Evaluation of a novel navigation platform for laparoscopic liver surgery with organ deformation compensation using injected fiducials

Pelanis, Egidijus; Teatini, Andrea; Eigl, Benjamin; Regensburger, Alois; Alzaga, Amilcar; Kumar, Rahul Prasanna; Rudolph, Tobias; Riediger, Carina; Kvarnström, Niclas; Elle, Ole Jakob; Edwin, Bjørn

doi:10.1016/j.media.2020.101946

Cited by 29 publications

(22 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Informed written consent was obtained from all participants included in the study. Manual delineations of the liver parenchyma, i.e., liver segmentation masks, were available as part of the Oslo-CoMet dataset [4]. Additionally, an approximate segmentation of the vascular structures was obtained using the segmentation model available in the public…”

Section: Datasetmentioning

confidence: 99%

“…However, non-rigid registration comes at the expense of higher computational needs and thus hardware constraints might hinder the development and deployment of such algorithms. In medicine, image registration is mandatory for fusing clinically relevant information across images; groundwork for enabling imageguided navigation during laparoscopic interventions [4,5]. Additionally, laparoscopic preoperative surgical planning benefits from abdominal computed tomography (CT) to magnetic resonance imaging (MRI) registration to better identify risk areas in a patient's anatomy [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation

et al. 2023

Self Cite

View full text Add to dashboard Cite

Purpose This study aims to explore training strategies to improve convolutional neural network-based image-to-image deformable registration for abdominal imaging. Methods Different training strategies, loss functions, and transfer learning schemes were considered. Furthermore, an augmentation layer which generates artificial training image pairs on-the-fly was proposed, in addition to a loss layer that enables dynamic loss weighting. Results Guiding registration using segmentations in the training step proved beneficial for deep-learning-based image registration. Finetuning the pretrained model from the brain MRI dataset to the abdominal CT dataset further improved performance on the latter application, removing the need for a large dataset to yield satisfactory performance. Dynamic loss weighting also marginally improved performance, all without impacting inference runtime. Conclusion Using simple concepts, we improved the performance of a commonly used deep image registration architecture, VoxelMorph. In future work, our framework, DDMR, should be validated on different datasets to further assess its value.

show abstract

Section: Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Target registration error and fiducial registration error were evaluated in those reports [49][50][51][52] and ranged from 3.0-14.0 mm. Such an AR overlay navigation system contributed to a reduction in vascular injury and more rapid postoperative recovery.…”

Section: Xrmentioning

confidence: 99%

“…In laparoscopic surgery, combination techniques with intraoperative calibration of the laparoscope and various landmarks to define the liver anatomy such as the falciform ligament, edge of the liver, and gall bladder are commonly used. 49 , 50 , 51 Pelanis et al 52 performed intraoperative cone‐beam computed tomography (CT) and used an optical tracking system in registration. Target registration error and fiducial registration error were evaluated in those reports 49 , 50 , 51 , 52 and ranged from 3.0–14.0 mm.…”

Section: Intraoperative Navigationmentioning

confidence: 99%

“… 49 , 50 , 51 Pelanis et al 52 performed intraoperative cone‐beam computed tomography (CT) and used an optical tracking system in registration. Target registration error and fiducial registration error were evaluated in those reports 49 , 50 , 51 , 52 and ranged from 3.0–14.0 mm. Such an AR overlay navigation system contributed to a reduction in vascular injury and more rapid postoperative recovery.…”

Section: Intraoperative Navigationmentioning

confidence: 99%

See 1 more Smart Citation

Essential updates 2020/2021: Current topics of simulation and navigation in hepatectomy

Saito

Shimada

Morine

et al. 2021

Annals of Gastroent Surgery

View full text Add to dashboard Cite

Advances in perioperative care and surgical techniques have significantly improved the outcomes of liver resection during the last three decades. Liver surgery has inherent challenges, including difficult anticipation of complex and variable intrahepatic anatomy and the need for cognitive analysis by the surgeon to integrate preoperative imaging information into the operative field. Therefore, simulation and navigation techniques have been developed in this field.In preoperative simulation, three-dimensional (3D) simulation technology was developed in Germany in the early 2000s, 1 and immediately thereafter software based on an original algorithm was developed in Japan. The development of intraoperative navigation techniques may also help surgeons to perform liver resections as planned. Intraoperative navigation began with intraoperative ultrasound (US) in 1980 2 and progressed to virtual hepatectomy (Hx), [3][4][5][6][7] real-time virtual sonography, 8-12 and finally indocyanine green (ICG) fluorescence. [13][14][15][16][17][18][19][20] Thus, intraoperative navigation has gradually evolved during the past 40 y. This biannual review discusses the essential updates to simulation and navigation in Hx that occurred in the 2-y period from 2020 to 2021. | PREOPER ATIVE S IMUL ATIONPreoperative 3D simulation has enabled surgeons to obtain a great deal of information, such as detailed anatomical visualization, the

show abstract

Current trends and prospects of surgical techniques for hepatoblastoma

Pu,

Li,

et al. 2024

Cancer Medicine

View full text Add to dashboard Cite

Hepatoblastoma, a common extracranial malignant solid tumor in childhood, is often detected at an advanced stage and is difficult to treat surgically. Despite the availability of multiple comprehensive treatments that can be combined with surgery, hepatoblastoma treatment outcomes remain poor. Surgery is the main treatment strategy for hepatoblastoma, but it faces many challenges, including tumor attachment to surrounding tissues, tumor wrapping or invading of vital organs and tissues, the presence of giant or multiple tumors, distant metastasis, the formation of a tumor thrombus, and significant surgical trauma. In this review, we discuss recent research advances and propose potential strategies for overcoming these challenges. Such strategies may improve the rate of hepatoblastoma resection and local control in children, as well as reduce complications and trauma.

show abstract

Evaluation of a novel navigation platform for laparoscopic liver surgery with organ deformation compensation using injected fiducials

Cited by 29 publications

References 33 publications

Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation

Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation

Essential updates 2020/2021: Current topics of simulation and navigation in hepatectomy

Current trends and prospects of surgical techniques for hepatoblastoma

Contact Info

Product

Resources

About