Dataset Information

HFCF-Net: A hybrid-feature cross fusion network for COVID-19 lesion segmentation from CT volumetric images.

ABSTRACT:

Background

The coronavirus disease 2019 (COVID-19) spreads rapidly across the globe, seriously threatening the health of people all over the world. To reduce the diagnostic pressure of front-line doctors, an accurate and automatic lesion segmentation method is highly desirable in clinic practice.

Purpose

Many proposed two-dimensional (2D) methods for sliced-based lesion segmentation cannot take full advantage of spatial information in the three-dimensional (3D) volume data, resulting in limited segmentation performance. Three-dimensional methods can utilize the spatial information but suffer from long training time and slow convergence speed. To solve these problems, we propose an end-to-end hybrid-feature cross fusion network (HFCF-Net) to fuse the 2D and 3D features at three scales for the accurate segmentation of COVID-19 lesions.

Methods

The proposed HFCF-Net incorporates 2D and 3D subnets to extract features within and between slices effectively. Then the cross fusion module is designed to bridge 2D and 3D decoders at the same scale to fuse both types of features. The module consists of three cross fusion blocks, each of which contains a prior fusion path and a context fusion path to jointly learn better lesion representations. The former aims to explicitly provide the 3D subnet with lesion-related prior knowledge, and the latter utilizes the 3D context information as the attention guidance of the 2D subnet, which promotes the precise segmentation of the lesion regions. Furthermore, we explore an imbalance-robust adaptive learning loss function that includes image-level loss and pixel-level loss to tackle the problems caused by the apparent imbalance between the proportions of the lesion and non-lesion voxels, providing a learning strategy to dynamically adjust the learning focus between 2D and 3D branches during the training process for effective supervision.

Result

Extensive experiments conducted on a publicly available dataset demonstrate that the proposed segmentation network significantly outperforms some state-of-the-art methods for the COVID-19 lesion segmentation, yielding a Dice similarity coefficient of 74.85%. The visual comparison of segmentation performance also proves the superiority of the proposed network in segmenting different-sized lesions.

Conclusions

In this paper, we propose a novel HFCF-Net for rapid and accurate COVID-19 lesion segmentation from chest computed tomography volume data. It innovatively fuses hybrid features in a cross manner for lesion segmentation, aiming to utilize the advantages of 2D and 3D subnets to complement each other for enhancing the segmentation performance. Benefitting from the cross fusion mechanism, the proposed HFCF-Net can segment the lesions more accurately with the knowledge acquired from both subnets.

SUBMITTER: Wang Y

PROVIDER: S-EPMC9088496 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The recent global outbreak and spread of coronavirus disease (COVID-19) makes it an imperative to develop accurate and efficient diagnostic tools for the disease as medical resources are getting increasingly constrained. Artificial intelligence (AI)-aided tools have exhibited desirable potential; for example, chest computed tomography (CT) has been demonstrated to play a major role in the diagnosis and evaluation of COVID-19. However, developing a CT-based AI diagnostic system for the disease detection has faced considerable challenges, which is mainly due to the lack of adequate manually-delineated samples for training, as well as the requirement of sufficient sensitivity to subtle lesions in the early infection stages. In this study, we developed a dual-branch combination network (DCN) for COVID-19 diagnosis that can simultaneously achieve individual-level classification and lesion segmentation. To focus the classification branch more intensively on the lesion areas, a novel lesion attention module was developed to integrate the intermediate segmentation results. Furthermore, to manage the potential influence of different imaging parameters from individual facilities, a slice probability mapping method was proposed to learn the transformation from slice-level to individual-level classification. We conducted experiments on a large dataset of 1202 subjects from ten institutes in China. The results demonstrated that 1) the proposed DCN attained a classification accuracy of 96.74% on the internal dataset and 92.87% on the external validation dataset, thereby outperforming other models; 2) DCN obtained comparable performance with fewer samples and exhibited higher sensitivity, especially in subtle lesion detection; and 3) DCN provided good interpretability on the loci of infection compared to other deep models due to its classification guided by high-level semantic information. An online CT-based diagnostic platform for COVID-19 derived from our proposed framework is now available.

Project description:Due to advances in the acquisition and analysis of medical imaging, it is currently possible to quantify the tumor phenotype. The emerging field of Radiomics addresses this issue by converting medical images into minable data by extracting a large number of quantitative imaging features. One of the main challenges of Radiomics is tumor segmentation. Where manual delineation is time consuming and prone to inter-observer variability, it has been shown that semi-automated approaches are fast and reduce inter-observer variability. In this study, a semiautomatic region growing volumetric segmentation algorithm, implemented in the free and publicly available 3D-Slicer platform, was investigated in terms of its robustness for quantitative imaging feature extraction. Fifty-six 3D-radiomic features, quantifying phenotypic differences based on tumor intensity, shape and texture, were extracted from the computed tomography images of twenty lung cancer patients. These radiomic features were derived from the 3D-tumor volumes defined by three independent observers twice using 3D-Slicer, and compared to manual slice-by-slice delineations of five independent physicians in terms of intra-class correlation coefficient (ICC) and feature range. Radiomic features extracted from 3D-Slicer segmentations had significantly higher reproducibility (ICC?=?0.85±0.15, p?=?0.0009) compared to the features extracted from the manual segmentations (ICC?=?0.77±0.17). Furthermore, we found that features extracted from 3D-Slicer segmentations were more robust, as the range was significantly smaller across observers (p?=?3.819e-07), and overlapping with the feature ranges extracted from manual contouring (boundary lower: p?=?0.007, higher: p?=?5.863e-06). Our results show that 3D-Slicer segmented tumor volumes provide a better alternative to the manual delineation for feature quantification, as they yield more reproducible imaging descriptors. Therefore, 3D-Slicer can be employed for quantitative image feature extraction and image data mining research in large patient cohorts.