COFE-Net: An ensemble strategy for Computer-Aided Detection for COVID-19. (January 2022)

• Record Type: Journal Article
• Authors: Banerjee, Avinandan; Bhattacharya, Rajdeep; Bhateja, Vikrant; Singh, Pawan Kumar; Lay-Ekuakille, Aime'; Sarkar, Ram
• Is Part Of: Measurement. Volume 187(2022)
• Publication Date: 2022-01
• Subjects: COVID-19 detection -- COFE-Net -- Deep learning -- Fuzzy integral -- Ensemble -- Classifier fusion -- Chest X-Ray -- CT Scan -- Biomedical measurement; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.110289
• Languages: English
• ISSNs: 0263-2241

Abstract

Abstract: Biomedical images contain a large volume of sensor measurements, which can reveal the descriptors of the disease under investigation. Computer-based analysis of such measurements helps detect the disease, and thereby swiftly aid medical professionals to choose adequate therapy. In this paper, we propose a robust deep learning ensemble framework known as COVID Fuzzy Ensemble Network, or COFE-Net. This strategy is proposed for the task of COVID-19 screening from chest X-rays (CXR) and CT Scans, as a part of Computer-Aided Detection (CADe) for medical practitioners. We leverage the strategy of Transfer Learning for Convolutional Neural Networks (CNNs) widely adopted in recent literature, and further propose an efficient ensemble network for their combination. The principles of fuzzy logic have been leveraged to combine the measured decision scores generated by three state-of-the-art CNNs – Inception V3, Inception ResNet V2 and DenseNet 201 – through the Choquet fuzzy integral. Experimental results support the efficacy of our approach over empirical ensembling, as the fuzzy ensembling strategy for biomedical measurement consists of dynamic refactoring of the classifier ensemble weights on the fly, based upon the confidence scores for coalitions of inputs. This is the chief advantage of our biomedical measurement strategy over others as other methods do not adjust to the multiple generated measurements dynamically unlike ours.Impressive results on multiple datasets demonstrate the effectiveness of the proposed method. The source code of our proposed method is made available at: https://github.com/theavicaster/covid-cade-ensemble . Highlights: Proposed a CNN ensemble framework for image based biomedical measurements. A COVID-19 Detection system for Chest X-ray images is established. Utilized Transfer Learning upon three Convolutional Neural Network Models. Choquet Fuzzy Integral supports dynamic coalition of classifier confidences. Appreciable results on a large public dataset verifies the efficacy of the method.