Leberchirurgie 4.0 - OP-Planung, Volumetrie, Navigation und Virtuelle
                    Realität

Huber, Tobias; Huettl, Florentine; Hanke, Laura Isabel; Vradelis, Lukas; Heinrich, Stefan; Hansen, Christian; Boedecker, Christian; Lang, Hauke

doi:10.1055/a-1844-0549

Cited by 4 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xiao et al [2] have proposed a lung nodule segmentation method based on computed tomography (CT) images for the early diagnosis of lung cancer where the recall rate of lung nodule detection reaches 99.1%. Alirr et al [3,4] have reported the application of 3D medical image segmentation to liver surgery, where the segmentation of liver, tumours and blood vessels have been done to determine the spatial relationship of the liver and calculate the required resection planning parameters. However, because of the variations in texture and shape of tumours among different individuals, the possible occurrence of the multiple tumours and their blurry boundaries, the efficient and accurate tumour segmentation is a highly challenging task.…”

Section: Introductionmentioning

confidence: 99%

Short‐term and long‐term memory self‐attention network for segmentation of tumours in 3D medical images

Wen

Zhou

Tao

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Tumour segmentation in medical images (especially 3D tumour segmentation) is highly challenging due to the possible similarity between tumours and adjacent tissues, occurrence of multiple tumours and variable tumour shapes and sizes. The popular deep learning‐based segmentation algorithms generally rely on the convolutional neural network (CNN) and Transformer. The former cannot extract the global image features effectively while the latter lacks the inductive bias and involves the complicated computation for 3D volume data. The existing hybrid CNN‐Transformer network can only provide the limited performance improvement or even poorer segmentation performance than the pure CNN. To address these issues, a short‐term and long‐term memory self‐attention network is proposed. Firstly, a distinctive self‐attention block uses the Transformer to explore the correlation among the region features at different levels extracted by the CNN. Then, the memory structure filters and combines the above information to exclude the similar regions and detect the multiple tumours. Finally, the multi‐layer reconstruction blocks will predict the tumour boundaries. Experimental results demonstrate that our method outperforms other methods in terms of subjective visual and quantitative evaluation. Compared with the most competitive method, the proposed method provides Dice (82.4% vs. 76.6%) and Hausdorff distance 95% (HD95) (10.66 vs. 11.54 mm) on the KiTS19 as well as Dice (80.2% vs. 78.4%) and HD95 (9.632 vs. 12.17 mm) on the LiTS.

show abstract

Section: Introductionmentioning

confidence: 99%

Short‐term and long‐term memory self‐attention network for segmentation of tumours in 3D medical images

Wen

Zhou

Tao

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

show abstract

“…In recent years, virtual reality (VR) head–mounted displays (HMD) have been introduced in various fields of medicine, such as the planning of liver surgery. 8 VR-HMDs have the advantage of allowing the participant to be completely immersed in the simulated situation and are ideal as point-of-care diagnostics due to their small size. In this study, we therefore aimed to develop an easily applicable point-of-care driving test with a focus on the reaction time to hazardous events based on VR, test its feasibility in patients with cirrhosis, and compare results between patients with cirrhosis and noncirrhotic controls.…”

Section: Introductionmentioning

confidence: 99%

Development and evaluation of a virtual reality driving test for patients with cirrhosis

Gairing,

Schleicher,

Kaps

et al. 2023

Hepatology Communications

View full text Add to dashboard Cite

Background: Patients with cirrhosis and especially those with HE may have impaired driving skills and may be prone to car accidents. This proof-of-concept study aimed to develop and evaluate the applicability of a virtual reality (VR)–based driving test in patients with cirrhosis. Additionally, the association between the results in the VR test and car accidents was investigated. Methods: A short driving test using a VR head–mounted display (HTC Vive Pro Eye) was developed to simulate five hazardous situations. The patient has to pull the brake when the hazardous situations occur. The time from triggering the event to pressing the brake is recorded as reaction time. Total reaction time (TRT) is defined as the combined reaction time to all 5 events. Car accidents were assessed retrospectively (previous 12 months) and patients were followed prospectively for 6 months. Minimal HE (MHE) was diagnosed using Psychometric Hepatic Encephalopathy Score. Results: In total, 112 outpatients with cirrhosis and 52 controls without cirrhosis were recruited. MHE was detected in 14% (n = 15). Patients with cirrhosis and MHE (5.67 s) had higher TRTs compared to patients without MHE (5.02 s) and controls without cirrhosis above the age of 50 (4.98 s) (MHE vs. no MHE or controls p<0.01, no MHE vs. controls: not significant). Seven patients reported car accidents during the twelve months prior to study inclusion. TRTs were numerically higher in patients with reported car accidents (p = 0.099). When patients who stopped driving for HE-related/cirrhosis-related reasons (n = 14) were added to the group of patients with accidents, then a longer TRT was significantly associated with the modeled outcome in univariable (p<0.01) and multivariable analyses (OR 2.83, p<0.01). Two car accidents occurred during follow-up. Both patients had TRTs above the 90th percentile. Conclusions: The VR driving test is easy and rapid to perform in patients with cirrhosis and could be helpful as a point-of-care tool for predicting car accidents.

show abstract