English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Background  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. 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.    Methods  Two 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 ( u 2 Net   Pig  ) 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 ( u 2 Net   Human  ). One manual segmentations (MS) was available for each scan, being a consensus by two experts. Transfer learning was then applied to train  u 2 Net   Pig   on the clinical data set generating  u 2 Net   Transfer  . 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 ( S   JI   and  S   BF  , 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.    Results  On the experimental data set,  u 2 Net   Pig   resulted in  JI  = 0.892 [0.88 : 091] (median [inter-quartile range]),  BF  = 0.995 [0.98 : 1.0] and slopes  S   JI   = −0.2 {95% conf. int. −0.23 : −0.16} and  S   BF   = −0.1 {−0.5 : −0.06}.  u 2 Net   Human   showed similar performance compared to  u 2 Net   Pig   in  JI ,  BF  but with reduced robustness  S   JI   = −0.29 {−0.36 : −0.22} and  S   BF   = −0.43 {−0.54 : −0.31}. Transfer learning improved overall  JI  = 0.92 [0.88 : 0.94],  P  &amp;lt; 0.001, but reduced robustness  S   JI   = −0.46 {−0.52 : −0.40}, and affected neither  BF  = 0.96 [0.91 : 0.98] nor  S   BF   = −0.48 {−0.59 : −0.36}.  u 2 Net   Transfer   improved  JI  compared to  u 2 Net   Human   in segmenting healthy ( P  = 0.008), ARDS ( P  &amp;lt; 0.001) and COPD ( P  = 0.004) patients but not in COVID-19 patients ( P  = 0.298). ACs and LV determined using  u 2 Net   Transfer   segmentations exhibited &amp;lt; 5% volume difference compared to MS.    Conclusion  Compared 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.

Automatic Lung Segmentation and Quantification of Aeration in Computed Tomography of the Chest Using 3D Transfer Learning