Get started
Work

A fully automatic artificial intelligence–based CT image analysis system for accurate detection, diagnosis, and quantitative severity evaluation of pulmonary tuberculosis

Year: 2021
Type: article
Abstract: Background: Accurate and rapid diagnosis of pulmonary tuberculosis (TB) plays a crucial role in timely prevention and appropriate medical treatment to the disease. This study aims to develop and evaluate an artificial intelligence (AI)-based fully automated CT image analysis system for detection, diagnosis, and burden quantification of pulmonary TB.Methods: From December 2007 to September 2020, 892 chest CT scans from pathogen-confirmed TB patients were retrospectively included. A deep learning based cascading framework was connected to create a processing pipeline. To train and validate the model, 1921 lesions were manually labeled, classified by six categories of critical imaging features, and visually scored for the lesion involvement as the ground truth. “TB score” was calculated by the network-activation map to assess the disease burden quantitively. Independent test datasets from two additional hospitals and NIH TB Portal were used to validate externally the performance of the AI model.Results: CT scans from 526 participants (mean age, 48.5 years±16.5; 206 women) were analyzed. The lung lesion detection subsystem yielded a mean average precision of 0.68 on the validation cohort. In the independent datasets, the overall classification accuracy for six pulmonary critical imaging findings indicative of TB were 81.08%-91.05%. A moderate to strong correlation was demonstrated between the AI model quantified “TB score” and the radiologist-estimated CT score.Conclusion: This end-to-end AI system based on chest CT can achieve human-level diagnostic performance, and holds great potential for early management and medical resource optimization of patients with pulmonary TB in clinical practice.
DOI: 10.1007/s00330-021-08365-z
Authors: Chenggong Yan, Lingfeng Wang, Jie Lin, Jun Xu, Tianjing Zhang, Jin Qi, Xiangying Li, Wei Ni, Guangyao Wu, Jianbin Huang, Yikai Xu, Henry C. Woodruff, Philippe Lambin
Institutions: Maastricht University, Nanfang Hospital, Southern Medical University, University of Electronic Science and Technology of China, Central South University, Philips (China), Wuhan Union Hospital, Huazhong University of Science and Technology, Maastricht University Medical Centre
Language: English
Field: Medicine
Open Access status: bronze
Funders: European Commission, Natural Science Foundation of Guangdong Province, KWF Kankerbestrijding, Interreg, H2020 European Research Council, Eurostars
Awards: G1298692384, G1369047972, A new era in personalised medicine: Radiomics as decision support tool for diagnostics and theragnostics in oncology, Tackling the Achilles Heel of Immunotherapy: Validating imaging biomarkers and targeting the immunological niche of tumour hypoxia, G2819054015, G4011247280, G434337789, A European Cancer Image Platform Linked to Biological and Health Data for Next-Generation Artificial Intelligence and Precision Medicine in Oncology, Clinical proof of concept through a randomised phase II study: a combination of immunotherapy and stereotactic ablative radiotherapy as a curative treatment for limited metastatic lung cancer, G626718788, Accelerating the lab to market transition of AI tools for cancer management, G7290274757, A fully automated deep learning-based software for fast, robust and accurate detection and segmentation of tumours and metastasis, Onnodige chirurgie voorkomen door goedaardige van kwaadaardige renale cysten te onderscheiden aan de hand van CT beeldvorming: Een kwantitatieve beeldvormingsbenadering, G8997633394
OpenAlex ID: W3217239252
FWCI: 5.443
Cites: 34
Cited by: 86
Related to: 10