Automatic deep learning system for COVID-19 infection quantification in chest CT

Abstract

The paper proposes an automatic deep learning system for COVID-19 infection areas segmentation in chest CT scans. CT imaging proved its ability to detect the COVID-19 disease even for asymptotic patients, which make it a trustworthy alternative for PCR. Coronavirus disease spread globally and PCR screening is the adopted diagnostic testing method for COVID-19 detection. However, PCR is criticized due its low sensitivity ratios, also, it is time-consuming and manual complicated process. The proposed framework includes different steps; it starts to prepare the region of interest by segmenting the lung organ, which then undergoes edge enhancing diffusion filtering (EED) to improve the infection areas contrast and intensity homogeneity. The proposed FCN is implemented using U-net architecture with modified residual block to include concatenation skip connection. The block improves the learning of gradient values by forwarding the infection area features through the network. The proposed system is evaluated using different measures and achieved dice overlapping score of 0.961 and 0.780 for lung and infection areas segmentation, respectively. The proposed system is trained and tested using many 2D CT slices extracted from diverse datasets from different sources, which demonstrate the system generalization and effectiveness. The use of more datasets from different sources helps to enhance the system accuracy and generalization, which can be accomplished based on the data availability in in the future.

COVID-19 infection segmentation using hybrid deep learning and image processing techniques

“…Besides, Ahuja et al 58 , presented a three-phase detection model using deep transfer learning to increase detection accuracy. On the other hand, a hybrid model using transfer learning has also been discussed in 39 using CT scans to detect COVID-19, and other researchers used infection segmentation techniques [59][60][61][62][63][64][65] , the author of 59 , for instance, developed a novel deep network named "Inf-Net" to automatically identify sick areas from chest CT slices. That approach is built around a parallel partial decoder that combines high-level characteristics to produce a world map.…”

Enhancing the UNet3+ architecture for deep learning segmentation of kidneys and cysts in autosomal dominant polycystic kidney disease (ADPKD)

“…To tackle these challenges, we have embraced the concept of Channel-wise Skip Connections (CSCs) as introduced by Omar [34]. In this approach, feature maps from the skip connections are combined with those of the current layer.…”

Deep transfer learning from limited source for abdominal CT and MR image segmentation

“…Building upon the findings of Zhou et al [30], who asserted that the encoder part of UNet3+ lacked sufficiency in propagating segmentation features, we retained the original UNet3+ foundation and introduced residual layers into the encoder section to enhance data propagation [31]. To address the challenge of fading gradients and preserve intricate characteristics, we replaced full-scale skip connections with concatenated skip connections [32]. Additionally, we substituted the default batch normalization with adaptable normalization, allowing the neural network to dynamically choose the appropriate normalization method for specific scenarios [33].…”

“…Surface Distance (sSD), were utilized. These metrics assess the degree of overlap between the predicted images and the ground truth images [32,33]. In presenting the data from this study, mean values, along with their corresponding standard deviations, are provided.…”