Computer-aided Quantification of Pulmonary Fibrosis in Patients with Lung Cancer: Relationship to Disease-free Survival

Abstract

here is increasing awareness of the clinical importance of incidentally detected interstitial lung abnormalities (ILAs) on non-contrast-enhanced chest CT images (1). Large cohort studies (2-5) of lung cancer screening have reported that ILAs are present in 8%-10% of participants. ILAs have been associated with a greater risk of all-cause mortality (l,2). Miller et al ( 6) recently reported that some subclinical ILAs at CT represent an early stage or a mild form of pulmonary fibrosis. Moreover, ILAs influence survival in patients with advanced lung cancer (7). Outcomes are reported to be poorer in patients with lung cancer with idiopathic pulmonary fibrosis (IPF) than in patients without IPF (8-10). However, quantitative evaluation of ILAs in patients with lung cancer and their influence on survival have not yet been fully investigated.Many computer-aided detection (CAD) systems have been developed to quantify diffuse lung abnormalities at . Subpleural abnormalities at CT, as measured by using the Gaussian histogram normalized correlation (GHNC) system, correspond to a histologic usual interstitial pneumonia (UIP) pattern of fibrosis in patients with interstitial lung diseases (ILDs) (15).Thus, we hypothesized that the volume of ILAs at CT measured using a GHNC-CAD system would be associated with the UIP CT pattern and worse prognosis in patients with lung cancer. The purpose of this study was to quantify ILAs at preoperative CT by using a GHNC-CAD system and to evaluate the extent of ILAs as a predictor of disease-free survival (DFS) in patients with lung cancer. We also evaluated the

Machine learning for lung CT texture analysis: Improvement of inter-observer agreement for radiological finding classification in patients with pulmonary diseases

“…Relatively higher intra-and inter-observer agreement with and without the software were therefore not unexpected, and further investigations are warranted involving larger numbers of physicians with different specialties, experience, and religious and educational backgrounds. Fifth, objective CT assessment has a potential for overcome subjective CT feature assessment in not only disease severity, but also therapeutic effect evaluations [18][19][20][21][22][23][24][25][26][27][28][29]. However, this study was not evaluated the capability of ML-based software for subjective CT feature assessment in the above-mentioned clinical purposes.…”

“…In addition, they are now necessary and trying to determine its' utility as promising tool for decision-making and therapeutic strategy in COPD, ILD or infectious disease by many investigators. Therefore, several investigators have proposed using AI and computer-aided diagnosis (CAD) based radiological findings for assessment of thin-section CT, and is firstly trying out certain software as a substitute for or in a complementary role with radiologists to differentiate lung parenchyma findings into those for 1) normal lung, 2) ground glass opacity (GGO), 3) reticulation, 4) emphysema, 5) nodular lesion, 6) consolidation and 7) honeycomb [6,[18][19][20][21][22][23][24][25][26][27][28][29].…”

Outcomes of Patients With Interstitial Lung Disease Receiving Programmed Cell Death 1 Inhibitors: A Retrospective Case Series

“…21 Among patients with cancer, a greater extent of lung fibrosis on CT in those with lung cancer was shown to be associated with a decreased diseasefree survival. 22 In addition, the presence of interstitial lung abnormalities was associated with a shorter overall survival in patients with advanced non-small cell lung cancer. 23 Our results raise the possibility that the presence of a UIP pattern may be a risk factor for increased cancer-related mortality and PD-1 inhibitor-induced pneumonitis compared with other forms of ILD; however, further research is needed.…”

Decision Support System for Classification Medullary Thyroid Cancer

“…Therefore medical image mining has become one of the recognized research area(s) of machine learning. Recently many CAD (Computer added diagnosis) systems were proposed to diagnose such as lung [7], [9], liver [10], [12], thyroid and others cancers by using medical images but minor variations in nuclei eccentric properties are need to be visualized to assist the doctors in more effective way [13], [16]. Since the nucleus deviation from its central point is an alarming variable to be considered for diagnosis of abnormalities among the tissues of MTC; because minor variation in the spatial location of nuclei could be over sighted which may become one of the leading cause of misdiagnosis.…”