A hybrid approach based on deep learning and level set formulation for liver segmentation in CT images

Abstract

Accurate liver segmentation is essential for radiation therapy planning of hepatocellular carcinoma and absorbed dose calculation. However, liver segmentation is a challenging task due to the anatomical variability in both shape and size and the low contrast between liver and its surrounding organs. Thus we propose a convolutional neural network (CNN) for automated liver segmentation. In our method, fractional differential enhancement is firstly applied for preprocessing. Subsequently, an initial liver segmentation is obtained by using a CNN. Finally, accurate liver segmentation is achieved by the evolution of an active contour model. Experimental results show that the proposed method outperforms existing methods. One hundred fifty CT scans are evaluated for the experiment. For liver segmentation, Dice of 95.8%, true positive rate of 95.1%, positive predictive value of 93.2%, and volume difference of 7% are calculated. In addition, the values of these evaluation measures show that the proposed method is able to provide a precise and robust segmentation estimate, which can also assist the manual liver segmentation task.

Transformer Skip‐Fusion Based SwinUNet for Liver Segmentation From CT Images

“…A method using Mask R-CNN with soft parameter selection was proposed by Dandil et al [37]. Gong et al [38] introduced a fractional differential enhancement-based CNN model. Senthilvelan and Jamshidi [39] introduced and automated workflow for liver segmentation using a cascaded approach (PADLLS).…”

A pair of deep learning auto‐contouring models for prostate cancer patients injected with a radio‐transparent versus radiopaque hydrogel spacer

“…17 Kawula et al trained a model using an in-house algorithm, and demonstrated DSC of 0.87, 0.97, and 0.89 for prostate, bladder, and rectum, respectively. 18 In addition to prostate cancer, CT-based DL auto-segmentation models have also been reported for other disease sites, such as brain, 19,20 head and neck, 21,22 lung, [23][24][25][26] breast, 27 esophagus, 28 liver, [29][30][31] pancreas, 32 bladder, 33 and gynecological cancers. 34,35 While the prior studies have demonstrated the feasibility of constructing DL models to automate the tedious contouring task in prostate treatment planning, the applicability of each model is limited by clinical protocol, particularly the immobilization method which can affect the shape and position of key organs.…”

“…trained a model using an in‐house algorithm, and demonstrated DSC of 0.87, 0.97, and 0.89 for prostate, bladder, and rectum, respectively 18 . In addition to prostate cancer, CT‐based DL auto‐segmentation models have also been reported for other disease sites, such as brain, 19,20 head and neck, 21,22 lung, 23–26 breast, 27 esophagus, 28 liver, 29–31 pancreas, 32 bladder, 33 and gynecological cancers 34,35 …”

Different applications of Artificial Intelligence in liver cancer: a scoping review – part II, from treatment planning and efficacy assessment to prognosis prediction and follow-up. (Preprint)

“…Based on the presence of mutations, the authors defined low and high fibroblasts activation classes and, on this variable, they analyzed HCC sensitivity to chemotherapy. Their results showed that patients with high activation of cancer-associated fibroblasts had increased response to chemotherapy.It is also worth to say that many authors have recently published different DL models to perform segmentation of liver cancer and vacularization with the aim to develop a tool useful for physicians to plan liver cancer treatment(21)(22)(23)(24)(25)(26)(27)(28)(29)(30). However, their results are limited to a comparison of accuracy between the proposed model and manual segmentation or segmentation performed by other models, without any proposed practical applications in clinical setting.…”