Multi-atlas pancreas segmentation: Atlas selection based on vessel structure

Karasawa, Ken’ichi; Oda, Masahiro; Kitasaka, Takayuki; Misawa, Kazunari; Fujiwara, Michitaka; Chu, Chengwen; Zheng, Guoyan; Rueckert, Daniel; Mori, Kensaku

doi:10.1016/j.media.2017.03.006

Cited by 78 publications

(50 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the maximization step (M-step), the goal is to find the performance parameters, θ, which maximize (16) with the current given parameters. Considering each S j and θ j independently, the expectation of log likelihood function in (16) can be expressed with the estimated voxelwise probability in E-step. Then the performance parameter of each segmentation can be formulated to find the solution which maximizes the summation of voxelwise probability as…”

Section: M-stepmentioning

confidence: 99%

Abdominal multi-organ segmentation with organ-attention networks and statistical fusion

Wang

Zhou

Shen

et al. 2019

Medical Image Analysis

178

117

View full text Add to dashboard Cite

Accurate and robust segmentation of abdominal organs on CT is essential for many clinical applications such as computer-aided diagnosis and computer-aided surgery. But this task is challenging due to the weak boundaries of organs, the complexity of the background, and the variable sizes of different organs. To address these challenges, we introduce a novel framework for multi-organ segmentation of abdominal regions by using organ-attention networks with reverse connections (OAN-RCs) which are applied to 2D views, of the 3D CT volume, and output estimates which are combined by statistical fusion exploiting structural similarity. More specifically, OAN is a two-stage deep convolutional network, where deep network features from the first stage are combined with the original image, in a second stage, to reduce the complex background and enhance the discriminative information for the target organs. Intuitively, OAN reduces the effect of the complex background by focusing attention so that each organ only needs to be discriminated from its local background. RCs are added to the first stage to give the lower layers more semantic information thereby enabling them to adapt to the sizes of different organs. Our networks are trained on 2D views (slices) enabling us to use holistic information and allowing efficient computation (compared to using 3D patches). To compensate for the limited cross-sectional information of the original 3D volumetric CT, e.g., the connectivity between neighbor slices, multi-sectional images are reconstructed from the three different 2D view directions. Then we combine the segmentation results from the different views using statistical fusion, with a novel term relating the structural similarity of the 2D views to the original 3D structure. To train the network and evaluate results, 13 structures were manually annotated by four human raters and confirmed by a senior expert on 236 normal cases. We tested our algorithm by 4-fold cross-validation and computed Dice-Sørensen similarity coefficients (DSC) and surface distances for evaluating our estimates of the 13 structures. Our experiments show that the proposed approach gives strong results and outperforms 2D-and 3D-patch based state-of-the-art methods in terms of DSC and mean surface distances.

show abstract

Section: M-stepmentioning

confidence: 99%

Abdominal multi-organ segmentation with organ-attention networks and statistical fusion

Wang

Zhou

Shen

et al. 2019

Medical Image Analysis

178

117

View full text Add to dashboard Cite

show abstract

“…One major group of related work on automatic pancreas segmentation in CT images is based on top-down multi-atlas registration and label fusion (MALF) [1]- [4]. Due to the high deformable shape and vague boundaries of the pancreas in CT scans from various patients, their reported segmentation accuracy results (measured in Dice Similarity Coefficient or DSC) range from 69.6±16.7% [3] to 78.5±14.0% [1], [4] under leave-one-patient-out (LOO) evaluation protocol.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore an end-to-end trainable deep learning model for pancreas segmentation may be more desirable to achieve superior results. Additionally, deep CNN based bottom-up pancreas segmentation methods also have significant advantages on run-time computational efficiency, such as 2 ∼ 4 hours in [4] versus 2 ∼ 3 minutes for [10] to process a new segmentation case.…”

Section: Introductionmentioning

confidence: 99%

Pancreas Segmentation in CT and MRI via Task-Specific Network Design and Recurrent Neural Contextual Learning

Cai

Lü

Xing

et al. 2019

Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics

View full text Add to dashboard Cite

Automatic pancreas segmentation in radiology images, e.g., computed tomography (CT) and magnetic resonance imaging (MRI), is frequently required by computer-aided screening, diagnosis, and quantitative assessment. Yet pancreas is a challenging abdominal organ to segment due to the high inter-patient anatomical variability in both shape and volume metrics. Recently, convolutional neural networks (CNNs) have demonstrated promising performance on accurate segmentation of pancreas. However, the CNN-based method often suffers from segmentation discontinuity for reasons such as noisy image quality and blurry pancreatic boundary. From this point, we propose to introduce recurrent neural networks (RNNs) to address the problem of spatial non-smoothness of inter-slice pancreas segmentation across adjacent image slices. To inference initial segmentation, we first train a 2D CNN sub-network, where we modify its network architecture with deep-supervision and multi-scale feature map aggregation so that it can be trained from scratch with small-sized training data and presents superior performance than transferred models. Thereafter, the successive CNN outputs are processed by another RNN sub-network, which refines the consistency of segmented shapes. More specifically, the RNN sub-network consists convolutional long short-term memory (CLSTM) units in both top-down and bottom-up directions, which regularizes the segmentation of an image by integrating predictions of its neighboring slices. We train the stacked CNN-RNN model endto-end and perform quantitative evaluations on both CT and MRI images.

show abstract

“…Atlases have recently been involved in several medical imaging problems, including the segmentation of brain tissues and lesions [1], [2], [3], prostate [4], lung [5], cardiac structures (e.g. myocardium) [6], [7], pancreas [8], [9], bones [10], cartilage [11], and multiple abdominal organ [12]. Atlases are used in segmentation problems based on image data originating from virtually all imaging modalities, including magnetic resonance images (MRI) [1], [2], [4], computed tomography (CT) [5], [9], [10], CT angiography [6], positron emission tomography (PET) [7], X-ray [13] and mammography [14].…”

Section: Introductionmentioning

confidence: 99%

Brain Tumor Segmentation from MRI Data Using Ensemble Learning and Multi-Atlas

Fulop

Győrfi

Suranyi

et al. 2020

2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI)

View full text Add to dashboard Cite

Atlases are frequently employed to assist medical image segmentation with prior information. This paper introduces a multi-atlas architecture that is trained to locally characterize the appearance (average intensity and standard deviation) of normal tissues in various observed and computed data channels of brain MRI records. The multiple atlas is then deployed to enhance the accuracy of an ensemble learning based brain tumor segmentation procedure that uses binary decision trees. The proposed method is validated using the low-grade tumor volumes of the BraTS 2016 train data set. The use of atlases improve the segmentation quality, causing a rise of up to 1.5% in average Dices scores.

show abstract

Multi-atlas pancreas segmentation: Atlas selection based on vessel structure

Cited by 78 publications

References 35 publications

Abdominal multi-organ segmentation with organ-attention networks and statistical fusion

Abdominal multi-organ segmentation with organ-attention networks and statistical fusion

Pancreas Segmentation in CT and MRI via Task-Specific Network Design and Recurrent Neural Contextual Learning

Brain Tumor Segmentation from MRI Data Using Ensemble Learning and Multi-Atlas

Contact Info

Product

Resources

About