Anam-Net: Anamorphic Depth Embedding-Based Lightweight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images

Abstract

Chest computed tomography (CT) imaging has become indispensable for staging and managing coronavirus disease 2019 (COVID-19), and current evaluation of anomalies/abnormalities associated with COVID-19 has been performed majorly by the visual score. The development of automated methods for quantifying COVID-19 abnormalities in these CT images is invaluable to clinicians. The hallmark of COVID-19 in chest CT images is the presence of ground-glass opacities in the lung region, which are tedious to segment manually. We propose anamorphic depth embedding-based lightweight CNN, called Anam-Net, to segment anomalies in COVID-19 chest CT images. The proposed Anam-Net has 7.8 times fewer parameters compared to the state-of-the-art UNet (or its variants), making it lightweight capable of providing inferences in mobile or resource constraint (point-of-care) platforms. The results from chest CT images (test cases) across different experiments showed that the proposed method could provide good Dice similarity scores for abnormal and normal regions in the lung. We have benchmarked Anam-Net with other state-of-the-art architectures, such as ENet, LEDNet, UNet++, SegNet, Attention UNet, and DeepLabV3+. The proposed Anam-Net was also deployed on embedded systems, such as Raspberry Pi 4, NVIDIA Jetson Xavier, and mobile-based Android application (Cov-Seg) embedded with Anam-Net to demonstrate its suitability for point-of-care platforms. The generated codes, models, and the mobile application are available for enthusiastic users at https://github.com/NaveenPaluru/Segmentation-COVID-19.

Learning to learn by yourself: Unsupervised meta‐learning with self‐knowledge distillation for COVID‐19 diagnosis from pneumonia cases

“…Most patients have an air bronchogram 60 . The distribution characteristics of the abnormalities on X‐ray images about these five types of pneumonia are similar to those of CT images (slices) 52,61‐73 . Although the collected 2D data (e.g., X‐ray images) in our proposed data set misses lots of information (original intensity level, spacing, etc.)…”

Mini-COVIDNet: Efficient Lightweight Deep Neural Network for Ultrasound Based Point-of-Care Detection of COVID-19

“…Many deep learning based architectures were proposed for detection of COVID including various pretrained architectures (including ResNet-50, LSTM, DenseNet-201, Location-attention etc. [9], [33]- [38]), architectures based on attention networks, and hybrid architectures. The achieved accuracy was as high as 98% even with number of samples available for training the network being less.…”

“…X-ray and CT imaging modalities have seen wider applicability for detection of COVID-19 as RT-PCR tests in the clinical setting have low sensitivity and specificity [4]. Various studies have shown the benefit of using CXR or CT and proven to improve results for detection of COVID-19 in the clinical scenario [5]- [9]. The low sensitivity of RT-PCR technique requires repeated negative tests resulting in short supply or unavailability of kits at various parts of the globe [5].…”

“…Also, CT scans can result in false negatives when the infection is in the early stages and requires time consuming detailed disinfection procedure. Although CT has the required promise for becoming modality of choice for detection of COVID-19 [9], lung US has got the attention recently due to US machines being widely available and are relatively cheaper with added advantage of being safe and easy to disinfect.…”

Improved 3D U-Net for COVID-19 Chest CT Image Segmentation

“…Numerous deep learning methods have been used to segment and quantitatively analyse infected areas in chest CT scans [11][12][13][14][15]. Li et al [11] proposed an automatic neural network architecture to detect COVID-19 from chest CT scans and distinguish it from other types of pneumonia and lung diseases.…”