A new software tool for planning interventional procedures in liver cancer.

INTRODUCTION: Intra-arterial therapy is an effective way of performing chemotherapy or radiation therapy in patients with primary liver cancer (i.e. hepatocellular carcinoma). Although this minimally invasive approach is now an established treatment option, support tools for pre-operative planning and intra-operative assistance might be helpful. MATERIAL AND METHODS: We developed an approach for semi-automatic segmentation of computed tomography angiography images of the main arterial branches (required for access path to the treatment site), automatic segmentation of the liver, arterial and venous tree, and interactive segmentation of the tumors (required for procedure-specific planning). This approach was then integrated into a liver-specific workflow within EndoSize® solution, a planning software for endovascular procedures. The main branches extraction approach was qualitatively evaluated inside the software, while the automatic segmentation methods were quantitatively assessed. RESULTS: Main branches extraction provides a success rate of 85% (i.e. all arteries correctly extracted) in a dataset of 172 patients. On public databases, a mean DICE of 0.91, 0.47 and 0.92 was obtained for liver, venous and arterial trees segmentation, respectively. CONCLUSIONS: This pipeline is suitable for directly accessing the treatment site, giving anatomic measurements, and visualizing the hepatic trees, liver, and surrounding arteries during the pre-operative planning. ABBREVIATIONS: HCC: hepatocellular carcinoma; TACE: transarterial chemoembolization; SIRT: selective internal radiation therapy; CT: computed tomography; CTA: computed tomography angiography; AMS: superior mesenteric artery; LGA: left gastric artery; RHA: right hepatic artery; LHA: left hepatic artery; rbHA: right branch of the hepatic artery; lbHA: left branch of the hepatic artery; GDA: gastroduodenal artery; VOI: volume of interest; SD: standard deviation; MICCAI: medical image computing and computer assisted interventions; MR: magnetic resonance.

Automatic aortic root segmentation and anatomical landmarks detection for TAVI procedure planning.

PURPOSE: Minimally invasive trans-catheter aortic valve implantation (TAVI) has emerged as a treatment of choice for high-risk patients with severe aortic stenosis. However, the planning of TAVI procedures would greatly benefit from automation to speed up, secure and guide the deployment of the prosthetic valve. We propose a hybrid approach allowing the computation of relevant anatomical measurements along with an enhanced visualization. MATERIAL AND METHODS: After an initial step of centerline detection and aorta segmentation, model-based and statistical-based methods are used in combination with 3 D active contour models to exploit the complementary aspects of these methods and automatically detect aortic leaflets and coronary ostia locations. Important anatomical measurements are then derived from these landmarks. RESULTS: A validation on 50 patients showed good precision with respect to expert sizing for the ascending aorta diameter calculation (2.2 ± 2.1 mm), the annulus diameter (1.31 ± 0.75 mm), and both the right and left coronary ostia detection (1.96 ± 0.87 mm and 1.80 ± 0.74 mm, respectively). The visualization is enhanced thanks to the aorta and aortic root segmentation, the latter showing good agreement with manual expert delineation (Jaccard index: 0.96 ± 0.03). CONCLUSION: This pipeline is promising and could greatly facilitate TAVI planning.

Evaluation of 2D and 3D ultrasound tracking algorithms and impact on ultrasound-guided liver radiotherapy margins.

PURPOSE: Compensation for respiratory motion is important during abdominal cancer treatments. In this work we report the results of the 2015 MICCAI Challenge on Liver Ultrasound Tracking and extend the 2D results to relate them to clinical relevance in form of reducing treatment margins and hence sparing healthy tissues, while maintaining full duty cycle. METHODS: We describe methodologies for estimating and temporally predicting respiratory liver motion from continuous ultrasound imaging, used during ultrasound-guided radiation therapy. Furthermore, we investigated the trade-off between tracking accuracy and runtime in combination with temporal prediction strategies and their impact on treatment margins. RESULTS: Based on 2D ultrasound sequences from 39 volunteers, a mean tracking accuracy of 0.9 mm was achieved when combining the results from the 4 challenge submissions (1.2 to 3.3 mm). The two submissions for the 3D sequences from 14 volunteers provided mean accuracies of 1.7 and 1.8 mm. In combination with temporal prediction, using the faster (41 vs 228 ms) but less accurate (1.4 vs 0.9 mm) tracking method resulted in substantially reduced treatment margins (70% vs 39%) in contrast to mid-ventilation margins, as it avoided non-linear temporal prediction by keeping the treatment system latency low (150 vs 400 ms). Acceleration of the best tracking method would improve the margin reduction to 75%. CONCLUSIONS: Liver motion estimation and prediction during free-breathing from 2D ultrasound images can substantially reduce the in-plane motion uncertainty and hence treatment margins. Employing an accurate tracking method while avoiding non-linear temporal prediction would be favorable. This approach has the potential to shorten treatment time compared to breath-hold and gated approaches, and increase treatment efficiency and safety.

Real-time target tracking of soft tissues in 3D ultrasound images based on robust visual information and mechanical simulation.

In this paper, we present a real-time approach that allows tracking deformable structures in 3D ultrasound sequences. Our method consists in obtaining the target displacements by combining robust dense motion estimation and mechanical model simulation. We perform evaluation of our method through simulated data, phantom data, and real-data. Results demonstrate that this novel approach has the advantage of providing correct motion estimation regarding different ultrasound shortcomings including speckle noise, large shadows and ultrasound gain variation. Furthermore, we show the good performance of our method with respect to state-of-the-art techniques by testing on the 3D databases provided by MICCAI CLUST'14 and CLUST'15 challenges.