Abstract
PurposeWe investigated the parameter configuration in the automatic liver and tumor segmentation using a convolutional neural network based on 2.5D model. The implementation of 2.5D model shows promising results since it allows the network to have a deeper and wider network architecture while still accommodates the 3D information. However, there has been no detailed investigation of the parameter configurations on this type of network model.MethodsSome parameters, such as the number of stacked layers, image contrast, and the number of network layers, were studied and implemented on neural networks based on 2.5D model. Networks are trained and tested by utilizing the dataset from liver and tumor segmentation challenge (LiTS). The network performance was further evaluated by comparing the network segmentation with manual segmentation from nine technical physicians and an experienced radiologist.ResultsSlice arrangement testing shows that multiple stacked layers have better performance than a single-layer network. However, the dice scores start decreasing when the number of stacked layers is more than three layers. Adding higher number of layers would cause overfitting on the training set. In contrast enhancement test, implementing contrast enhancement method did not show a statistically significant different to the network performance. While in the network layer test, adding more layers to the network architecture does not always correspond to the increasing dice score result of the network.ConclusionsThis paper compares the performance of the network based on 2.5D model using different parameter configurations. The result obtained shows the effect of each parameter and allow the selection of the best configuration in order to improve the network performance in the application of automatic liver and tumor segmentation.
Highlights
Liver cancer is among the leading causes of cancer death globally (2015:810.000) with increasing diagnosed cases (2015:854.000) [1]
The dataset in this study was obtained from liver and tumor segmentation (LiTS) challenge that is organized in conjunction with Medical Image Computing and Computer Assisted Intervention (MICCAI) 2017 and IEEE International Symposium on Biomedical Imaging (ISBI) 2017
In the image normalization step, increasing the contrast in the computed tomography (CT) image has been implemented by windowing and normalizing the image on a specific intensity range, which we address this technique as basic contrast enhancement
Summary
Liver cancer is among the leading causes of cancer death globally (2015:810.000) with increasing diagnosed cases (2015:854.000) [1]. Prevention and treatment of liver disease are urgent since an early action can significantly reduce the progression of the disease. Clinicians utilize medical imaging to provide an early diagnosis by providing a clear picture of the possible lesion inside the patient body. Information such as size, shape, and the exact location of the lesions are obtained by segmentation. One of the segmentation strategies, manual segmentation, is still used regularly by the radiologists. Even though this method can provide precise liver shape and volume, the method requires long processing time, laborious, and subjective, which make it dependent on the clinician’s performance
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Computer Assisted Radiology and Surgery
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
