International Journal of Computer Assisted Radiology and Surgery最新文献

Purpose: Differentiating pulmonary lymphoma from lung infections using CT images is challenging. Existing deep neural network-based lung CT classification models rely on 2D slices, lacking comprehensive information and requiring manual selection. 3D models that involve chunking compromise image information and struggle with parameter reduction, limiting performance. These limitations must be addressed to improve accuracy and practicality.

Methods: We propose a transformer sequential feature encoding structure to integrate multi-level information from complete CT images, inspired by the clinical practice of using a sequence of cross-sectional slices for diagnosis. We incorporate position encoding and cross-level long-range information fusion modules into the feature extraction CNN network for cross-sectional slices, ensuring high-precision feature extraction.

Results: We conducted comprehensive experiments on a dataset of 124 patients, with respective sizes of 64, 20 and 40 for training, validation and testing. The results of ablation experiments and comparative experiments demonstrated the effectiveness of our approach. Our method outperforms existing state-of-the-art methods in the 3D CT image classification problem of distinguishing between lung infections and pulmonary lymphoma, achieving an accuracy of 0.875, AUC of 0.953 and F1 score of 0.889.

Conclusion: The experiments verified that our proposed position-enhanced transformer-based sequential feature encoding model is capable of effectively performing high-precision feature extraction and contextual feature fusion in the lungs. It enhances the ability of a standalone CNN network or transformer to extract features, thereby improving the classification performance. The source code is accessible at https://github.com/imchuyu/PTSFE .

Purpose: Robot-assisted systems offer an opportunity to support the diagnostic and therapeutic treatment of vascular diseases to reduce radiation exposure and support the limited medical staff in vascular medicine. In the diagnosis and follow-up care of vascular pathologies, Doppler ultrasound has become the preferred diagnostic tool. The study presents a robotic system for automatic Doppler ultrasound examinations of patients' leg vessels.

Methods: The robotic system consists of a redundant 7 DoF serial manipulator, to which a 3D ultrasound probe is attached. A compliant control was employed, whereby the transducer was guided along the vessel with a defined contact force. Visual servoing was used to correct the position of the probe during the scan so that the vessel can always be properly visualized. To track the vessel's position, methods based on template matching and Doppler sonography were used.

Results: Our system was able to successfully scan the femoral artery of seven volunteers automatically for a distance of 20 cm. In particular, our approach using Doppler ultrasound data showed high robustness and an accuracy of 10.7 (±3.1) px in determining the vessel's position and thus outperformed our template matching approach, whereby an accuracy of 13.9 (±6.4) px was achieved.

Conclusions: The developed system enables automated robotic ultrasound examinations of vessels and thus represents an opportunity to reduce radiation exposure and staff workload. The integration of Doppler ultrasound improves the accuracy and robustness of vessel tracking, and could thus contribute to the realization of routine robotic vascular examinations and potential endovascular interventions.

Purpose: As an increasing number of cochlear implant candidates exhibit residual inner ear function, hearing preservation strategies during implant insertion are gaining importance. Manual implantation is known to induce traumatic force and pressure peaks. In this study, we use a validated in-vitro model to comprehensively evaluate a novel surgical tool that addresses these challenges through motorized movement of a forceps.

Methods: Using lateral wall electrodes, we examined two subgroups of insertions: 30 insertions were performed manually by experienced surgeons, and another 30 insertions were conducted with a robot-assisted system under the same surgeons' supervision. We utilized a realistic, validated model of the temporal bone. This model accurately reproduces intracochlear frictional conditions and allows for the synchronous recording of forces on intracochlear structures, intracochlear pressure, and the position and deformation of the electrode array within the scala tympani.

Results: We identified a significant reduction in force variation during robot-assisted insertions compared to the conventional procedure, with average values of 12 mN/s and 32 mN/s, respectively. Robotic assistance was also associated with a significant reduction of strong pressure peaks and a 17 dB reduction in intracochlear pressure levels. Furthermore, our study highlights that the release of the insertion tool represents a critical phase requiring surgical training.

Conclusion: Robotic assistance demonstrated more consistent insertion speeds compared to manual techniques. Its use can significantly reduce factors associated with intracochlear trauma, highlighting its potential for improved hearing preservation. Finally, the system does not mitigate the impact of subsequent surgical steps like electrode cable routing and cochlear access sealing, pointing to areas in need of further research.

Purpose: Model-Guided Medicine (MGM) is a transformative approach to health care that offers a comprehensive and integrative perspective that goes far beyond our current concepts. In this editorial, we want to take a closer look at this innovative concept and how health care could benefit from its further development and application.

Methods: The information presented here is primarily the opinion of the authors and is based on their knowledge in the fields of information technology, computer science, and medicine. The contents are also the result of numerous discussions and scientific meetings within the CARS Society and the CARS Workshop on Model-Guided Medicine and are substantially stimulated by the available literature on the subject.

Results: The current healthcare landscape, with its reliance on isolated data points and broad population-based recommendations, often fails to integrate the dynamic and patient-specific factors necessary for truly personalised care. MGM addresses these limitations by integrating recent advancements in data processing, artificial intelligence, and human-computer interaction for the creation of individual models which integrate the available information and knowledge of patients, healthcare providers, devices, environment, etc. Based on a holistic concept, MGM will become effective tool for modern medicine, which shows a unique ability to assess and analyse interconnected relations and the combined impact of multiple factors on the individual. MGM emphasises transparency, reproducibility, and interpretability, ensuring that models are not black boxes but tools that healthcare professionals can fully understand, validate, and apply in clinical practice.

Conclusion: The practical applications of MGM are vast, ranging from optimising individual treatment plans to enhancing the efficiency of entire healthcare systems. The research community is called upon to pioneer new projects that demonstrate MGM's potential, establishing it as a central pillar of future health care, where more personalised, predictive, and effective medical practices will hopefully become the standard.

Purpose: The search for heart components in robotic transthoracic echocardiography is a time-consuming process. This paper proposes an optimized robotic navigation system for heart components using deep reinforcement learning to achieve an efficient and effective search technique for heart components.

Method: The proposed method introduces (i) an optimized search behavior generation algorithm that avoids multiple local solutions and searches for the optimal solution and (ii) an optimized path generation algorithm that minimizes the search path, thereby realizing short search times.

Results: The mitral valve search with the proposed method reaches the optimal solution with a probability of 74.4%, the mitral valve confidence loss rate when the local solution stops is 16.3% on average, and the inspection time with the generated path is 48.6 s on average, which is 56.6% of the time cost of the conventional method.

Conclusion: The results indicate that the proposed method improves the search efficiency, and the optimal location can be searched in many cases with the proposed method, and the loss rate of the confidence in the mitral valve was low even when a local solution rather than the optimal solution was reached. It is suggested that the proposed method enables accurate and quick robotic navigation to find heart components.

Purpose

In order to produce a surgical gesture recognition system that can support a wide variety of procedures, either a very large annotated dataset must be acquired, or fitted models must generalize to new labels (so-called zero-shot capability). In this paper we investigate the feasibility of latter option.

Methods

Leveraging the bridge-prompt framework, we prompt-tune a pre-trained vision-text model (CLIP) for gesture recognition in surgical videos. This can utilize extensive outside video data such as text, but also make use of label meta-data and weakly supervised contrastive losses.

Results

Our experiments show that prompt-based video encoder outperforms standard encoders in surgical gesture recognition tasks. Notably, it displays strong performance in zero-shot scenarios, where gestures/tasks that were not provided during the encoder training phase are included in the prediction phase. Additionally, we measure the benefit of inclusion text descriptions in the feature extractor training schema.

Conclusion

Bridge-prompt and similar pre-trained + prompt-tuned video encoder models present significant visual representation for surgical robotics, especially in gesture recognition tasks. Given the diverse range of surgical tasks (gestures), the ability of these models to zero-shot transfer without the need for any task (gesture) specific retraining makes them invaluable.

Purpose

Ultrasound imaging has emerged as a promising cost-effective and portable non-irradiant modality for the diagnosis and follow-up of diseases. Motion analysis can be performed by segmenting anatomical structures of interest before tracking them over time. However, doing so in a robust way is challenging as ultrasound images often display a low contrast and blurry boundaries.

Methods

In this paper, a robust descriptor inspired from the fractal dimension is presented to locally characterize the gray-level variations of an image. This descriptor is an adaptive grid pattern whose scale locally varies as the gray-level variations of the image. Robust features are then located based on the gray-level variations, which are more likely to be consistently tracked over time despite the presence of noise.

Results

The method was validated on three datasets: segmentation of the left ventricle on simulated echocardiography (Dice coefficient, DC), accuracy of diaphragm motion tracking for healthy subjects (mean sum of distances, MSD) and for a scoliosis patient (root mean square error, RMSE). Results show that the method segments the left ventricle accurately ((textrm{DC}=0.84)) and robustly tracks the diaphragm motion for healthy subjects ((textrm{MSD}=1.10) mm) and for the scoliosis patient ((textrm{RMSE}=1.22) mm).

Conclusions

This method has the potential to segment structures of interest according to their texture in an unsupervised fashion, as well as to help analyze the deformation of tissues. Possible applications are not limited to US image. The same principle could also be applied to other medical imaging modalities such as MRI or CT scans.

Purpose

Countertraction is a vital technique in laparoscopic surgery, stretching the tissue surface for incision and dissection. Due to the technical challenges and frequency of countertraction, autonomous countertraction has the potential to significantly reduce surgeons’ workload. Despite several methods proposed for automation, achieving optimal tissue visibility and tension for incision remains unrealized. Therefore, we propose a method for autonomous countertraction that enhances tissue surface planarity and visibility.

Methods

We constructed a neural network that integrates a point cloud convolutional neural network (CNN) with a deep reinforcement learning (RL) model. This network continuously controls the forceps position based on the surface shape observed by a camera and the forceps position. RL is conducted in a physical simulation environment, with verification experiments performed in both simulation and phantom environments. The evaluation was performed based on plane error, representing the average distance between the tissue surface and its least-squares plane, and angle error, indicating the angle between the tissue surface vector and the camera’s optical axis vector.

Results

The plane error decreased under all conditions both simulation and phantom environments, with 93.3% of case showing a reduction in angle error. In simulations, the plane error decreased from (3.6 pm 1.5{text{ mm}}) to (1.1 pm 1.8 {text{mm}}), and the angle error from (29 pm 19 ^circ) to (14 pm 13 ^circ). In the phantom environment, the plane error decreased from (0.96 pm 0.24{text{ mm}}) to (0.39 pm 0.23 {text{mm}}), and the angle error from (32 pm 29 ^circ) to (17 pm 20 ^circ).

Conclusion

The proposed neural network was validated in both simulation and phantom experimental settings, confirming that traction control improved tissue planarity and visibility. These results demonstrate the feasibility of automating countertraction using the proposed model.

Purpose

A critical piece of information for prostate intervention and cancer treatment is provided by the complementary medical imaging modalities of ultrasound (US) and magnetic resonance imaging (MRI). Therefore, MRI–US image fusion is often required during prostate examination to provide contrast-enhanced TRUS, in which image registration is a key step in multimodal image fusion.

Methods

We propose a novel multi-scale feature-crossing network for the prostate MRI–US image registration task. We designed a feature-crossing module to enhance information flow in the hidden layer by integrating intermediate features between adjacent scales. Additionally, an attention block utilizing three-dimensional convolution interacts information between channels, improving the correlation between different modal features. We used 100 cases randomly selected from The Cancer Imaging Archive (TCIA) for our experiments. A fivefold cross-validation method was applied, dividing the dataset into five subsets. Four subsets were used for training, and one for testing, repeating this process five times to ensure each subset served as the test set once.

Results

We test and evaluate our technique using fivefold cross-validation. The cross-validation trials result in a median target registration error of 2.20 mm on landmark centroids and a median Dice of 0.87 on prostate glands, both of which were better than the baseline model. In addition, the standard deviation of the dice similarity coefficient is 0.06, which suggests that the model is stable.

Conclusion

We propose a novel multi-scale feature-crossing network for the prostate MRI–US image registration task. A random selection of 100 cases from The Cancer Imaging Archive (TCIA) was used to test and evaluate our approach using fivefold cross-validation. The experimental results showed that our method improves the registration accuracy. After registration, MRI and TURS images were more similar in structure and morphology, and the location and morphology of cancer were more accurately reflected in the images.

Purpose

Hip dysplasia is the second most common orthopedic condition in children with cerebral palsy (CP) and may result in disability and pain. The migration percentage (MP) is a widely used metric in hip surveillance, calculated based on an anterior–posterior pelvis radiograph. However, manual quantification of MP values using hip X-ray scans in current standard practice has challenges including being time-intensive, requiring expert knowledge, and not considering human bias. The purpose of this study is to develop a machine learning algorithm to automatically quantify MP values using a hip X-ray scan, and hence provide an assessment for severity, which then can be used for surveillance, treatment planning, and management.

Methods

X-ray scans from 210 patients were curated, pre-processed, and manually annotated at our clinical center. Several machine learning models were trained using pre-trained weights from Inception ResNet-V2, VGG-16, and VGG-19, with different strategies (pre-processing, with and without region of interest (ROI) detection, with and without data augmentation) to find an optimal model for automatic hip landmarking. The predicted landmarks were then used by our geometric algorithm to quantify the MP value for the input hip X-ray scan.

Results

The pre-trained VGG-19 model, fine-tuned with additional custom layers, outputted the lowest mean squared error values for both train and test data, when ROI cropped images were used along with data augmentation for model training. The MP value calculated by the algorithm was compared to manual ground truth labels from our orthopedic fellows using the hip screen application for benchmarking.

Conclusion

The results showed the feasibility of the machine learning model in automatic hip landmark detection for reliably quantifying MP value from hip X-ray scans. The algorithm could be used as an accurate and reliable tool in orthopedic care for diagnosing, severity assessment, and hence treatment and surgical planning for hip displacement.