Automatic lung tumor segmentation with leaks removal in follow-up CT studies

Vivanti, Refael; Joskowicz, Leo; Karaaslan, Onur

doi:10.1007/s11548-015-1150-0

Cited by 19 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vivanti et al. demonstrated a four‐step process involving deformation registration, segmentation of lung tumors, leak detection, and tumor boundary regularization 12 . Methods based on active contouring algorithms 13 and sparse field active models 14 have also been investigated to segment lung tumor on 3D image sets.…”

Section: Introductionmentioning

confidence: 99%

Lung tumor segmentation in 4D CT images using motion convolutional neural networks

et al. 2021

View full text Add to dashboard Cite

Purpose Manual delineation on all breathing phases of lung cancer 4D CT image datasets can be challenging, exhaustive, and prone to subjective errors because of both the large number of images in the datasets and variations in the spatial location of tumors secondary to respiratory motion. The purpose of this work is to present a new deep learning‐based framework for fast and accurate segmentation of lung tumors on 4D CT image sets. Methods The proposed DL framework leverages motion region convolutional neural network (R‐CNN). Through integration of global and local motion estimation network architectures, the network can learn both major and minor changes caused by tumor motion. Our network design first extracts tumor motion information by feeding 4D CT images with consecutive phases into an integrated backbone network architecture, locating volume‐of‐interest (VOIs) via a regional proposal network and removing irrelevant information via a regional convolutional neural network. Extracted motion information is then advanced into the subsequent global and local motion head network architecture to predict corresponding deformation vector fields (DVFs) and further adjust tumor VOIs. Binary masks of tumors are then segmented within adjusted VOIs via a mask head. A self‐attention strategy is incorporated in the mask head network to remove any noisy features that might impact segmentation performance. We performed two sets of experiments. In the first experiment, a five‐fold cross‐validation on 20 4D CT datasets, each consisting of 10 breathing phases (i.e., 200 3D image volumes in total). The network performance was also evaluated on an additional unseen 200 3D images volumes from 20 hold‐out 4D CT datasets. In the second experiment, we trained another model with 40 patients’ 4D CT datasets from experiment 1 and evaluated on additional unseen nine patients’ 4D CT datasets. The Dice similarity coefficient (DSC), center of mass distance (CMD), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and volume difference (VD) between the manual and segmented tumor contour were computed to evaluate tumor detection and segmentation accuracy. The performance of our method was quantitatively evaluated against four different methods (VoxelMorph, U‐Net, network without global and local networks, and network without attention gate strategy) across all evaluation metrics through a paired t‐test. Results The proposed fully automated DL method yielded good overall agreement with the ground truth for contoured tumor volume and segmentation accuracy. Our model yielded significantly better values of evaluation metrics (p < 0.05) than all four competing methods in both experiments. On hold‐out datasets of experiment 1 and 2, our method yielded DSC of 0.86 and 0.90 compared to 0.82 and 0.87, 0.75 and 0.83, 081 and 0.89, and 0.81 and 0.89 yielded by VoxelMorph, U‐Net, network without global and local networks, and networks without attention gate strategy. Tumor VD between ground truth and our method was the smal...

show abstract

Section: Introductionmentioning

confidence: 99%

Lung tumor segmentation in 4D CT images using motion convolutional neural networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Figure shows typical examples of lung‐boundary adhesion large tumors, where a large tumor remains confined to the damaged lung or if the ratio of the tumor area to the damaged lung area is much less than unity, it is categorized as a moderate large‐sized (ML) tumor; otherwise, it is categorized as a giant large‐sized (GL) tumor. In the past, numerous methods have been proposed to mainly segment on small lung masses attached to lung boundaries (e.g., juxta‐pleural nodules) including region‐growing or watershed followed by morphological processing, supervised segmentation models based on feature extraction and support vector machines or neural networks, and energy minimization models with prior knowledge . With the intensive investigation of sparse representation, the sparse constraints have been used to model shape priors, which explicitly model spatially contiguous gross errors (non‐Gaussian errors) in input shapes with sparse vectors and assume that these gross errors are sparse with respect to the given shape information .…”

Section: Introductionmentioning

confidence: 99%

Spline curve deformation model with prior shapes for identifying adhesion boundaries between large lung tumors and tissues around lungs in CT images

et al. 2020

View full text Add to dashboard Cite

Purpose Automated segmentation of lung tumors attached to anatomic structures such as the chest wall or mediastinum remains a technical challenge because of the similar Hounsfield units of these structures. To address this challenge, we propose herein a spline curve deformation model that combines prior shapes to correct large spatially contiguous errors (LSCEs) in input shapes derived from image‐appearance cues.The model is then used to identify the adhesion boundaries between large lung tumors and tissue around the lungs. Methods The deformation of the whole curve is driven by the transformation of the control points (CPs) of the spline curve, which are influenced by external and internal forces. The external force drives the model to fit the positions of the non‐LSCEs of the input shapes while the internal force ensures the local similarity of the displacements of the neighboring CPs. The proposed model corrects the gross errors in the lung input shape caused by large lung tumors, where the initial lung shape for the model is inferred from the training shapes by shape group‐based sparse prior information and the input lung shape is inferred by adaptive‐thresholding‐based segmentation followed by morphological refinement. Results The accuracy of the proposed model is verified by applying it to images of lungs with either moderate large‐sized (ML) tumors or giant large‐sized (GL) tumors. The quantitative results in terms of the averages of the dice similarity coefficient (DSC) and the Jaccard similarity index (SI) are 0.982 ± 0.006 and 0.965 ± 0.012 for segmentation of lungs adhered by ML tumors, and 0.952 ± 0.048 and 0.926 ± 0.059 for segmentation of lungs adhered by GL tumors, which give 0.943 ± 0.021 and 0.897 ± 0.041 for segmentation of the ML tumors, and 0.907 ± 0.057 and 0.888 ± 0.091 for segmentation of the GL tumors, respectively. In addition, the bidirectional Hausdorff distances are 5.7 ± 1.4 and 11.3 ± 2.5 mm for segmentation of lungs with ML and GL tumors, respectively. Conclusions When combined with prior shapes, the proposed spline curve deformation can deal with large spatially consecutive errors in object shapes obtained from image‐appearance information. We verified this method by applying it to the segmentation of lungs with large tumors adhered to the tissue around the lungs and the large tumors. Both the qualitative and quantitative results are more accurate and repeatable than results obtained with current state‐of‐the‐art techniques.

show abstract

“…An ensemble segmentation was obtained from multiple regions that were grown from different seed points followed by voting. Vivanti et al [7] proposed a method for the segmentation of lung tumors. Their method consists of four steps: deformation registration, segmentation of lung tumor, leaks detection and tumor boundary regularization.…”

Section: Introductionmentioning

confidence: 99%

Multi-phase simultaneous segmentation of tumor in lung 4D-CT data with context information

Shen¹,

Wang²,

Xi³

et al. 2017

PLoS ONE

View full text Add to dashboard Cite

Lung 4D computed tomography (4D-CT) plays an important role in high-precision radiotherapy because it characterizes respiratory motion, which is crucial for accurate target definition. However, the manual segmentation of a lung tumor is a heavy workload for doctors because of the large number of lung 4D-CT data slices. Meanwhile, tumor segmentation is still a notoriously challenging problem in computer-aided diagnosis. In this paper, we propose a new method based on an improved graph cut algorithm with context information constraint to find a convenient and robust approach of lung 4D-CT tumor segmentation. We combine all phases of the lung 4D-CT into a global graph, and construct a global energy function accordingly. The sub-graph is first constructed for each phase. A context cost term is enforced to achieve segmentation results in every phase by adding a context constraint between neighboring phases. A global energy function is finally constructed by combining all cost terms. The optimization is achieved by solving a max-flow/min-cut problem, which leads to simultaneous and robust segmentation of the tumor in all the lung 4D-CT phases. The effectiveness of our approach is validated through experiments on 10 different lung 4D-CT cases. The comparison with the graph cut without context constraint, the level set method and the graph cut with star shape prior demonstrates that the proposed method obtains more accurate and robust segmentation results.

show abstract

Automatic lung tumor segmentation with leaks removal in follow-up CT studies

Abstract: The key advantage of our method is that it automatically builds a patient-specific prior to the tumor. Using this prior in the segmentation process, we developed an algorithm that increases segmentation accuracy and robustness and reduces observer variability.

Cited by 19 publications

References 20 publications

Lung tumor segmentation in 4D CT images using motion convolutional neural networks

Lung tumor segmentation in 4D CT images using motion convolutional neural networks

Spline curve deformation model with prior shapes for identifying adhesion boundaries between large lung tumors and tissues around lungs in CT images

Multi-phase simultaneous segmentation of tumor in lung 4D-CT data with context information

Contact Info

Product

Resources

About