影像研究
[Keywords] rectal cancer;lymph node metastasis;magnetic resonance imaging;clinical management;imaging research

李帝良    万丽娟    张红梅 *  

国家癌症中心/国家肿瘤临床医学研究中心/中国医学科学院北京协和医学院肿瘤医院影像诊断科,北京 100021

通信作者:张红梅,E-mail: 13581968865@163.com

作者贡献声明:张红梅确定本综述的方向并参与构思和设计,为稿件修改提供意见,获得中国医学科学院医学与健康科技创新工程项目及北京协和医学院课程思政教改项目的资助;李帝良检索与综述方向相关的文献,分析并解释文献的内容,进行稿件的起草与撰写工作;万丽娟参与综述的构思与设计,对稿件的重要内容进行了修改,获得国家自然科学基金及北京协和医学院中央高校基本科研项目的资助;全体作者都同意发表最后的修改稿,同意对本研究的所有方面负责,确保本研究的准确性和诚信。


基金项目: 国家自然科学基金项目 82402229 中国医学科学院医学与健康科技创新工程项目 2024-I2M-C&T-A-007 北京协和医学院中央高校基本科研项目 3332024050 北京协和医学院课程思政教改项目 2024KCSZ019
收稿日期:2025-04-03
接受日期:2025-06-05
中图分类号:R445.2  R735.37 
文献标识码:A
DOI: 10.12015/issn.1674-8034.2025.07.030
本文引用格式:李帝良, 万丽娟, 张红梅. 直肠癌淋巴结转移的临床与MRI研究进展[J]. 磁共振成像, 2025, 16(7): 185-191. DOI:10.12015/issn.1674-8034.2025.07.030.

0 引言

       国家癌症中心发布最新的全国癌症统计数据显示,结直肠癌全国每年新发病例数高达51.71万,也是第四大癌症死亡原因[1]。淋巴结转移(lymph node metastasis, LNM)是直肠癌的最重要转移方式之一,与患者治疗方案的选择与预后密切相关[2, 3]。对于无LNM的早期直肠癌患者(cT1~2,N0),可选择损伤较小的局部手术切除,且预后良好,当发生LNM时,患者5年相对生存率从96%降低到78%[4],治疗方案则需从直接手术变更为新辅助放化疗(neoadjuvant chemoradiotherapy, nCRT)后手术切除[5]。对于nCRT后达到临床完全缓解的患者可考虑实行等待观察策略,以减少不必要的手术创伤和术后并发症,但临床完全缓解的条件之一为区域淋巴结内无肿瘤残留证据[6]。对于部分拒绝或不耐受nCRT的T3~4期直肠癌患者,N分期的情况将决定其是否需行扩大淋巴结清扫手术。此外,大量研究表明侧方淋巴结受累也与较差的总生存期和无转移生存期相关[7, 8, 9],在实施nCRT+全直肠系膜切除术(total mesorectal excision, TME)的基础上附加侧方淋巴结清扫,能有效降低患者的侧方局部复发率(19.5%~5.7%)[10]。因此,临床工作中我们需要准确地评估不同阶段患者的系膜内及侧方淋巴结状态,以便临床选择更为个体化的诊疗方案,使患者更大程度受益。

       目前,常规MRI是临床工作中无创预测淋巴结状态的重要手段,根据形态学标准预测淋巴结状态依赖于影像科医生的主观经验,其敏感度仅为58%,未能满足精准医疗的需求[11]。随着功能性MRI技术的优化和人工智能的应用,近年来影像学在直肠癌淋巴结状态预测方面展现出较好的预测价值,然而尚缺乏全面总结二者进展的新近综述。因此,本文梳理了直肠癌LNM的途径与分期,总结了近年来从淋巴结形态学改变、功能改变及人工智能应用方面检测直肠癌LNM的研究,以期帮助读者了解该领域的最新进展,为未来淋巴结评估提供方向参考。

1 直肠癌LNM途径与分期

       LNM被视为直肠癌远处转移的关键,其与肿瘤复发和生存率降低密切相关[12, 13]。直肠癌LNM途径主要包括上行、下行和侧方转移三个途径,少数情况下可发生跳跃性转移。上行转移沿直肠上动脉走行,并最终引流至肠系膜下动脉根部淋巴结,为最常见的转移途径。任何位置的直肠癌均可发生上行转移。下行转移主要见于齿状线以下的肿瘤,引流至髂总动脉周围淋巴结[14, 15]。侧方转移主要包括三种方式:(1)向前外侧经由闭孔动脉等转移至髂外动脉内侧缘的淋巴结;(2)向后沿骶正中动脉至骶岬、腹主动脉分叉处等部位的淋巴结;(3)向外侧沿直肠中动脉至闭孔、髂外、髂总等部位的淋巴结[15]。侧方转移是腹膜反折以下直肠癌的主要转移途径之一,约占41.8%,相比之下,位于腹膜反折以上的直肠癌发生侧方转移的几率仅为1.6%~3.6%[16]。正确认识直肠癌LNM途径有助于临床实践中的影像学评估及指导后续手术清扫范围。

       根据第八版美国癌症联合委员会(American Joint Committee on Cancer, AJCC)指南的TNM分期系统[17],直肠癌区域淋巴结分期为:N0(无区域LNM)、N1(1~3枚LNM)和N2(4枚或以上区域LNM)。直肠系膜内淋巴结可在常规的TME中被清除,是广泛认定的区域淋巴结,但侧方淋巴结的分区却存在争议[18]。第八版AJCC指南中并未将髂外淋巴结归类为区域淋巴结。第九版日本大肠癌规约则将髂内、髂总、闭孔、髂外、骶外侧、骶正中及腹主动脉分叉处淋巴结均视为区域淋巴结[19]。我国直肠癌侧方LNM诊疗专家共识(2024版)采用髂内、闭孔、髂外、髂总的区域淋巴结分类方法[20]。基于此,推荐在日常影像评估工作中可注明可疑侧方淋巴结的位置以辅助临床制订更加合理的治疗方案。

2 影像学对直肠癌LNM的评价

2.1 形态学评价

       美国国立综合癌症网络指南推荐直肠癌患者行MRI检查以评估淋巴结状态。淋巴结短径大小是评估LNM的重要指标,欧洲胃肠与腹部放射学会(European Society of Gastrointestinal and Abdominal Radiology, ESGAR)共识建议将初诊短径≥9 mm、新辅助治疗后短径≥5 mm的淋巴结视为转移[21],但良恶性淋巴结大小之间存在广泛重叠[22]。例如,细菌或病毒感染、肿瘤刺激的免疫反应等均可引起淋巴结非转移性增大,而早期LNM并不表现为淋巴结大小的改变。一项研究通过对10 473枚直肠癌淋巴结进行短径大小分析,发现28.4%(95/334)的转移淋巴结短径不超过3 mm[23]。由此可见,单纯依靠短径大小鉴别良恶性淋巴结的方法并不十分可靠,难以满足精准医疗时代的需求。ESGAR共识提出可结合淋巴结的形态学特征(如形状、边缘与内部信号)用于鉴别良恶性淋巴结[21],后续的荟萃分析证明相比于单纯的短径大小,联合形态学指标可提高转移性淋巴结的诊断效能,但敏感度仅为54%[24]

       为了进一步提高淋巴结评估准确性,一些新的形态学特征被陆续发现。ZHANG等[25]于2017年提出使用化学位移效应(chemical shift effect, CSE)鉴别良恶性淋巴结,他们通过将MRI图像上的淋巴结与术后病理大切片的淋巴结进行一一对照,发现71.4%(182/255)的良性淋巴结存在光滑且连续的CSE,而80.0%(28/35)的恶性淋巴结不存在CSE,差异具有统计学意义。与淋巴结的边缘、内部信号等指标相比,CSE的诊断效能及观察者间一致性得到了较明显的提高。但CSE的临床应用价值仍需多中心、大样本的前瞻性研究进一步验证。此外,也有学者定义了106例直肠癌患者对比增强T1加权脂肪抑制序列上的淋巴结内部低信号核心为“牛油果征”,其在诊断区域淋巴结的曲线下面积(area under the curve, AUC)为0.87[26]。LI等[27]的研究表明当MRI图像上出现淋巴结被膜外侵犯时意味着为转移淋巴结,但遗憾的是,超过一半的转移淋巴结并不出现这一征象。因此,未来还需要更多的临床实践总结和探索以提高淋巴结状态评估准确性。

       另外,由于侧方淋巴结解剖位置等的特殊性,既往研究多集中于直肠系膜内淋巴结的评估,针对侧方淋巴结评估的影像研究相对较少。目前,临床实践中普遍采用侧方淋巴结短径大小作为判定其是否发生转移的主要依据[28, 29]。一项纳入741例患者的多国家、多中心研究建议,对于初诊患者,将短径≥7 mm的淋巴结定义为转移,对于接受新辅助治疗的患者,则应将髂内淋巴结短径≥4 mm、闭孔淋巴结短径≥6 mm作为诊断阈值[30]。但用于判定侧方LNM的短径大小的截断值尚存在争议,亦有学者将5 mm作为截断值进行研究[31, 32]。ESGAR共识提议侧方淋巴结评估可参考系膜内淋巴结评估标准,结合短径与形态学特征进行综合评估[21]。一项多中心研究发现,除短径大小外,壁外血管侵犯、系膜内癌结节、原发灶含黏液等非侧方淋巴结自身特征同样为其发生转移的独立预测因子[33]。ABE等[34]证明联合MRI评估的壁外血管侵犯可提高侧方LNM诊断准确性。虽然先前的研究已经提出一些评估侧方淋巴结的影像学方法,但这些方法仍未达成共识,还需进一步的研究提供更加可靠的循证医学证据以制定统一的评价标准,进而推广应用。

2.2 功能性成像技术

       当淋巴结发生转移时,其在病理生理学上的改变要早于形态学改变,单纯依靠常规MRI序列难以实现早期淋巴结微转移的精准识别。近年来,功能性MRI技术被逐步应用于直肠癌LNM的评估,其中主要包括扩散加权成像(diffusion weighted imaging, DWI)、体素内不相干运动DWI(intravoxel incoherent motion-DWI, IVIM-DWI)、动态对比增强MRI(dynamic contrast enhancement-MRI, DCE-MRI)及正电子发射断层显像-MRI(position emission tomography-MRI, PET-MRI)等。

2.2.1 DWI

       DWI是一种基于水分子布朗运动的非侵入性功能成像技术,而表观扩散系数(apparent diffusion coefficient, ADC)作为DWI的定量指标可更加直观地解释病变信息[35]。研究表明,转移性淋巴结由于细胞密度增高、细胞外间隙变窄,通常较良性淋巴结具有更高的DWI信号和更低的ADC值[36]。然而,不同的研究中对b值的选择并不一致,考虑到图像信噪比、伪影、解剖结构可识别性等指标,目前多数研究的b值选择集中在1000 s/mm2[37, 38]。近期一项研究提出了超高b值DWIb2000的对比噪声比优于DWIb1000和DWIb3000[39],但其用于淋巴结的评估还需要进一步的研究证实。上述研究均通过测量淋巴结的ADC值评估淋巴结状态,XU等[40]的研究发现基于肿瘤原发灶的ADC值也是LNM的有效预测因子。不过,笔者发现,目前不同的研究在b值选取、ADC阈值界定等方面尚未达到统一标准,因此后续的研究应当致力于制定标准化方案来实现DWI技术在临床实践中的推广[41, 42]

       相较于使用单指数模型获得的ADC值,IVIM-DWI是依据双指数模型的多b值DWI,其能够区分单纯水分子扩散运动和组织微循环灌注,弥补了传统DWI的局限性[43]。一项研究发现,相比于非转移淋巴结,转移淋巴结具有更高的纯扩散系数(D)值和更低的灌注分数(f)值[44]。在另一项研究中[45]虽然转移性淋巴结表现出同样更高的D值,但f值在两组之间并不存在显著差异。另外,ZHOU等[46]指出LNM组的f值高于非转移组,但两组的D值和伪扩散系数(D*)值之间差异无统计学意义。由此可见,IVIM参数在LNM鉴别中仍然缺乏稳定性[47],还需要进一步开展研究探索其临床实用价值,增加结果稳定性[41, 42]

2.2.2 DCE-MRI

       DCE-MRI是一种通过在对比剂给药后采集感兴趣器官的多个连续T1WI来评估血管分布的技术,可用于观测肿瘤血流动力学过程和新生血管生成[48]。常见的DCE-MRI参数包括容积转移常数(volumn transfer constant, Ktrans)、速率常数(rate constant, Kep)和血管外细胞外间隙容积分数(extracellular-extravascular volumn fraction, Ve)。YANG等[49]发现,在短径<5 mm的淋巴结中,转移淋巴结表现出较低的Ktrans值,但Kep和Ve值在两组之间差异无统计学意义。除了评估淋巴结本身之外,ZHOU等[50]的研究表明肿瘤原发灶的DCE-MRI参数也是LNM的有效预测因子,转移组的Ktrans和Kep值高于非转移组,但Ve值在两组之间差异无统计学意义。另外,也有研究支持LNM组患者的Ktrans值高于非转移组[51]。由此可见,利用Ktrans、Kep和Ve等指标评估直肠癌淋巴结状态仍存在争议,且存在无统一截断值、扫描时间过长、扫描技术规范不一致等问题,尚需后续大量研究对此进行优化。

2.2.3 PET-MRI

       受限于计算机断层成像(computed tomography, CT)对比分辨力不足,PET-MRI结合了PET的分子成像优势和MRI的软组织高分辨力,有望成为PET-CT和MRI的替代方案,其在准确评估LNM方面具备极大的潜力[52]。研究表明,相较于单独的MRI,PET-MRI能够改善对患者淋巴结状态的评估,诊断准确性从58.0%~76.1%提升至78.3%~79.0%[53]。既往研究的显像剂多采用18F标记的氟代脱氧葡萄糖(18F-fluorodeoxyglucose, 18F-FDG),其能被葡萄糖代谢高的细胞吸收,可以反映肿瘤的代谢活性[54]。然而,18F-FDG在肠道也会发生生理性摄取,可能掩盖疾病部位的信息而影响观察,因此近年来出现了一些新型显像剂来弥补传统显像剂的不足,如68Ga标记成纤维细胞活化蛋白抑制剂(68Ga-fibroblast activation protein inhibitor, 68Ga-FAPI)[52]68Ga-FAPI/PET能揭示肿瘤微环境,包括基质、成纤维细胞活性等,和18F-FDG/PET提供了互补的生物学信息[54]。目前已有少量研究表明,与FDG-PET相比,FAPI-PET在检测淋巴结受累方面的敏感度和特异度更高,但由于样本量小等问题,尚需更多的研究进一步证实FAPI-PET/MRI在直肠癌LNM的效用[55, 56, 57]。同时,FAPI/FDG双示踪显像在临床中亦有应用。然而PET-MRI存在尚无统一的最大标准摄取阈值、检查时间长、检查费用昂贵、新型显像剂的安全性等问题,且PET-MRI一体化扫描仪暂未在国内普及。

2.2.4 其他

       酰胺质子转移加权(amide proton transfer- weighted, APTw)成像是化学交换饱和转移的内源性分子成像技术的一种,可用于检测内源性游离蛋白和多肽分子的含量,恶性肿瘤往往表现出更高的APTw信号强度,已被成功应用于肿瘤代谢、复发、治疗反应等方面[58, 59]。WEI等[60]纳入了125例直肠癌患者,在T2WI和APTw图像上勾画了肿瘤的感兴趣体积,临床影像组学模型结合逻辑回归算法在预测LNM上得到了最佳性能,AUC高达0.929,准确率为88.9%,表明APTw图像在识别转移性淋巴结方面的潜能。另外也有研究团队发现APTw信号强度与LNM之间无相关性,分析其原因为淋巴结评估受炎症、肿瘤特征等各种因素的影响[61]。合成MRI(synthetic MRI, SyMRI)是一种新型的磁共振定量弛豫技术,其能够通过单次短时间的扫描获取如T1值、T2值、质子密度等量化参数,可以反映基本的组织特性[62]。ZHAO等[63]对94例直肠癌患者进行SyMRI扫描,结果显示LNM组的T1和T2值显著低于非转移组,AUC分别为0.883和0.821,均优于放射科医生的主观评价。总之,尽管目前APTw成像、SyMRI等功能序列应用于预测直肠癌淋巴结状态的研究较少,但已在非小细胞肺癌、宫颈癌、鼻咽癌等其他部位肿瘤中陆续得到验证[64, 65, 66],因此,其在未来研究中有望助力直肠癌淋巴结评估。

       钆基对比剂是目前临床实践中使用最广泛的对比剂,考虑到其非特异性积聚而无法区分良恶性淋巴结,有团队研发了单细胞趋化蛋白1-钆胶束,用于通过分子靶向c-c趋化因子受体2检测LNM和复发,并在小鼠实验中验证了该对比剂在MRI上评估淋巴结状态的价值[67]。与钆基对比剂不同,铁基对比剂具备无肾毒性、用量更小等优点,有望成为下一代MRI对比剂[68]。超微超顺磁性氧化铁(ultrasmall superparamagnetic iron oxide, USPIO)是一种通过静脉系统给药的铁基对比剂,可被正常淋巴结组织摄取导致T2WI信号降低,而转移性淋巴结的USPIO摄取受到抑制呈相对T2WI高信号[69]。STIJNS等[70]对10例患者进行USPIO增强MRI扫描,结果显示USPIO增强MRI上信号减弱的淋巴结常为正常淋巴结,并且对20枚表现为高信号的淋巴结进行病理切片复查也并未发现癌细胞转移。另外,锰基对比剂目前也在临床开发中,在小鼠实验中,正常淋巴结在注射锰基对比剂后出现均匀强化,而转移性淋巴结由于被肿瘤细胞占据,巨噬细胞分布不均匀而表现为不均匀强化[71]。由此可见,新型对比剂的出现拓展了增强MRI在淋巴结评估的前景,未来需要在确保安全性的前提下于临床试验中得到进一步实践。

3 人工智能

3.1 影像组学

       传统的形态学评估基于放射医师的主观评估,受经验影响较大,而功能性MRI技术临床应用价值还有待考究,临床迫切需要新的技术突破这些局限。影像组学通过高通量提取医学图像中肉眼无法识别的定量特征,通过人工智能算法进一步分析构建模型,近年来影像组学已经被广泛应用于预测直肠癌LNM [72]。ZHUANG等[73]在斜轴位T2WI上勾画了淋巴结最大横截面的感兴趣区(region of interest, ROI),通过特征筛选与降维获得8个影像组学特征用于构建淋巴结预测模型,发现影像组学特征在联合临床特征后获得了最佳的LNM预测性能,在训练集和验证集中AUC值分别为0.818和0.922。此外,也有研究开展基于肿瘤原发灶的特征提取,从而避免由于淋巴结过小导致的ROI勾画困难[74]。针对接受nCRT后患者的淋巴结状态评估,有学者在nCRT前后T2WI和DWI上勾画肿瘤原发灶的ROI以构建多序列融合模型,发现与其他模型相比,融合模型在预测nCRT后LNM方面表现出最佳的诊断性能(AUC值为0.831)[75]。除了上述对淋巴结和原发灶特征提取之外,瘤周微环境对LNM的潜在预测价值也值得我们关注。LIU等[76]构建了基于T2WI和DWI的多区域影像组学预测模型,结果显示,在训练集和验证集中,基于单一肿瘤原发灶特征构建的模型的AUC值分别为0.786和0.702,在联合直肠系膜特征后模型的AUC值分别提升至0.834和0.736。

       另外,也有少数针对侧方淋巴结的影像组学研究。相较于之前仅针对侧方淋巴结自身特征的研究,ZHAO等[77]的研究同时提取肿瘤原发灶与侧方淋巴结的影像组学特征,并联合临床危险因素如环周切缘状态、侧方淋巴结短径大小等构建了临床-影像组学融合模型,其在测试集中评估侧方LNM的AUC值为0.836。尽管影像组学模型为改善LNM预测提供了技术参考,但仍存在诊断效能不稳定、模型泛化能力不足、需手动勾画ROI等问题,需要后续进一步解决。

3.2 深度学习

       深度学习是一种新兴的机器学习技术,包括卷积神经网络(convolutional neural network, CNN)、循环神经网络、图神经网络等模型,相较于传统的影像组学,深度学习模型可以通过自动神经网络提取和选择高位特征,减少了手动预处理的步骤[78, 79]。研究表明,其在诊断直肠癌LNM方面比影像组学模型更准确,或在二者融合后进一步提升模型的性能[80, 81, 82]

       一项研究[83]通过分析来自293名直肠癌患者的5789枚淋巴结的多参数MRI,构建了基于深度学习框架Mask R-CNN的全自动淋巴结检测与分割模型。全自动模型与放射医师识别每例患者的淋巴结所需的时间分别约1.37秒和200秒。由此可见,基于深度学习的模型在缩短淋巴结评估时间方面极具应用价值。然而,该研究并未纳入短径小于3 mm的淋巴结,也并未对淋巴结的良恶性进行鉴别。另一项研究[84]收集了28 080张有LNM的MRI图像用于训练快速区域的CNN(faster region-based CNN, Faster R-CNN)模型,在检测淋巴结位置的同时判断转移性淋巴结的数目并对其进行分期,结果显示该模型在外部验证集中AUC值高达0.912。不足的是,该研究在训练模型时采用的是放射医师主观评估作为结果输入而非病理金标准。在此基础上,该团队进一步纳入了由病理学家诊断的转移性淋巴结数目,在诊断淋巴结数目方面,放射科医生、病理科医生和Faster R-CNN模型中任意两者之间都存在显著相关性,其中放射科医生与Faster R-CNN模型的相关性系数高达0.912。另外,相较于放射科医生,Faster R-CNN的诊断更符合病理学诊断(r分别为0.448、0.134),但准确性仍有待提高。

       考虑到在回顾性研究中将MRI上检测到的淋巴结与病理上淋巴结匹配的困难,XIA等[85]基于患者MRI上淋巴结本身的特征和临床病理信息开发了弱监督模型,该模型能够挖掘常规MRI数据与患者水平病理信息之间的关联,识别可疑转移性淋巴结的位置和数量。在弱监督模型辅助之下,低年资医生(AUC:0.69~0.80)和高年资医生(AUC:0.79~0.88)的诊断性能得到进一步提升。此外,也有学者[86]基于肿瘤原发灶MRI图像构建了深度学习预测模型,发现深度学习模型具有优于放射医师主观评估的直肠癌LNM诊断效能(AUC:0.79 vs. 0.54)。在侧方淋巴结评估方面,OZAKI等[87]基于共计3547枚侧方淋巴结的MRI图像开发了深度学习模型,在验证集中模型的AUC值为0.870。虽然深度学习模型展现巨大的临床应用前景,但同时也面临不少问题,如大多数研究缺乏多中心的外部验证导致模型泛化能力差、各中心建模所用的仪器扫描参数不一、模型可解释性差等,尚需更深入的探索促进其临床转化。

4 总结与展望

       总之,直肠癌LNM与患者的治疗决策和疾病预后密切相关。了解LNM的途径有助于影像科医生全面地评估各个位置的淋巴结,目前临床工作中常用的影像学检查为常规MRI,然而其诊断淋巴结良恶性的准确性有待提高。功能性MRI技术和人工智能在此方面展现出广阔的前景,未来的研究需致力于在多中心、大样本的前瞻队列中进一步验证新技术的临床使用稳定性,同时制定标准化的检查方案,使患者更大程度受益。

[1]
HAN B F, ZHENG R S, ZENG H M, et al. Cancer incidence and mortality in China, 2022[J]. J Natl Cancer Cent, 2024, 4(1): 47-53. DOI: 10.1016/j.jncc.2024.01.006.
[2]
PENG W, QIAO H M, MO L F, et al. Progress in the diagnosis of lymph node metastasis in rectal cancer: A review[J/OL]. Front Oncol, 2023, 13: 1167289 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10374255/. DOI: 10.3389/fonc.2023.1167289.
[3]
BOGVERADZE N, SNAEBJORNSSON P, GROTENHUIS B A, et al. MRI anatomy of the rectum: key concepts important for rectal cancer staging and treatment planning[J/OL]. Insights Imaging, 2023, 14(1): 13 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC9849549/. DOI: 10.1186/s13244-022-01348-8.
[4]
QADERI S M, DICKMAN P W, DE WILT J H W, et al. Conditional survival and cure of patients with colon or rectal cancer: a population-based study[J]. J Natl Compr Canc Netw, 2020, 18(9): 1230-1237. DOI: 10.6004/jnccn.2020.7568.
[5]
WO J Y, ANKER C J, ASHMAN J B, et al. Radiation therapy for rectal cancer: executive summary of an ASTRO clinical practice guideline[J]. Pract Radiat Oncol, 2021, 11(1): 13-25. DOI: 10.1016/j.prro.2020.08.004.
[6]
中国直肠癌新辅助治疗后等待观察数据库研究协作组, 中华医学会外科学分会结直肠外科学组, 中国医师协会结直肠肿瘤医师专业委员会, 等. 直肠癌新辅助治疗后等待观察策略中国专家共识(2024版)[J]. 中华胃肠外科杂志, 2024(4): 301-315. DOI: 10.3760/cma.j.cn441530-20240227-00075.
Chinese Watch & Wait Database Research Cooperation Group (CWWD), Colorectal Surgery Group of the Surgery Branch in the Chinese Medical Association (CMA), Colorectal Cancer Physician Specialty Committee of Chinese Medical Doctor Association, et al. Chinese expert consensus on the watch and wait strategy in rectal cancer patients after neoadjuvant treatment(2024 version)[J]. Chin J Gastrointest Surg, 2024(4): 301-315. DOI: 10.3760/cma.j.cn441530-20240227-00075.
[7]
NOGUCHI T, AKIYOSHI T, SAKAMOTO T, et al. Features of lateral pelvic lymph nodes associated with pathological involvement after total neoadjuvant therapy in patients undergoing lateral pelvic lymph node dissection[J]. Dis Colon Rectum, 2025, 68(3): 316-326. DOI: 10.1097/DCR.0000000000003590.
[8]
CHEN L N, JIANG J, JIANG L M, et al. Post-hoc analysis of clinicopathological factors affecting lateral lymph node metastasis based on STELLAR study for rectal cancer[J/OL]. Radiother Oncol, 2024, 200: 110512 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/39216825/. DOI: 10.1016/j.radonc.2024.110512.
[9]
LEE T, HORVAT N, GOLLUB M J, et al. Prognostic value of lateral lymph node metastasis in pretreatment MRI for rectal cancer in patients undergoing neoadjuvant chemoradiation followed by surgical resection without lateral lymph node dissection: A systemic review and meta-analysis[J/OL]. Eur J Radiol, 2024, 178: 111601 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/38972182/. DOI: 10.1016/j.ejrad.2024.111601.
[10]
OGURA A, KONISHI T, CUNNINGHAM C, et al. Neoadjuvant (chemo)radiotherapy with total mesorectal excision only is not sufficient to prevent lateral local recurrence in enlarged nodes: results of the multicenter lateral node study of patients with low cT3/4 rectal cancer[J]. J Clin Oncol, 2019, 37(1): 33-43. DOI: 10.1200/JCO.18.00032.
[11]
NIU Y, YU S Q, CHEN P, et al. Diagnostic performance of Node-RADS score for mesorectal lymph node metastasis in rectal cancer[J]. Abdom Radiol (NY), 2025, 50(1): 38-48. DOI: 10.1007/s00261-024-04497-0.
[12]
BROUWER N P M, OGUZ ERDOGAN A S, VAN VLIET S, et al. Unraveling the routes to distant metastases in colorectal cancer: Tumor deposits and lymph node metastases as the gateway[J]. Cancer Commun (Lond), 2024, 44(10): 1209-1213. DOI: 10.1002/cac2.12598.
[13]
JI H R, HU C, YANG X H, et al. Lymph node metastasis in cancer progression: molecular mechanisms, clinical significance and therapeutic interventions[J/OL]. Signal Transduct Target Ther, 2023, 8(1): 367 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10522642/. DOI: 10.1038/s41392-023-01576-4.
[14]
BATES D D B, HOMSI M E, CHANG K J, et al. MRI for rectal cancer: staging, mrCRM, EMVI, lymph node staging and post-treatment response[J]. Clin Colorectal Cancer, 2022, 21(1): 10-18. DOI: 10.1016/j.clcc.2021.10.007.
[15]
王治杰, 刘骞. 直肠和乙状结肠癌区域淋巴结清扫的规范化开展[J]. 中华胃肠外科杂志, 2022(4): 309-314. DOI: 10.3760/cma.j.cn441530-20220104-00007.
WANG Z J, LIU Q. Standardization in performing regional lymph node dissection for rectum and sigmoid colon cancer[J]. Chin J Gastrointest Surg, 2022(4): 309-314. DOI: 10.3760/cma.j.cn441530-20220104-00007.
[16]
KAUR H, ERNST R D, RAUCH G M, et al. Nodal drainage pathways in primary rectal cancer: anatomy of regional and distant nodal spread[J]. Abdom Radiol (NY), 2019, 44(11): 3527-3535. DOI: 10.1007/s00261-019-02094-0.
[17]
BRIERLEY J, GOSPODAROWICZ M K, WITTRKIND C. TNM classification of malignant tumours[M]. 8th ed. Chichester, West Sussex, UK & Hoboken, NJ: John Wiley & Sons, Inc, 2017.
[18]
张无忌, 张晓燕, 孙应实. 低位直肠癌侧方淋巴结转移诊断和治疗的历史、争议与进展[J]. 中华放射学杂志, 2024, 58(5): 474-478. DOI: 10.3760/cma.j.cn112149-20231017-00299.
ZHANG W J, ZHANG X Y, SUN Y S. History, controversies and advancements in the diagnosis and treatment of lateral lymph nodemetastasisinlowrectalcancer[J]. Chin J Radiol, 2024, 58(5): 474-478. DOI: 10.3760/cma.j.cn112149-20231017-00299.
[19]
Japanese Society for Cancer of the Colon and Rectum. Japanese classification of colorectal, appendiceal, and anal carcinoma: the 3d English edition [secondary publication[J]. J Anus Rectum Colon, 2019, 3(4): 175-195. DOI: 10.23922/jarc.2019-018.
[20]
中国医师协会内镜医师分会腹腔镜外科专业委员会, 中国医师协会结直肠肿瘤专业委员会腹腔镜专业委员会, 中华医学会外科学分会结直肠外科学组, 等. 中国直肠癌侧方淋巴结转移诊疗专家共识(2024版)[J]. 中华胃肠外科杂志, 2024(1): 1-14. DOI: 10.3760/cma.j.cn441530-20231212-00211.
Laparoscopic Surgery Committee of the Endoscopist Branch in the Chinese Medical Doctor Association, Laparoscopic Surgery Committee of Colorectal Cancer Committee of Chinese Medical Doctor Association, Colorectal Surgery Group of the Surgery Branch in the Chinese Medical Association, et al. Chinese expert consensus on the diagnosis and treatment for lateral lymph node metastasis of rectal cancer (2024 edition)[J]. Chin J Gastrointest Surg, 2024(1): 1-14. DOI: 10.3760/cma.j.cn441530-20231212-00211.
[21]
BEETS-TAN R G H, LAMBREGTS D M J, MAAS M, et al. Magnetic resonance imaging for clinical management of rectal cancer: Updated recommendations from the 2016 European Society of Gastrointestinal and Abdominal Radiology (ESGAR) consensus meeting[J]. Eur Radiol, 2018, 28(4): 1465-1475. DOI: 10.1007/s00330-017-5026-2.
[22]
ZHANG Z W, CHEN Y, WEN Z Q, et al. MRI for nodal restaging after neoadjuvant therapy in rectal cancer with histopathologic comparison[J/OL]. Cancer Imaging, 2023, 23(1): 67 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10339540/. DOI: 10.1186/s40644-023-00589-0.
[23]
LANGMAN G, PATEL A, BOWLEY D M. Size and distribution of lymph nodes in rectal cancer resection specimens[J]. Dis Colon Rectum, 2015, 58(4): 406-414. DOI: 10.1097/DCR.0000000000000321.
[24]
RUTEGÅRD M K, BÅTSMAN M, BLOMQVIST L, et al. Evaluation of MRI characterisation of histopathologically matched lymph nodes and other mesorectal nodal structures in rectal cancer[J/OL]. Eur Radiol, 2025 [2025-04-05]. https://pubmed.ncbi.nlm.nih.gov/39838092/. DOI: 10.1007/s00330-025-11361-2.
[25]
ZHANG H M, ZHANG C D, ZHENG Z X, et al. Chemical shift effect predicting lymph node status in rectal cancer using high-resolution MR imaging with node-for-node matched histopathological validation[J]. Eur Radiol, 2017, 27(9): 3845-3855. DOI: 10.1007/s00330-017-4738-7.
[26]
LURZ M, SCHÄFER A O. The Avocado Sign: a novel imaging marker for nodal staging in rectal cancer[J/OL]. Eur Radiol, 2025 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/40009088/. DOI: 10.1007/s00330-025-11462-y.
[27]
LI Q Y, YANG D, GUAN Z, et al. Extranodal extension at pretreatment MRI and the prognostic value for patients with rectal cancer[J/OL]. Radiology, 2024, 310(3): e232605 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/38530176/. DOI: 10.1148/radiol.232605.
[28]
LEE S, KASSAM Z, BAHETI A D, et al. Rectal cancer lexicon 2023 revised and updated consensus statement from the Society of Abdominal Radiology Colorectal and Anal Cancer Disease-Focused Panel[J]. Abdom Radiol (NY), 2023, 48(9): 2792-2806. DOI: 10.1007/s00261-023-03893-2.
[29]
VAN GEFFEN E M, KUSTERS M. Positive lateral lymph node turned negative after neoadjuvant therapy-surgery or observation [J/OL]. Tech Coloproctol, 2025, 29(1): 53 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/39847226/. DOI: 10.1007/s10151-024-03080-5.
[30]
OGURA A, KONISHI T, BEETS G L, et al. Lateral nodal features on restaging magnetic resonance imaging associated with lateral local recurrence in low rectal cancer after neoadjuvant chemoradiotherapy or radiotherapy[J/OL]. JAMA Surg, 2019, 154(9): e192172 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC6613303/. DOI: 10.1001/jamasurg.2019.2172.
[31]
KROON H M, MALAKORN S, DUDI-VENKATA N N, et al. Local recurrences in western low rectal cancer patients treated with or without lateral lymph node dissection after neoadjuvant (chemo)radiotherapy: an international multi-centre comparative study[J]. Eur J Surg Oncol, 2021, 47(9): 2441-2449. DOI: 10.1016/j.ejso.2021.06.004.
[32]
HIDA K, NISHIZAKI D, SUMII A, et al. Prognostic impact of lateral pelvic node dissection on the survival of patients in low rectal cancer subgroups based on lymph node size[J]. Ann Surg Oncol, 2021, 28(11): 6179-6188. DOI: 10.1245/s10434-021-10312-7.
[33]
KASAI S, SHIOMI A, SHIMIZU H, et al. Risk factors and development of machine learning diagnostic models for lateral lymph node metastasis in rectal cancer: multicentre study[J/OL]. BJS Open, 2024, 8(4): zrae073 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/39016280/. DOI: 10.1093/bjsopen/zrae073.
[34]
ABE T, YASUI M, IMAMURA H, et al. Combination of extramural venous invasion and lateral lymph node size detected with magnetic resonance imaging is a reliable biomarker for lateral lymph node metastasis in patients with rectal cancer[J/OL]. World J Surg Oncol, 2022, 20(1): 5 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC8728915/. DOI: 10.1186/s12957-021-02464-3.
[35]
YANG T, LI Y, YE Z, et al. Diffusion weighted imaging of the abdomen and pelvis: recent technical advances and clinical applications[J]. Acad Radiol, 2023, 30(3): 470-482. DOI: 10.1016/j.acra.2022.07.018.
[36]
SUROV A, MEYER H J, PECH M, et al. Apparent diffusion coefficient cannot discriminate metastatic and non-metastatic lymph nodes in rectal cancer: A meta-analysis[J]. Int J Colorectal Dis, 2021, 36(10): 2189-2197. DOI: 10.1007/s00384-021-03986-8.
[37]
LI C L, YIN J D. Radiomics based on T2-weighted imaging and apparent diffusion coefficient images for preoperative evaluation of lymph node metastasis in rectal cancer patients[J/OL]. Front Oncol, 2021, 11: 671354 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC8141802/. DOI: 10.3389/fonc.2021.671354.
[38]
YIN J D, SONG L R, LU H C, et al. Prediction of different stages of rectal cancer: Texture analysis based on diffusion-weighted images and apparent diffusion coefficient maps[J]. World J Gastroenterol, 2020, 26(17): 2082-2096. DOI: 10.3748/wjg.v26.i17.2082.
[39]
HAO Y F, ZHENG J Y, LI W Q, et al. Ultra-high b-value DWI in rectal cancer: image quality assessment and regional lymph node prediction based on radiomics[J]. Eur Radiol, 2025, 35(1): 49-60. DOI: 10.1007/s00330-024-10958-3.
[40]
XU H S, ZHAO W Y, GUO W B, et al. Prediction model combining clinical and MR data for diagnosis of lymph node metastasis in patients with rectal cancer[J]. J Magn Reson Imaging, 2021, 53(3): 874-883. DOI: 10.1002/jmri.27369.
[41]
YACHEVA A, DARDANOV D, ZLATAREVA D. The multipurpose usage of diffusion-weighted MRI in rectal cancer[J/OL]. Medicina (Kaunas), 2023, 59(12): 2162 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10744943/. DOI: 10.3390/medicina59122162.
[42]
ZHAO L, LIANG M, YANG Y, et al. Value of multiple models of diffusion-weighted imaging for improving the nodal staging of preoperatively node-negative rectal cancer[J]. Abdom Radiol (NY), 2021, 46(10): 4548-4555. DOI: 10.1007/s00261-021-03125-5.
[43]
WANG Q, YU G H, QIU J F, et al. Application of intravoxel incoherent motion in clinical liver imaging: a literature review[J]. J Magn Reson Imaging, 2024, 60(2): 417-440. DOI: 10.1002/jmri.29086.
[44]
YANG X Y, CHEN Y, WEN Z Q, et al. Non-invasive MR assessment of the microstructure and microcirculation in regional lymph nodes for rectal cancer: a study of intravoxel incoherent motion imaging[J/OL]. Cancer Imaging, 2019, 19(1): 70 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC6829929/. DOI: 10.1186/s40644-019-0255-z.
[45]
WANG C, YU J, LU M, et al. Diagnostic efficiency of diffusion sequences and a clinical nomogram for detecting lymph node metastases from rectal cancer[J]. Acad Radiol, 2022, 29(9): 1287-1295. DOI: 10.1016/j.acra.2021.10.009.
[46]
ZHOU M, CHEN M Y, LUO M F, et al. Pathological prognostic factors of rectal cancer based on diffusion-weighted imaging, intravoxel incoherent motion, and diffusion kurtosis imaging[J]. Eur Radiol, 2025, 35(2): 979-988. DOI: 10.1007/s00330-024-11025-7.
[47]
RAJU J, USHADEVI AMMA C, JOHN A. A novel approach for b-value optimization in intravoxel incoherent motion imaging using metaheuristic algorithm[J/OL]. Expert Syst Appl, 2021, 168: 114270 [2025-03-24]. https://www.sciencedirect.com/science/article/abs/pii/S0957417420309805via%3Dihub. DOI: 10.1016/j.eswa.2020.114270.
[48]
SAHA A, GIBBS H, PECK K K, et al. Comprehensive review of the utility of dynamic contrast-enhanced MRI for the diagnosis and treatment assessment of spinal benign and malignant osseous disease[J]. AJNR Am J Neuroradiol, 2025, 46(3): 465-475. DOI: 10.3174/ajnr.A8398.
[49]
YANG X Y, CHEN Y, WEN Z Q, et al. Role of quantitative dynamic contrast-enhanced MRI in evaluating regional lymph nodes with a short-axis diameter of less than 5 mm in rectal cancer[J]. AJR Am J Roentgenol, 2019, 212(1): 77-83. DOI: 10.2214/AJR.18.19866.
[50]
ZHOU M, HUANG H, FAN Y, et al. The application of quantitative perfusion analysis of golden-angle radial sparse parallel MRI and R2 value for predicting pathological prognostic factors in rectal cancer[J]. Clin Radiol, 2024, 79(2): 124-132. DOI: 10.1016/j.crad.2023.10.027.
[51]
XU J Q, ZHONG M, PENG W, et al. Correlation study of functional magnetic resonance index and clinicopathological features of rectal cancer[J]. Abdom Radiol (NY), 2024, 49(7): 2368-2386. DOI: 10.1007/s00261-024-04375-9.
[52]
JAYAPRAKASAM V S, INCE S, SUMAN G, et al. PET/MRI in colorectal and anal cancers: an update[J]. Abdom Radiol (NY), 2023, 48(12): 3558-3583. DOI: 10.1007/s00261-023-03897-y.
[53]
LO H Z, CHOY K T, KONG J C H. FDG-PET/MRI in colorectal cancer care: an updated systematic review[J]. Abdom Radiol (NY), 2025, 50(1): 49-63. DOI: 10.1007/s00261-024-04460-z.
[54]
LIN Y, GAO H P, ZHENG J F, et al. Clinical explorations of [68Ga] Ga-FAPI-04 and [18F] FDG dual-tracer total-body PET/CT and PET/MR imaging[J]. Semin Nucl Med, 2024, 54(6): 904-913. DOI: 10.1053/j.semnuclmed.2024.09.009.
[55]
LI H, LI Z, QIN J, et al. Diagnostic performance of [68Ga] Ga-FAPI-04 PET vs. [18F] FDG PET in detecting lymph node metastasis in digestive system cancers: a head-to-head comparative meta-analysis[J/OL]. Front Med (Lausanne), 2025, 12: 1541461 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11968752/. DOI: 10.3389/fmed.2025.1541461.
[56]
HUANG D L, WU J H, ZHONG H S, et al. 68Ga] Ga-FAPI PET for the evaluation of digestive system tumors: systematic review and meta-analysis[J]. Eur J Nucl Med Mol Imaging, 2023, 50(3): 908-920. DOI: 10.1007/s00259-022-06021-2.
[57]
KÖMEK H, CAN C N, KAPLAN İ, et al. Comparison of [68Ga] Ga-DOTA-FAPI-04 PET/CT and [18F] FDG PET/CT in colorectal cancer[J]. Eur J Nucl Med Mol Imaging, 2022, 49(11): 3898-3909. DOI: 10.1007/s00259-022-05839-0.
[58]
CHEN W C, LIU G Q, CHEN J L, et al. Whole-tumor amide proton transfer-weighted imaging histogram analysis to predict pathological extramural venous invasion in rectal adenocarcinoma: A preliminary study[J]. Eur Radiol, 2023, 33(7): 5159-5171. DOI: 10.1007/s00330-023-09418-1.
[59]
SU H Y, CHAN K W Y. Design chemical exchange saturation transfer contrast agents and nanocarriers for imaging proton exchange in vivo[J]. ACS Nano, 2024, 18(50): 33775-33791. DOI: 10.1021/acsnano.4c05923.
[60]
WEI Q R, YUAN W J, JIA Z Q, et al. Preoperative MR radiomics based on high-resolution T2-weighted images and amide proton transfer-weighted imaging for predicting lymph node metastasis in rectal adenocarcinoma[J]. Abdom Radiol (NY), 2023, 48(2): 458-470. DOI: 10.1007/s00261-022-03731-x.
[61]
ZHANG C X, CHEN J Y, LIU Y F, et al. Amide proton transfer-weighted MRI for assessing rectal adenocarcinoma T-staging and perineural invasion: A prospective study[J]. Eur Radiol, 2025, 35(2): 968-978. DOI: 10.1007/s00330-024-11000-2.
[62]
LIAN S S, LIU H M, MENG T B, et al. Quantitative synthetic MRI for predicting locally advanced rectal cancer response to neoadjuvant chemoradiotherapy[J]. Eur Radiol, 2023, 33(3): 1737-1745. DOI: 10.1007/s00330-022-09191-7.
[63]
ZHAO L, LIANG M, XIE L Z, et al. Prediction of pathological prognostic factors of rectal cancer by relaxation maps from synthetic magnetic resonance imaging[J/OL]. Eur J Radiol, 2021, 138: 109658 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/33744506/. DOI: 10.1016/j.ejrad.2021.109658.
[64]
YANG F, LI X L, LI Y J, et al. Histogram analysis of quantitative parameters from synthetic MRI: correlations with prognostic factors in nasopharyngeal carcinoma[J]. Eur Radiol, 2023, 33(8): 5344-5354. DOI: 10.1007/s00330-023-09553-9.
[65]
MENG N, LIU X, ZHOU Y H, et al. Multiparametric 18F-FDG PET/MRI based on restrictive spectrum imaging and amide proton transfer-weighted imaging facilitates the assessment of lymph node metastases in non-small cell lung cancer[J/OL]. Radiol Med, 2025 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/40232656/. DOI: 10.1007/s11547-025-01992-2.
[66]
XU Q H, SONG Q L, WANG Y, et al. Amide proton transfer weighted combined with diffusion kurtosis imaging for predicting lymph node metastasis in cervical cancer[J]. Magn Reson Imaging, 2024, 106: 85-90. DOI: 10.1016/j.mri.2023.12.001.
[67]
TRAC N, CHEN Z, OH H S, et al. MRI detection of lymph node metastasis through molecular targeting of C-C chemokine receptor type 2 and monocyte hitchhiking[J]. ACS Nano, 2024, 18(3): 2091-2104. DOI: 10.1021/acsnano.3c09201.
[68]
SI G X, DU Y, TANG P, et al. Correction to: unveiling the next generation of MRI contrast agents: current insights and perspectives on ferumoxytol-enhanced MRI[J/OL]. Natl Sci Rev, 2024, 11(6): nwae156 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11177880/. DOI: 10.1093/nsr/nwae156.
[69]
MAATMAN I T, MAAS M C, YPMA S, et al. High-resolution free-breathing chemical-shift-encoded MRI for characterizing lymph nodes in the upper abdomen[J]. Invest Radiol, 2025, 60(7): 434-443. DOI: 10.1097/rli.0000000000001147.
[70]
STIJNS R C H, PHILIPS B W J, NAGTEGAAL I D, et al. USPIO-enhanced MRI of lymph nodes in rectal cancer: A node-to-node comparison with histopathology[J/OL]. Eur J Radiol, 2021, 138: 109636 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/33721766/. DOI: 10.1016/j.ejrad.2021.109636.
[71]
CHEN K, CAI Z Y, CAO Y Z, et al. Kinetically inert manganese (Ⅱ)-based hybrid micellar complexes for magnetic resonance imaging of lymph node metastasis[J/OL]. Regen Biomater, 2023, 10: rbad053 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10244211/. DOI: 10.1093/rb/rbad053.
[72]
INCHINGOLO R, MAINO C, CANNELLA R, et al. Radiomics in colorectal cancer patients[J]. World J Gastroenterol, 2023, 29(19): 2888-2904. DOI: 10.3748/wjg.v29.i19.2888.
[73]
ZHUANG Z X, ZHANG Y, YANG X Y, et al. T2WI-based texture analysis predicts preoperative lymph node metastasis of rectal cancer[J]. Abdom Radiol (NY), 2024, 49(6): 2008-2016. DOI: 10.1007/s00261-024-04209-8.
[74]
NIU Y, YU X P, WEN L, et al. Comparison of preoperative CT- and MRI-based multiparametric radiomics in the prediction of lymph node metastasis in rectal cancer[J/OL]. Front Oncol, 2023, 13: 1230698. DOI: 10.3389/fonc.2023.1230698.
[75]
WEI Q R, CHEN L, HOU X Y, et al. Multiparametric MRI-based radiomic model for predicting lymph node metastasis after neoadjuvant chemoradiotherapy in locally advanced rectal cancer[J/OL]. Insights Imaging, 2024, 15(1): 163 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11208366/. DOI: 10.1186/s13244-024-01726-4.
[76]
LIU X C, YANG Q, ZHANG C Y, et al. Multiregional-based magnetic resonance imaging radiomics combined with clinical data improves efficacy in predicting lymph node metastasis of rectal cancer[J/OL]. Front Oncol, 2021, 10: 585767 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC7930475/. DOI: 10.3389/fonc.2020.585767.
[77]
ZHAO W, XU H, ZHAO R, et al. MRI-based radiomics model for preoperative prediction of lateral pelvic lymph node metastasis in locally advanced rectal cancer[J]. Acad Radiol, 2024, 31(7): 2753-2772. DOI: 10.1016/j.acra.2023.07.016.
[78]
YANG M W, YANG M Y, YANG L L, et al. Deep learning for MRI lesion segmentation in rectal cancer[J/OL]. Front Med (Lausanne), 2024, 11: 1394262 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11231084/. DOI: 10.3389/fmed.2024.1394262.
[79]
JIANG X F, ZHAO H Y, SALDANHA O L, et al. An MRI deep learning model predicts outcome in rectal cancer[J/OL]. Radiology, 2023, 307(5): e222223 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/37278629/. DOI: 10.1148/radiol.222223.
[80]
BEDRIKOVETSKI S, DUDI-VENKATA N N, KROON H M, et al. Artificial intelligence for pre-operative lymph node staging in colorectal cancer: A systematic review and meta-analysis[J]. BMC Cancer, 2021, 21(1): 1058 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC8474828/. DOI: 10.1186/s12885-021-08773-w.
[81]
SUN Y, LU Z X, YANG H J, et al. Prediction of lateral lymph node metastasis in rectal cancer patients based on MRI using clinical, deep transfer learning, radiomic, and fusion models[J/OL]. Front Oncol, 2024, 14: 1433190 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11294238/. DOI: 10.3389/fonc.2024.1433190.
[82]
YANG Y J, HAN K T, XU Z Y, et al. Development and validation of multiparametric MRI-based interpretable deep learning radiomics fusion model for predicting lymph node metastasis and prognosis in rectal cancer: A two-center study[J]. Acad Radiol, 2025, 32(5): 2642-2654. DOI: 10.1016/j.acra.2024.11.045.
[83]
ZHAO X Y, XIE P Y, WANG M M, et al. Deep learning-based fully automated detection and segmentation of lymph nodes on multiparametric-MRI for rectal cancer: A multicentre study[J/OL]. EBioMedicine, 2020, 56: 102780 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC7276514/. DOI: 10.1016/j.ebiom.2020.102780.
[84]
LU Y, YU Q Y, GAO Y X, et al. Identification of metastatic lymph nodes in MR imaging with faster region-based convolutional neural networks[J]. Cancer Res, 2018, 78(17): 5135-5143. DOI: 10.1158/0008-5472.CAN-18-0494.
[85]
XIA W, LI D D, HE W G, et al. Multicenter evaluation of a weakly supervised deep learning model for lymph node diagnosis in rectal cancer at MRI[J/OL]. Radiol Artif Intell, 2024, 6(2): e230152 [2025-03-24]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10982819/. DOI: 10.1148/ryai.230152.
[86]
WAN L J, HU J S, CHEN S, et al. Prediction of lymph node metastasis in stage T1-2 rectal cancers with MRI-based deep learning[J]. Eur Radiol, 2023, 33(5): 3638-3646. DOI: 10.1007/s00330-023-09450-1.
[87]
OZAKI K, KUROSE Y, KAWAI K, et al. Development of a diagnostic artificial intelligence tool for lateral lymph node metastasis in advanced rectal cancer[J/OL]. Dis Colon Rectum, 2023, 66(12): e1246-e1253 [2025-03-24]. https://pubmed.ncbi.nlm.nih.gov/37260284/. DOI: 10.1097/DCR.0000000000002719.

上一篇 影像组学在胃癌诊断和治疗应用中的研究进展
下一篇 前列腺癌的人工智能研究进展
  
诚聘英才 | 广告合作 | 免责声明 | 版权声明
联系电话:010-67113815
京ICP备19028836号-2