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.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...

Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound

“…The segmentation method applied in this evaluation study belongs to the class of graph-based algorithms 27 and the section follows the explanations in ref. 24 . Graph-based algorithms convert an image or parts of it into a graph G ( V , E ) that consists of nodes n ∈ V and edges e ∈ E .…”

“…The algorithm was applied as described before 24 . First, a seed point was applied in the middle of the liver lesion, which could additionally be improved by dragging the seed point around (inside the lesion).…”

“…The segmentation method applied in this evaluation study belongs to the class of graph-based algorithms 27 and the section follows the explanations in ref. 24 . Graph-based algorithms convert an image or parts of it into a graph G(V, E) that consists of nodes n ∈ V and edges e ∈ E. The nodes n ∈ V are sampled in the image joined by two virtual nodes s ∈ V and t ∈ V, which are called the source and the sink, respectively.…”

“…The fundamental method has already been successfully applied to the segmentation of pituitary adenomas 20 , prostate central glands (PCG) 21 , vertebral bodies 22 , aneurysms and stenosis 22 , and even liver ablation zones 23 . A detailed description of translating the basic method for the application of US images has been previously reported by the authors 24 . In this study however, we aim to evaluate the method by users that never worked with the algorithm before and on a much larger set of data.…”

Ultrasound liver tumor segmentation using adaptively regularized kernel-based fuzzy C means with enhanced level set algorithm

“…In ultrasound imaging, the texture between abnormal and normal regions is intermixed, too complex, and also it is difficult to correct the interpretation of lesion regions in the images (Egger et al , 2016). In addition, liver tumors have higher variability in location, poor contrast and deformable shape with respect to the surrounding tissues (Egger et al , 2017a, b). For clinical diagnosis, the prevention and treatment of liver disease are a major focus of present research works.…”