摘要:鼻咽癌是一種惡性度較高的癌癥,早期頸部淋巴結(jié)轉(zhuǎn)移為其典型特征之一,顯著影響患者預(yù)后。應(yīng)用影像學(xué)方法進(jìn)行頸部淋巴結(jié)檢查可盡早篩查出鼻咽癌。本文簡要概述了鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移的主要影像學(xué)特征,探討了MRI、CT、超聲等常用影像學(xué)診斷方法和PET、熒光成像等新技術(shù)在鼻咽癌頸淋巴結(jié)轉(zhuǎn)移診斷中的研究進(jìn)展,以及人工智能輔助影像診斷轉(zhuǎn)移性頸部淋巴結(jié)的最新應(yīng)用。隨著人工智能等新技術(shù)的不斷發(fā)展,影像學(xué)方法在鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移診斷中的應(yīng)用將更加精準(zhǔn),可為疾病的早期發(fā)現(xiàn)、精準(zhǔn)治療及預(yù)后評估提供有力支持。
關(guān)鍵詞:鼻咽癌;淋巴結(jié)轉(zhuǎn)移;影像學(xué)檢查;人工智能
Advances in the application of medical imaging methods in the diagnosis of cervical lymph node metastasis in nasopharyngeal carcinoma
LIU Yiwei1, 2, WANG Gang2, ZHOU Zibo3, ZHU Tongyao4, ZHAO Haina1, LING Wenwu1
1Department of Medical Ultrasound, West China Hospital of Sichuan University, Chengdu 610041, China; 2West China School of Medicine of Sichuan University, Chengdu 610041, China; 3College of Computer Science of Sichuan University, Chengdu 610041, China; 4Pittsburgh Institute of Sichuan University, Chengdu 610041, China
Abstract: Nasopharyngeal carcinoma is a type of cancer with high malignancy, and early cervical lymph node metastasis is one of its typical characteristics, which significantly affects the prognosis of patients. Imaging methods can be used for cervical lymph node examination to screen nasopharyngeal carcinoma as early as possible. This article briefly summarizes the imaging features of cervical lymph node metastasis in nasopharyngeal carcinoma, deeply discusses the research progress of commonly used imaging diagnostic methods such as MRI, CT, ultrasound, as well as new technologies such as PET and fluorescence imaging in the examination of cervical lymph node, and the latest application of AI-assisted imaging in the diagnosis of metastatic cervical lymph node. With the continuous development of new technologies such as AI, the application of imaging methods in the diagnosis of cervical lymph node metastasis in nasopharyngeal carcinoma will be more precise, providing strong support for early detection, precise treatment, and prognosis evaluation of the disease.
Keywords: nasopharyngeal carcinoma; lymph node metastasis; imaging examination; artificial intelligence
鼻咽癌是一種起源于鼻咽黏膜內(nèi)層的上皮癌,在東亞和東南亞的發(fā)病率較高,其誘因包括EB病毒感染、宿主遺傳和環(huán)境因素等[1]。鼻咽癌可以侵入附近組織,甚至通過血液或淋巴系統(tǒng)轉(zhuǎn)移到全身多處器官。鼻咽癌具有較高的頸部淋巴結(jié)轉(zhuǎn)移傾向,雙側(cè)頸部淋巴結(jié)轉(zhuǎn)移通常發(fā)生在疾病早期,且患者生存率與轉(zhuǎn)移淋巴結(jié)數(shù)目呈負(fù)相關(guān)[2-4]。因此,盡早篩查出鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移有助于臨床選擇合適的治療方式,對提高患者生存率具有重要意義。目前,臨床上主要使用影像學(xué)方法進(jìn)行頸部淋巴結(jié)檢查,因此本綜述旨在探討鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移的影像學(xué)特征及相關(guān)研究進(jìn)展,以期為鼻咽癌的早期診療、分期和預(yù)后等提供參考。
1" 鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移特征
淋巴結(jié)是人體重要的免疫器官,頸淋巴結(jié)浸潤程度是鼻咽癌的主要預(yù)后因素[5]。以往研究表明,鼻咽癌具有很高的淋巴結(jié)轉(zhuǎn)移率(可達(dá)94.5%),轉(zhuǎn)移多沿頸部有序擴(kuò)散,很少發(fā)生跳躍轉(zhuǎn)移[4, 6, 7]。頸部淋巴結(jié)的水平分類有助于鼻咽癌的定性診斷和分級分期,對于患者的生存和局部復(fù)發(fā)及遠(yuǎn)處轉(zhuǎn)移的檢測具有重要價值[8]。根據(jù)2017年國際抗癌聯(lián)盟和美國癌癥聯(lián)合委員會公布的第八版TNM分期系統(tǒng),隨著淋巴結(jié)受累程度和范圍的增加,可依次用N1~N3來表示鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移的不同階段。
針對第八版TNM分期系統(tǒng),有學(xué)者指出其局限性并提出了相應(yīng)的建議。如有研究證實(shí)單側(cè)咽后淋巴結(jié)轉(zhuǎn)移的鼻咽癌患者比雙側(cè)咽后淋巴結(jié)轉(zhuǎn)移患者具有更高的生存率,建議將后者從N1升級為N2[9]。有研究表明,鼻咽癌患者頸部V區(qū)后區(qū)淋巴結(jié)轉(zhuǎn)移預(yù)后差,遠(yuǎn)處轉(zhuǎn)移風(fēng)險(xiǎn)高,提示該區(qū)可能是鼻咽癌的一個新的頸部淋巴結(jié)節(jié)段[10]。有學(xué)者認(rèn)為,將多發(fā)性頸部淋巴結(jié)壞死患者分類為N3可以改善當(dāng)前TNM分期系統(tǒng)的預(yù)后[11]。也有研究證明,鼻咽癌轉(zhuǎn)移淋巴結(jié)的數(shù)量是患者生存的主要獨(dú)立預(yù)后因素,應(yīng)納入N分期系統(tǒng)以提高預(yù)測準(zhǔn)確性[12]。以上研究對于TNM分期系統(tǒng)的完善、鼻咽癌的分期及預(yù)后具有重要的參考價值。因此,準(zhǔn)確評估鼻咽癌患者頸部淋巴結(jié)是否存在轉(zhuǎn)移,對鼻咽癌的診療具有重要臨床意義。
2" 影像學(xué)檢查在鼻咽癌頸淋巴結(jié)轉(zhuǎn)移中的應(yīng)用價值
細(xì)針穿刺活檢是鑒別鼻咽癌患者頸部淋巴結(jié)轉(zhuǎn)移的金標(biāo)準(zhǔn)。然而,由于獲得有效細(xì)胞量不一,部分患者診斷困難[13]。影像學(xué)檢查包括MRI、CT、PET、超聲等,對于頭頸部腫瘤患者頸淋巴結(jié)轉(zhuǎn)移具有良好的診斷性能,在轉(zhuǎn)移性淋巴結(jié)的診斷中發(fā)揮重要作用[14, 15]。
MRI對軟組織分辨率較高,是檢查淋巴結(jié)的常用手段[16]。有學(xué)者認(rèn)為,MRI可精確顯示早期原發(fā)性腫瘤,并且更易發(fā)現(xiàn)深部原發(fā)性腫瘤浸潤,建議應(yīng)優(yōu)先使用MRI進(jìn)行鼻咽癌分期[17]。有學(xué)者認(rèn)為,MRI確定的轉(zhuǎn)移淋巴結(jié)最大軸向直徑大于4 cm是鼻咽癌獨(dú)立陰性預(yù)后因素,建議將此參數(shù)作為TNM分期系統(tǒng)中N3分類的亞群[18]。此外,有研究結(jié)合合成MRI參數(shù)、擴(kuò)散加權(quán)成像參數(shù)與淋巴結(jié)形態(tài)學(xué)特征,顯著提高了鼻咽癌良惡性淋巴結(jié)診斷效率[19]。也有學(xué)者基于PET/MR進(jìn)行鼻咽癌相關(guān)研究。如有研究證實(shí)同步全身18F-FDG PET/MR對轉(zhuǎn)移性淋巴結(jié)的評估有著更高的敏感度,可用于鼻咽癌患者分期[20]。
除淋巴結(jié)的大小、位置、偏側(cè)性等參數(shù),由MRI確定的其他淋巴結(jié)狀態(tài)包括分組、壞死、包膜外擴(kuò)散和融合等。有研究將淋巴結(jié)分組納入預(yù)后生存列線圖模型,發(fā)現(xiàn)淋巴結(jié)分組是MRI檢測到的區(qū)域淋巴結(jié)預(yù)測總體生存率的重要預(yù)后因素[21]。有學(xué)者開發(fā)了基于MRI的列線圖,發(fā)現(xiàn)頸部淋巴結(jié)壞死可有效預(yù)測鼻咽癌患者的生存風(fēng)險(xiǎn)[22]。影像學(xué)淋巴結(jié)外擴(kuò)散(rENE),即淋巴結(jié)包膜外擴(kuò)散的影像學(xué)表現(xiàn)。有研究依據(jù)浸潤程度將rENE分為4級,并發(fā)現(xiàn)第3級rENE是影響鼻咽癌患者5年生存期的獨(dú)立不良指標(biāo)[23]。有學(xué)者使用簇狀淋巴結(jié)的MRI圖像構(gòu)建了列線圖,發(fā)現(xiàn)簇狀淋巴結(jié)是鼻咽癌患者無遠(yuǎn)處轉(zhuǎn)移生存期的獨(dú)立預(yù)后因素,有助于評估患者遠(yuǎn)處轉(zhuǎn)移風(fēng)險(xiǎn)[24]。有學(xué)者對轉(zhuǎn)移性淋巴結(jié)的MRI特征作出以下解釋:淋巴結(jié)外腫瘤組織浸潤淋巴結(jié)周圍脂肪組織,或淋巴結(jié)周圍結(jié)締組織增生,導(dǎo)致其邊界模糊;腫瘤浸潤和淋巴結(jié)內(nèi)軟化或壞死,導(dǎo)致T2加權(quán)圖像上的信號強(qiáng)度不規(guī)則,而對比增強(qiáng)的T1加權(quán)圖像上的信號強(qiáng)度不均勻。依據(jù)以上形態(tài)學(xué)特征,可有助于MRI對頭頸部腫瘤患者淋巴結(jié)轉(zhuǎn)移的檢測[25]。上述研究均表明,MRI確定的轉(zhuǎn)移性頸淋巴結(jié)特征可顯著影響鼻咽癌患者的預(yù)后,具有重要的臨床意義。
CT是檢查頸淋巴結(jié)的良好手段,研究已證實(shí)了其在甲狀腺癌[26]、口腔癌[27]等癌癥的頸淋巴結(jié)轉(zhuǎn)移診斷中有較好的應(yīng)用價值。相比于CT,PET/CT結(jié)合組織代謝功能與解剖形態(tài),可更準(zhǔn)確地識別轉(zhuǎn)移性淋巴結(jié)[28]。以往研究表明,PET/CT較MRI可更精準(zhǔn)地診斷鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移,有利于鼻咽癌分期[29, 30]。有研究表明,PET/CT比MRI和超聲能更準(zhǔn)確地檢測鼻咽癌患者的復(fù)發(fā)淋巴結(jié)[31]。而也有學(xué)者認(rèn)為,相較于具有高空間分辨率的超聲、CT和MRI,PET/CT的敏感度和陰性預(yù)測值最高,但也具有最低的特異度和準(zhǔn)確度以及最高的假陽性率[32]。多項(xiàng)研究表明,聯(lián)合使用MRI和PET/CT可以清楚顯示鼻咽癌的淋巴結(jié)擴(kuò)散模式,對鼻咽癌重新分期的準(zhǔn)確性優(yōu)于單獨(dú)使用其中一種手段[30, 33-34]。
臨床上常用18F-FDG等作為PET顯像劑,由于采用的顯像劑不同,相關(guān)研究的結(jié)論存在差異。如有學(xué)者比較了鎵-68標(biāo)記的成溴細(xì)胞活化蛋白抑制劑(68Ga-FAPI)和18F-FDG頭頸部PET/MR對鼻咽癌患者的診斷效果,發(fā)現(xiàn)18F-FDG能檢測出更多的陽性淋巴結(jié)[35]。在一項(xiàng)病例報(bào)告中,1例鼻咽癌患者被18F-FDG PET/CT誤診為雙側(cè)頸淋巴結(jié)轉(zhuǎn)移,而在非轉(zhuǎn)移性淋巴結(jié)中沒有觀察到異常的68Ga-FAPI攝取,該研究據(jù)此推測68Ga-FAPI PET/CT可能比18F-FDG PET/CT更好地評估鼻咽癌患者治療前的淋巴結(jié)狀態(tài)[36]。上述研究提示,在鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移檢查中采用不同的成像方法,可能會產(chǎn)生不同的診斷結(jié)果。
相較于CT和MRI,超聲檢查無輻射、價格低廉、操作便捷,對較小的或早期轉(zhuǎn)移性淋巴結(jié)具有更高的分辨率[37]。目前,臨床上常用的超聲檢查包括B超、彩色多普勒成像等常規(guī)手段,以及彈性超聲和超聲造影等新技術(shù)。B超依據(jù)淋巴結(jié)大小鑒別良惡性淋巴結(jié),無法排除惡性浸潤,因此在淋巴結(jié)診斷方面受限;彩色多普勒成像可顯示大血管結(jié)構(gòu),提升良惡性淋巴結(jié)鑒別的準(zhǔn)確率,但微血管結(jié)構(gòu)顯示不佳[38]。因此,超聲檢查新技術(shù)在良惡性淋巴結(jié)診斷中發(fā)揮重要作用。
超聲彈性成像對組織硬度敏感,并被證實(shí)在鼻咽癌頸淋巴結(jié)轉(zhuǎn)移的診斷中具有優(yōu)勢。例如有學(xué)者采用剪切波彈性成像并獲得了較高的敏感度、特異度和準(zhǔn)確度,證明其可以作為鼻咽癌頸淋巴結(jié)常規(guī)檢查的輔助成像方式[39]。研究發(fā)現(xiàn),鼻咽癌良惡性淋巴結(jié)的最大和平均彈性指數(shù)存在具有統(tǒng)計(jì)學(xué)意義的差異,剪切波彈性成像有助于鼻咽癌N分期和生存預(yù)后[40]。
超聲造影通過使用微泡造影劑提供組織灌注信息,實(shí)現(xiàn)血液供應(yīng)的實(shí)時可視化,可更好地顯示淋巴結(jié)微血管狀況,具有更高的診斷準(zhǔn)確性[37, 41, 42]。已有研究證明,相較于頸部良性淋巴結(jié),鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移在超聲造影圖像上呈現(xiàn)具有統(tǒng)計(jì)學(xué)意義的特征,包括向心灌注、不均勻強(qiáng)化、明顯的高強(qiáng)化和出現(xiàn)無灌注區(qū)[13]。然而,超聲造影具有很高的時空復(fù)雜性,這使其定量評估有一定難度[43]。
熒光成像是一種新穎的分子影像學(xué)技術(shù),已廣泛應(yīng)用于多種癌癥的淋巴結(jié)轉(zhuǎn)移檢查中。例如,有研究制備了對淋巴結(jié)微轉(zhuǎn)移有更高的分辨率的近紅外熒光探針,成功將其應(yīng)用于乳腺癌轉(zhuǎn)移性淋巴結(jié)的術(shù)前評估和術(shù)中導(dǎo)航[44]。有研究采用吲哚菁綠熒光導(dǎo)航腹腔鏡檢測盆腔淋巴結(jié),可有效治療晚期直腸癌[45]。在鼻咽癌淋巴結(jié)轉(zhuǎn)移診斷中,有研究使用吲哚菁綠進(jìn)行術(shù)中實(shí)時熒光成像并成功定位復(fù)發(fā)性鼻咽癌前哨淋巴結(jié),有助于患者的淋巴結(jié)分期[46]。目前有關(guān)熒光成像在鼻咽癌轉(zhuǎn)移性淋巴結(jié)中的應(yīng)用報(bào)道較少。這為未來的研究提供了思路,熒光成像可能在鼻咽癌轉(zhuǎn)移性淋巴結(jié)的檢查與診斷中有著廣闊的應(yīng)用前景。
綜上,影像學(xué)檢查在鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移診斷中具有顯著的優(yōu)勢,但也存在一定的局限性。以超聲檢查為例,其診斷表現(xiàn)受醫(yī)師經(jīng)驗(yàn)、患者合作性、淋巴結(jié)大小和位置的影響較大[47]。由于診斷過程存在一定主觀性,不同醫(yī)生的診斷結(jié)果也不可避免地存在分歧[42]。而近年來AI技術(shù)的發(fā)展,或?qū)⒂兄诟珳?zhǔn)的鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移影像學(xué)診斷。
3" AI模型在轉(zhuǎn)移性淋巴結(jié)影像診斷中的應(yīng)用
AI已廣泛應(yīng)用于影像輔助診斷,其技術(shù)手段包括機(jī)器學(xué)習(xí)(ML)和深度學(xué)習(xí)(DL)等。ML常用的算法類型有支持向量機(jī)和隨機(jī)森林等,卷積神經(jīng)網(wǎng)絡(luò)則是最重要的DL算法,可高效地進(jìn)行圖像分類[48, 49]。ML方法依賴專家從感興趣區(qū)提取圖像特征并輸入ML分類器中,而DL算法可以從數(shù)據(jù)中自動學(xué)習(xí)特征表示,減少了對手動預(yù)處理步驟的需求[50]。
目前,臨床上已經(jīng)使用AI技術(shù)進(jìn)行醫(yī)學(xué)圖像識別,用于輔助多種癌癥的淋巴結(jié)轉(zhuǎn)移診斷。例如,有研究依據(jù)原發(fā)性乳腺癌患者的腋窩淋巴結(jié)超聲圖像構(gòu)建的DL模型,能有效預(yù)測淋巴結(jié)轉(zhuǎn)移風(fēng)險(xiǎn)[51]。有學(xué)者利用ML技術(shù)開發(fā)了一種基于術(shù)前MRI的影像組學(xué)評估方法,可有效識別早期浸潤性乳腺癌腋窩淋巴結(jié)轉(zhuǎn)移[52]。有研究開發(fā)了一種術(shù)前自動AI算法,用于腫瘤和淋巴結(jié)的CT圖像分割,可預(yù)測胰腺導(dǎo)管腺癌患者的淋巴結(jié)轉(zhuǎn)移[53]。AI技術(shù)在影像學(xué)領(lǐng)域的應(yīng)用,一定程度地提高了診斷效率,有著極大的應(yīng)用價值。
近年來,有學(xué)者提出了用于鼻咽癌頸淋巴結(jié)轉(zhuǎn)移影像診斷的AI方法。有研究通過淋巴結(jié)MRI圖像特征構(gòu)建列線圖,可以很好地預(yù)測鼻咽癌患者的遠(yuǎn)處轉(zhuǎn)移風(fēng)險(xiǎn),有助于指導(dǎo)臨床決策和鼻咽癌患者的治療后監(jiān)測[54]。有學(xué)者構(gòu)建了一種基于MRI的全自動圖像分割模型,可有效地對鼻咽癌原發(fā)性病灶和轉(zhuǎn)移性淋巴結(jié)圖像進(jìn)行聯(lián)合分割并輔助鼻咽癌分期,有利于預(yù)后預(yù)測和有針對性的放療計(jì)劃[55]。有研究利用治療前MRI技術(shù)開發(fā)卷積神經(jīng)網(wǎng)絡(luò),用于分析鼻咽癌患者的頸部轉(zhuǎn)移性淋巴結(jié),并很好地預(yù)測了患者的遠(yuǎn)處轉(zhuǎn)移[56]。使用AI模型輔助鼻咽癌轉(zhuǎn)移性頸部淋巴結(jié)的診斷,可以減輕影像科醫(yī)師的負(fù)擔(dān),并有效地進(jìn)行鼻咽癌診斷、分期和預(yù)測。然而,現(xiàn)有的研究主要集中在使用AI模型輔助鼻咽癌原發(fā)性腫瘤的影像診斷[57],有關(guān)鼻咽癌轉(zhuǎn)移性淋巴結(jié)的文獻(xiàn)報(bào)道較少?;谏鲜鲅芯砍晒梢灶A(yù)見,AI技術(shù)在輔助鼻咽癌轉(zhuǎn)移性淋巴結(jié)診斷中有著巨大的潛力。
4" 總結(jié)與展望
鼻咽癌是一種惡性度較高的癌癥,頸部淋巴結(jié)轉(zhuǎn)移狀態(tài)是其重要的預(yù)后因素。多種影像學(xué)檢查手段和AI技術(shù)的輔助應(yīng)用在鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移的診斷中均發(fā)揮了重要的作用,可以從頸部淋巴結(jié)的大小、分布及形態(tài)用于輔助淋巴結(jié)轉(zhuǎn)移的診斷,以提高臨床對腫瘤進(jìn)行分期及預(yù)后的判斷的準(zhǔn)確性,是治療后隨訪的最重要方法。但現(xiàn)有的影像學(xué)檢查技術(shù)及AI研究仍存在局限性:影像學(xué)檢查對轉(zhuǎn)移性淋巴結(jié)判斷的精準(zhǔn)度仍有待于提高;大多數(shù)AI研究缺乏多中心的驗(yàn)證,所構(gòu)建模型的精準(zhǔn)度依賴于病灶的精準(zhǔn)勾畫等,難以應(yīng)用推廣。隨著分子影像學(xué)及AI技術(shù)的快速發(fā)展,有望進(jìn)一步提高鼻咽癌頸部淋巴結(jié)轉(zhuǎn)移診斷的準(zhǔn)確性,為其診療提供更多有價值的信息特征。
參考文獻(xiàn):
[1]" "Chen YP, Chan ATC, Le QT, et al. Nasopharyngeal carcinoma[J]. Lancet, 2019, 394(10192): 64-80.
[2] Lin M, Zhang XL, You R, et al. Evolutionary route of nasopharyngeal carcinoma metastasis and its clinical significance[J]. Nat Commun, 2023, 14(1): 610.
[3]" "Yeung DCM, Yeung Z, Wong EWY, et al. Neck lymph node status on survival of regionally recurrent or persistent nasopharyngeal carcinoma[J]. Sci Rep, 2020, 10(1): 5622.
[4]" "Ho FCH, Tham IWK, Earnest A, et al. Patterns of regional lymph node metastasis of nasopharyngeal carcinoma: a meta-analysis of clinical evidence[J]. BMC Cancer, 2012, 12: 98.
[5]" Sham JS, Choy D, Wei WI. Nasopharyngeal carcinoma: orderly neck node spread[J]. Int J Radiat Oncol Biol Phys, 1990, 19(4): 929-33.
[6]" "Liu LZ, Zhang GY, Xie CM, et al. Magnetic resonance imaging of retropharyngeal lymph node metastasis in nasopharyngeal carcinoma: patterns of spread[J]. Int J Radiat Oncol Biol Phys, 2006, 66(3): 721-30.
[7]" "Wang L, Wu Z, He Q, et al. Distribution of regional lymph nodes metastasis in 870 cases of nasopharyngeal carcinoma and the suggestions for individualized elective prophylactic neck irradiation with intensity-modulated radiotherapy[J]. Cancer Med, 2024, 13(3): e6723.
[8]" "Liu YT, Zhao JJ, Luo QY, et al. Automated classification of cervical lymph?node?level from ultrasound using Depthwise Separable Convolutional Swin Transformer[J]. Comput Biol Med, 2022, 148: 105821.
[9]" "Huang L, Zhang Y, Liu YF, et al. Prognostic value of retropharyngeal lymph node metastasis laterality in nasopharyngeal carcinoma and a proposed modification to the UICC/AJCC N staging system[J]. Radiother Oncol, 2019, 140: 90-7.
[10] Jiang CY, Gao H, Zhang L, et al. Distribution pattern and prognosis of metastatic lymph nodes in cervical posterior to level V in nasopharyngeal carcinoma patients[J]. BMC Cancer, 2020, 20(1): 667.
[11] Li J, Zhao Q, Zhang Y, et al. Prognostic value of quantitative cervical nodal necrosis burden on MRI in nasopharyngeal carcinoma and its role as a stratification marker for induction chemotherapy[J]. Eur Radiol, 2022, 32(11): 7710-21.
[12] Ma HL, Liang SB, Cui CY, et al. Prognostic significance of quantitative metastatic lymph node burden on magnetic resonance imaging in nasopharyngeal carcinoma: a retrospective study of 1224 patients from two centers[J]. Radiother Oncol, 2020, 151: 40-6.
[13] Ling WW, Nie J, Zhang DY, et al. Role of contrast-enhanced ultrasound (CEUS) in the diagnosis of cervical lymph node metastasis in nasopharyngeal carcinoma (NPC) patients[J]. Front Oncol, 2020, 10: 972.
[14] Abdel Khalek Abdel Razek A, King A. MRI and CT of nasopharyngeal carcinoma[J]. AJR Am J Roentgenol, 2012, 198(1): 11-8.
[15]" Liao LJ, Lo WC, Hsu WL, et al. Detection of cervical lymph node metastasis in head and neck cancer patients with clinically N0 neck-a meta-analysis comparing different imaging modalities[J]. BMC Cancer, 2012, 12: 236.
[16]" Amin MB, Greene FL, Edge SB, et al. The Eighth Edition AJCC Cancer Staging Manual: continuing to build a bridge from a population?based to a more \"personalized\" approach to cancer staging[J]. CA Cancer J Clin, 2017, 67(2): 93-9.
[17]" Liao XB, Mao YP, Liu LZ, et al. How does magnetic resonance imaging influence staging according to AJCC staging system for nasopharyngeal carcinoma compared with computed tomography?[J]. Int J Radiat Oncol Biol Phys, 2008, 72(5): 1368-77.
[18] Huang CL, Chen Y, Guo R, et al. Prognostic value of MRI-determined cervical lymph node size in nasopharyngeal carcinoma[J]. Cancer Med, 2020, 9(19): 7100-6.
[19]" Wang P, Hu SD, Wang XY, et al. Synthetic MRI in differentiating benign from metastatic retropharyngeal lymph node: combination with diffusion-weighted imaging[J]. Eur Radiol, 2023, 33(1): 152-61.
[20] Chan SC, Yeh CH, Yen TC, et al. Clinical utility of simultaneous whole-body 18F-FDG PET/MRI as a single-step imaging modality in the staging of primary nasopharyngeal carcinoma[J]. Eur J Nucl Med Mol Imag, 2018, 45(8): 1297-308.
[21] Wan YZ, Tian L, Zhang GY, et al. The value of detailed MR imaging report of primary tumor and lymph nodes on prognostic nomograms for nasopharyngeal carcinoma after intensity-modulated radiotherapy[J]. Radiother Oncol, 2019, 131: 35-44.
[22] Liu KY, Lin ST, Ke LR, et al. Prognostic value and the potential role of treatment options for cervical lymph node necrosis in nasopharyngeal carcinoma[J]. Oral Oncol, 2020, 109: 104864.
[23] Mao YP, Wang SX, Lydiatt W, et al. Unambiguous advanced radiologic extranodal extension determined by MRI predicts worse outcomes in nasopharyngeal carcinoma: potential improvement for future editions of N category systems[J]. Radiother Oncol, 2021, 157: 114-21.
[24]" Ma HL, Qiu YY, Li HJ, et al. Prognostic value of nodal matting on MRI in nasopharyngeal carcinoma patients[J]. J Magn Reson Imaging, 2021, 53(1): 152-64.
[25]" de Bondt RBJ, Nelemans PJ, Bakers F, et al. Morphological MRI criteria improve the detection of lymph node metastases in head and neck squamous cell carcinoma: multivariate logistic regression analysis of MRI features of cervical lymph nodes[J]. Eur Radiol, 2009, 19(3): 626-33.
[26] Lee DH, Kim YK, Yu HW, et al. Computed tomography for detecting cervical lymph node metastasis in patients who have papillary thyroid microcarcinoma with tumor characteristics appropriate for active surveillance[J]. Thyroid, 2019, 29(11): 1653-9.
[27]" Luo YH, Mei XL, Liu QR, et al. Diagnosing cervical lymph node metastasis in oral squamous cell carcinoma based on third-generation dual-source, dual-energy computed tomography[J]. Eur Radiol, 2023, 33(1): 162-71.
[28]" Lai V, Khong PL. Updates on MR imaging and 18F-FDG PET/CT imaging in nasopharyngeal carcinoma[J]. Oral Oncol, 2014, 50(6): 539-48.
[29]Ng SH, Chan SC, Yen TC, et al. Staging of untreated nasopharyngeal carcinoma with PET/CT: comparison with conventional imaging work-up[J]. Eur J Nucl Med Mol Imaging, 2009, 36(1): 12-22.
[30]" Yang SS, Wu YS, Chen WC, et al. Benefit of [18F]-FDG PET/CT for treatment-na?ve nasopharyngeal carcinoma[J]. Eur J Nucl Med Mol Imaging, 2022, 49(3): 980-91.
[31]" OuYang PY, Liu ZQ, Lin QG, et al. Benefit of[18F]FDG PET/CT in the diagnosis and salvage treatment of recurrent nasopharyngeal carcinoma[J]. Eur J Nucl Med Mol Imaging, 2023, 50(3): 881-91.
[32] Takamura M, Nikkuni Y, Hayashi T, et al. Comparing the diagnostic accuracy of ultrasonography, CT, MRI, and PET/CT in cervical lymph node metastasis of oral squamous cell carcinoma[J]. Biomedicines, 2023, 11(12): 3119.
[33] Comoretto M, Balestreri L, Borsatti E, et al. Detection and restaging of residual and/or recurrent nasopharyngeal carcinoma after chemotherapy and radiation therapy: comparison of MR imaging and FDG PET/CT[J]. Radiology, 2008, 249(1): 203-11.
[34]Ng SH, Chang JTC, Chan SC, et al. Nodal metastases of nasopharyngeal carcinoma: patterns of disease on MRI and FDG PET[J]. Eur J Nucl Med Mol Imaging, 2004, 31(8): 1073-80.
[35]" Qin CX, Liu F, Huang J, et al. A head-to-head comparison of 68Ga-DOTA?FAPI?04 and 18F?FDG PET/MR in patients with nasopharyngeal carcinoma: a prospective study[J]. Eur J Nucl Med Mol Imaging, 2021, 48(10): 3228-37.
[36]Shang QH, Zhao L, Pang YZ, et al. 68Ga?FAPI PET/CT distinguishes the reactive lymph nodes from tumor metastatic lymph nodes in a patient with nasopharyngeal carcinoma[J]. Clin Nucl Med, 2022, 47(4): 367-8.
[37]" Ding SW, Xiong P, Zuo JX. Value of contrast-enhanced ultrasound in predicting early lymph-node metastasis in oral cancer[J]." Dentomaxillofac Radiol, 2022, 51(3): 20210293.
[38] Cui XW, Hocke M, Jenssen C, et al. Conventional ultrasound for lymph node evaluation, update 2013[J]. Z Gastroenterol, 2014, 52(2): 212-21.
[39] Chen BB, Li J, Guan Y, et al. The value of shear wave elastography in predicting for undiagnosed small cervical lymph node metastasis in nasopharyngeal carcinoma: a preliminary study[J]. Eur J Radiol, 2018, 103: 19-24.
[40]" Guan Y, Liu S, Li AC, et al. A pilot study: N-staging assessment of shear wave elastrography in small cervical lymph nodes for nasopharyngeal carcinoma[J]. Front Oncol, 2020, 10: 520.
[41] Wilson SR, Burns PN. Microbubble contrast for radiological imaging: 2. Applications[J]. Ultrasound Q, 2006, 22(1): 15-8.
[42] Nie J, Ling WW, Yang QR, et al. The value of CEUS in distinguishing cancerous lymph nodes from the primary lymphoma of the head and neck[J]. Front Oncol, 2020, 10: 473.
[43] Zhang YF, Wei QY, Huang YN, et al. Deep learning of liver contrast?enhanced ultrasound to predict microvascular invasion and prognosis in hepatocellular carcinoma[J]. Front Oncol, 2022, 12: 878061.
[44]" Zhao D, Xu MH, Yang SY, et al. Specific diagnosis of lymph node micrometastasis in breast cancer by targeting activatable near-infrared fluorescence imaging[J]. Biomaterials, 2022, 282: 121388.
[45] Su H, Xu Z, Bao M, et al. Lateral pelvic sentinel lymph node biopsy using indocyanine green fluorescence navigation: can it be a powerful supplement tool for predicting the status of lateral pelvic lymph nodes in advanced lower rectal cancer[J]. Surg Endosc, 2023, 37(5): 4088-96.
[46] Chan JYW, Tsang RKY, Wong STS, et al. Indocyanine green fluorescence mapping of sentinel lymph node in patients with recurrent nasopharyngeal carcinoma after previous radiotherapy[J]. Head Neck, 2015, 37(12): E169-73.
[47]" Ryu SW, Bok GH, Jang JY, et al. Clinically useful diagnostic tool of contrast enhanced ultrasonography for focal liver masses: comparison to computed tomography and magnetic resonance imaging[J]. Gut Liver, 2014, 8(3): 292-7.
[48]" Mitsala A, Tsalikidis C, Pitiakoudis M, et al. Artificial intelligence in colorectal cancer screening, diagnosis and treatment. A new era[J]. Curr Oncol, 2021, 28(3): 1581-607.
[49]Barragán?Montero A, Javaid U, Valdés G, et al. Artificial intelligence and machine learning for medical imaging: a technology review[J]. Phys Med, 2021, 83: 242-56.
[50]" Hosny A, Parmar C, Quackenbush J, et al. Artificial intelligence in radiology[J]. Nat Rev Cancer, 2018, 18(8): 500-10.
[51] Zhou LQ, Wu XL, Huang SY, et al. Lymph node metastasis prediction from primary breast cancer US images using deep learning[J]. Radiology, 2020, 294(1): 19-28.
[52] Yu YF, He ZF, Ouyang J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study[J]. EBio Med, 2021, 69: 103460.
[53]" Bian Y, Zheng ZL, Fang X, et al. Artificial intelligence to predict lymph node metastasis at CT in pancreatic ductal adenocarcinoma[J]. Radiology, 2023, 306(1): 160-9.
[54]" Xie CB, Li HJ, Yan Y, et al. A nomogram for predicting distant metastasis using nodal?related features among patients with nasopharyngeal carcinoma[J]. Front Oncol, 2020, 10: 616.
[55]" Li Y, Dan TT, Li HJ, et al. NPCNet: jointly segment primary nasopharyngeal carcinoma tumors and metastatic lymph nodes in MR images[J]. IEEE Trans Med Imaging, 2022, 41(7): 1639-50.
[56]" Hua HL, Deng YQ, Li S, et al. Deep learning for predicting distant metastasis in patients with nasopharyngeal carcinoma based on pre-radiotherapy magnetic resonance imaging[J]. Comb Chem High Throughput Screen, 2023, 26(7): 1351-63.
[57]" Wang ZP, Fang MJ, Zhang J, et al. Radiomics and deep learning in nasopharyngeal carcinoma: a review[J]. IEEE Rev Biomed Eng, 2024, 17: 118-35.
(編輯:郎" 朗)