人工智能在结缔组织病相关间质性肺疾病诊断及预后评估中的应用进展 ^*

Artificial intelligence in connective tissue disease-associated interstitial lung diseases: emerging tools for diagnosis and prognostic assessment

摘要

结缔组织病相关间质性肺疾病 (CTD-ILD) 是老年结缔组织病常见且复杂的肺部病变, 其诊断和评估依赖多学科协作。 随着人工智能 (AI) 技术在医学影像领域应用的迅速发展, 老年 CTD-ILD 的肺部影像分析、 疾病的诊断、 进展的预测和分级有了新的方法和工具。 本文对 AI 在 CTD-ILD 领域的应用进展进行综述, 探讨其未来发展方向与挑战, 旨在为老年 CTD-ILD 早期诊断和精准预后评估提供参考。

Abstract

Connective tissue disease-related interstitial lung disease (CTD-ILD) is a prevalent and intricate pulmonary condition in older individuals with connective tissue disorders. The diagnosis and evaluation of this condition depend on interdisciplinary. In recent years, the swift advancement of artificial intelligence technology (AI) in medical imaging has led to the emergence of novel methodologies and tools for analyzing lung pictures, diagnosing, and predicting and grading disease progression in older CTD-ILD patients. This paper comprehensively examines the advancements of AI in CTD-ILD, investigates future developmental trajectories and problems, and seeks to offer a reference for the early diagnosis and accurate prognostic evaluation of senior CTD-ILD patients.

关键词

结缔组织病相关间质性肺疾病 / 人工智能 / 诊断 / 预后

Key words

Connective tissue disease-related interstitial lung disease / Artificial intelligence / Diagnosis / Prognosis

参考文献

[1] 中国医师协会风湿免疫科医师分会风湿病相关肺血管/间质病学组, 国家风湿病数据中心 . 2018 中国结缔组织病相关间质性肺病诊断和治疗专家共识[J]. 中华内科杂志, 2018, 57(8): 558-565.

[2] Rheumatic Disease—Related Pulmonary Vascular/Interstitial Disease Group of the Rheumatologists and Immunologists Branch of the Chinese Medical Doctors' Association, National Rheumatic Disease Data Center. 2018 Chinese expert—based consensus statement regarding the diagnosis and treatment of interstitial lung disease associated with connective tissue diseases[J]. Chin J Int Med, 2018, 57(8): 558-565.

[3] Knarborg M, Løkke A, Hilberg O, et al. Direct and indirect costs of systemic sclerosis and associated interstitial lung disease: a nationwide population—based cohort study[J]. Respirology, 2022, 27(5): 341-349.

[4] Koo S M, Kim S Y, Choi S M, et al. Korean guidelines for diagnosis and management of interstitial lung diseases: part 5. Connective tissue disease associated interstitial lung disease[J]. Tuberc Respir Dis, 2019, 82(4): 285.

[5] 孟轲, 王道清 . ILDV%NL%HRCT 评分在老年结缔组织相关性肺间质病变患者肺功能及病情严重程度评估中的价值[J]. 临床心身疾病杂志, 2023, 29(1): 7—12, 21.

[6] Meng K , Wang D Q . The value of ILDV%, NL% and HRCT scores in the evaluation of lung function and disease severity in elderly patients with connective tissue disease associated interstitial lung disease[J]. J Clin Psychosom Dis, 2023, 29(1): 7-12,21.

[7] 杨刘敏, 马天罡, 吕雪娇, 等 . 肿瘤标志物与结缔组织病相关间质性肺病的相关性[J]. 中国老年学杂志, 2022, 42(21): 5407-5411.

[8] Yang L M , Ma T G , Lv X J . Correlation between tumor markers and connective tissue disease—associated interstitial lung disease[J]. Chin J Gerontol, 2022, 42(21): 5407-5411.

[9] 刘力, 陈宏, 钟威, 等 . 人工智能 CT 定量分析预测并评估 COVID—19 肺炎临床分型的研究[J]. CT 理论与应用研究, 2021, 30(6): 743-751.

[10] Liu L , Chen H , Zhong W , et al. Study on predicting and evaluating clinical classification of COVID—19 pneumonia by artificial intelligence CT quantitative analysis[J]. Comput Tomogr Theory Appl, 2021, 30(6): 743-751.

[11] Ohno Y, Aoyagi K, Takenaka D, et al. Machine learning for lung CT texture analysis: improvement of inter—observer agreement for radiological finding classification in patients with pulmonary diseases[J]. Eur J Radiol, 2021, 134: 109410.

[12] 秦瑞遥, 王沄, 宋伟, 等 . 深度学习算法在超重肺间质性病变患者中的应用研究[J]. 中国医疗设备, 2022, 37(8): 93-98.

[13] Qin R Y , Wang Y , Song W , et al. Application of deep learning algorithm in overweight patients with interstitial lung disease[J]. China Med Devices, 2022, 37(8): 93-98.

[14] Cai G W, Liu Y B, Feng Q J, et al. Semi—supervised segmentation of interstitial lung disease patterns from CT images via self—training with selective re—training[J]. Bioengineering, 2023, 10(7): 830.

[15] Ito Y, Ichikawa Y, Murashima S, et al. Novel deep—learning analysis for connective tissue disease—related interstitial lung disease extent assessment on CT: a preliminary cross—sectional study[J]. Rheumatology (Oxford), 2024:keae491 [pii].

[16] Xu W, Wu W, Zheng Y, et al. A computed tomography radiomics—based prediction model on interstitial lung disease in anti—MDA5—positive dermatomyositis[J]. Front Med (Lausanne), 2021, 8: 768052.

[17] Le Gall A, Hoang—Thi T, Porcher R, et al. Prognostic value of automated assessment of interstitial lung disease on CT in systemic sclerosis[J]. Rheumatology, 2024, (1). doi: 10.1093/rheumatology/kead164.

[18] Su N, Hou F, Zhu H, et al. Assessing the severity of connective tissue—related interstitial lung disease using computed tomography quantitative analysis parameters[J]. J Comput Assist Tomogr, 2025, 49(3): 448-455.

[19] 储晨, 方宇, 孙艺, 等 . 人工智能定量分析在 CTD—ILD 诊断和分级中的应用研究[J]. 医学影像学杂志, 2024, 34(8): 54-57.

[20] Chu C , Fang Y , Sun Y , et al. Artificial intelligence quantitative evaluation in diagnosis and grading of CTD—ILD[J]. J Med Imaging, 2024, 34(8): 54-57.

[21] Pawar S P, Talbar S N . Two—stage hybrid approach of deep learning networks for interstitial lung disease classification[J]. Biomed Res Int, 2022, 2022: 7340902.

[22] Dianat B, La Torraca P, Manfredi A, et al. Classification of pulmonary sounds through deep learning for the diagnosis of interstitial lung diseases secondary to connective tissue diseases[J]. Comput Biol Med, 2023, 160: 106928.

[23] Taylor M J, Chitwood C P, Xie Z, et al. Disease diagnosis and severity classification in pulmonary fibrosis using carbonyl volatile organic compounds in exhaled breath[J]. Respir Med, 2024, 222: 107534.

[24] 张辉, 赵凤莲, 闫冰迪, 等 . 血清标志物联合检测在特发性肺纤维化早期诊断中的价值[J]. 国际老年医学杂志, 2020, 41(1): 13-17.

[25] Zhang H , Zhao F L , Yan B D , et al. Application of serum markers in early diagnosis of idiopathic pulmonary fibrosis[J]. Int J Geriatr, 2020, 41(1): 13-17.

[26] 陈萍, 武剑 . 结缔组织病相关间质性肺病的生物标志物研究进展[J]. 中国医药科学, 2024, 14(2): 20-24.

[27] Chen P , Wu J . Research progress on biomarkers of connective tissue disease—associated interstitial lung disease[J]. China Med Pharm, 2024, 14(2): 20-24.

[28] Mueller A N, Miller H A, Taylor M J, et al. Identification of idiopathic pulmonary fibrosis and prediction of disease severity via machine learning analysis of comprehensive metabolic panel and complete blood count data[J]. Lung, 2024, 202(2): 139-150.

[29] Martini K, Baessler B, Bogowicz M, et al. Applicability of radiomics in interstitial lung disease associated with systemic sclerosis: proof of concept[J]. Eur Radiol, 2021, 31(4): 1987-1998.

[30] Chassagnon G, Vakalopoulou M, Régent A, et al. Elastic registration—driven deep learning for longitudinal assessment of systemic sclerosis interstitial lung disease at CT[J]. Radiology, 2021, 298(1): 189-198.

[31] Schniering J, Maciukiewicz M, Gabrys H S, et al. Computed tomography—based radiomics decodes prognostic and molecular differences in interstitial lung disease related to systemic sclerosis[J]. Eur Respir J, 2022, 59(5): 2004503.

[32] Sun D, Wang Y, Liu Q, et al. Prediction of long—term mortality by using machine learning models in Chinese patients with connective tissue disease—associated interstitial lung disease[J]. Respir Res, 2022, 23(1): 4.

[33] Mei X, Liu Z, Singh A, et al. Interstitial lung disease diagnosis and prognosis using an AI system integrating longitudinal data[J]. Nat Commun, 2023, 14(1): 2272.

[34] Maldonado F, Moua T, Rajagopalan S, et al. Automated quantification of radiological patterns predicts survival in idiopathic pulmonary fibrosis[J]. Eur Respir J, 2014, 43(1): 204-212.

[35] Feng D Y, Zhou Y Q, Xing Y F, et al. Selection of glucocorticoid—sensitive patients in interstitial lung disease secondary to connective tissue diseases population by radiomics[J]. Ther Clin Risk Manag, 2018, 14: 1975-1986.

[36] Ley B, Ryerson C J, Vittinghoff E, et al. A multidimensional index and staging system for idiopathic pulmonary fibrosis[J]. Ann Intern Med, 2012, 156(10): 684-691.

[37] Ryerson C J, Vittinghoff E, Ley B, et al. Predicting survival across chronic interstitial lung disease: the ILD—GAP model[J]. Chest, 2014, 145(4): 723-728.

[38] Long B, Li R, Wang R, et al. A computed tomography—based deep learning radiomics model for predicting the gender—age—physiology stage of patients with connective tissue disease—associated interstitial lung disease[J]. Comput Biol Med, 2025, 191: 110128.

[39] Jiang X, Su N, Quan S, et al. Computed tomography radiomics—based prediction model for gender—age—physiology staging of connective tissue disease—associated interstitial lung disease[J]. Acad Radiol, 2023, 30(11): 2598-2605.

[40] Krizhevsky A, Sutskever I, Hinton G E . ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.

[41] Yasaka K, Akai H, Kunimatsu A, et al. Deep learning with convolutional neural network in radiology[J] JPN J Radiol, 2018, 36(4): 257-272.

基金资助

^*吉林省医疗卫生人才专项(2024WSZX-B04)