Segmenting Lungs from Whole-Body CT Scans

Walczak, Maksym; Burda, Izabela; Nalepa, Jakub; Kawulok, Michał

doi:10.1007/978-3-319-58274-0_32

Cited by 1 publication

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method leverages deep neural networks to automatically learn complex features and structures in images, making it suitable for handling complex scenes and large-scale datasets. Take the work of Walczak et al [6] as an example. To achieve good segmentation results, their method consists of numerous steps, including false-positive elimination, lung segmentation, and post-processing.…”

Section: Discussionmentioning

confidence: 99%

“…Nevertheless, this method overlooks lesion areas and may result in inadequate segmentation when applied to complex CT lesion images. Walczak et al [6] enhanced an automated lung segmentation method [7] by incorporating false-positive elimination processing and refining the procedure for separating the two lungs. However, this algorithm does not explicitly segment structures such as pulmonary nodules, small airways, and bronchi.…”

Section: A Threshold-based Segmentation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Lung Parenchyma Segmentation Based on U-Net Fused With Shape Stream

Zhu,

Cai,

Liao

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Accurate lung parenchyma segmentation is vital for computer-aided lung cancer diagnosis. Existing lung parenchyma segmentation networks excel at segmenting large and clear lung parenchyma regions, but struggle with small and blurry regions. This study proposes an improved network structure to improve the segmentation performance of small and blurry lung parenchyma regions while maintaining accuracy for large and clear lung parenchyma regions. The proposed network is an improved network based on U-Net. A shape stream branch and multi-scale convolutional blocks are introduced into the network. The proposed network takes computed tomography (CT) images as inputs and generates corresponding binary masks as outputs. In this study, the original CT images are derived from the Open Source Imaging Consortium (OSIC) Pulmonary Fibrosis Progression dataset. In the experimental results, the overall mean Dice Similarity Coefficient (DSC) of the proposed network reaches 0.932907, which is 0.64% higher than that of the secondbest network. The segment test results show that the proposed network has significantly better segmentation performance than other networks when the lung parenchyma is relatively small. On a patient-by-patient basis, the mean DSC of the proposed network is 0.63% higher than that of the second-best network. The proposed network improves the segmentation performance of small and blurry lung parenchyma while maintaining accuracy for large and clear lung parenchyma.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: A Threshold-based Segmentation Methodsmentioning

confidence: 99%