Segmentation of lung lobes and lesions in chest CT for the classification of COVID-19 severity.

Publication date: Nov 28, 2023

To precisely determine the severity of COVID-19-related pneumonia, computed tomography (CT) is an imaging modality beneficial for patient monitoring and therapy planning. Thus, we aimed to develop a deep learning-based image segmentation model to automatically assess lung lesions related to COVID-19 infection and calculate the total severity score (TSS). The entire dataset consisted of 124 COVID-19 patients acquired from Chulabhorn Hospital, divided into 28 cases without lung lesions and 96 cases with lung lesions categorized severity by radiologists regarding TSS. The model used a 3D-UNet along with DenseNet and ResNet models that had already been trained to separate the lobes of the lungs and figure out the percentage of lung involvement due to COVID-19 infection. It also used the Dice similarity coefficient (DSC) to measure TSS. Our final model, consisting of 3D-UNet integrated with DenseNet169, achieved segmentation of lung lobes and lesions with the Dice similarity coefficients of 91. 52% and 76. 89%, respectively. The calculated TSS values were similar to those evaluated by radiologists, with an R2 of 0. 842. The correlation between the ground-truth TSS and model prediction was greater than that of the radiologist, which was 0. 890 and 0. 709, respectively.

Open Access PDF

Concepts Keywords
Beneficial 3d
Ct Covid
Densenet169 Dice
Pneumonia Imaging
Therapy Infection
Lesions
Lobes
Lung
Radiologists
Related
Segmentation
Severity
Similarity
Tss
Unet

Semantics

Type Source Name
disease MESH COVID-19
disease MESH pneumonia
disease MESH infection
drug DRUGBANK Coenzyme M
disease VO time
disease MESH abnormalities
drug DRUGBANK Trestolone
disease VO efficient
disease MESH COPD
disease MESH lung cancer
disease VO effectiveness
drug DRUGBANK Flunarizine
drug DRUGBANK Aspartame
disease IDO object
disease VO volume
disease VO protocol
disease VO effective
disease IDO process
drug DRUGBANK Gold
disease IDO algorithm
drug DRUGBANK Isoxaflutole
drug DRUGBANK Fenamole
disease VO efficiency
disease VO frequency
disease VO vaccinated
disease VO unvaccinated
disease MESH metastases
disease VO company
drug DRUGBANK Guanosine

Original Article

(Visited 1 times, 1 visits today)