分享:
分享到微信朋友圈
X
综述
直肠癌淋巴结转移MRI人工智能研究进展
杨心悦 温志波

Cite this article as: YANG X Y, WEN Z B. MRI-Based Artificial Intelligence in Lymph Node Metastasis of Rectal Cancer[J]. Chin J Magn Reson Imaging, 2024, 15(10): 205-210.本文引用格式:杨心悦, 温志波. 直肠癌淋巴结转移MRI人工智能研究进展[J]. 磁共振成像, 2024, 15(10): 205-210. DOI:10.12015/issn.1674-8034.2024.10.035.


[摘要] 直肠癌是常见的消化系统恶性肿瘤,转移方式以淋巴转移为主,淋巴结转移决定治疗方案及疾病预后。目前评价直肠癌淋巴结转移主要依赖高分辨MRI,但基于MRI形态学诊断淋巴结转移的主观性强,诊断结果无法完全一致。人工智能(artificial intelligence, AI)能够深度挖掘医学图像的定量信息,为评估直肠癌淋巴结转移提供了新的途径。本文总结了近年来基于MRI的AI评估直肠癌治疗前和新辅助治疗后淋巴结转移的研究进展,并进行小结和展望,以期帮助读者了解基于直肠癌MRI评估淋巴结转移的AI研究存在回顾性研究多、数据集规模不一、模型效能参差的局限,为未来设计前瞻性、多中心、大数据的AI研究提供参考。
[Abstract] Rectal cancer is one of the most common malignancies in the digestive tract. Cancer cells usually disseminate from rectal tumors to distant sites via lymphatic vessels. Thus, lymph node involvement, which influences treatment and prognosis, plays a crucial role in patients with rectal cancer. High resolution MRI has been used to estimate lymph node metastasis in rectal cancer. However, the morphological criteria were influenced by the subjective judgement of different observers. Artificial intelligence (AI) can mine and learn quantitative features from medical images, thus providing a new method for us to distinguish metastatic lymph nodes. In this review, we summarize the research progress of MRI-based AI in the evaluation of nodal metastasis with rectal cancer before and after the neoadjuvant chemoradiotherapy. We further discuss the challenges and provide prospects of AI research to help researchers understand the limitations of MRI-based AI in evaluation of nodal involvement in rectal cancer and offer guidance for future prospective, multi-center, big-data AI research.
[关键词] 直肠癌;淋巴结;磁共振成像;人工智能
[Keywords] rectal cancer;lymph node;magnetic resonance imaging;artificial intelligence

杨心悦    温志波 *  

南方医科大学珠江医院影像诊断科,广州 510280

通信作者:温志波,E-mail: zhibowen@163.com

作者贡献声明:温志波设计本研究的方案,对稿件重要内容进行了修改;杨心悦起草和撰写稿件,获取、分析和解释本研究的数据,获得了国家自然科学基金资助;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 82302128
收稿日期:2024-06-03
接受日期:2024-10-10
中图分类号:R445.2  R735.37 
文献标识码:A
DOI: 10.12015/issn.1674-8034.2024.10.035
本文引用格式:杨心悦, 温志波. 直肠癌淋巴结转移MRI人工智能研究进展[J]. 磁共振成像, 2024, 15(10): 205-210. DOI:10.12015/issn.1674-8034.2024.10.035.

0 引言

       结直肠癌是消化系统常见的恶性肿瘤之一[1],发病率居于全球常见肿瘤第三位[2]。近二十年中国结直肠癌发病率呈现上升趋势,发病人群趋于年轻化[3]。结直肠癌中约1/3为直肠癌,直肠癌局部复发率高且预后差,5年生存率约64.7%,严重威胁国民健康[3, 4]

       直肠癌转移以淋巴转移为主,淋巴结转移是决定直肠癌预后的重要因素[4]。美国国立综合癌症网络(National Comprehensive Cancer Network, NCCN)直肠癌指南明确指出,若治疗前存在淋巴结转移,均推荐进行新辅助放化疗(neoadjuvant chemoradiotherapy, nCRT)[5]。对于局部进展期直肠癌(local advanced rectal cancer, LARC),若nCRT后仍存在转移淋巴结,则需延长nCRT时间或调整nCRT方案[5]。目前,评估直肠癌淋巴结转移主要依赖MRI[6]。高分辨MRI作为NCCN指南推荐的常规检查项目,具有良好的软组织分辨力,能清晰显示淋巴结[5, 7]。但高分辨MRI诊断转移淋巴结的短径界值存在争议[4, 8],且直肠癌约50%转移淋巴结短径小于5 mm[9],形态学征象的人为判读主观性强,因而基于高分辨MRI评价淋巴结转移难度大、结果难以完全统一[4]。由于转移淋巴结的病理生理改变早于形态改变,功能MRI被逐步应用于评价直肠癌淋巴结转移,主要包括弥散加权成像(diffusion-weighted imaging, DWI)、体素内不相干运动MRI(intravoxel incoherent motion MRI, IVIM-MRI)及动态对比增强MRI(dynamic contrast-enhanced MRI, DCE-MRI)[10]。但良恶性淋巴结表观弥散系数(apparent diffusion coefficient, ADC)存在重叠,IVIM-MRI部分定量参数的可重复性较低,DCE-MRI扫描时间长、需静脉团注钆剂,目前仅应用于科研[10]

       基于高分辨MRI评价直肠癌淋巴结转移的主观性较强,功能MRI的临床应用价值有限,因而亟需一种客观、高效且便捷的技术,辅以评估淋巴结转移,故人工智能(artificial intelligence, AI)引起学界的研究兴趣。AI不仅能够自动识别多种模式的医学图像,还能提取医学图像的定量特征进行挖掘,已被广泛应用于医学研究[11]。医学研究中应用的AI技术主要是机器学习,机器学习包括影像组学和深度学习两种方法[12]。影像组学通过高通量提取医学图像的定量特征,将图像转换为高维数据,采用传统统计学方法进行分析,筛选关键特征构建预测模型,辅以临床决策[13, 14]。影像组学具有良好的特征可解释性,且模型的参数较少,因而在小数据集效能更优,但在大数据集则较为逊色[12]。深度学习则在大数据集展示出优越性能,其中卷积神经网络(convolutional neural network, CNN)在医学影像研究中的应用尤为关键[15, 16]。CNN由卷积层、池化层、线性整流层及全连接层构成,是一种“端到端”的学习模型,经过训练即可自动识别并提取图像的深度特征,实现任务的分割及分类[17, 18]。但由于CNN具有大量隐藏层,模型的可解释性较影像组学低[12]。AI在直肠癌MRI研究中的成果丰硕[12, 19],提示AI不仅能够有效规避人为判读的主观性,还能深度挖掘肉眼无法识别的定量特征,且AI模型运行耗时短、效率高,为评估直肠癌淋巴结转移提供了新途径。但直肠癌淋巴结MRI的AI研究多为回顾性、数据集规模不一、模型效能参差,尚存在一定局限。本综述将分别叙述基于MRI的AI评估直肠癌治疗前、nCRT后淋巴结转移的研究现状,并进行小结与展望,为后续前瞻性、多中心、大数据研究提供参考。

1 基于MRI的人工智能评估直肠癌治疗前淋巴结转移

       直肠的壁外淋巴管伴随直肠上、中、下动脉走行,因此,直肠淋巴引流包括上方引流、侧方引流、下方引流共三个途径,以上方引流为主[20]。直肠癌淋巴结转移遵循直肠淋巴引流途径进行,NCCN指南将区域淋巴结(regional lymph node, RLN)定义为直肠系膜内、直肠上及肠系膜下动脉旁、闭孔及髂内动脉旁淋巴结,根据RLN转移数目进行N分期评价[5]。侧方淋巴结(lateral lymph node, LLN)则包括闭孔及髂内动脉旁、髂外动脉旁、髂总动脉旁淋巴结,其中髂外和髂总动脉旁淋巴结转移属于NCCN指南“远处转移”范畴,不同国家间LLN转移的治疗方案差异较大[5, 21, 22]。治疗前精准评估直肠癌不同引流区淋巴结转移,不仅是制订个体化治疗方案的关键,还是影像学研究的热点。评估直肠癌治疗前淋巴结转移的AI研究仅纳入未经nCRT直接行全直肠系膜切除术(total mesorectal excision, TME)的病例,本部分内容将分别阐述基于MRI的AI评估治疗前直肠癌RLN和LLN转移的研究进展。

1.1 基于MRI的人工智能评估直肠癌治疗前区域淋巴结转移

       近年来,利用AI评估直肠癌治疗前RLN的研究,基于治疗前MRI,经历了单序列到多序列、单感兴趣区到多感兴趣区、单影像特征到多影像特征与临床特征相结合、单中心到多中心的逐步发展过程。近年来国内外部分研究的主要内容如表1所示。

       不同于大部分回顾性研究,ZHUANG等[37]设计前瞻性研究,进行淋巴结影像-病理“结-结”匹配,以各枚淋巴结病理结果作为分类“金标准”,分割淋巴结提取影像特征,构建精准诊断模型,但研究数据集小、匹配淋巴结数量少,模型的准确率仅为64.7%。在淋巴结自动检出方面,深度学习表现出优越性能。ZHAO等[27]利用Mask区域CNN构建淋巴结自动检出模型,模型识别和分割直肠癌MRI淋巴结仅需1.3秒/例,临床转化应用价值极为可观。在大数据集中的淋巴结分类方面,深度学习也展现出独特优势。由于大宗病例的回顾性研究难以完成逐枚淋巴结影像-病理匹配,XIA等[39]收集3个中心共1014例直肠癌病例,尝试以病理N分期作为分类标准,基于弱监督学习构建诊断淋巴结转移的AI模型WISDOM,并利用治疗前淋巴结轴位T2WI和ADC图训练WISDOM。针对单一病例淋巴结转移与否的二分类问题,WISDOM的AUC为0.81,诊断特异度超过80%,但敏感度较低,为70.2%,WISDOM判断转移淋巴结个数的平均绝对误差为1.049。针对单一病例淋巴结N分期(N0期、N1期、N2期)的三分类问题,WISDOM的总体一致性指数为0.765,模型诊断N0期的准确率约80%,而诊断N1期及N2期的准确性则较低,提示AI解决二分类问题效能较好,而三分类问题对于AI而言仍充满挑战。

       本部分研究以回顾性为主,均纳入未经nCRT直接行TME病例的术前MRI,主要利用影像组学技术,解决淋巴结转移与否的二分类问题。虽然模型的受试者工作特征(receiver operating characteristic, ROC)曲线下面积(area under the curve, AUC)为0.740~0.986,诊断效能为中等至优良,但大多数研究数据集较小,且仅来源于单中心,缺乏外部验证集,模型的泛化能力尚有待考量。多序列、多感兴趣区影像特征联合临床特征虽有助于提升模型效能,但各研究多感兴趣区分割方案尚未统一。功能MRI对于效能提升亦有所助益,然而,大多数研究仅应用DWI,而对于IVIM-MRI、DCE-MRI所蕴含的活体生物学信息挖掘程度低,未能充分利用功能MRI的特征。未来尚需更多研究规范感兴趣区分割和进一步探索功能MRI的价值。

表1  直肠癌治疗前区域淋巴结转移MRI人工智能研究的主要内容
Tab. 1  Main contents of MRI artificial intelligence research on regional lymph node metastasis in rectal cancer before treatment

1.2 基于MRI的人工智能评估直肠癌治疗前侧方淋巴结转移

       低位LARC发生LLN转移的概率约为16%~23%[40],存在LLN转移的LARC预后差、局部复发率高[41, 42]。不同国家间LLN转移的治疗方案差异较大[5, 21, 22]。NCCN指南将“nCRT+TME”作为存在LLN转移的标准治疗方案[5],然而在日本,TME联合LLN清扫是低位LARC的标准术式[43]。但LLN清扫可能会导致手术时间延长、术中出血量增加、因术中神经损伤所致泌尿生殖功能障碍的风险增大[40, 44]。故中国直肠癌专家共识建议,对于可疑存在LLN转移的LARC进行选择性LLN清扫[21]。因此,治疗前准确评估LLN转移,对于制订个体化治疗策略尤为关键。

       不同于RLN的AI研究大多分割肿瘤提取特征,LLN的AI研究则以分割LLN提取特征为主。YAN等[45]提取LLN轴位T2WI特征,联合临床指标,构建预测LLN转移模型的AUC为0.843。ZHAO等[40]筛选LLN和全肿瘤的轴位T2WI特征,结合临床危险因素,所构建诺模图的AUC为0.891,表明加入肿瘤特征有助于提升模型效能,提示多感兴趣区影像组学可作为LLN转移研究的一个切入点。YANG等[46]综合利用LLN和肿瘤的轴位T2WI和电子计算机断层扫描(computed tomography, CT)特征建模预测LLN转移,模型的AUC为0.957,决策曲线分析显示模型的预测效能高,提示多模态影像组学可作为LLN转移研究的又一切入点。

       因LLN转移的病例相对RLN转移少,故数据集小是AI评估LLN转移研究的主要局限,模型的效能也需要更多数据进行验证。未来联合多中心建立LLN转移病例数据库,结合多模态影像资料,包括MRI、CT、超声等,利用AI技术探索LLN转移预测方法,或可提高模型的预测效能和泛化能力。

2 基于MRI的人工智能预测直肠癌新辅助治疗后淋巴结转移

       LARC的nCRT疗效决定后续治疗方式,nCRT后达到临床完全缓解的患者可接受局部切除手术或实施“观察-等待”方案,有望保留肛门,提高生活质量[47]。目前,LARC基于MRI的AI研究主要关注nCRT后肿瘤是否完全消退,而预测nCRT后淋巴结转移的AI研究则相对较少[12]。nCRT后肿瘤完全消退但仍存在淋巴结转移的LARC局部复发率高、预后差[48],需要延长nCRT时间或改变治疗方案[5]。依据nCRT后淋巴结MRI形态学征象诊断转移的敏感度为67%~88%,特异度为63%~95%,由于放疗导致淋巴结MRI形态学改变,诊断小淋巴结转移的难度增大,尤其是直径小于3 mm的淋巴结[49]。AI为评估LARC患者nCRT后淋巴结转移提供了新契机,nCRT前后的MRI均可被用于挖掘特征,构建淋巴结转移的辅助预测模型。

       ZHOU等[50]基于LARC患者nCRT前多参数MRI,包括轴位T1WI、T2WI、增强T1WI、ADC图,分割全肿瘤提取特征,联合nCRT后基于MRI的T分期、N分期,构建预测nCRT后淋巴结转移的诺模图,模型在验证集中的AUC为0.818,阴性预测值(negative predictive value, NPV)为93.7%,提示基于多序列的AI有助于评估nCRT后淋巴结转移。FANG等[49]基于nCRT前后轴位T2WI、ADC图,提取全肿瘤特征,并计算nCRT前后肿瘤的特征差异Delta,联合临床特征与肿瘤的Delta-ADC特征及nCRT后的T2WI特征建模,模型预测nCRT后淋巴结转移的AUC为0.913,提示nCRT前后肿瘤的特征差异更具研究潜能。

       此外,分割LARC淋巴结进行AI研究同样值得研究者予以重视。ZHANG等[51]联合nCRT前淋巴结轴位T2WI组学特征及MRI形态学征象,构建预测nCRT后淋巴结转移的诺模图,模型的AUC为0.925。ZHU等[52]基于nCRT前后轴位T2WI,共提取412个淋巴结特征及82个肿瘤特征,从中分别各筛选出7个特征建模,预测nCRT后淋巴结转移,基于淋巴结特征所建模型的AUC为0.818,而基于肿瘤特征所建模型的AUC仅为0.517。这两项研究均提示淋巴结的特征更具有深入研究的价值。

       在本部分预测直肠癌nCRT后淋巴结转移的AI研究中,若只应用nCRT前MRI进行图像分割和特征提取,则无法避免个体差异,nCRT前后的特征差异更具研究价值。但由于nCRT后肿瘤退缩及纤维化,手动勾画nCRT后残余肿瘤的难度较大。除去肿瘤和淋巴结,本部分研究对于瘤周系膜的关注度较低,未来的研究或可尝试挖掘nCRT前后瘤周系膜的MRI特征辅以建模。

3 小结与展望

       直肠癌淋巴结转移决定治疗策略和疾病预后。高分辨MRI淋巴结恶性形态征象人为判读的主观性强,而功能MRI的临床应用价值有限。基于MRI的AI为预测直肠癌淋巴结转移提供了新途径,预测治疗前及nCRT后淋巴结转移的AI模型效能良好,淋巴结自动检出AI模型耗时短、效率高。虽然AI的优势可圈可点,但机遇与挑战并存。首先,基于MRI的直肠癌淋巴结转移AI研究大多为回顾性、单中心、小数据集研究,模型泛化能力有待验证。其次,不同研究间MRI扫描参数存在差异,感兴趣区分割方法并不统一,模型的稳定性有待考究。若希望将AI真正应用于临床直肠癌淋巴结转移评估,未来研究需要多中心通力合作,建立直肠癌MRI公共数据库,对来自不同中心的MRI数据进行清洗和标准化,保护患者隐私数据,并制定感兴趣区分割共识,对数据库中的MRI进行统一标注,为训练AI模型提供高质量的大数据集。同时,还需设计前瞻性研究,对AI模型的效能进行验证。

       综上所述,AI作为评估直肠癌淋巴结转移的辅助工具,能够减轻影像医师日常工作负担,协助医师进行诊断。未来研究需要联合多中心建立大规模、高质量直肠癌MRI数据库,优化机器学习算法,改进AI模型性能,最终完成AI模型的临床转化,辅助医生评估直肠癌淋巴结转移,制订个体化治疗策略,使更多患者获益。

[1]
BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3): 229-263. DOI: 10.3322/caac.21834.
[2]
SIEGEL R L, MILLER K D, WAGLE N S, et al. Cancer statistics, 2023[J]. CA A Cancer J Clinicians, 2023, 73(1): 17-48. DOI: 10.3322/caac.21763.
[3]
XIA C F, DONG X S, LI H, et al. Cancer statistics in China and United States, 2022: profiles, trends, and determinants[J]. Chin Med J, 2022, 135(5): 584-590. DOI: 10.1097/CM9.0000000000002108.
[4]
BORGHERESI A, MUZIO F D, AGOSTINI A, et al. Lymph nodes evaluation in rectal cancer: where do we stand and future perspective[J/OL]. J Clin Med, 2022, 11(9): 2599 [2024-10-21]. https://www.mdpi.com/2077-0383/11/9/2599. DOI: 10.3390/jcm11092599.
[5]
BENSON A B, VENOOK A P, AL-HAWARY M M, et al. Rectal cancer, version 2.2022, NCCN clinical practice guidelines in oncology[J]. J Natl Compr Canc Netw, 2022, 20(10): 1139-1167. DOI: 10.6004/jnccn.2022.0051.
[6]
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, 2023, 48(9): 2792-2806. DOI: 10.1007/s00261-023-03893-2.
[7]
CRIMÌ F, CABRELLE G, CAMPI C, et al. Nodal staging with MRI after neoadjuvant chemo-radiotherapy for locally advanced rectal cancer: a fast and reliable method[J]. Eur Radiol, 2024, 34(5): 3205-3214. DOI: 10.1007/s00330-023-10265-3.
[8]
PEACOCK O, MANISUNDARAM N, KIM Y, et al. Therapeutic lateral pelvic lymph node dissection in rectal cancer: when to dissect? Size is not everything[J]. Br J Surg, 2023, 110(8): 985-986. DOI: 10.1093/bjs/znad115.
[9]
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.
[10]
樊竞泓, 张胜潮. MRI评估直肠癌区域淋巴结转移的研究进展[J]. 磁共振成像, 2023, 14(12): 187-191. DOI: 10.12015/issn.1674-8034.2023.12.034.
FAN J H, ZHANG S C. Research progress of magnetic resonance imaging in evaluating regional lymph node metastasis of rectal cancer[J]. Chin J Magn Reson Imag, 2023, 14(12): 187-191. DOI: 10.12015/issn.1674-8034.2023.12.034.
[11]
SHEN H, JIN Z, CHEN Q Y, et al. Image-based artificial intelligence for the prediction of pathological complete response to neoadjuvant chemoradiotherapy in patients with rectal cancer: a systematic review and meta-analysis[J]. Radiol Med, 2024, 129(4): 598-614. DOI: 10.1007/s11547-024-01796-w.
[12]
WONG C, FU Y, LI M Y, et al. MRI-based artificial intelligence in rectal cancer[J]. J Magn Reson Imaging, 2023, 57(1): 45-56. DOI: 10.1002/jmri.28381.
[13]
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.
[14]
GUO X F, HE Y Y, YUAN Z L, et al. Association analysis between intratumoral and peritumoral MRI radiomics features and overall survival of neoadjuvant therapy in rectal cancer[J/OL]. J Magn Reson Imaging, 2024 [2024-10-21]. https://pubmed.ncbi.nlm.nih.gov/38733601. DOI: 10.1002/jmri.29396.
[15]
CARTER D, BYKHOVSKY D, HASKY A, et al. Convolutional neural network deep learning model accurately detects rectal cancer in endoanal ultrasounds[J/OL]. Tech Coloproctol, 2024, 28(1): 44 [2024-10-21]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10984882. DOI: 10.1007/s10151-024-02917-3.
[16]
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 [2024-10-21]. https://pubs.rsna.org/doi/10.1148/radiol.222223?url_ver=Z39.88-2003&rfr_id=ori:rid:crossref.org&rfr_dat=cr_pub%20%200pubmed. DOI: 10.1148/radiol.222223.
[17]
ZHANG H T, YANG X T, LI D A, et al. Dual parallel net: a novel deep learning model for rectal tumor segmentation via CNN and transformer with Gaussian Mixture prior[J/OL]. J Biomed Inform, 2023, 139: 104304 [2024-10-21]. https://www.sciencedirect.com/science/article/pii/S1532046423000254?via%3Dihub. DOI: 10.1016/j.jbi.2023.104304.
[18]
LI J, SONG Y, WU Y C, et al. Clinical evaluation on automatic segmentation results of convolutional neural networks in rectal cancer radiotherapy[J]. Front Oncol, 2023, 13: 1158315 [2024-10-21]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1158315/full. DOI: 10.3389/fonc.2023.1158315.
[19]
朱钰, 欧阳治强, 单海燕, 等. 基于MRI的人工智能在直肠癌中的应用进展[J]. 磁共振成像, 2023, 14(9): 176-180. DOI: 10.12015/issn.1674-8034.2023.09.032.
ZHU Y, OUYANG Z Q, SHAN H Y, et al. Application progress of MRI based artificial intelligence in rectal cancer[J]. Chin J Magn Reson Imag, 2023, 14(9): 176-180. DOI: 10.12015/issn.1674-8034.2023.09.032.
[20]
YOO R N, CHO H M, KYE B H, et al. Reappraisal of the lymphatic drainage system of the distal rectum: functional lymphatic flow into the presacral space and its clinical implication in rectal cancer treatment[J/OL]. Biomedicines, 2023, 11(2): 274 [2024-10-21]. https://www.mdpi.com/2227-9059/11/2/274. DOI: 10.3390/biomedicines11020274.
[21]
国家卫生健康委员会医政司, 中华医学会肿瘤学分会. 国家卫生健康委员会中国结直肠癌诊疗规范(2023版)[J]. 中华胃肠外科杂志, 2023, 26(6): 505-528. DOI: 10.3760/cma.j.cn441530-20230525-00182.
Department of Medical Administration of National Health Comimission, Chinese Society of Oncology. Chinese protocol of diagnosis and treatment of colorectal cancer of the National Health Commission (2023 edition)[J]. Chin J Gastrointest Surg, 2023, 26(6): 505-528. DOI: 10.3760/cma.j.cn441530-20230525-00182.
[22]
FERNANDES M C, GOLLUB M J, BROWN G. The importance of MRI for rectal cancer evaluation[J/OL]. Surg Oncol, 2022, 43: 101739 [2024-10-21]. https://www.sciencedirect.com/science/article/pii/S0960740422000329?via%3Dihub. DOI: 10.1016/j.suronc.2022.101739.
[23]
YANG L Q, LIU D, FANG X, et al. Rectal cancer: can T2WI histogram of the primary tumor help predict the existence of lymph node metastasis?[J]. Eur Radiol, 2019, 29(12): 6469-6476. DOI: 10.1007/s00330-019-06328-z.
[24]
MENG X C, XIA W, XIE P Y, et al. Preoperative radiomic signature based on multiparametric magnetic resonance imaging for noninvasive evaluation of biological characteristics in rectal cancer[J]. Eur Radiol, 2019, 29(6): 3200-3209. DOI: 10.1007/s00330-018-5763-x.
[25]
周云朋, 李硕, 张宪祥, 等. 基于深度神经网络的高分辨MRI直肠淋巴结辅助诊断系统的临床应用价值研究[J]. 中华外科杂志, 2019, 57(2): 108-113. DOI: 10.3760/cma.j.issn.0529-5815.2019.02.007.
ZHOU Y P, LI S, ZHANG X X, et al. High definition MRI rectal lymph node aided diagnostic system based on deep neural network[J]. Chin J Surg, 2019, 57(2): 108-113. DOI: 10.3760/cma.j.issn.0529-5815.2019.02.007.
[26]
LI J, ZHOU Y, WANG X X, et al. An MRI-based multi-objective radiomics model predicts lymph node status in patients with rectal cancer[J]. Abdom Radiol, 2021, 46(5): 1816-1824. DOI: 10.1007/s00261-020-02863-2.
[27]
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 [2024-10-21]. https://www.sciencedirect.com/science/article/pii/S2352396420301559?via%3Dihub. DOI: 10.1016/j.ebiom.2020.102780.
[28]
SONG L R, YIN J D. Application of texture analysis based on sagittal fat-suppression and oblique axial T2-weighted magnetic resonance imaging to identify lymph node invasion status of rectal cancer[J/OL]. Front Oncol, 2020, 10: 1364 [2024-10-21]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2020.01364/full. DOI: 10.3389/fonc.2020.01364.
[29]
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, 2020, 10: 585767 [2024-10-21]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2020.585767/full. DOI: 10.3389/fonc.2020.585767.
[30]
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 [2024-10-21]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.671354/full. DOI: 10.3389/fonc.2021.671354.
[31]
ZHOU Y, YANG R, WANG Y, et al. Histogram analysis of diffusion-weighted magnetic resonance imaging as a biomarker to predict LNM in T3 stage rectal carcinoma[J/OL]. BMC Med Imaging, 2021, 21(1): 176 [2024-10-21]. https://bmcmedimaging.biomedcentral.com/articles/10.1186/s12880-021-00706-0. DOI: 10.1186/s12880-021-00706-0.
[32]
JIA H D, JIANG X Y, ZHANG K Y, et al. A nomogram of combining IVIM-DWI and MRI radiomics from the primary lesion of rectal adenocarcinoma to assess nonenlarged lymph node metastasis preoperatively[J]. J Magn Reson Imaging, 2022, 56(3): 658-667. DOI: 10.1002/jmri.28068.
[33]
ATRE I D, EURBOONYANUN K, NODA Y, et al. Utility of texture analysis on T2-weighted MR for differentiating tumor deposits from mesorectal nodes in rectal cancer patients, in a retrospective cohort[J]. Abdom Radiol, 2021, 46(2): 459-468. DOI: 10.1007/s00261-020-02653-w.
[34]
SU Y X, ZHAO H Y, LIU P F, et al. A nomogram model based on MRI and radiomic features developed and validated for the evaluation of lymph node metastasis in patients with rectal cancer[J]. Abdom Radiol, 2022, 47(12): 4103-4114. DOI: 10.1007/s00261-022-03672-5.
[35]
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, 2023, 48(2): 458-470. DOI: 10.1007/s00261-022-03731-x.
[36]
DONG X, REN G, CHEN Y H, et al. Effects of MRI radiomics combined with clinical data in evaluating lymph node metastasis in mrT1-3a staging rectal cancer[J/OL]. Front Oncol, 2023, 13: 1194120 [2024-10-21]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1194120/full. DOI: 10.3389/fonc.2023.1194120.
[37]
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, 2024, 49(6): 2008-2016. DOI: 10.1007/s00261-024-04209-8.
[38]
MENG Y, AI Q, HU Y, et al. Clinical development of MRI-based multi-sequence multi-regional radiomics model to predict lymph node metastasis in rectal cancer[J]. Abdom Radiol, 2024, 49(6): 1805-1815. DOI: 10.1007/s00261-024-04204-z.
[39]
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 [2024-10-21]. https://pubs.rsna.org/doi/10.1148/ryai.230152?url_ver=Z39.88-2003&rfr_id=ori:rid:crossref.org&rfr_dat=cr_pub%20%200pubmed. DOI: 10.1148/ryai.230152.
[40]
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.
[41]
TAKAO M, KAWAI K, NAKANO D, et al. Recurrence of rectal cancer on the pelvic sidewall after lateral lymph node dissection[J]. Int J Colorectal Dis, 2024, 39(1): 80-88. DOI: 10.1007/s00384-024-04650-7.
[42]
SLUCKIN T C, HEKHUIS M, KOL S Q, et al. A deep learning framework with explainability for the prediction of lateral locoregional recurrences in rectal cancer patients with suspicious lateral lymph nodes[J/OL]. Diagnostics, 2023, 13(19): 3099 [2024-10-21]. https://www.mdpi.com/2075-4418/13/19/3099. DOI: 10.3390/diagnostics13193099.
[43]
HASHIGUCHI Y, MURO K, SAITO Y, et al. Japanese Society for Cancer of the Colon and Rectum (JSCCR) guidelines 2019 for the treatment of colorectal cancer[J]. Int J Clin Oncol, 2020, 25(1): 1-42. DOI: 10.1007/s10147-019-01485-z.
[44]
ZHENG Y Z, YAN F F, LUO L X. Feasibility and limitations of combined treatment for lateral pelvic lymph node metastases in rectal cancer[J]. World J Clin Oncol, 2024, 15(5): 591-593. DOI: 10.5306/wjco.v15.i5.591.
[45]
YAN H, YANG H J, JIANG P S, et al. A radiomics model based on T2WI and clinical indexes for prediction of lateral lymph node metastasis in rectal cancer[J]. Asian J Surg, 2024, 47(1): 450-458. DOI: 10.1016/j.asjsur.2023.09.156.
[46]
YANG H J, JIANG P S, DONG L C, et al. Diagnostic value of a radiomics model based on CT and MRI for prediction of lateral lymph node metastasis of rectal cancer[J]. Updates Surg, 2023, 75(8): 2225-2234. DOI: 10.1007/s13304-023-01618-0.
[47]
HINDSON J. Organ preservation versus radical surgery for early-stage rectal cancer[J/OL]. Nat Rev Gastroenterol Hepatol, 2021, 18(2): 82 [2024-10-21]. https://www.nature.com/articles/s41575-021-00414-8. DOI: 10.1038/s41575-021-00414-8.
[48]
FRANCA A L, MUTTILLO E M, MADAFFARI I, et al. Lymph node metastasis in extraperitoneal rectal cancer after neoadjuvant therapy: an unsolved problem?[J]. Anticancer Res, 2023, 43(6): 2813-2820. DOI: 10.21873/anticanres.16450.
[49]
FANG Z, PU H, CHEN X L, et al. MRI radiomics signature to predict lymph node metastasis after neoadjuvant chemoradiation therapy in locally advanced rectal cancer[J]. Abdom Radiol, 2023, 48(7): 2270-2283. DOI: 10.1007/s00261-023-03910-4.
[50]
ZHOU X Z, YI Y J, LIU Z Y, et al. Radiomics-based preoperative prediction of lymph node status following neoadjuvant therapy in locally advanced rectal cancer[J/OL]. Front Oncol, 2020, 10: 604 [2024-10-21]. https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2020.00604/full. DOI: 10.3389/fonc.2020.00604.
[51]
ZHANG S Y, TANG B, YU M R, et al. Development and validation of a radiomics model based on lymph-node regression grading after neoadjuvant chemoradiotherapy in locally advanced rectal cancer[J]. Int J Radiat Oncol Biol Phys, 2023, 117(4): 821-833. DOI: 10.1016/j.ijrobp.2023.05.027.
[52]
ZHU H T, ZHANG X Y, LI X T, et al. Prediction of pathological nodal stage of locally advanced rectal cancer by collective features of multiple lymph nodes in magnetic resonance images before and after neoadjuvant chemoradiotherapy[J]. Chin J Cancer Res, 2019, 31(6): 984-992. DOI: 10.21147/j.issn.1000-9604.2019.06.14.

上一篇 MRI评估肝细胞癌消融治疗疗效的研究进展
下一篇 影像基因组学在泌尿系统肿瘤中的评估机制及研究进展
  
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