Abstract
BackgroundIdentification of lung parenchyma on computer tomographic (CT) scans in the research setting is done semi-automatically and requires cumbersome manual correction. This is especially true in pathological conditions, hindering the clinical application of aeration compartment (AC) analysis. Deep learning based algorithms have lately been shown to be reliable and time-efficient in segmenting pathologic lungs. In this contribution, we thus propose a novel 3D transfer learning based approach to quantify lung volumes, aeration compartments and lung recruitability.MethodsTwo convolutional neural networks developed for biomedical image segmentation (uNet), with different resolutions and fields of view, were implemented using Matlab. Training and evaluation was done on 180 scans of 18 pigs in experimental ARDS (u2NetPig) and on a clinical data set of 150 scans from 58 ICU patients with lung conditions varying from healthy, to COPD, to ARDS and COVID-19 (u2NetHuman). One manual segmentations (MS) was available for each scan, being a consensus by two experts. Transfer learning was then applied to train u2NetPig on the clinical data set generating u2NetTransfer. General segmentation quality was quantified using the Jaccard index (JI) and the Boundary Function score (BF). The slope between JI or BF and relative volume of non-aerated compartment (SJI and SBF, respectively) was calculated over data sets to assess robustness toward non-aerated lung regions. Additionally, the relative volume of ACs and lung volumes (LV) were compared between automatic and MS.ResultsOn the experimental data set, u2NetPig resulted in JI = 0.892 [0.88 : 091] (median [inter-quartile range]), BF = 0.995 [0.98 : 1.0] and slopes SJI = −0.2 {95% conf. int. −0.23 : −0.16} and SBF = −0.1 {−0.5 : −0.06}. u2NetHuman showed similar performance compared to u2NetPig in JI, BF but with reduced robustness SJI = −0.29 {−0.36 : −0.22} and SBF = −0.43 {−0.54 : −0.31}. Transfer learning improved overall JI = 0.92 [0.88 : 0.94], P < 0.001, but reduced robustness SJI = −0.46 {−0.52 : −0.40}, and affected neither BF = 0.96 [0.91 : 0.98] nor SBF = −0.48 {−0.59 : −0.36}. u2NetTransfer improved JI compared to u2NetHuman in segmenting healthy (P = 0.008), ARDS (P < 0.001) and COPD (P = 0.004) patients but not in COVID-19 patients (P = 0.298). ACs and LV determined using u2NetTransfer segmentations exhibited < 5% volume difference compared to MS.ConclusionCompared to manual segmentations, automatic uNet based 3D lung segmentation provides acceptable quality for both clinical and scientific purposes in the quantification of lung volumes, aeration compartments, and recruitability.
Highlights
The ongoing COVID-19 pandemic has focused attention on Acute Lung Injury and the Acute Respiratory Distress Syndrome (ARDS), a disease mainly characterized by impaired gas exchange driven by an inflammatory state of the lung (Ferguson et al, 2012; The ARDS Definition Task Force*, 2012)
To do so we compared measures derived from lung computer tomographic (CT) segmentations, such as aeration compartments, effective lung volume and recruitability, as calculated from convolutional neural networks (CNN)-segmentations against the same measures calculated from manual CT segmentations
This study investigated the effects of different degrees of spontaneous breathing during biphasic positive airway pressure (BIPAP) ventilation on neutrophilic inflammation in a double-hit ARDS model composed of repeated lung lavage with Horowitz ratio below 200 mmHg for 30 min
Summary
The ongoing COVID-19 pandemic has focused attention on Acute Lung Injury and the Acute Respiratory Distress Syndrome (ARDS), a disease mainly characterized by impaired gas exchange driven by an inflammatory state of the lung (Ferguson et al, 2012; The ARDS Definition Task Force*, 2012) Optimal treatment of this pathology is currently being debated and different approaches have been proposed (Amato et al, 2009; Calfee et al, 2014; Coppola et al, 2018; Pelosi et al, 2018; Hodgson et al, 2019; Robba et al, 2020). Identification of lung parenchyma on computer tomographic (CT) scans in the research setting is done semi-automatically and requires cumbersome manual correction This is especially true in pathological conditions, hindering the clinical application of aeration compartment (AC) analysis. We propose a novel 3D transfer learning based approach to quantify lung volumes, aeration compartments and lung recruitability
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
