Medical image segmentation via atlases and fuzzy object models: Improving efficacy through optimum object search and fewer models

Phellan, Renzo; Falcão, Alexandre X.; Udupa, Jayaram K.

doi:10.1118/1.4938577

Cited by 19 publications

(32 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Methods based on PAs estimate a prior probabilistic map P where each voxel has a prior probability of belonging to a given object independent of its value in the image . The construction of P requires deformable image registration to place object masks from X on to a common coordinate system — the domain of a template (reference 3D image) .…”

Section: Introductionmentioning

confidence: 99%

“…In Grau et al, for instance, the authors binarize P , apply morphological operations, and estimate seeds for object delineation by watershed transform. Phellan et al in turn have demonstrated that if we acknowledge errors in registration, the accuracy of PAs may be significantly improved as long as a local search for the object is performed with the model. For this purpose, its statistical object model, named SOSM‐S, translates over the test image in the reference space for more accurate object localization and delineation by using the Image Foresting Transform (IFT) algorithm .…”

Section: Introductionmentioning

confidence: 99%

“… Image delineation by SOSM‐S . (a) Coronal slice of a three‐dimensional (3D) brain image after left temporal lobe resection (arrow).…”

Section: Introductionmentioning

confidence: 99%

“…AdaPro is an extension of our previous method SOSM‐A, which in turn is derived from SOSM‐S . Its main contributions are: (a) we increase the uncertainty region of the statistical shape model (by erosion and dilation) and apply a binary classifier to identify anomalous and CSF voxels under the region of the model.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An adaptive probabilistic atlas for anomalous brain segmentation in MR images

et al. 2019

View full text Add to dashboard Cite

Purpose: Automated segmentation of brain structures (objects) in MR three-dimensional (3D) images for quantitative analysis has been a challenge and probabilistic atlases (PAs) are among the most well-succeeded approaches. However, the existing models do not adapt to possible object anomalies due to the presence of a disease or a surgical procedure. Post-processing operation does not solve the problem, for example, tissue classification to detect and remove such anomalies inside the resulting segmentation mask, because segmentation errors on healthy tissues cannot be fixed. Such anomalies very often alter the shape and texture of the brain structures, making them different from the appearance of the model. In this paper, we present an effective and efficient adaptive probabilistic atlas, named AdaPro, to circumvent the problem and evaluate it on a challenging taskthe segmentation of the left hemisphere, right hemisphere, and cerebellum, without pons and medulla, in 3D MR-T1 brain images of Epilepsy patients. This task is challenging due to temporal lobe resections, artifacts, and the absence of contrast in some parts between the structures of interest. Methods: In AdaPro, we first build one probabilistic atlas per object of interest from a training set with normal 3D images and the corresponding 3D object masks. Second, we incorporate a texture classifier based on convex optimization which dynamically indicates the regions of the target 3D image where the PAs (shape constraints) should be further adapted. This strategy is mathematically more elegant and avoids problems with post-processing. Third, we add a new object-based delineation algorithm based on combinatorial optimization and diffusion filtering. AdaPro can then be used to locate and delineate the objects in the coordinate space of the atlas or of the test image. We also compare AdaPro with three other state-of-the-art methods: an statistical shape model based on synergistic object search and delineation, and two methods based on multi-atlas label fusion (MALF). Results: We evaluate the methods quantitatively on 3D MR-T1 brain images of 2T and 3T from epilepsy patients, before and after temporal lobe resections, and on the template and native coordinate spaces. The results show that AdaPro is considerably faster and consistently more accurate than the baselines with statistical significance in both coordinate spaces. Conclusion: AdaPro can be used as a fast and effective step for brain tissue segmentation and it can also be easily extended to segment subcortical brain structures. By choice of its components, probabilistic atlas, texture classifier, and delineation algorithm, it can also be extended to other organs and imaging modalities.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“… Image delineation by SOSM‐S . (a) Coronal slice of a three‐dimensional (3D) brain image after left temporal lobe resection (arrow).…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An adaptive probabilistic atlas for anomalous brain segmentation in MR images

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Image segmentation is according to the certain rules to divide the image into the several mutually disjoint that has certain properties of the area, the attention to a part extracted from the image of the further research and analysis and processing [1][2]. The result of image segmentation is the basis of the image feature extraction and the recognition of image understanding, the study of image segmentation has been a hot spot and focus in the study of the digital image processing techniques that makes the subsequent image analysis and image segmentation to identify the amount of data to be processed by the advanced stage of processing, such as greatly reduced, and retain information about the image structure characteristics at the same time [3][4].…”

Section: Introductionmentioning

confidence: 99%

A Novel MRI Image Segmentation Algorithm based on Modified Neural Network Model

Yang¹,

Xia-zhen²,

Zhang³

et al. 2016

IJSIP

View full text Add to dashboard Cite

show abstract

ALTIS: A fast and automatic lung and trachea CT‐image segmentation method

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose: The automated segmentation of each lung and trachea in CT scans is commonly taken as a solved problem. Indeed, existing approaches may easily fail in the presence of some abnormalities caused by a disease, trauma, or previous surgery. For robustness, we present ALTIS (implementation is available at http://lids.ic.unicamp.br/downloads)a fast automatic lung and trachea CT-image segmentation method that relies on image features and relative shape-and intensity-based characteristics less affected by most appearance variations of abnormal lungs and trachea. Methods: ALTIS consists of a sequence of image foresting transforms (IFTs) organized in three main steps: (a) lung-and-trachea extraction, (b) seed estimation inside background, trachea, left lung, and right lung, and (c) their delineation such that each object is defined by an optimum-path forest rooted at its internal seeds. We compare ALTIS with two methods based on shape models (SOSM-S and MALF), and one algorithm based on seeded region growing (PTK). Results:The experiments involve the highest number of scans found in literature -1255 scans, from multiple public data sets containing many anomalous cases, being only 50 normal scans used for training and 1205 scans used for testing the methods. Quantitative experiments are based on two metrics, DICE and ASSD. Furthermore, we also demonstrate the robustness of ALTIS in seed estimation. Considering the test set, the proposed method achieves an average DICE of 0.987 for both lungs and 0.898 for the trachea, whereas an average ASSD of 0.938 for the right lung, 0.856 for the left lung, and 1.316 for the trachea. These results indicate that ALTIS is statistically more accurate and considerably faster than the compared methods, being able to complete segmentation in a few seconds on modern PCs. Conclusion: ALTIS is the most effective and efficient choice among the compared methods to segment left lung, right lung, and trachea in anomalous CT scans for subsequent detection, segmentation, and quantitative analysis of abnormal structures in the lung parenchyma and pleural space.

show abstract

Medical image segmentation via atlases and fuzzy object models: Improving efficacy through optimum object search and fewer models

Cited by 19 publications

References 40 publications

An adaptive probabilistic atlas for anomalous brain segmentation in MR images

An adaptive probabilistic atlas for anomalous brain segmentation in MR images

A Novel MRI Image Segmentation Algorithm based on Modified Neural Network Model

ALTIS: A fast and automatic lung and trachea CT‐image segmentation method

Contact Info

Product

Resources

About