Bilateral adaptive graph convolutional network on CT based Covid-19 diagnosis with uncertainty-aware consensus-assisted multiple instance learning

Meng, Yanda; Bridge, Joshua; Addison, Cliff; Wang, Manhui; Merritt, Cristin; Franks, Stu; Mackey, Maria; Messenger, Steve; Sun, Renrong; FitzMaurice, Thomas Simon; McCann, Caroline; Li, Qiang; Zhao, Yitian; Zheng, Yalin

doi:10.1016/j.media.2022.102722

Cited by 24 publications

(9 citation statements)

References 132 publications

(261 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, it can minimize the impact of non-lung regions on model learning, thereby enhancing the accuracy of diagnosis. Additionally, lung segmentation can assist in precisely locating specific structures or lesions in medical images, which is fundamental for accurate identification of pulmonary abnormalities and timely treatment decisions [13]. We hope that our research will contribute to the application of artificial intelligence in diagnosing COVID-19, and we are committed to using AI technology to segment infected areas in COVID-19 lung CT images automatically.…”

Section: Deep Learning In Covid-19 Diagnosismentioning

confidence: 97%

Global Adaptive Histogram Feature Network for Automatic Segmentation of Infection Regions in CT Images

Min,

Liu,

Zhou

et al. 2023

Preprint

View full text Add to dashboard Cite

We applied deep learning techniques in lung CT image diagnosis of COVID-19 for accurate segmentation of disease diagnosis. We propose a new deep learning framework, GAHFNet, specifically designed for automatic segmentation of COVID-19 lung CT images. GAHFNet outperforms other traditional and the state-of-the-art methods in various evaluation metrics, demonstrating the effectiveness and the efficiency of the proposed method in this task. This article discusses the limitations of current diagnostic methods, such as RT-PCR, and highlights the advantages of deep learning, including its ability to automatically learn features and handle complex lesion morphology and texture. Furthermore, the proposed method addresses the challenges in lung CT image segmentation, such as the complex image structure and difficulties of distinguishing COVID-19 pneumonia lesions from other pathologies. We provide the detailed description of the proposed GAHFNet. Finally, comprehensive experiments are carried out to evaluate the performance of GAHFNet, demonstrating that GAHFNet is able to facilitate the application of artificial intelligence in COVID-19 diagnosis and achieve accurate automatic segmentation of infected areas in COVID-19 lung CT images.

show abstract

Section: Deep Learning In Covid-19 Diagnosismentioning

confidence: 97%

Global Adaptive Histogram Feature Network for Automatic Segmentation of Infection Regions in CT Images

Min,

Liu,

Zhou

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the feature mapping strategies used in these methods heavily rely on prior knowledge or pre-determined node numbers, leading to limited generalization and adaptability. Meng et al (2023), proposed an uncertainty-aware consensus-assisted multiple instance learning model for simultaneous 2D-level feature extraction and automatic slice selection in CT scans. However, when feature mapping is represented by a fully connected graph, the semantic differences of features may be overlooked.…”

Section: Graph Representationmentioning

confidence: 99%

SM-GRSNet: sparse mapping-based graph representation segmentation network for honeycomb lung lesion

Zhang,

Feng,

Dong

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Abstract:Objective: Honeycomb lung is a rare but severe disease characterized by honeycomb-like imaging features and distinct radiological characteristics. Therefore, this study aims to develop a deep-learning model capable of segmenting honeycomb lung lesions from CT scans to address the efficacy issue of honeycomb lung segmentation.Methods: This study proposes a Sparse Mapping-based Graph Representation Segmentation Network (SM-GRSNet). SM-GRSNet integrates an attention affinity mechanism to effectively filter redundant features at a coarse-grained region level. The attention encoder generated by this mechanism specifically focuses on the lesion area. Additionally, we introduce a graph representation module based on sparse links in SM-GRSNet. Subsequently, graph representation operations are performed on the sparse graph, yielding detailed lesion segmentation results. Finally, we construct a pyramid-structured cascaded decoder in SM-GRSNet, which combines features from the sparse link-based graph representation modules and attention encoders to generate the final segmentation mask.Results: Experimental results demonstrate that the proposed SM-GRSNet achieves state-of-the-art performance on a dataset comprising 7170 honeycomb lung CT images. Our model attains the highest IOU (87.62%), Dice(93.41%). Furthermore, our model also achieves the lowest HD95 (6.95) and ASD (2.47). Significance: The SM-GRSNet method proposed in this paper can be used for automatic segmentation of honeycomb lung CT images, which enhances the segmentation performance of Honeycomb lung lesions under small sample datasets. It will help doctors with early screening, accurate diagnosis ,and customized treatment. This method maintains a high correlation and consistency between the automatic segmentation results and the expert manual segmentation results. Accurate automatic segmentation of the honeycomb lung lesion area is clinically important.

show abstract

Section: Introductionmentioning

confidence: 99%

“…With the spread of the COVID-19 pandemic and the huge number of infected persons, it is very important to provide efficient artificial intelligence solutions that can aid medical staff in the fighting against future pandemics [10]. In the last years, many efficient approaches have been proposed to detect, diagnose, and evaluate COVID-19 infection using various medical imaging modalities [11,12] In general, the quantification of COVID-19 infection from CT scans is performed by segmenting the infected regions from the CT slice, which is then compared with the entire lung regions on the same CT slice [13,14]. However, creating adequate segmentation datasets to train deep learning methods is a tedious task, which was especially true during the pandemic [9,15,16].…”

Section: Introductionmentioning

confidence: 99%

COVID-19 Infection Percentage Estimation from Computed Tomography Scans: Results and Insights from the International Per-COVID-19 Challenge

Bougourzi,

Distante,

Dornaika

et al. 2024

Sensors

View full text Add to dashboard Cite

COVID-19 analysis from medical imaging is an important task that has been intensively studied in the last years due to the spread of the COVID-19 pandemic. In fact, medical imaging has often been used as a complementary or main tool to recognize the infected persons. On the other hand, medical imaging has the ability to provide more details about COVID-19 infection, including its severity and spread, which makes it possible to evaluate the infection and follow-up the patient’s state. CT scans are the most informative tool for COVID-19 infection, where the evaluation of COVID-19 infection is usually performed through infection segmentation. However, segmentation is a tedious task that requires much effort and time from expert radiologists. To deal with this limitation, an efficient framework for estimating COVID-19 infection as a regression task is proposed. The goal of the Per-COVID-19 challenge is to test the efficiency of modern deep learning methods on COVID-19 infection percentage estimation (CIPE) from CT scans. Participants had to develop an efficient deep learning approach that can learn from noisy data. In addition, participants had to cope with many challenges, including those related to COVID-19 infection complexity and crossdataset scenarios. This paper provides an overview of the COVID-19 infection percentage estimation challenge (Per-COVID-19) held at MIA-COVID-2022. Details of the competition data, challenges, and evaluation metrics are presented. The best performing approaches and their results are described and discussed.

show abstract

Bilateral adaptive graph convolutional network on CT based Covid-19 diagnosis with uncertainty-aware consensus-assisted multiple instance learning

Cited by 24 publications

References 132 publications

Global Adaptive Histogram Feature Network for Automatic Segmentation of Infection Regions in CT Images

Global Adaptive Histogram Feature Network for Automatic Segmentation of Infection Regions in CT Images

SM-GRSNet: sparse mapping-based graph representation segmentation network for honeycomb lung lesion

COVID-19 Infection Percentage Estimation from Computed Tomography Scans: Results and Insights from the International Per-COVID-19 Challenge

Contact Info

Product

Resources

About