Effects of Automatic Deep-Learning-Based Lung Analysis on Quantification of Interstitial Lung Disease: Correlation with Pulmonary Function Test Results and Prognosis

Abstract

We investigated the feasibility of a new deep-learning (DL)-based lung analysis method for the evaluation of interstitial lung disease (ILD) by comparing it with evaluation using the traditional computer-aided diagnosis (CAD) system and patients’ clinical outcomes. We prospectively included 104 patients (84 with and 20 without ILD). An expert radiologist defined regions of interest in the typical areas of normal, ground-glass opacity, consolidation, consolidation with fibrosis (traction bronchiectasis), honeycombing, reticulation, traction bronchiectasis, and emphysema, and compared them with the CAD and DL-based analysis results. Next, we measured the extent of ILD lesions with the CAD and DL-based analysis and compared them. Finally, we compared the lesion extent on computed tomography (CT) images, as measured with the DL-based analysis, with pulmonary function tests results and patients’ overall survival. Pearson’s correlation analysis revealed a significant correlation between DL-based analysis and CAD results. Forced vital capacity was significantly correlated with DL-based analysis (r = 0.789, p < 0.001 for normal lung volume and r = −0.316, p = 0.001 for consolidation with fibrosis volume). Consolidation with fibrosis measured using DL-based analysis was independently associated with poor survival. The lesion extent measured using DL-based analysis showed a negative correlation with the pulmonary function test results and prognosis.

Quantitative Analysis for Lung Disease on Thin-Section CT

“…However, in ILD, a simple density mask approach cannot effectively distinguish the lung from the chest wall due to lesions with high attenuation, such as consolidation and fibrosis [ 90 ]. Therefore, it is recommended to employ dedicated software for the automatic segmentation of the lung, as mentioned above [ 78 , 82 , 85 , 91 ].…”

“…The BV5% value, calculated as the proportion of BV5 to total BV, was found to be a prognostic factor for adverse outcomes (intubation or mortality) in patients with COVID-19 [ 139 ]. In thin-section CT scans of COVID-19 pneumonia, bilateral distribution and subsegmental vessel enlargement are usually observed in clinical situations [ 85 , 140 , 141 ]. These vascular abnormalities are consistent with the results of dual-energy CT [ 142 , 143 ] and microvascular observations using video microscopy [ 143 ].…”

Recent Advances of Artificial Intelligence Applications in Interstitial Lung Diseases

“…Additionally, regarding the risk of malignancy development or coexistence, in a recent study of Liang et al, it is mentioned that whole-lung CT texture analysis is a promising tool for the lung cancer risk stratification of IPF patients [ 32 ]. Moreover, Aoki et al [ 33 ] using deep-learning-based analysis and measured consolidation with fibrosis, found that it was independently associated with poor survival. They also found that the lesion extent measured using deep-learning-based analysis showed a negative correlation with pulmonary function test results and prognosis.…”

“…A summarizing table (Table 1) for the included studies has been added at the end of this section. [30] Prognosis 465 patients Imaging -Budzikowski et al [31] Prognosis 169 patients Imaging and Genomic -Liang et al [32] Prognosis 116 patients Imaging AUC = 0.870 Aoki et al [33] Prognosis 104 patients Imaging -Bowman et al [34] Prognosis 589 patients Proteomic Sensitivity: 90% Mayr et al [35] Prognosis 124 patients Proteomic Accuracy: 83%…”

Longitudinal assessment of interstitial lung abnormalities on CT in patients with COPD using artificial intelligence-based segmentation: a prospective observational study

“…AI-based image analysis has advantages in terms of high reliability and reproducibility over other methods. Furthermore, indices derived from AI-based image analysis have been associated with pulmonary function decline, exacerbation, and prognosis in ILD [11][12][13]. Artificial intelligence based quantitative CT image analysis software (AIQCT) is an AI-based image analysis software that can automatically classify chest CT images into normal lung, ground-glass opacities (GGOs), reticulations, consolidations, honeycombing, nodules, hyperlucencies, interlobular septum, bronchi, and vessels [14].…”