Liver tumor segmentation using G-Unet and the impact of preprocessing and postprocessing methods

• Published in: Multimedia tools and applications Vol. 83; no. 34; pp. 81383 - 81411
• Main Authors: D J, Deepak, B S, Sunil Kumar
• Format: Journal Article
• Language: English
• Published: New York Springer US 07.03.2024; Springer Nature B.V
• Subjects: Accuracy; Artificial neural networks; Computer Communication Networks; Computer Science; Conditional random fields; Data Structures and Information Theory; Lesions; Liver; Medical research; Multimedia Information Systems; Neural networks; Preprocessing; Segmentation; Special Purpose and Application-Based Systems; State-of-the-art reviews; Track 2: Medical Applications of Multimedia; Tumors; DenseNet; Liver tumor segmentation; Computed tomography images; U-Net; ResNet
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-024-18759-y

Accurate liver and lesion segmentation plays a crucial role in the clinical assessment and therapeutic planning of hepatic diseases. The segmentation of the liver and lesions using automated techniques is a crucial undertaking that holds the potential to facilitate the early detection of malignancies and the effective management of patients’ treatment requirements by medical professionals. This research presents the Generalized U-Net (G-Unet), a unique hybrid model designed for segmentation tasks. The G-Unet model is capable of incorporating other models such as convolutional neural networks (CNN), residual networks (ResNets), and densely connected convolutional neural networks (DenseNet) into the general U-Net framework. The G-Unet model, which consists of three distinct configurations, was assessed using the LiTS dataset. The results indicate that G-Unet demonstrated a high level of accuracy in segmenting the data. Specifically, the G-Unet model, configured with DenseNet architecture, produced a liver tumor segmentation accuracy of 72.9% dice global score. This performance is comparable to the existing state-of-the-art methodologies. The study also showcases the influence of different preprocessing and postprocessing techniques on the accuracy of segmentation. The utilization of Hounsfield Unit (HU) windowing and histogram equalization as preprocessing approaches, together with the implementation of conditional random fields as postprocessing techniques, resulted in a notable enhancement of 3.35% in the accuracy of tumor segmentation.