Primary objective: - To develop an automatic segmentation algorithm using artificial intelligence for real-time intra-operative vessel segmentationSecondary objectives: - Post-operative evaluating the accuracy of different…
ID
Source
Brief title
Condition
- Miscellaneous and site unspecified neoplasms malignant and unspecified
Synonym
Research involving
Sponsors and support
Intervention
- Medical device
N.a.
Outcome measures
Primary outcome
<p>The number and quality of ultrasound sweeps for automatic segmentation of the<br />
vessels.</p>
Secondary outcome
<p>Localization of clinical targets with an electromagnetically tracked pointer to<br />
compute a target registration error.</p>
Background summary
Image-guided navigation surgery allows for full utilization of pre-operative
imaging during surgery and has the potential of reducing both irradical
resections and morbidity. To use navigation, a registration procedure is
required to correlate pre-operative imaging with the patient's position on the
operating room (OR). Currently, registration is done by Cone-Beam CT (CBCT)
scanning on the OR prior to navigation surgery. However, the main limitation of
the CBCT method is that it cannot compensate for per-operative changes such as
bed rotation, retractor placement and tissue displacement due to the surgery.
Alternatively, by using intra-operative tracked ultrasound and vessel-based
patient registration, changing conditions during surgery can better be dealt
with. This improved patient registration method could lead to an increased
navigation accuracy and improved clinical usability and outcomes.
The main difference between CBCT and proposed ultrasound registration is that
CBCT is based on bones, while the ultrasound is based on vessels. Bones can be
very easily imaged on the CBCT and therefore used for bone-bone registration
with pre-operative CT-scans. However, vessels are more difficult to acquire,
especially with ultrasound, and an automatic registration process with
pre-operative imaging is needed for efficient clinical usability. For this, the
vessels need to be extracted from the tracked ultrasound images to create a 3D
representation that can be registered. Therefore, an algorithm needs to be
developed that can automatically segment the vessels from ultrasound
images.
Study objective
Primary objective:
- To develop an automatic segmentation algorithm using artificial intelligence
for real-time intra-operative vessel segmentation
Secondary objectives:
- Post-operative evaluating the accuracy of different registration methods,
such as 3D model or centerline registration
- The usability of the tracked ultrasound setup (SUS-score)
Study design
A single center observational feasibility study.
Intervention
This is a feasibility study, without any impacts on the surgical procedure itself. The total study-related delay of the surgical procedure will be approximately 10 minutes. Participation in the study will not involve additional visits to the hospital or additional radiation dose for the included patients. Informed consent will be obtained during the pre-operative outpatient clinic appointment or upon admission to the hospital at least one day before operation.
Surgery starts according to the standard procedure, which includes incision and preparation of the internal tissue required for the surgery. For this study, optimal ultrasound image acquisition of the vessels (without compressing the tissue with the ultrasound probe) is required. For laparotomy, the abdominal cavity will partly be filled with standard warm saline. Subsequently, intra-abdominal ultrasound is acquired using the BK ultrasound system linked to the NDI Aurora electromagnetic tracking system. For robotic assisted lymph node dissections, intra-operative ultrasound could be acquired percutaneously and/or intra-abdominal using a drop-in ultrasound transducer. If accessible, the abdominal aorta, left and right iliac arteries and both internal and external iliac arteries will be imaged as well as the pubic bone, sacrum and iliac crests; or other relevant arteries and bones close to the target area. For offline validation of the registration accuracy, a sterile electromagnetic pointer is used to pinpoint several anatomical landmarks, such as the aortic bifurcation or lymph nodes. All ultrasound and tracking data will be recorded during the measurements and post-operatively analyzed and used to train an automatic vessel segmentation algorithm.
Study burden and risks
No additional burden or risks are expected apart from to the extended surgery
time, approximately 10 minutes, for the included patients. Ultrasound imaging
takes place in the same way that conventional intra-operative ultrasound is
acquired (for example during liver surgeries), using the same standardized
sterile cover or sterilized ultrasound transducer. The electromagnetic tracking
system (NDI Aurora) including the tracked pointer is the same system as applied
during conventional abdominal navigated surgeries at the NKI-AvL and multiple
navigation studies.
M.A.J. Hiep
Plesmanlaan 121
Amsterdam 1066CX
Netherlands
020-5121751
ma.hiep@nki.nl
M.A.J. Hiep
Plesmanlaan 121
Amsterdam 1066CX
Netherlands
020-5121751
ma.hiep@nki.nl
Trial sites in the Netherlands
Listed location countries
Age
Inclusion criteria
- >= 18 years old
- Scheduled for laparotomy (first 30 patients) or robotic assisted lymph node dissection (second 20 patients)
- A pre-operative CT scan is available
- Patient provides written informed consent
Exclusion criteria
- Metal implants which could influence the 3D modelling or tracking accuracy
- Patients with a pacemaker or defibrillator
- Patient received treatment, e.g. surgery or radiotherapy, between the pre-operative CT scan and surgery, which might altered the patient's anatomy
Design
Recruitment
Medical products/devices used
IPD sharing statement
Plan description
Followed up by the following (possibly more current) registration
No registrations found.
Other (possibly less up-to-date) registrations in this register
No registrations found.
In other registers
Register | ID |
---|---|
ClinicalTrials.gov | NCT05637346 |
CCMO | NL78660.031.21 |
Research portal | NL-007499 |