A multi-output network with U-net enhanced class activation map and robust classification performance for medical imaging analysis

Computer vision in medical diagnosis has achieved a high level of success in diagnosing diseases with high accuracy. However, conventional classifiers that produce an image-to-label result provide insufficient information for medical professionals to judge and raise concerns over the trust and reliability of a model with results that cannot be explained. To gain local insight of cancerous regions, separate tasks such as imaging segmentation needs to be implemented to aid the doctors in treating patients which doubles the training time and costs which renders the diagnosis system inefficient and difficult to be accepted by the public. To tackle this issue and drive the AI-first medical solutions further, this paper proposes a multi-output network which follows a U-Net architecture for image segmentation output and features an additional CNN module for auxiliary classification output. Class Activation Maps or CAMs are a method of providing insight into a convolutional neural network's feature maps that lead to its classification but in the case of lung diseases, the region of interest is enhanced by U-net assisted Class Activation Mapping (CAM) visualization. Therefore, our proposed model combines image segmentation models and classifiers to crop out only the lung region of a chest X-ray's class activation map to provide a visualization that improves the explainability and can generate classification results simultaneously which builds trust for AI-led diagnosis system. The proposed U-Net model achieves 97.72% accuracy and a dice coefficient of 0.9691 on a testing data from the COVID-QU-Ex Dataset which includes both diseased and healthy lungs.

Covid-19 Detection using Deep Learning

The fast and precise screening of suspected instances is limited due to a lack of resources and tight test environment requirements. In rare circumstances of RT-PCR inspection, erroneous negative results are also encountered. Detection of COVID-19 now requires at least one day to produce a result. Using an X-ray image, this method will provide quick and accurate findings. In this project using CNN algorithm the system recognises COVID-19. Two different publicly available datasets were used in this project. DL-based models provide a precise and well organised system for detecting it, resulting in a considerable increase of accuracy in image processing. This model has ac © 2022 IEEE.

Classification of Covid-19 Diseases Through Lung CT-Scan Image Using the ResNet-50 Architecture

Covid-19 is a disease of the respiratory tract caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) virus. One way to diagnose Covid-19 can be done by examining lung abnormalities on the results of a Computed Tomography Scan (CT-Scan) of the lungs. However, the determination of the diagnostic results obtained requires high accuracy and quite a long time. For this reason, an automatic system is needed to make it easier for medical personnel to diagnose Covid-19 disease quickly and accurately. One way to do this with the help of a computer is pattern recognition. In this study, pattern recognition techniques were used which were divided into three stages, namely pre-processing, feature extraction and classification. The methods used in the pre-processing stage are grayscale and Contrast Limited Adaptive Histogram Equalization (CLAHE) to improve image quality and contrast. The extraction stage uses the Principal Component Analysis (PCA) method, because it can reduce data dimensions without eliminating important features in the data. For the classification stage, a deep learning-based method is used, namely the Convolutional Neural Network (CNN). The CNN architecture used in this study is Resnet-50. The method proposed in this research is evaluated by measuring the performance values of accuracy, recall, precision, F1-score, and Cohen Kappa. The results of the study indicate that the PCA method has worked optimally in dimension reduction, without losing important features on CT-scan images of the lungs. Besides that, the proposed method has succeeded in classifying Covid-19 very well, as seen from the accuracy, Recall, Precision, F1-Score and Cohen Kappa values above 90%.

Learning label diffusion maps for semi-automatic segmentation of lung CT images with COVID-19

[Display omitted] • A fully end-to-end deep learning approach for COVID-19 CT image segmentation. • The trained model induces the diffusion of seeds by taking as input a marked slice. • The method learns diffusion maps by predicting edge weights via deep contour learning, • The use of deep contour learning and seeded segmentation as an integrated method. Deep Learning (DL) has become one of the key approaches for dealing with many challenges in medical imaging, which includes lung segmentation in Computed Tomography (CT). The use of seeded segmentation methods is another effective approach to get accurate partitions from complex CT images, as they give users autonomy, flexibility and easy usability when selecting specific targets for measurement purposes or pharmaceutical interventions. In this paper, we combine the accuracy of deep contour leaning with the versatility of seeded segmentation to yield a semi-automatic framework for segmenting lung CT images from patients affected by COVID-19. More specifically, we design a DL-driven approach that learns label diffusion maps from a contour detection network integrated with a label propagation model, used to diffuse the seeds over the CT images. Moreover, the trained model induces the diffusion of the seeds by only taking as input a marked CT-scan, segmenting hundreds of CT slices in an unsupervised and recursive way. Another important trait of our framework is that it is capable of segmenting lung structures even in the lack of well-defined boundaries and regardless of the level of COVID-19 infection. The accuracy and effectiveness of our learned diffusion model are attested to by both qualitative as well as quantitative comparisons involving several user-steered segmentations methods and eight CT data sets containing different types of lesions caused by COVID-19. [ FROM AUTHOR]

Advances and opportunities in nanoimaging agents for the diagnosis of inflammatory lung diseases.

The development of rapid, noninvasive diagnostics to detect lung diseases is a great need after the COVID-2019 outbreak. The nanotechnology-based approach has improved imaging and facilitates the early diagnosis of inflammatory lung diseases. The multifunctional properties of nanoprobes enable better spatial-temporal resolution and a high signal-to-noise ratio in imaging. Targeted nanoimaging agents have been used to bind specific tissues in inflammatory lungs for early-stage diagnosis. However, nanobased imaging approaches for inflammatory lung diseases are still in their infancy. This review provides a solution-focused approach to exploring medical imaging technologies and nanoprobes for the detection of inflammatory lung diseases. Prospects for the development of contrast agents for lung disease detection are also discussed.