Analysis of Prognosis of Coronavirus Disease 2019 Using Quantitative Measurement of Deep Learning
-
摘要: 目的：分析基于深度学习定量测量新型冠状病毒感染（COVID-19）患者胸部CT炎性病灶的特征，预警重症的发生，提高对COVID-19预后的认识。方法：回顾性分析477例首次确诊为中型COVID-19患者的胸部CT，男276例，女201例，根据是否转为重症（重型/危重型）分为A组（未转为重症）、B组（转为重症），比较两组病例病灶分布、累及肺叶侧别、数目等CT基本征象及基于深度学习的病灶体积、体积占比和密度等的差异。结果：477例COVID-19患者均有流行病学史，年龄、性别在两组间的差异无统计学意义。B组全肺及各肺叶病灶体积及体积占比高于A组。A组病灶以右肺下叶为主，占比高于其它肺叶，达3.32％；其次为左肺下叶，占比为2.08％；左肺上叶病灶体积占比较其他肺叶低，仅为0.25％。A组部分患者右肺上叶、右肺中叶及左肺上叶无病灶。B组病灶呈双肺分布，各肺叶均有；其中以右肺下叶、左肺下叶分布为主，占比最高，分别为57.86％ 和54.76％；右肺中叶体积占比较其他肺叶低，为34.73％。各组病灶均以磨玻璃密度影为主。A组以密度为 -570～-470 HU病灶为主，占比达13.89％；其次为 -470～-370 HU，占比为11.07％；密度为30～70 HU实性病灶及密度为 -70～30 HU较少，占比仅3.22％ 和4.75％。B组大部分呈磨玻璃密度影，以病灶密度为 -570～-470 HU、-470～-370 HU与 -370～-270 HU为主，占比分别为13.18％、12.58％、12.52％；密度为 -570～-470 HU的病灶占比与A组差异无统计学意义，余各密度病灶体积及体积占比高于A组，呈病灶密度越高，B组占比较A组越高的趋势。结论：感染病灶体积较大、实性成分较多及多种CT征象并存常提示肺部炎症较重，容易进展为重症，基于深度学习的胸部CT定量测量有助于评估COVID-19预后及预警重症。Abstract: Objective: To analyze the differences of chest computed tomography (CT) inflammatory lesions in patients with coronavirus disease 2019 (COVID-19), which were quantitatively measured based on deep learning, to warn the occurrence of severe cases and improve the understanding of the prognosis of COVID-19. Methods: The chest CT scans of 477 local patients with COVID-19 diagnosed for the first time at Inner Mongolia Autonomous Region People's Hospital were retrospectively analyzed. A total of 276 men and 201 women were divided into group A (not serious) and group B (serious) based on whether their diseases turned serious (severe/critical). Comparison was made between the two groups on the basic CT signs, such as lesion distribution, involved lobe side, number, differences in lesion volume, volume proportion, and density based on deep learning. Results: All 477 patients with COVID-19 had epidemiological history, and no statistical difference was noted in age and gender between the two groups. The volume and proportion of the lesions in the whole lung and each lobe of the lung in group B were higher than those in group A. The lesions in group A were mainly in the lower lobe of the right lung, accounting for 3.32% more than that in other lobes. The lower lobe of the left lung was the next, accounting for 2.08%. The volume of lesions in the upper lobe of the left lung was lower than that in other lobes, accounting for only 0.25%. No lesions were noted in the upper lobe of the right lung, middle lobe of the right lung, and upper lobe of the left lung in part of group A. In group B, the lesions were distributed in both lungs and in each lung lobe. The lower lobes of the right lung and left lung were predominant, accounting for 57.86% and 54.76%, respectively. The volume of the middle lobe of the right lung was 34.73% compared with the other lobes. The main lesions in each group were ground-glass density shadows, and the main lesions in group A were −570 ~ −470 HU density, accounting for 13.89%, followed by −470 ~ −370 HU, accounting for 11.07%. Only 3.22% and 4.75% of solid lesions with densities of 30 ~ 70 HU and −70 ~ 30 HU were found. Most of the lesions in group B were ground-glass density shadows, and the focal densities were mainly −570 ~ −470 HU, −470 ~ −370 HU, and −370 ~ −270 HU, accounting for 13.18%, 12.58%, and 12.52%, respectively. No statistical difference was noted between the proportion of lesions with a density of −570 ~ −470 HU and that of group A; however, the volume and proportion of other lesions with different densities were higher than those of group A, showing a trend that the higher the density of the lesions, the higher the proportion of group B was compared with group A. Conclusion: Larger infection volume, more lesion solid components, and multiple CT signs often indicate more severe lung inflammation, which easily progresses to severe disease. Quantitative measurement of chest CT based on deep learning is helpful for the prognosis assessment of COVID-19 and the early warning of severe outcome.
-
Keywords:
- deep learning /
- tomography /
- X-ray computed /
- coronavirus disease 2019
-
结肠神经节缺乏症（colon innervation defect）在临床为少见病，术前诊断困难，其临床表现不典型；常以腹胀、腹痛、便秘和排便周期延长为主要临床表现；症状严重时可有恶心、呕吐症状，综合患者的病史均符合便秘和不完全性肠梗阻的临床特点；患者病程往往较长，部分患者病程长达5年；发病人群为成年人，以中老年人多见；临床误诊率较高[1-4]，易误诊为缺血性肠病、中毒性巨结肠和结肠癌伴肠梗阻等疾病。
由于早期对结肠神经节缺乏症的认识不足，很多患者并没有明确诊断为结肠神经节缺乏症，也未得到恰当的临床治疗。了解肠壁神经节变性、缺乏所致成人结肠神经节缺乏症发病机制、临床表现以及影像特征，及时正确诊断以及对患者给予有效的治疗，使成人结肠神经节缺乏症患者获益。
1. 材料与方法
1.1 临床资料
收集我院2007年1月至2021年12月间手术病理证实的结肠神经节缺乏症患者5例，女性3例，男性2例，均为成年人，年龄51～78岁。收集汇总患者的临床资料、影像学资料以及手术病理结果。
1.2 MSCT检查方法
使用GE Discovery 750 HD宝石能谱CT和Philips Brilliance Ingenuity 128层多层螺旋CT，使用相同的扫描参数，层厚1 mm，层间距1 mm，管电压120 kV，自动管电流，扫描范围自膈顶扫描至双侧耻骨联合下缘。由于结肠神经节缺乏症患者结肠肠管大量食物残渣集聚，清洁灌肠效果不佳，反而导致肠腔大量积气反而影响观察效果，故建议在肠道自然状态下CT扫描（本研究组患者均未做肠道准备、不清洁灌肠和洗肠），扫描后在CT工作站进行MPR三维重建，重建资料在PACS系统存档分析。
增强扫描技术参数与平扫相同，增强扫描对比剂采用江苏省恒瑞医药生产的320 mgI/mL规格的碘佛醇，静脉注射，用量100 mL，注射流速4 mL/s，腹主动脉上端设置兴趣区自动触发扫描。
1.3 研究方法
总结结肠神经节缺乏症患者的临床表现特点；观察MSCT病变段肠管位置，分别测量扩张段和狭窄段肠壁厚度；病理医师测量狭窄段（病变段）肠管长度；多期MSCT增强扫描观察肠道蠕动、判断肠道功能情况；通过MSCT三期增强检查观察病变狭窄段和扩张段肠管的血运情况。
2. 结果
结肠神经节缺乏症的临床特点表现为成年人长期的便秘和不完全性肠梗阻。本组5例结肠神经节缺乏症患者MSCT均表现为病变段结肠肠腔相对狭窄与病变段近端结肠肠腔明显扩张（图1～图3），影像特征为结肠肠腔扩张后狭窄，扩张段结肠管壁厚度正常或不均一增厚，本组结肠肠壁厚度大于0.3 cm、小于0.9 cm，狭窄段结肠肠壁厚度正常、无增厚改变（图1～图3）。
![]()
图 1 上腹CT平扫，横结肠脾曲肠腔扩张内径7 cm，肠壁均一弥漫性增厚，厚约0.5 cm，扩张肠腔内大量粪便集聚；结肠脾曲肠腔相对狭窄（空白箭），肠壁厚0.4～0.6 cmFigure 1. CT image of the abdomen，The splenic flexure of colon intestinal lumen was dilated, with an internal diameter of 6 cm, and the intestinal wall was diffuse and thickened, about 0.5 cm thick, and a large number of feces were concentrated in the dilated intestinal lumen. Colonic spleen curved intestinal lumen is relatively narrow (blank arrow), and the intestinal wall is 0.4～0.6 cm thick![]()
图 2 上腹CT平扫，横结肠肠腔扩张，大部分肠壁厚度正常、局部肠壁轻微增厚，最厚约0.4 cm，扩张的肠腔内大量粪便；降结肠病变段肠管相对狭窄（空白箭），肠壁厚约0.8 cmFigure 2. CT image of the abdomen，The transverse colon lumen is dilated, with uneven thickening, the thickest intestinal wall diameter is about 0.4 cm, a large number of fees were concentrated in the dilated intestinallumen. The diseased segment of the descending colon is relatively narrow (blank arrow), the local thickness is about 0.8 cm![]()
本组术后病变段肠管长度介于4.3～8.6 cm之间；扩张段肠管管腔内大量粪便聚集；多期增强CT显示狭窄段和扩张段肠管形态固定，提示结肠蠕动功能丧失；病变区域系膜血管和结肠肠壁MSCT增强扫描无异常强化，提示结肠肠壁血供正常；病变位置分布特点：病变肠管分布于降结肠3例，分布于结肠脾曲2例。
本组5例CT扫描显示病变段以远的结肠形态自然、肠腔无扩张和狭窄，肠壁无异常增厚，即病变段结肠厚度与扩张段和无病变段结肠肠壁比较无异常增厚改变（图3黑箭所示区域），提示影像学不能判断病变段肠管的范围；本组小肠扩张、肠腔内散在积气、积液2例，部分区域小肠肠腔可见内气液平形成，呈小肠梗阻改变（图3白箭所示区域）。
本组5例术后病理均诊断为结肠神经节缺乏症（图4和图5），免疫组化S-100，显示狭窄段肠粘膜下层及肌间神经节细胞数量显著减少。而在扩张段肠粘膜下层神经纤维略显增多。
![]()
图 4 图1患者术后大体标本，肉眼所见：全结肠切除标本：结肠长68 cm，周径5～12 cm，回肠长7 cm，周径3 cm。扩张段肠管长15 cm，周径12 cm，壁厚0.5 cm，粘膜灰红色，质软，皱襞较清晰；狭窄段肠管，长5 cm，周径5 cm，壁厚0.5 cmFigure 4. The Patient of fig.1, postoperative gross specimen, as seen by the naked eye. Total colon resection specimen: The colon is 68 cm long, the peripheral diameter is 5~12 cm, The ileum was 7 cm long with a circumference diameter of 3 cm. The intestine of the dilated segment was 15 cm long, Peridiameter 12 cm, wall thickness 0.5 cm, Mucosal membrane is grey-red, soft, The wrinkles are clear; The arrow segment intestine, 5 cm long, The circumference diameter is 5 cm and the wall thickness is 0.5 cm![]()
图 5 与图1同一患者，HE染色10×10结合免疫组化S-100，显示狭窄段肠黏膜下层及肌间神经节细胞数量显著减少。病理诊断：结肠神经节缺乏症（结肠假性）Figure 5. The same patient of fig.1, HE pathological staining, 10×10 combined with immunohistochemistry S-100, a narrow segment of the intestinal mucosa is shown the number of lower and myomuscular ganglion cells was significantly reduced. Pathological diagnosis: Colonic innervation defect (Hirschsprung' Disease)3. 讨论
3.1 成人巨结肠疾病流行病学
在临床，成人巨结肠疾病是一组临床疾病，包括成人先天性巨结肠、成人特发性巨结肠、结肠神经节缺乏症、中毒性巨结肠、医源性巨结肠等。成人先天性巨结肠为先天性出生缺陷性疾病，大部分患者年幼发病，在幼儿或儿童时期已经得到外科干预，仅部分短段型和超短段型幼儿期症状轻微未得到及时处理，拖延至青年时期发病或就医，导致就诊时病变肠段近端的正常肠段高度扩张、肌层代偿性增厚形成橡皮样的肠壁[1-3]。成人特发性巨结肠与成人先天性巨结肠有很多相似之处，从症状来说，两者均有排粪困难、腹痛腹胀等表现，排粪后临床症状可缓解，一般到青年时均得到手术治疗。
特发性巨结肠没有明显狭窄的肠段，其扩张的肠段即为病变肠段，该肠段的特点在于肠壁肌间神经节数量减少、变性，该病术前较难诊断，容易误诊为成人先天性巨结肠[1]。结肠神经节缺乏症与其他类型成人巨结肠在临床和MSCT表现上无明显差异，有报道指出，神经节细胞缺乏症相对发病年龄更大，且女性比例高[1,5-6]。结肠神经节缺乏症术中可以发现相对的狭窄段，狭窄段主要位于降结肠或乙状结肠，病变肠段内神经节细胞数量的明显低于正常，近端肠管明显扩张呈巨结肠样改变。
3.2 成人结肠神经节缺乏症临床特点与处理方案
成人结肠神经节缺乏症多见于中老年人，以慢性肠梗阻、便秘为临床表现，术后病理学为肠壁神经节变性、缺乏所致慢性疾病[1,7]，患者病程较长，临床术前诊断困难。由于病变段肠壁神经节减少、变性与缺失，病变段肠管失去扩张与蠕动功能，导致肠内容物阻滞、近端肠管扩张形成不全肠梗阻，影像学检查表现为不全肠梗阻、肠腔扩张后狭窄影像学改变，肠壁厚度对疾病诊断无帮助[8-9]。本组病例术后病理学与相关报道相符，结肠神经节缺乏症均表现为狭窄段结肠肠壁神经丛减少或变性、缺失，扩张段肠壁神经纤维反而有所增多。
由于患者病变段肠管相对狭窄以及蠕动功能丧失，肠腔内大量粪便集聚，病变段肠管近端管腔明显扩张，肠道内容物和较多积气干扰和影响了B超和磁共振的检查效果，临床多采用MSCT作为首选的检查手段。结肠神经节缺乏症患者在CT检查前不必要做肠道清洁灌肠准备工作，在自然状态下进行检查更能够反映结肠神经节缺乏症肠道扩张、粪便集聚的本来的面貌以及影像特点。
MSCT同样也印证了扩张以及狭窄段结肠的功能情况：MSCT三期增强扫描显示狭窄段以及扩张段肠管均形态固定,提示扩张以及狭窄段肠管均无运动功能、即肠管蠕动功能丧失，由此临床手术方式也大多选择次全结肠切除[1,10-11]。关于结肠神经节缺乏症供血，MSCT三期增强扫描观察肠壁和系膜血供无异常，依据病理学提供的病变段肠管的长度，回顾性分析影像学狭窄段的肠管与其远端正常肠管在形态、密度以及MSCT平扫+增强检查的表现，均没有显著的影像学差异。值得关注的是手术时术者无法依据望诊和触诊的物理手段确定狭窄区域病变段肠管切除范围，需依靠术中快速冰冻病理确定切缘位置。
对于成人先天性巨结肠，临床多采用改良Duhamel术、金陵术、低位前切除术或者拖出式低位前切除术[1,11]。对于特发性巨结肠患者可在术前准备充分的情况下，选择一期结直肠次全切除术治疗，部分以急诊肠梗阻入院的患者可先行保守治疗或者结肠镜减压好转后行择期手术治疗。对于神经节细胞缺乏症患者，手术方式采用和特发性巨结肠一致的结直肠次全切除术，将扩张的近端肠段和狭窄的远端肠段一并切除，行回肠直肠吻合或者升结肠直肠吻合[1,10-11]。
由于成人结肠神经节缺乏症临床病例少见，本研究组样本量小，需在以后采取多中心、持续扩大样本量进一步深入研究，以提高成人巨结肠之结肠神经节缺乏症影像学研究的水平，使成人结肠神经节缺乏症患者获益。
-
![]()
图 1 推想人工智能评估新型冠状病毒奥密克戎变异株感染患者肺内病灶体积示意图
患者，男，86岁，确诊为新型冠状病毒奥密克戎变异株感染。
Figure 1. Schematic diagram of InferVision artificial Intelligence evaluating the volume of lesions in the lung of patients infected with the COVID-19 omicron variant
![]()
图 2 新型冠状病毒感染中型未转重症患者
男，34岁，右肺上叶胸膜下斑片状磨玻璃密度影，可见小血管穿行。
Figure 2. COVID-19 medium type that was not converted to a severe case
![]()
图 4 新型冠状病毒感染中型未转重症患者
女，59岁,左肺上叶胸膜下束带状实变影、周围磨玻璃影。
Figure 4. COVID-19 medium type that was not converted to a severe case
![]()
图 3 新型冠状病毒感染中型未转重症患者
男，52岁,双肺下叶多发斑片状、小片状或小结节状磨玻璃密度影及条索，外带为主，可见小血管穿行。
Figure 3. COVID-19 medium type that was not converted to a severe case
![]()
图 5 新型冠状病毒感染中型未转重症患者
男性，53岁。（a）和（b）2022.12.15右肺下叶胸膜下斑片状磨玻璃密度影，边缘模糊、内可见增粗小血管。（c）和（d）2023.01.06复查，病灶基本吸收，可见淡薄磨玻璃影残留。
Figure 5. COVID-19 medium type that was not converted to a severe case
![]()
图 6 新型冠状病毒感染中型未转重症患者
男性，66岁，右肺上叶片状GGO，左肺上叶斑片状GGO，可见小叶间隔增厚及增粗小血管。
Figure 6. COVID-19 medium type that was not converted to a severe case
![]()
图 7 新型冠状病毒感染中型转重症患者
男性，67岁，双肺外周带分布磨玻璃密度影,沿支气管血管束分布，内见网格影、条索，血管增粗及胸膜增厚。
Figure 7. COVID-19 medium type that was converted to a severe case
表 1 A组和B组全肺及各肺叶病灶体积及体积占比
Table 1 The lesion volume and proportion of the whole lung and each lung lobe in groups A and B
指标 组别 统计检验 A组（n=450） B组（n=27） Z P 全肺病灶体积占比/％ 2.43（0.45～7.43） 40.45（33.47～46.60） 75.868 ＜0.001 全肺病灶体积 87.12（17.73～262.20） 1239.21（841.54～1395.12） 72.842 ＜0.001 右肺上叶病灶体积占比/％ 0.50（0～3.00） 35.70（20.84～50.32） 69.027 ＜0.001 右肺上叶病灶体积 4.56（0～24.22） 225.10（120.17～317.48） 64.978 ＜0.001 右肺中叶病灶体积占比/％ 0.53（0～4.45） 34.73（20.29～51.61） 64.665 ＜0.001 右肺中叶病灶体积 1.87（0～12.77） 101.87（54.41～153.72） 62.733 ＜0.001 右肺下叶病灶体积占比/％ 3.32（0.42～14.45） 57.96（38.89～63.36） 67.346 ＜0.001 右肺下叶病灶体积 28.11（3.75～86.83） 292.99（219.19～430.41） 62.544 ＜0.001 左肺上叶病灶体积占比/％ 0.25（0～2.49） 36.66（19.28～53.40） 72.725 ＜0.001 左肺上叶病灶体积 2.46（0～22.60） 217.79（128.16～347.07） 70.645 ＜0.001 左肺下叶病灶体积占比/％ 2.08（0.20～12.09） 54.76（37.02～64.50） 57.120 ＜0.001 左肺下叶病灶体积 15.62（1.64～73.52） 283.51（168.11～329.39） 53.018 ＜0.001 
下载: 导出CSV
表 2 A组和B组病灶密度及各密度病灶体积占比
Table 2 Lesion densities and volume proportion of each density in groups A and B
病灶密度（HU）及占比 组别 统计检验 A组 B组 Z P -570～-470体积 12.15（2.46～35.315） 141.75（101.24～197.83） 70.193 ＜0.001 -570～-470体积占比/％ 13.89（11.38～16.24） 13.18（11.11～15.10） 0.662 0.416 -470～-370体积 9.79（1.91～28.07） 144.65（113.14～181.30） 73.162 ＜0.001 -470～-370体积占比/％ 11.07（8.58～13.55） 12.58（10.80～15.05） 8.352 0.004 -370～-270体积 7.42（1.37～21.21） 125.49（100.26～174.70） 73.630 ＜0.001 -370～-270体积占比/％ 8.48（6.12～10.93） 12.52（9.88～15.32） 22.392 ＜0.001 -270～-170体积 5.28（1.03～15.84） 107.73（84.18～174.06） 72.647 ＜0.001 -270～-170体积占比/％ 6.27（4.32～8.95） 10.10（8.18～14.70） 22.871 ＜0.001 -170～-70体积 3.76（0.72～12.42） 88.10（55.36～146.54） 68.923 ＜0.001 -170～-70体积占比/％ 4.75（2.76～7.27） 7.69（6.34～11.04） 17.093 ＜0.001 -70～30体积 2.33（0.44～9.57） 62.38（29.04～83.22） 63.385 ＜0.001 -70～30体积占比/％ 3.22（1.49～5.77） 5.25（3.41～6.60） 9.336 0.002 30～70体积 0.47（0.05～2.08） 10.84（5.74～18.90） 57.192 ＜0.001 30～70体积占比/％ 0.60（0.18～1.50） 1.27（0.60～1.63） 5.928 0.015 其他 39.63（8.42～110.95） 307.92（250.60～534.06） 57.426 ＜0.001 其他占比/％ 47.91（35.69～59.69） 36.02（23.45～42.65） 16.879 ＜0.001
下载: 导出CSV
-
[1] 中华人民共和国国家卫生健康委员会. 关于印发对新型冠状病毒感染实施“乙类乙管”总体方案的通知 [EB/OL]. (2022-12-26)[2023-01-05]. http://www.nhc.gov.cn/xcs/zhengcwj/202212/e97e4c449d7a475794624b8ea12123c6.shtml. [2] 中华医学会放射学分会. 新型冠状病毒肺炎的放射学诊断: 中华医学会放射学分会专家推荐意见(第一版)[J]. 中华放射学杂志, 2020,54: E001−E001. DOI: 10.3760/cma.j.issn.1005-1201.2020.0001. Chinese Society of Radiology. Radiological diagnosis of new coronavirus infected pneumonitis: Expert recommendation from the Chinese Society of Radiology (First edition)[J]. Chinese Journal of Radiology, 2020, 54: E001−E001. DOI: 10.3760/cma.j.issn.1005-1201.2020.0001. (in Chinese).
[3] 孙莹, 李玲, 刘晓燕, 等. 早期新型冠状病毒肺炎的胸部薄层平扫CT表现特征[J]. CT理论与应用研究, 2023,32(1): 131−138. DOI: 10.15953/j.ctta.2023.006. SUN Y, LI L, LIU X Y, et al. Imaging features of early COVID-19 on chest thin-slice non-enhanced CT[J]. CT Theory and Applications, 2023, 32(1): 131−138. DOI: 10.15953/j.ctta.2023.006. (in Chinese).
[4] 中华人民共和国国家卫生健康委员会. 新型冠状病毒感染诊疗方案(试行第十版)[EB/OL]. (2023-01-06)[2023-01-20]. http://www.nhc.gov.cn/ylyjs/pqt/202301/32de5b2ff9bf4eaa88e75bdf7223a65a.shtml. [5] LI Q, GUAN X, WU P, et al. Early transmission dynamics in Wuhan, china, of novel coronavirus infected pneumonia[J]. The New England Journal of Medicine, 2020, 382(13): 1199−1207. DOI: 10.1056/NEJMoa2001316.
[6] MUNSTER V J, KOOPMANS M, VAN D N, et al. A novel coronavirus emerging in China-key questions for impact assessment[J]. The New England Journal of Medicine, 2020, 382(8): 692−694. DOI: 10.1056/NEJMp2000929.
[7] 靳英辉, 蔡林, 程真顺, 等. 新型冠状病毒 (2019-nCoV) 感染的肺炎诊疗快速建议指南(标准版)[J]. 解放军医学杂志, 2020,45(1): 1−20. DOI: 10.11855/j.issn.0577-7402.2020.01.01. JIN Y H, CAI L, CHENG Z S, et al. A rapid advice guideline for the diagnosis and treatment of 2019 novel coronavirus (2019-nCoV) infected pneumonia (Standard version)[J]. Medical Journal of Chinese People's Liberation Army, 2020, 45(1): 1−20. DOI: 10.11855/j.issn.0577-7402.2020.01.01. (in Chinese).
[8] KERMANY D S, GOLDBAUM M, CAI W J, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5): 1122−1131. DOI: 10.1016/j.cell.2018.02.010.
[9] CHEN J, WU L L, ZHANG J, et al. Deep learning-based model for detecting 2019 novel coronaviruspneumonia on high-resolution computed tomography[J]. Scientificreports, 2020, 10(1): 1−11. DOI: 10.1038/s41598-020-76282-0.
[10] YANG S, JIANG L, CAO Z, et al. Deep learning for detecting corona virus disease 2019 (COVID-19) on high resolution computed tomography: A pilot study[J]. Annals of Translational Medicine, 2020, 8(7): 450. DOI: 10.21037/atm.2020.03.132.
[11] WANG R, JIAO Z, YANG L, et al. Artificial intelligence for prediction of COVID-19 progression using CT imaging and clinical data[J]. European Radiology, 2022, 32(1): 205−212. DOI: 10.1007/s00330-021-08049-8.
[12] NICHOLLS J M, POON L L, LEE K C, et al. Lung pathology of severe acute respiratory syndrome[J]. Lancet, 2003, 361(9371): 1773−1778. DOI: 10.1016/s0140-6736(03)13413-7.
[13] HUANG C L, WANG Y M, LI X W, et al. Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China[J]. Lancet, 2020, 395(10223): 497−506. DOI: 10.1016/S0140-6736(20)30183-5.
[14] 黄益龙, 张振光, 李翔, 等. CT影像组学联合征象鉴别新型冠状病毒肺炎与其他病毒性肺炎的价值[J]. 中华放射学杂志, 2022,56(1): 36−42. DOI: 10.3760/cma.j.cn112149-20201220-01318. HUANG Y L, ZHANG Z G, LI X, et al. The value of CT signs combined with radiomics in the differentiation of COVID-19 from other viral pneumonias[J]. Chinese Journal of Radiology, 2022, 56(1): 36−42. DOI: 10.3760/cma.j.cn112149-20201220-01318. (in Chinese).
[15] 赵小二, 邓克学, 王朋. 不同阶段新型冠状病毒肺炎的CT影像演变分析[J]. 实用放射学杂志, 2021,37(8): 1254−1257. doi: 10.3969/j.issn.1002-1671.2021.08.008 ZHAO X E, DENG K X, WANG P. Analysis of the CT manifestations changes of COVID-19 at different stages[J]. Journal of Practical Radiology, 2021, 37(8): 1254−1257. (in Chinese). doi: 10.3969/j.issn.1002-1671.2021.08.008
[16] 吴杰, 肖安岭, 顾金凤. 多层螺旋CT对新型冠状病毒肺炎的临床诊断价值[J]. 实用放射学杂志, 2021,37(5): 746−748. DOI: 10.3969/j.issn.1002-1671.2021.05.013. WU J, XIAO A L, GU J F. Clinical value of MSCT in the diagnosis of COVID-19[J]. Journal of Practical Radiology, 2021, 37(5): 746−748. DOI: 10.3969/j.issn.1002-1671.2021.05.013. (in Chinese).
[17] 余成成, 杨彦鸿, 胡天丽, 等. 新型冠状病毒B.1.617.2变异株感染者高分辨率CT与临床特点[J]. 中华放射学杂志, 2021,55(10): 1054−1058. DOI: 10.3760/cma.j.cn112149-20210618-00574. YU C C, YANG Y H, HU T L, et al. High resolution CT findings and clinical features of the novel corona-virus B.1.617.2 variant[J]. Chinese Journal of Radiology, 2021, 55(10): 1054−1058. DOI: 10.3760/cma.j.cn112149-20210618-00574. (in Chinese).
[18] 赵建华, 柴军, 张晓琴, 等. 基于深度学习的新型冠状病毒肺炎转归胸部CT评价[J]. 国际放射医学核医学杂志, 2020,44(12): 737−743. DOI: 10.3760/cma.j.cn121381-202004048-00101. ZHAO J H, CHAI J, ZHANG X Q, et al. Chest CT evaluation of COVID-19 outcome based on deep learning[J]. International Journal of Radiation Medicine and Nuclear Medicine, 2020, 44(12): 737−743. DOI: 10.3760/cma.j.cn121381-202004048-00101. (in Chinese).
[19] 谢正平, 戴峰, 蒋燕, 等. 重症甲型H1N1流感急性肺损伤的高分辨率CT影像学分析[J]. 现代医学, 2012,40(3): 276−280. doi: 10.3969/j.issn.1671-7562.2012.03.007 XIE Z P, DAI F, JIANG Y, et al. HRCT imaging analysis of influenza a H1N1 complicated with severe lung injury[J]. Modern Medical Journal, 2012, 40(3): 276−280. (in Chinese). doi: 10.3969/j.issn.1671-7562.2012.03.007
[20] 刘玉建, 仲建全, 冯浩, 等. 新型冠状病毒肺炎患者的高分辨率CT影像学特征[J]. 医疗装备, 2022,35(11): 1−4. doi: 10.3969/j.issn.1002-2376.2022.11.001 LIU Y J, ZHONG J Q, FENG H, et al. Imaging characteristics of high resolution CT for patients with corona virus disease 2019[J]. Medical Equipment, 2022, 35(11): 1−4. (in Chinese). doi: 10.3969/j.issn.1002-2376.2022.11.001
计量
- 文章访问数: 190
- HTML全文浏览量: 58
- PDF下载量: 27
