ABSTRACT
PURPOSE: Most recently transformer models became the state of the art in various medical image segmentation tasks and challenges, outperforming most of the conventional deep learning approaches. Picking up on that trend, this study aims at applying various transformer models to the highly challenging task of colorectal cancer (CRC) segmentation in CT imaging and assessing how they hold up to the current state-of-the-art convolutional neural network (CNN), the nnUnet. Furthermore, we wanted to investigate the impact of the network size on the resulting accuracies, since transformer models tend to be significantly larger than conventional network architectures. METHODS: For this purpose, six different transformer models, with specific architectural advancements and network sizes were implemented alongside the aforementioned nnUnet and were applied to the CRC segmentation task of the medical segmentation decathlon. RESULTS: The best results were achieved with the Swin-UNETR, D-Former, and VT-Unet, each transformer models, with a Dice similarity coefficient (DSC) of 0.60, 0.59 and 0.59, respectively. Therefore, the current state-of-the-art CNN, the nnUnet could be outperformed by transformer architectures regarding this task. Furthermore, a comparison with the inter-observer variability (IOV) of approx. 0.64 DSC indicates almost expert-level accuracy. The comparatively low IOV emphasizes the complexity and challenge of CRC segmentation, as well as indicating limitations regarding the achievable segmentation accuracy. CONCLUSION: As a result of this study, transformer models underline their current upward trend in producing state-of-the-art results also for the challenging task of CRC segmentation. However, with ever smaller advances in total accuracies, as demonstrated in this study by the on par performances of multiple network variants, other advantages like efficiency, low computation demands, or ease of adaption to new tasks become more and more relevant.
ABSTRACT
The surgical management of anterior communicating artery aneurysms (AcomA) is challenging due to their deep midline position and proximity to complex skull base anatomy. This study compares the pterional craniotomy with the interhemispheric approach based on the specific aneurysm angulation. A total of 129 AcomA cases were analyzed, with 50 undergoing microsurgical clipping via either the pterional or interhemispheric approach. All selected cases had computed tomography-angiography with sagittal imaging slices and 2D-angiography. Using an interactive tool, 14 cases treated via the interhemispheric approach were matched with 14 cases approached pterionally based on clinical and morphological parameters, emphasizing intracranial aneurysm (IA) dome angulation relative to the frontal skull base. Outcomes included IA occlusion, temporary clipping incidence, intraoperative rupture, postoperative strokes, hemorrhages, hydrocephalus, vasospasm, and patient functionality. Matched cohorts had consistent demographics. Both approaches resulted in similar IA occlusion rates, but the interhemispheric approach led to improved clinical outcomes, measured by the modified Rankin Scale. It also had a lower incidence of hydrocephalus and reduced need for permanent ventriculoperitoneal shunt placement. Vasospasms and postoperative infarction rates were comparable between the groups. Our findings suggest potential advantages of the interhemispheric approach in managing AcomA, depending on aneurysm angulation. Despite a small sample size, the results highlight the importance of customized surgical decision-making based on the unique traits of each aneurysm and the surgeon's expertise.
Subject(s)
Intracranial Aneurysm , Microsurgery , Neurosurgical Procedures , Humans , Intracranial Aneurysm/surgery , Male , Female , Middle Aged , Microsurgery/methods , Aged , Neurosurgical Procedures/methods , Adult , Craniotomy/methods , Treatment Outcome , Cerebral Angiography , Computed Tomography AngiographyABSTRACT
BACKGROUND AND OBJECTIVES: Traditional neurosurgical education has relied heavily on the Halstedian "see one, do one, teach one" approach which is increasingly perceived as inefficient in contemporary settings marked by a steady decline in surgical caseload. In recent years, simulation training has emerged as an effective and accessible training alternative. To date, however, there is no standardized criterion pertaining to the quality and implementation of simulators in neurosurgical education and training. This research aims to compare the efficacy of virtual reality (VR) and Phantom-based simulation training in the context of neurosurgical skill acquisition, with a focus on middle cerebral artery aneurysm clipping. METHODS: An immersive VR clipping tool and a haptic clipping simulator incorporating 3-dimensional printing, additive manufacturing, and rheological analyses were developed. Twenty-two participants, comprising 12 medical students, 6 neurosurgical residents, and 4 experienced neurosurgeons, tested and evaluated both simulators for face and content validity. Construct and predictive validity of the simulators were assessed using an objective structured assessment scale for aneurysm clipping, measuring participants' performances and progress. RESULTS: Both modalities were deemed highly advantageous for educational purposes. Objective evaluations, however, revealed measurable differences in usability, efficacy, and transferability of the learned skills with VR excelling in procedural planning and visualization while Phantom simulation being noticeably superior in conveying surgical skills. CONCLUSION: Simulation training can accelerate the neurosurgical learning curve. The results of this study highlight the importance of establishing standardized criteria for the implementation and assessment of simulation modalities, ensuring consistent quality and efficacy in neurosurgical education.
ABSTRACT
PURPOSE: The contour neurovascular system (CNS) is a novel device to treat intracranial wide-necked bifurcation aneurysms, with few studies assessing its long-term effects. Particularly its impact on aneurysm morphology has not been explored yet. We present a preliminary study to explore this impact for the first time, focusing on the neck curve and ostium of the aneurysm. METHODS: We investigated seven aneurysms treated with the CNS to assess ostium deformation after CNS deployment by comparing models extracted from in vivo medical pre-treatment and follow-up scans via morphological analysis. Time between pre- and follow-up scans was ten months on average. Size and shape indices like area, neck diameter, ellipticity index, undulation index, and more were assessed. RESULTS: Ostium size was reduced after treatment. On average, ostium area was reduced at a rate of - 0.58 (± 4.88) mm2 per year, from 15.52 (± 3.51) mm2 to 13.30 (± 2.27) mm2, and ostium width from 5.01 (± 0.54) mm to 4.49 (± 0.45) mm, with an average reduction of - 0.59 (± 0.87) mm. This shrinking positively correlated with time passing. Shape deformation was low, though notably mean ellipticity index was reduced by 0.06 (± 0.15) on average, indicating ostia were less elongated after treatment. CONCLUSION: We interpret the shrinking of the ostium as part of the healing process. Shape changes were found to be small enough to conclude no shape deformation of the ostium from CNS deployment, but the analysis of more cases with more parameters and information is necessary.
ABSTRACT
There is a lack of systematic research exploring cross-species variation in liver lobular geometry and zonation patterns of critical drug-metabolizing enzymes, a knowledge gap essential for translational studies. This study investigated the critical interplay between lobular geometry and key cytochrome P450 (CYP) zonation in four species: mouse, rat, pig, and human. We developed an automated pipeline based on whole slide images (WSI) of hematoxylin-eosin-stained liver sections and immunohistochemistry. This pipeline allows accurate quantification of both lobular geometry and zonation patterns of essential CYP proteins. Our analysis of CYP zonal expression shows that all CYP enzymes (besides CYP2D6 with panlobular expression) were observed in the pericentral region in all species, but with distinct differences. Comparison of normalized gradient intensity shows a high similarity between mice and humans, followed by rats. Specifically, CYP1A2 was expressed throughout the pericentral region in mice and humans, whereas it was restricted to a narrow pericentral rim in rats and showed a panlobular pattern in pigs. Similarly, CYP3A4 is present in the pericentral region, but its extent varies considerably in rats and appears panlobular in pigs. CYP2D6 zonal expression consistently shows a panlobular pattern in all species, although the intensity varies. CYP2E1 zonal expression covered the entire pericentral region with extension into the midzone in all four species, suggesting its potential for further cross-species analysis. Analysis of lobular geometry revealed an increase in lobular size with increasing species size, whereas lobular compactness was similar. Based on our results, zonated CYP expression in mice is most similar to humans. Therefore, mice appear to be the most appropriate species for drug metabolism studies unless larger species are required for other purposes, e.g., surgical reasons. CYP selection should be based on species, with CYP2E1 and CYP2D6 being the most preferable to compare four species. CYP1A2 could be considered as an additional CYP for rodent versus human comparisons, and CYP3A4 for mouse/human comparisons. In conclusion, our image analysis pipeline together with suggestions for species and CYP selection can serve to improve future cross-species and translational drug metabolism studies.
ABSTRACT
OBJECTIVE: Signal enhancement of vascular walls on vessel wall MRI might be a biomarker for inflammation. It has been theorized that contrast enhancement on vessel wall imaging (VWI) in draining veins of intracranial arteriovenous malformations (AVMs) may be associated with disease progression and development of venous stenosis. The aim of this study was to investigate the relationship between vessel wall enhancement and hemodynamic stressors along AVM draining veins. METHODS: Eight AVM patients with 15 draining veins visualized on VWI were included. Based on MR venography data, patient-specific 3D surface models of the venous anatomy distal to the nidus were segmented. The enhanced vascular wall regions were manually extracted and mapped onto the venous surface models after registration of image data. Using image-based blood flow simulations applying patient-specific boundary conditions based on phase-contrast quantitative MR angiography, hemodynamics were investigated in the enhanced vasculature. For the shear-related parameters, time-averaged wall shear stress (TAWSS), oscillatory shear index (OSI), and relative residence time (RRT) were calculated. Velocity, oscillatory velocity index (OVI), and vorticity were extracted for the intraluminal flow-related hemodynamics. RESULTS: Visual observations demonstrated overlap of enhancement with local lower shear stresses resulting from decreased velocities. Thus, higher RRT values were measured in the enhanced areas. Furthermore, nonenhancing draining veins showed on average slightly higher flow velocities and TAWSS. Significant decreases of 55% (p = 0.03) for TAWSS and of 24% (p = 0.03) for vorticity were identified in enhanced areas compared with near distal and proximal domains. Velocity magnitude in the enhanced region showed a nonsignificant decrease of 14% (p = 0.06). Furthermore, increases were present in the OSI (32%, p = 0.3), RRT (25%, p = 0.15), and OVI (26%, p = 0.3) in enhanced vessel sections, although the differences were not significant. CONCLUSIONS: This novel multimodal investigation of hemodynamics in AVM draining veins allows for precise prediction of occurring shear- and flow-related phenomena in enhanced vessel walls. These findings may suggest low shear to be a local predisposing factor for venous stenosis in AVMs.
Subject(s)
Cerebral Veins , Hemodynamics , Intracranial Arteriovenous Malformations , Magnetic Resonance Angiography , Humans , Intracranial Arteriovenous Malformations/diagnostic imaging , Intracranial Arteriovenous Malformations/physiopathology , Hemodynamics/physiology , Male , Female , Adult , Middle Aged , Cerebral Veins/diagnostic imaging , Cerebral Veins/physiopathology , Inflammation/diagnostic imaging , Young AdultABSTRACT
Traditional navigational bronchoscopy procedures rely on preprocedural computed tomography (CT) and intraoperative chest radiography and cone-beam CT (CBCT) to biopsy peripheral lung lesions. This navigational approach is challenging due to the projective nature of radiography, and the high radiation dose, long imaging time, and large footprints of CBCT. Digital tomosynthesis (DTS) is considered an attractive alternative combining the advantages of radiography and CBCT. Only the depth resolution cannot match a full CBCT image due to the limited angle acquisition. To address this issue, preoperative CT is a good auxiliary in guiding bronchoscopy interventions. Nevertheless, CT-to-body divergence caused by anatomic changes and respiratory motion, hinders the effective use of CT imaging. To mitigate CT-to-body divergence, we propose a novel deformable 3D/3D CT-to-DTS registration algorithm employing a multistage, multiresolution approach and using affine and elastic B-spline transformation models with bone and lung mask images. A multiresolution strategy with a Gaussian image pyramid and a multigrid strategy within the B-spline model are applied. The normalized correlation coefficient is included in the cost function for the affine model and a multimetric weighted cost function is used for the B-spline model, with weights determined heuristically. Tested on simulated and real patient bronchoscopy data, the algorithm yields promising results. Assessed qualitatively by visual inspection and quantitatively by computing the Dice coefficient (DC) and the average symmetric surface distance (ASSD), the algorithm achieves mean DC of 0.82±0.05 and 0.74±0.05, and mean ASSD of 0.65±0.29mm and 0.93±0.43mm for simulated and real data, respectively. This algorithm lays the groundwork for CT-aided intraoperative DTS imaging in image-guided bronchoscopy interventions with future studies focusing on automated metric weight setting.
Subject(s)
Bronchoscopy , Radiographic Image Enhancement , Humans , Radiographic Image Enhancement/methods , Tomography, X-Ray Computed/methods , Cone-Beam Computed Tomography/methods , AlgorithmsABSTRACT
Intracranial aneurysms (IAs) located in the anterior and posterior circulations of the Circle of Willis present differential rupture risks. This study aimed to compare the rupture risk and clinical outcomes of anterior communicating artery aneurysms (AcomA) and basilar tip aneurysms (BAs); two IA types located along the midline within the Circle of Willis. We retrospectively collected data from 1026 patients presenting with saccular IAs. Only AcomA and BAs with a 3D angiography were included. Out of 186 included IAs, a cohort of 32 BAs was matched with AcomA based on the patients' pre-existing conditions and morphological parameters of IAs. Clinical outcomes, including rupture risk, hydrocephalus development, vasospasm incidence, and patients' outcome, were compared. The analysis revealed no significant difference in rupture risk, development of hydrocephalus, need for ventricular drainage, or vasospasm incidence between the matched AcomA and BA cohorts. Furthermore, the clinical outcomes post-rupture did not significantly differ between the two groups, except for a higher Fisher Grade associated with BAs. Once accounting for morphological and patient factors, the rupture risk between AcomA and BAs is comparable. These findings underscore the importance of tailored management strategies for specific IA types and suggest that further investigations should focus on the role of individual patient and aneurysm characteristics in IA rupture risk and clinical outcomes.
Subject(s)
Hydrocephalus , Intracranial Aneurysm , Humans , Retrospective Studies , AngiographyABSTRACT
PURPOSE: Hemodynamics play an important role in the assessment of intracranial aneurysm (IA) development and rupture risk. The purpose of this study was to examine the impact of complex vasculatures onto the intra-vessel and intra-aneurysmal blood flow. METHODS: Complex segmentation of a subject-specific, 60-outlet and 3-inlet circle of Willis model captured with 7T magnetic resonance imaging was performed. This model was trimmed to a 10-outlet model version. Two patient-specific IAs were added onto both models yielding two pathological versions, and image-based blood flow simulations of the four resulting cases were carried out. To capture the differences between complex and trimmed model, time-averaged and centerline velocities were compared. The assessment of intra-saccular blood flow within the IAs involved the evaluation of wall shear stresses (WSS) at the IA wall and neck inflow rates (NIR). RESULTS: Lower flow values are observed in the majority of the complex model. However, at specific locations (left middle cerebral artery 0.5 m/s, left posterior cerebral artery 0.25 m/s), higher flow rates were visible when compared to the trimmed counterpart. Furthermore, at the centerlines the total velocity values reveal differences up to 0.15 m/s. In the IAs, the reduction in the neck inflow rate and WSS in the complex model was observed for the first IA (IA-A δNIRmean = - 0.07ml/s, PCA.l δWSSmean = - 0.05 Pa). The second IA featured an increase in the neck inflow rate and WSS (IA-B δNIRmean = 0.04 ml/s, PCA.l δWSSmean = 0.07 Pa). CONCLUSION: Both the magnitude and shape of the flow distribution vary depending on the model's complexity. The magnitude is primarily influenced by the global vessel model, while the shape is determined by the local structure. Furthermore, intra-aneurysmal flow strongly depends on the location in the vessel tree, emphasizing the need for complex model geometries for realistic hemodynamic assessment and rupture risk analysis.
Subject(s)
Intracranial Aneurysm , Humans , Intracranial Aneurysm/diagnostic imaging , Hemodynamics , Magnetic Resonance Imaging , Cerebrovascular Circulation , Stress, Mechanical , Models, Cardiovascular , Blood Flow VelocityABSTRACT
Minimally-invasive therapies are well-established treatment methods for saccular intracranial aneurysms (SIAs). Knowledge concerning fusiform IAs (FIAs) is low, due to their wide and alternating lumen and their infrequent occurrence. However, FIAs carry risks like ischemia and thus require further in-depth investigation. Six patient-specific IAs, comprising three position-identical FIAs and SIAs, with the FIAs showing a non-typical FIA shape, were compared, respectively. For each model, a healthy counterpart and a treated version with a flow diverting stent were created. Eighteen time-dependent simulations were performed to analyze morphological and hemodynamic parameters focusing on the treatment effect (TE). The stent expansion is higher for FIAs than SIAs. For FIAs, the reduction in vorticity is higher (Δ35-75% case 2/3) and the reduction in the oscillatory velocity index is lower (Δ15-68% case 2/3). Velocity is reduced equally for FIAs and SIAs with a TE of 37-60% in FIAs and of 41-72% in SIAs. Time-averaged wall shear stress (TAWSS) is less reduced within FIAs than SIAs (Δ30-105%). Within this study, the positive TE of FDS deployed in FIAs is shown and a similarity in parameters found due to the non-typical FIA shape. Despite the higher stent expansion, velocity and vorticity are equally reduced compared to identically located SIAs.