TY - JOUR
TI - COVLIAS 1.0: Lung Segmentation in COVID-19 Computed Tomography Scans
Using Hybrid Deep Learning Artificial Intelligence Models
AU - Suri, Jasjit S.
AU - Agarwal, Sushant
AU - Pathak, Rajesh
AU - Ketireddy,
AU - Vedmanvitha
AU - Columbu, Marta
AU - Saba, Luca
AU - Gupta, Suneet K. and
AU - Faa, Gavino
AU - Singh, Inder M.
AU - Turk, Monika
AU - Chadha, Paramjit S.
AU - and Johri, Amer M.
AU - Khanna, Narendra N.
AU - Viskovic, Klaudija and
AU - Mavrogeni, Sophie
AU - Laird, John R.
AU - Pareek, Gyan
AU - Miner, Martin
AU - and Sobel, David W.
AU - Balestrieri, Antonella
AU - Sfikakis, Petros P.
AU - and Tsoulfas, George
AU - Protogerou, Athanasios
AU - Misra, Durga
AU - Prasanna
AU - Agarwal, Vikas
AU - Kitas, George D.
AU - Teji, Jagjit S. and
AU - Al-Maini, Mustafa
AU - Dhanjil, Surinder K.
AU - Nicolaides, Andrew and
AU - Sharma, Aditya
AU - Rathore, Vijay
AU - Fatemi, Mostafa
AU - Alizad, Azra
AU - and Krishnan, Pudukode R.
AU - Frence, Nagy
AU - Ruzsa, Zoltan
AU - Gupta,
AU - Archna
AU - Naidu, Subbaram
AU - Kalra, Mannudeep
JO - DIAGNOSTIC ONCOLOGY
PY - 2021
VL - 11
TODO - 8
SP - null
PB - MDPI
SN - null
TODO - 10.3390/diagnostics11081405
TODO - COVID-19; computed tomography; lungs; segmentation; hybrid deep learning
TODO - Background: COVID-19 lung segmentation using Computed Tomography (CT)
scans is important for the diagnosis of lung severity. The process of
automated lung segmentation is challenging due to (a) CT radiation
dosage and (b) ground-glass opacities caused by COVID-19. The lung
segmentation methodologies proposed in 2020 were semi- or automated but
not reliable, accurate, and user-friendly. The proposed study presents a
COVID Lung Image Analysis System (COVLIAS 1.0, AtheroPoint (TM),
Roseville, CA, USA) consisting of hybrid deep learning (HDL) models for
lung segmentation. Methodology: The COVLIAS 1.0 consists of three
methods based on solo deep learning (SDL) or hybrid deep learning (HDL).
SegNet is proposed in the SDL category while VGG-SegNet and
ResNet-SegNet are designed under the HDL paradigm. The three proposed AI
approaches were benchmarked against the National Institute of Health
(NIH)-based conventional segmentation model using fuzzy-connectedness. A
cross-validation protocol with a 40:60 ratio between training and
testing was designed, with 10% validation data. The ground truth (GT)
was manually traced by a radiologist trained personnel. For performance
evaluation, nine different criteria were selected to perform the
evaluation of SDL or HDL lung segmentation regions and lungs long axis
against GT. Results: Using the database of 5000 chest CT images (from 72
patients), COVLIAS 1.0 yielded AUC of similar to 0.96, similar to 0.97,
similar to 0.98, and similar to 0.96 (p-value < 0.001), respectively
within 5% range of GT area, for SegNet, VGG-SegNet, ResNet-SegNet, and
NIH. The mean Figure of Merit using four models (left and right lung)
was above 94%. On benchmarking against the National Institute of Health
(NIH) segmentation method, the proposed model demonstrated a 58% and
44% improvement in ResNet-SegNet, 52% and 36% improvement in
VGG-SegNet for lung area, and lung long axis, respectively. The PE
statistics performance was in the following order: ResNet-SegNet >
VGG-SegNet > NIH > SegNet. The HDL runs in <1 s on test data per image.
Conclusions: The COVLIAS 1.0 system can be applied in real-time for
radiology-based clinical settings.
ER -