Interactive Outlining of Pancreatic Cancer Liver Metastases in Ultrasound Images

Jan Egger, Dieter Schmalstieg, Xiaojun Chen, Wolfram G Zoller, Alexander Hann

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

Abstract

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.

Originalspracheenglisch
Seiten (von - bis)892
FachzeitschriftScientific reports
Jahrgang7
Ausgabenummer1
DOIs
PublikationsstatusVeröffentlicht - 18 Apr 2017

Fingerprint

Liver Neoplasms
Pancreatic Neoplasms
Neoplasm Metastasis
Liver
Costs and Cost Analysis
Neoplasms

Schlagwörter

    Dies zitieren

    Interactive Outlining of Pancreatic Cancer Liver Metastases in Ultrasound Images. / Egger, Jan; Schmalstieg, Dieter; Chen, Xiaojun; Zoller, Wolfram G; Hann, Alexander.

    in: Scientific reports, Jahrgang 7, Nr. 1, 18.04.2017, S. 892.

    Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

    Egger, Jan ; Schmalstieg, Dieter ; Chen, Xiaojun ; Zoller, Wolfram G ; Hann, Alexander. / Interactive Outlining of Pancreatic Cancer Liver Metastases in Ultrasound Images. in: Scientific reports. 2017 ; Jahrgang 7, Nr. 1. S. 892.
    @article{86ec85d6c5664263a1556362d0383891,
    title = "Interactive Outlining of Pancreatic Cancer Liver Metastases in Ultrasound Images",
    abstract = "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.",
    keywords = "Journal Article",
    author = "Jan Egger and Dieter Schmalstieg and Xiaojun Chen and Zoller, {Wolfram G} and Alexander Hann",
    year = "2017",
    month = "4",
    day = "18",
    doi = "10.1038/s41598-017-00940-z",
    language = "English",
    volume = "7",
    pages = "892",
    journal = "Scientific reports",
    issn = "2045-2322",
    publisher = "Nature Publishing Group",
    number = "1",

    }

    TY - JOUR

    T1 - Interactive Outlining of Pancreatic Cancer Liver Metastases in Ultrasound Images

    AU - Egger, Jan

    AU - Schmalstieg, Dieter

    AU - Chen, Xiaojun

    AU - Zoller, Wolfram G

    AU - Hann, Alexander

    PY - 2017/4/18

    Y1 - 2017/4/18

    N2 - 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.

    AB - 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.

    KW - Journal Article

    U2 - 10.1038/s41598-017-00940-z

    DO - 10.1038/s41598-017-00940-z

    M3 - Article

    VL - 7

    SP - 892

    JO - Scientific reports

    JF - Scientific reports

    SN - 2045-2322

    IS - 1

    ER -