Artificial intelligence chest CT imaging for the diagnosis of tuberculosis-destroyed lung with PH

Wei Yu; Min Liu; Wei Qin; Jixiang Liu; Shi Chen; Yinjie Chen; Bingzu Hu; Ying Chen; Enhong Liu; Xiao Jin; Shuang Liu; Chenghong Li; Ziyang Zhu

doi:10.1016/j.rmed.2025.108377

Artificial intelligence chest CT imaging for the diagnosis of tuberculosis-destroyed lung with PH

Respir Med. 2025 Nov:248:108377. doi: 10.1016/j.rmed.2025.108377. Epub 2025 Sep 24.

Authors

Wei Yu¹, Min Liu¹, Wei Qin¹, Jixiang Liu², Shi Chen¹, Yinjie Chen¹, Bingzu Hu¹, Ying Chen¹, Enhong Liu¹, Xiao Jin¹, Shuang Liu¹, Chenghong Li³, Ziyang Zhu⁴

Affiliations

¹ Department of Pulmonary and Critical Care Medicine, Affiliated Hospital of Jianghan University, No.168 Hongkong Road, Wuhan, 430000, Hubei, China.
² National Center for Respiratory Medicine, State Key Laboratory of Respiratory Health and Multimorbidity, National Clinical Research Center for Respiratory Diseases, Institute of Respiratory Medicine, Chinese Academy of Medical Sciences, Department of Pulmonary and Critical Care Medicine, Center of Respiratory Medicine, China-Japan Friendship Hospital, No 2, East Yinghua Road, Beijing, 100029, China.
³ Department of Pulmonary and Critical Care Medicine, Affiliated Hospital of Jianghan University, No.168 Hongkong Road, Wuhan, 430000, Hubei, China. Electronic address: 15827636399@163.com.
⁴ Department of Pulmonary and Critical Care Medicine, Affiliated Hospital of Jianghan University, No.168 Hongkong Road, Wuhan, 430000, Hubei, China. Electronic address: 48594416@qq.com.

PMID: 41005682
DOI: 10.1016/j.rmed.2025.108377

Abstract

Objective: Explore the clinical characteristics of Tuberculosis Destroyed Lung (TDL) with pulmonary hypertension. Use Artificial Intelligence (AI) CT Imaging for the Diagnosis of TDL Patients with PH.

Methods: 51 cases of TDL patients. Based on the results of the right heart catheterization examination, the patients were divided into two groups: TDL with group (n = 31) and TDL Non-PH (n = 20). The original chest CT data of the patients were reconstructed, segmented, and rendered using AI, and lung volume-related data were calculated. The differences in clinical data, hemodynamic data, and lung volume-related data between the two groups of patients were compared.

Results: The proportion of TDL patients with PH is significantly higher than those without TDL (61.82 % vs. 22.64 %, P < 0.01). There were significant differences between the two groups of patients in terms of pulmonary function, PCWP/PVR, PASP/TRV and total volume of destroyed lung tissue (V_TDLT) (P < 0.05), and V_TDLT is positively correlated with mean pulmonary arterial pressure (mPAP). Combined Diagnosis (V_TDLT + PSAP): The area under the AUC was 0.917 (95 %CI: 0.802-1), with a predicted probability of 0.51 and a Youden index of 0.789. The sensitivity was 90 % and specificity was 88.9 %.

Conclusions: Patients with TDL accompanied by pulmonary hypertension are related to restrictive disorders. The V_TDLT is positively correlated with mPAP. By calculating the V_TDLT and combining it with the estimated PASP from echocardiography, it assists in the diagnosis of PH in these patients.

Keywords: AI; PH; Radiomics; TDL; V(TDLT).

MeSH terms

Adult
Aged
Artificial Intelligence*
Female
Humans
Hypertension, Pulmonary* / diagnostic imaging
Hypertension, Pulmonary* / etiology
Hypertension, Pulmonary* / physiopathology
Lung* / diagnostic imaging
Lung* / pathology
Lung* / physiopathology
Male
Middle Aged
Tomography, X-Ray Computed* / methods
Tuberculosis, Pulmonary* / complications
Tuberculosis, Pulmonary* / diagnostic imaging
Tuberculosis, Pulmonary* / physiopathology