Dataset Information

Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound.

ABSTRACT: Manual segmentation of hepatic metastases in ultrasound images acquired from patients suffering from pancreatic cancer is common practice. Semiautomatic measurements promising assistance in this process are often assessed using a small number of lesions performed by examiners who already know the algorithm. In this work, we present the application of an algorithm for the segmentation of liver metastases due to pancreatic cancer using a set of 105 different images of metastases. The algorithm and the two examiners had never assessed the images before. The examiners first performed a manual segmentation and, after five weeks, a semiautomatic segmentation using the algorithm. They were satisfied in up to 90% of the cases with the semiautomatic segmentation results. Using the algorithm was significantly faster and resulted in a median Dice similarity score of over 80%. Estimation of the inter-operator variability by using the intra class correlation coefficient was good with 0.8. In conclusion, the algorithm facilitates fast and accurate segmentation of liver metastases, comparable to the current gold standard of manual segmentation.

SUBMITTER: Hann A

PROVIDER: S-EPMC5630585 | biostudies-literature | 2017 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound.

Hann Alexander A Bettac Lucas L Haenle Mark M MM Graeter Tilmann T Berger Andreas W AW Dreyhaupt Jens J Schmalstieg Dieter D Zoller Wolfram G WG Egger Jan J

Scientific reports 20171006 1

Manual segmentation of hepatic metastases in ultrasound images acquired from patients suffering from pancreatic cancer is common practice. Semiautomatic measurements promising assistance in this process are often assessed using a small number of lesions performed by examiners who already know the algorithm. In this work, we present the application of an algorithm for the segmentation of liver metastases due to pancreatic cancer using a set of 105 different images of metastases. The algorithm and ...[more]

PMID: 28986569

Similar Datasets

Project description:Aim:The aim of this study was to compare the diagnostic adequacy of computed tomography (CT)-ultrasound (US) fusion image-guided fine needle aspiration (FNA) and US-guided FNA in patients with suspected hepatic metastases. Methods:Thirty consecutive patients of either sex with known or unknown primary malignancy suspected of having liver metastases on both US and CT, whose multiphasic contrast-enhanced computed tomography was performed using a 64-slice or a higher slice CT scanner, and who were referred for percutaneous FNA were included in this prospective study approved by the institutional review board of the study institute. CT-ultrasound fusion image-guided FNA of the largest lesion using electromagnetic tracking and with freehand ultrasound-guided FNA were performed in the same sitting. Value of fitness, which is a rough estimate of how well the fusion has been achieved, was recorded. Diagnostic adequacy of smears was assessed by a scoring system based on cellular material, background blood/clot, degree of cellular degeneration or trauma, and retention of architecture. Results:The size of the lesions ranged from 1 to 10 cm, and the depth of location of the lesions ranged from 1.4 to 9.3 cm. The fusion fitness values ranged from 1.2 to 10 mm. The scores of the smears did not correlate with lesion size, depth of location, and fusion fitness value. Diagnostic adequacy was seen in 90% and 93.3% of lesions sampled by fusion image guidance and ultrasound guidance, respectively (p = 0.655). All the lesions that yielded inadequate smears by fusion guidance were deep-seated lesions (>5 cm). All the lesions that yielded inadequate smears by ultrasound guidance were small lesions (<3 cm). No complications were encountered in any of the patients. Conclusion:Fusion image-guided FNA is a safe procedure with a high diagnostic adequacy rate. Fusion image-guided FNA is not better than US-guided FNA for conspicuous hepatic lesions; however, it may be useful in inconspicuous lesions.

Dataset Information

Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound.

Publications

Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets