| Web | https://www.thu.de/franz |
Prototypes for medical navigation often require complex hardware and software setups. Students at THU have developed a Java-based example that can be easily compiled. It is built using Gradle and can be connected to other tools such as MITK-IGT or PLUS via OpenIGTLink. At BVM they demonstrated a use case for stroke research: A catheter in a brain vessel dummy was localized using AI in simulated fluoroscopy images and navigated to a target.
A good prosthetic fit is crucial for comfort and mobility, but measuring the exact anatomical shape of a residual limb is still challenging. A group of THU students investigated 3D reconstruction of residual limbs using freehand ultrasound and a liner with integrated fiducial markers, all without external tracking. Interested? Read the BVM paper or visit poster P13 at this year’s BVM workshop.
https://link.springer.com/chapter/10.1007/978-3-658-51100-5_37
#MedicalResearch #MedTech #Prosthetics #MedicalImaging #Ultrasound
Students at THU are researching a system for 3D reconstruction of residual limbs using ultrasound. We will be presenting our latest publication on this next week at the BVM Workshop 2025.
https://link.springer.com/chapter/10.1007/978-3-658-47422-5_21
When manufacturing leg prostheses, accurate measurement of the geometry of residual limbs is essential. Conventionally, this is done using plaster casts or optical scanners. Ultrasound (US) appears to be a promising complementary method, as it can be used to scan...
We have successfully tested a setup for live AI support in interventional radiology. Interested? Read more about it in our latest open-access publication.
https://www.degruyter.com/document/doi/10.1515/cdbme-2024-2094/html
Artificial intelligence (AI) has the potential to support time-critical stroke treatment. In a previous study we demonstrated the feasibility of deep learning based automatic classification for thrombus detection during thrombectomies, a catheter-guided procedure to remove occlusions of cerebral vessels. However, this method has yet to be tested during a live intervention. In this work, we present a setup to integrate AI based support in an angiography suite. A classification PC was connected to the angiography by means of a real-time video connection as well as a research interface for control signals. We found that video conversion in real-time does not affect the classification result in comparison to offline classification of DICOM data. Analyzing 50 video streams of previous cases, the system could classify digital-subtraction angiography (DSA) sequences within 13.3 seconds on average. This processing time can further be reduced to an average of 7.9 seconds with GPU acceleration. Additionally, the system successfully classified two DSA sequences acquired during live thrombectomy, identifying the presence of thrombi in less than 5 seconds. So far, the classification result has only been displayed in the control room of the angiography suite to demonstrate feasibility. In the outlook, however, we also discuss how the result can be displayed directly on the angiography screen.
AI-based detection of digital subtraction angiography (DSA) sequences that show vascular occlusions was investigated in another study. A demonstrator for classification of these sequences, which was developed at THU, was also presented at the BVM Workshop 2023.
In the event of stroke, a catheter-guided procedure (thrombectomy) is used to remove blood clots. Feasibility of machine learning based automatic classifications for thrombus detection on digital substraction angiography (DSA) sequences has been demonstrated. It was however not used live in the clinic, yet. We present an open-source tool for automatic thrombus classification and test it on three selected clinical cases regarding functionality and classification runtime. With our trained model all large vessel occlusions in the M1 segment were correctly classified. One small remaining M3 thrombus was not detected. Runtime was in the range from 1 to 10 seconds depending on the used hardware. We conclude that our open-source software tool enables clinical staff to classify DSA sequences in (close to) realtime and can be used for further studies in clinics.
In the field of stroke treatment, we are researching the navigation of instruments during thrombectomy. For example, a student project on instrument localization was presented at the BVM Workshop 2023.
https://link.springer.com/chapter/10.1007/978-3-658-41657-7_61
Mechanical thrombectomy as a therapeutic option for ischemic stroke can possibly be supported by localizing the used catheters and guidewires during the intervention. In this study we equipped a probing catheter and a guidewire with electromagnetic (EM) sensors that...
Besides cancer treatment, our work also focuses on the treatment of strokes. In this context, students at THU have developed an open-science vascular phantom so that interventions to treat strokes can be simulated in studies. You can find everything about this project under this link in the Open Science Framework.
Purpose Fusing image information has become increasingly important for optimal diagnosis and treatment of the patient. Despite intensive research towards markerless registration approaches, fiducial marker-based methods remain the default choice for a wide range of applications in clinical practice. However, as especially non-invasive markers cannot be positioned reproducibly in the same pose on the patient, pre-interventional imaging has to be performed immediately before the intervention for fiducial marker-based registrations. Methods We propose a new non-invasive, reattachable fiducial skin marker concept for multi-modal registration approaches including the use of electromagnetic or optical tracking technologies. We furthermore describe a robust, automatic fiducial marker localization algorithm for computed tomography (CT) and magnetic resonance imaging (MRI) images. Localization of the new fiducial marker has been assessed for different marker configurations using both CT and MRI. Furthermore, we applied the marker in an abdominal phantom study. For this, we attached the marker at three poses to the phantom, registered ten segmented targets of the phantom’s CT image to live ultrasound images and determined the target registration error (TRE) for each target and each marker pose. Results Reattachment of the marker was possible with a mean precision of 0.02 mm ± 0.01 mm. Our algorithm successfully localized the marker automatically in all ( $$n=201$$ n = 201 ) evaluated CT/MRI images. Depending on the marker pose, the mean ( $$n=10$$ n = 10 ) TRE of the abdominal phantom study ranged from 1.51 ± 0.75 mm to 4.65 ± 1.22 mm. Conclusions The non-invasive, reattachable skin marker concept allows reproducible positioning of the marker and automatic localization in different imaging modalities. The low TREs indicate the potential applicability of the marker concept for clinical interventions, such as the puncture of abdominal lesions, where current image-based registration approaches still lack robustness and existing marker-based methods are often impractical.
Another research project in the lab involves the fusion of different image modalities, e.g. computed tomography and ultrasound. Benjamin, a THU master's and doctoral graduate, won third place in the DEMA Award in 2020. You can watch a video presenting the project here.
https://www.youtube.com/watch?v=j7CRw1qJ--Q&feature=youtu.be
