Robust extraction for low-contrast liver tumors using modified adaptive likelihood estimation

Multiple objective planning for thermal ablation of liver tumors

PURPOSE

Preoperative treatment planning is key to ensure successful thermal ablation of liver tumors. The planning aims to minimize the number of electrodes required for complete ablation and the damage to the surrounding tissues while satisfying multiple clinical constraints. This is a challenging multiple objective planning problem, in which the trade-off between different objectives must be considered.

METHODS

We propose a novel method to solve the multiple objective planning problem, which combines the set cover-based model and Pareto optimization. The set cover-based model considers multiple clinical constraints and generates several clinically feasible treatment plans, among which the Pareto optimization is performed to find the trade-off between different objectives.

RESULTS

We evaluated the proposed method on 20 tumors of 11 patients in two different situations used in common thermal ablation approaches: with and without the pull-back technique. Pareto optimal plans were found and verified to be clinically acceptable in all cases, which can find the trade-off between the number of electrodes and the damage to the surrounding tissues.

CONCLUSION

The proposed method performs well in the two different situations we considered: with or without the pull-back technique. It can generate Pareto optimal plans satisfying multiple clinical constraints. These plans consider the trade-off between different planning objectives.

Automatic Radiofrequency Ablation Planning for Liver Tumors With Multiple Constraints Based on Set Covering

Radiofrequency ablation (RFA) is now a widely used minimally invasive treatment method for hepatic tumors. Preoperative planning plays a vital role in RFA therapy. With increasing tumor size, multiple overlapping ablations are needed, which are challenging to optimize while considering clinical constraints. In this paper, we present a new automatic RFA planning method. First, a 2-steps set cover-based model is formulated, which can integrate multiple clinical constraints for optimization of overlapping ablations. To ensure that the planning model can be solved in a reasonable time, a search space reducing strategy is then proposed. We also developed an algorithm for automatic RFA electrode selection, which provides a proper electrode ablation zone for the planning model. The proposed method was evaluated with 20 tumors of varying sizes (0.92 cm³ to 28.4 cm³). Results showed that the proposed method can generate clinical feasible RFA plans with a minimum number of RFA electrodes and ablations, complete tumor coverage and minimized ablation of normal tissue.

Dynamic Regulation of Level Set Parameters Using 3D Convolutional Neural Network for Liver Tumor Segmentation

Segmentation of liver tumors plays an important role in the choice of therapeutic strategies for liver disease and treatment monitoring. In this paper, we generalize the process of a level set with a novel algorithm of dynamic regulation to energy functional parameters. The presented method is fully automatic once the tumor has been detected. First, a 3D convolutional neural network with dense layers for classification is used to estimate current contour location relative to the tumor boundary. Second, the output 3D CNN probabilities can dynamically regulate parameters of the level set functional over the process of segmentation. Finally, for full automation, appropriate initializations and local window size are generated based on the current contour position probabilities. We demonstrate the proposed method on the dataset of MICCAI 2017 LiTS Challenge and 3DIRCADb that include low contrast and heterogeneous tumors as well as noisy images. To illustrate the strength of our method, we evaluated it against the state-of-the-art methods. Compared with the level set framework with fixed parameters, our method performed better significantly with an average DICE improvement of 0.15. We also analyzed a challenging dataset 3DIRCADb of tumors and obtained a competitive DICE of 0.85 ± 0.06 with the proposed method.