Automatic lung segmentation in COVID-19 patients: Impact on quantitative computed tomography analysis
| Autor: | C. De Mattia, Diana Artioli, Angelo Vanzulli, F Travaglini, L. Berta, P.E. Colombo, Alberto Torresin, L Bianchi, Domenico Lizio, M. Felisi, Stefano Carrazza, Francesco Rizzetto, S Gelmini |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
2019-20 coronavirus outbreak
Percentile Coronavirus disease 2019 (COVID-19) Computer science Biophysics General Physics and Astronomy Convolutional neural network 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Lung segmentation Histogram Image Processing Computer-Assisted medicine Humans Radiology Nuclear Medicine and imaging Segmentation Quantitative computed tomography Lung medicine.diagnostic_test SARS-CoV-2 business.industry COVID-19 Pattern recognition General Medicine 030220 oncology & carcinogenesis Neural Networks Computer Artificial intelligence Tomography X-Ray Computed business Algorithms |
| Zdroj: | Physica Medica. 87:115-122 |
| ISSN: | 1120-1797 |
| DOI: | 10.1016/j.ejmp.2021.06.001 |
| Popis: | Purpose To assess the impact of lung segmentation accuracy in an automatic pipeline for quantitative analysis of CT images. Methods Four different platforms for automatic lung segmentation based on convolutional neural network (CNN), region-growing technique and atlas-based algorithm were considered. The platforms were tested using CT images of 55 COVID-19 patients with severe lung impairment. Four radiologists assessed the segmentations using a 5-point qualitative score (QS). For each CT series, a manually revised reference segmentation (RS) was obtained. Histogram-based quantitative metrics (QM) were calculated from CT histogram using lung segmentationsfrom all platforms and RS. Dice index (DI) and differences of QMs (ΔQMs) were calculated between RS and other segmentations. Results Highest QS and lower ΔQMs values were associated to the CNN algorithm. However, only 45% CNN segmentations were judged to need no or only minimal corrections, and in only 17 cases (31%), automatic segmentations provided RS without manual corrections. Median values of the DI for the four algorithms ranged from 0.993 to 0.904. Significant differences for all QMs calculated between automatic segmentations and RS were found both when data were pooled together and stratified according to QS, indicating a relationship between qualitative and quantitative measurements. The most unstable QM was the histogram 90th percentile, with median ΔQMs values ranging from 10HU and 158HU between different algorithms. Conclusions None of tested algorithms provided fully reliable segmentation. Segmentation accuracy impacts differently on different quantitative metrics, and each of them should be individually evaluated according to the purpose of subsequent analyses. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect