Diagnostic performance of electronic nose technology in chronic lung allograft dysfunction

The diagnosis and management of chronic lung allograft dysfunction

PURPOSE OF REVIEW

Chronic lung allograft dysfunction (CLAD) remains a life-threatening complication following lung transplantation. Different CLAD phenotypes have recently been defined, based on the combination of pulmonary function testing and chest computed tomography (CT) scanning and spurred renewed interests in differential diagnosis, risk factors and management of CLAD.

RECENT FINDINGS

Given their crucial importance in the differential diagnosis, we will discuss the latest development in assessing the pulmonary function and chest CT scan, but also their limitations in proper CLAD phenotyping, especially with regards to patients with baseline allograft dysfunction. Since no definitive treatment exists, it remains important to timely identify clinical risk factors, but also to assess the presence of specific patterns or biomarkers in tissue or in broncho alveolar lavage in relation to CLAD (phenotypes). We will provide a comprehensive overview of the latest advances in risk factors and biomarker research in CLAD. Lastly, we will also review novel preventive and curative treatment strategies for CLAD.

SUMMARY

Although this knowledge has significantly advanced the field of lung transplantation, more research is warranted because CLAD remains a life-threatening complication for all lung transplant recipients.

Multiround Transfer Learning and Modified Generative Adversarial Network for Lung Cancer Detection

Lung cancer has been the leading cause of cancer death for many decades. With the advent of artificial intelligence, various machine learning models have been proposed for lung cancer detection (LCD). Typically, challenges in building an accurate LCD model are the small-scale datasets, the poor generalizability to detect unseen data, and the selection of useful source domains and prioritization of multiple source domains for transfer learning. In this paper, a multiround transfer learning and modified generative adversarial network (MTL-MGAN) algorithm is proposed for LCD. The MTL transfers the knowledge between the prioritized source domains and target domain to get rid of exhaust search of datasets prioritization among multiple datasets, maximizing the transferability with a multiround transfer learning process, and avoiding negative transfer via customization of loss functions in the aspects of domain, instance, and feature. In regard to the MGAN, it not only generates additional training data but also creates intermediate domains to bridge the gap between the source domains and target domains. 10 benchmark datasets are chosen for the performance evaluation and analysis of the MTL-MGAN. The proposed algorithm has significantly improved the accuracy compared with related works. To examine the contributions of the individual components of the MTL-MGAN, ablation studies are conducted to confirm the effectiveness of the prioritization algorithm, the MTL, the negative transfer avoidance via loss functions, and the MGAN. The research implications are to confirm the feasibility of multiround transfer learning to enhance the optimal solution of the target model and to provide a generic approach to bridge the gap between the source domain and target domain using MGAN.