Refinement-Cut: User-Guided Segmentation Algorithm for Translational Science

Egger, Jan

doi:10.1038/srep05164

Cited by 19 publications

(10 citation statements)

References 43 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Afterwards, for a consistent comparison for the evaluation, the datasets have been reformatted to isotropic resolutions (twice to 0.63x0.63x0.63 mm 3 and once to 0.73x0.73x0.73 mm 3 ) to sizes of 512x512x113, 512x512x113 and 512x512x70. The images have previously been used in [12][13][14][15][16][17] and the freely available datasets can be found here: http://www.cg.informatik.uni-siegen.de/de/spine-segmentation-and-analysis…”

Section: Methodsmentioning

confidence: 99%

Cellular automata segmentation of the boundary between the compacta of vertebral bodies and surrounding structures

Egger

Nimsky

2016

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Due to the aging population, spinal diseases get more and more common nowadays; e.g., lifetime risk of osteoporotic fracture is 40% for white women and 13% for white men in the United States. Thus the numbers of surgical spinal procedures are also increasing with the aging population and precise diagnosis plays a vital role in reducing complication and recurrence of symptoms. Spinal imaging of vertebral column is a tedious process subjected to interpretation errors. In this contribution, we aim to reduce time and error for vertebral interpretation by applying and studying the GrowCutalgorithm for boundary segmentation between vertebral body compacta and surrounding structures. GrowCut is a competitive region growing algorithm using cellular automata. For our study, vertebral T2-weighted Magnetic Resonance Imaging (MRI) scans were first manually outlined by neurosurgeons. Then, the vertebral bodies were segmented in the medical images by a GrowCut-trained physician using the semi-automated GrowCut-algorithm. Afterwards, results of both segmentation processes were compared using the Dice Similarity Coefficient (DSC) and the Hausdorff Distance (HD) which yielded to a DSC of 82.99±5.03% and a HD of 18.91±7.2 voxel, respectively. In addition, the times have been measured during the manual and the GrowCut segmentations, showing that a GrowCutsegmentation -with an average time of less than six minutes (5.77±0.73) -is significantly shorter than a pure manual outlining.

show abstract

Section: Methodsmentioning

confidence: 99%

Cellular automata segmentation of the boundary between the compacta of vertebral bodies and surrounding structures

Egger

Nimsky

2016

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the RSS, several parameters had to be defined: The Approximate Volume, the Intensity Homogeneity, the Boundary Smoothness and the Max running time (min). 58 , mean value (µ) and standard deviation (σ). Firstly, we identified a parameter setting that achieved a high DSC for the first case in The yellow line represents the result of the semi-automatic segmentation (see also Fig.…”

Section: Figurementioning

confidence: 99%

Interactive Outlining of Pancreatic Cancer Liver Metastases in Ultrasound Images

Egger¹,

Schmalstieg²,

Chen³

et al. 2017

Sci Rep

Self Cite

View full text Add to dashboard Cite

Ultrasound (US) is the most commonly used liver imaging modality worldwide. Due to its low cost, it is increasingly used in the follow-up of cancer patients with metastases localized in the liver. In this contribution, we present the results of an interactive segmentation approach for liver metastases in US acquisitions. A (semi-) automatic segmentation is still very challenging because of the low image quality and the low contrast between the metastasis and the surrounding liver tissue. Thus, the state of the art in clinical practice is still manual measurement and outlining of the metastases in the US images. We tackle the problem by providing an interactive segmentation approach providing real-time feedback of the segmentation results. The approach has been evaluated with typical US acquisitions from the clinical routine, and the datasets consisted of pancreatic cancer metastases. Even for difficult cases, satisfying segmentations results could be achieved because of the interactive real-time behavior of the approach. In total, 40 clinical images have been evaluated with our method by comparing the results against manual ground truth segmentations. This evaluation yielded to an average Dice Score of 85% and an average Hausdorff Distance of 13 pixels.Compared to computed tomography (CT) or magnetic resonance imaging (MRI), ultrasound (US) is a more easily accessible and less expensive imaging procedure, and, for the liver, the most commonly used imaging modality worldwide. The preference for US is owed to the multiple access points of the liver for the US examination. The intercostal and subcostal route allow for the examination of the whole organ in most of the patients. Hence, the usage of US is also one of the first procedures for evaluating liver metastases, when a patient is diagnosed with cancer. After a subsequent initial staging using CT of the thorax and the abdomen, US is often used to evaluate for treatment response of cancer patients with metastases solely localized in the liver. In case of pancreatic cancer, additional staging of the primary tumor can be done with endoscopic ultrasound. Due to the good accuracy of US in diagnosis and follow-up of liver metastases compared to CT or MRI 1 , the current ESMO -ESDO clinical practice guideline recommend US for the response evaluation in the palliative setting of pancreatic cancer patients 2 . Additionally to the appearance of a new metastases during follow-up, the change in size of preexisting metastases plays an important role in the evaluation of treatment response. Nevertheless, the liver metastases appearance in US acquisitions is highly variable 3 . A schematic overview of the different echo-patterns is presented in Fig. 1: Compared to the surrounding liver tissue, metastases can appear, for example, hyperechoic/brighter (A) or hypoechoic/darker (C) in B-mode. However, isoechoic (B) masses can have a very similar echo-pattern compared to the surrounding liver tissue and can be hard to detect. Consequently, the size determination of isoechoic masse...

show abstract

“…This allows the user to drag the seed point around (inside the lesion) to improve the result until a satisfying segmentation is reached [53]. However, for difficult cases, the user can place additional seeds on the border of the metastasis, which restrict and support the interactive segmentation and was worked already in other structures [54]- [57]. Figure 1 presents the high-level workflow for the semiautomatic segmentation using the so-called US-Cut approach.…”

Section: Algorithmmentioning

confidence: 99%

In-depth assessment of an interactive graph-based approach for the segmentation for pancreatic metastasis in ultrasound acquisitions of the liver with two specialists in Internal Medicine

Egger

Schmalstieg

Bettac

et al. 2017

2017 10th Biomedical Engineering International Conference (BMEiCON)

Self Cite

View full text Add to dashboard Cite

The manual outlining of hepatic metastasis in (US) ultrasound acquisitions from patients suffering from pancreatic cancer is common practice. However, such pure manual measurements are often very time consuming, and the results repeatedly differ between the raters. In this contribution, we study the in-depth assessment of an interactive graph-based approach for the segmentation for pancreatic metastasis in US images of the liver with two specialists in Internal Medicine. Thereby, evaluating the approach with over one hundred different acquisitions of metastases. The two physicians or the algorithm had never assessed the acquisitions before the evaluation. In summary, the physicians first performed a pure manual outlining followed by an algorithmic segmentation over one month later. As a result, the experts satisfied in up to ninety percent of algorithmic segmentation results. Furthermore, the algorithmic segmentation was much faster than manual outlining and achieved a median Dice Similarity Coefficient (DSC) of over eighty percent. Ultimately, the algorithm enables a fast and accurate segmentation of liver metastasis in clinical US images, which can support the manual outlining in daily practice.

show abstract

Refinement-Cut: User-Guided Segmentation Algorithm for Translational Science

Cited by 19 publications

References 43 publications

Cellular automata segmentation of the boundary between the compacta of vertebral bodies and surrounding structures

Cellular automata segmentation of the boundary between the compacta of vertebral bodies and surrounding structures

Interactive Outlining of Pancreatic Cancer Liver Metastases in Ultrasound Images

In-depth assessment of an interactive graph-based approach for the segmentation for pancreatic metastasis in ultrasound acquisitions of the liver with two specialists in Internal Medicine

Contact Info

Product

Resources

About