Coordinate-based fast lightweight path search algorithm for electromagnetic navigation bronchoscopy.

Electromagnetic navigation bronchoscopy (ENB) uses electromagnetic positioning technology to guide the bronchoscope to accurately and quickly reach the lesion along the planned path. However, enormous data in high-resolution lung computed tomography (CT) and the complex structure of multilevel branching bronchial tree make fast path search challenging for path planning. We propose a coordinate-based fast lightweight path search (CPS) algorithm for ENB. First, the centerline is extracted from the bronchial tree by applying topological thinning. Then, Euclidean-distance-based coordinate search is applied. The centerline points are represented by their coordinates, and adjacent points along the navigation path are selected considering the shortest Euclidean distance to the target on the centerline nearest the lesion. From the top of the trachea centerline, search is repeated until reaching the target. In 50 high-resolution lung CT images acquired from five scanners, the CPS algorithm achieves accuracy, average search time, and average memory consumption of 100%, 88.5 ms, and 166.0 MB, respectively, reducing search time by 74.3% and 73.1% and memory consumption by 83.3% and 83.0% compared with Dijkstra and A* algorithms, respectively. CPS algorithm is suitable for path search in multilevel branching bronchial tree navigation based on high-resolution lung CT images.

Developing an explainable deep learning boundary correction method by incorporating cascaded x-Dim models to improve segmentation defects in liver CT images.

Deep learning methods achieved remarkable results in medical image analysis tasks but it has not yet been widely used by medical professionals. One of the main reasons for this restricted usage is the uncertainty of the reasons that influence the decision of the model. Explainable AI methods have been developed to improve the transparency, interpretability, and explainability of the black-box AI methods. The result of an explainable segmentation method will be more trusted by experts. In this study, we designed an explainable deep correction method by incorporating cascaded 1D and 2D models to refine the output of other models and provide reliable yet accurate results. We implemented a 2-step loop with a 1D local boundary validation model in the first step, and a 2D image patch segmentation model in the second step, to refine incorrect segmented regions slice-by-slice. The proposed method improved the result of the CNN segmentation models and achieved state-of-the-art results on 3D liver segmentation with the average dice coefficient of 98.27 on the Sliver07 dataset.

Integration of CNN, CBMIR, and Visualization Techniques for Diagnosis and Quantification of Covid-19 Disease.

Diagnosis techniques based on medical image modalities have higher sensitivities compared to conventional RT-PCT tests. We propose two methods for diagnosing COVID-19 disease using X-ray images and differentiating it from viral pneumonia. The diagnosis section is based on deep neural networks, and the discriminating uses an image retrieval approach. Both units were trained by healthy, pneumonia, and COVID-19 images. In COVID-19 patients, the maximum intensity projection of the lung CT is visualized to a physician, and the CT Involvement Score is calculated. The performance of the CNN and image retrieval algorithms were improved by transfer learning and hashing functions. We achieved an accuracy of 97% and an overall prec@10 of 87%, respectively, concerning the CNN and the retrieval methods.

Incorporating prior shape knowledge via data-driven loss model to improve 3D liver segmentation in deep CNNs.

PURPOSE: Convolutional neural networks (CNNs) have obtained enormous success in liver segmentation. However, there are several challenges, including low-contrast images, and large variations in the shape, and appearance of the liver. Incorporating prior knowledge in deep CNN models improves their performance and generalization. METHODS: A convolutional denoising auto-encoder is utilized to learn global information about 3D liver shapes in a low-dimensional latent space. Then, the deep data-driven knowledge is used to define a loss function and combine it with the Dice loss in the main segmentation model. The resultant hybrid model would be forced to learn the global shape information as prior knowledge, while it tries to produce accurate results and increase the Dice score. RESULTS: The proposed training strategy improved the performance of the 3D U-Net model and reached the Dice score of 97.62% on the Sliver07-I liver dataset, which is competitive to the state-of-the-art automatic segmentation methods. The proposed algorithm enhanced the generalization and robustness of the hybrid model and outperformed the 3D U-Net model in the prediction of unseen images. CONCLUSIONS: The results indicate that the incorporation of prior shape knowledge enhances liver segmentation tasks in deep CNN models. The proposed method improves the generalization and robustness of the hybrid model due to the abstract features provided by the data-driven loss model.

A projected landmark method for reduction of registration error in image-guided surgery systems.

PURPOSE: Image-guided surgery systems are limited by registration error, so practical and effective methods to improve accuracy are necessary. A projection point-based method for reducing the surface registration error in image-guided surgery was developed and tested. METHODS: Checkerboard patterns are projected on visible surfaces to create projected landmarks over a region of interest. Surface information thus becomes available in the form of point clouds of surface point coordinates with submillimeter resolution. The reconstructed 3D point cloud is registered using iterative closest point (ICP) approximation to a 3D point cloud extracted from preoperative CT images of the same region of interest. The projected landmark surface registration method was compared with two other methods using a facial surface phantom: (a) landmark registration using anatomical features, and (b) surface matching based on an additional 40 surface points. RESULTS: The mean error for the projected landmark surface registration method was 0.64 mm, which was 47.4 and 35.3 % lower relative to mean errors of the anatomical landmark registration and the surface-matching methods, respectively. After applying the proposed method, using target registration error as a gold standard, the resulting mean error was 1.1 mm or a reduction of 61.2 % compared to the anatomical landmark registration. CONCLUSION: Optical checkerboard pattern projection onto visible surfaces was used to acquire surface point clouds for image-guided surgery registration. A projected landmark method eliminated the effects of unwanted and overlapping points by acquiring the desired points at specific locations. The results were more accurate than conventional landmark or surface registration.

Accuracy assessment of a marker-free method for registration of CT and stereo images applied in image-guided implantology: a phantom study.

To assess the accuracy of a proposed marker-free registration method as opposed to the conventional marker-based method using an image-guided dental system, and investigating the best configurations of anatomical landmarks for various surgical fields in a phantom study, a CT-compatible dental phantom consisting of implanted targets was used. Two marker-free registration methods were evaluated, first using dental anatomical landmarks and second, using a reference marker tool. Six implanted markers, distributed in the inner space of the phantom were used as the targets; the values of target registration error (TRE) for each target were measured and compared with the marker-based method. Then, the effects of different landmark configurations on TRE values, measured using the Parsiss IV Guided Navigation system (Parsiss, Tehran, Iran), were investigated to find the best landmark arrangement for reaching the minimum registration error in each target region. It was proved that marker-free registration can be as precise as the marker-based method. This has a great impact on image-guided implantology systems whereby the drawbacks of fiducial markers for patient and surgeon are removed. It was also shown that smaller values of TRE could be achieved by using appropriate landmark configurations and moving the center of the landmark set closer to the surgery target. Other common factors would not necessarily decrease the TRE value so the conventional rules accepted in the clinical community about the ways to reduce TRE should be adapted to the selected field of dental surgery.

A region-based anatomical landmark configuration for sinus surgery using image guided navigation system: a phantom-study.

PURPOSE: To evaluate the current beliefs about the ways to reduce target registration error (TRE) values in image guided Sinus surgery by rearranging the fiducial configuration, and investigating the best configurations for various surgical fields in a phantom study. METHODS: A new CT-compatible skull phantom consisting of implanted targets was designed to enable direct measurement of TRE in four fields of sinus surgery, Frontal, Ethmoid, Sphenoid and Maxillary. The effects of different landmark configurations on TRE values, measured by the Parsiss-IV navigation system were investigated to find the best landmark arrangement for each region, and compared to the TRE prediction formula to assess the clinically accepted landmark selection approaches based on this formula. RESULTS: It was shown that smaller values of TRE could be attained by arranging the center of the fiducials to be more focused on the surgery target. The addition of more fiducials and keeping non-linear arrangement of landmark would not necessarily decrease the TRE value. CONCLUSION: Optimizing the landmark configuration is important for increasing the localization accuracy in image guided sinus surgery. The common beliefs accepted in the clinical community about the ways to reduce the TRE are very general and should be adapted to specific field of image guided surgery.