Weakly-Supervised Network for Detection of COVID-19 in Chest CT Scans

Abstract

Deep Learning-based chest Computed Tomography (CT) analysis has been proven to be effective and efficient for COVID-19 diagnosis. Existing deep learning approaches heavily rely on large labeled data sets, which are difficult to acquire in this pandemic situation. Therefore, weakly-supervised approaches are in demand. In this paper, we propose an end-to-end weakly-supervised COVID-19 detection approach, ResNext+, that only requires volume level data labels and can provide slice level prediction. The proposed approach incorporates a lung segmentation mask as well as spatial and channel attention to extract spatial features. Besides, Long Short Term Memory (LSTM) is utilized to acquire the axial dependency of the slices. Moreover, a slice attention module is applied before the final fully connected layer to generate the slice level prediction without additional supervision. An ablation study is conducted to show the efficiency of the attention blocks and the segmentation mask block. Experimental results, obtained from publicly available datasets, show a precision of 81.9% and F1 score of 81.4%. The closest state-of-the-art gives 76.7% precision and 78.8% F1 score. The 5% improvement in precision and 3% in the F1 score demonstrate the effectiveness of the proposed method. It is worth noticing that, applying image enhancement approaches do not improve the performance of the proposed method, sometimes even harm the scores, although the enhanced images have better perceptual quality.

Performing Weakly Supervised Retail Instance Segmentation via Region Normalization

“…Given the inefficiency of pixel-level annotations, previous efforts have explored various alternative weak annotations, such as the point on the example, the object bounding box, the scribble, and the foreground of human selection [22]- [24]. Although these methods achieve improved performance, they require more labor than methods only using image-level labels [25], [26]. Some works use object cues in an unsupervised condition [27] [28].…”

An Interpretation Architecture for Deep Learning Models with the Application of COVID-19 Diagnosis

“…Chest CT is more sensitive Entropy 2021, 23, 204 2 of 19 but less specific than RT-PCR [9,10]. To alleviate the burden of clinician in reading CT scans, some studies [11][12][13][14][15][16] have been conducted trying to develop methods to identify the infected patients automatically based on computer-aided diagnosis (CAD) strategy. Most of these studies employ deep learning methods, especially the convolutional neural network (CNN), in order to classify images of CT scans as infected or not.…”

COVID-19 Diagnosis from chest CT Scans: A Weakly Supervised CNN-LSTM Approach

“…The healthcare providers are facing intense workload due to the pandemic [8]. To relieve the overwhelming workload, AI systems are being used to detect and identify COVID-19 using medical imaging technologies [9][10][11][12][13][14][15][16][17]. Recent studies on radiology demonstrate promising results on COVID-19 pneumonia classification using chest CTs with the help of deep learning methodologies.…”

“…There are different class definition approaches in the COVID-19 related studies like binary or multiclass. Binary classification is usually applied as Covid pneumonia and non-Covid pneumonia [12,17] or Covid positive and Covid negative [14,16]. Multiclass classification separates Covid negative further into Covid pneumonia, non-Covid pneumonia and no pneumonia [9][10][11]13,15].…”