Real-Time Tracking of Guidewire Robot Tips Using Deep Convolutional Neural Networks on Successive Localized Frames

Ullah, Ihsan; Chikontwe, Philip; Park, Sang Hyun

doi:10.1109/access.2019.2950263

Cited by 14 publications

(8 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the excellent performance of the CNNs in segmentation tasks, which are notably in biomedical imaging, the CNN-based approaches 5 , 16 have quickly gained popularity. Moreover, deep learning methods, such as U-Net have substantially improved segmentation in medical applications, which include vascular segmentation 17 , catheter segmentation in X-rays and realistic images 18 – 20 , and the lungs segmentation in chest radiography 21 . However, the interest region in the medical images can have similar appearances, which makes it difficult to segment them using U-Net 22 .…”

Section: Introductionmentioning

confidence: 99%

A deep learning based dual encoder–decoder framework for anatomical structure segmentation in chest X-ray images

Ullah

Ali

Shah

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Automated multi-organ segmentation plays an essential part in the computer-aided diagnostic (CAD) of chest X-ray fluoroscopy. However, developing a CAD system for the anatomical structure segmentation remains challenging due to several indistinct structures, variations in the anatomical structure shape among different individuals, the presence of medical tools, such as pacemakers and catheters, and various artifacts in the chest radiographic images. In this paper, we propose a robust deep learning segmentation framework for the anatomical structure in chest radiographs that utilizes a dual encoder–decoder convolutional neural network (CNN). The first network in the dual encoder–decoder structure effectively utilizes a pre-trained VGG19 as an encoder for the segmentation task. The pre-trained encoder output is fed into the squeeze-and-excitation (SE) to boost the network’s representation power, which enables it to perform dynamic channel-wise feature calibrations. The calibrated features are efficiently passed into the first decoder to generate the mask. We integrated the generated mask with the input image and passed it through a second encoder–decoder network with the recurrent residual blocks and an attention the gate module to capture the additional contextual features and improve the segmentation of the smaller regions. Three public chest X-ray datasets are used to evaluate the proposed method for multi-organs segmentation, such as the heart, lungs, and clavicles, and single-organ segmentation, which include only lungs. The results from the experiment show that our proposed technique outperformed the existing multi-class and single-class segmentation methods.

show abstract

Section: Introductionmentioning

confidence: 99%

A deep learning based dual encoder–decoder framework for anatomical structure segmentation in chest X-ray images

Ullah

Ali

Shah

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, push-ability requires a high axial stiffness and more tool flexibility. The latter is needed to catheterize tortuous vessel though excessive levels would lead to kinking of guidewire tip [52], [53]. Selecting the higher stiffness of the guidewire leads to greater bending force and the friction [54], which improved the risk of injuring the blood vessel wall [55].…”

Section: Discussionmentioning

confidence: 99%

Exploration of Interventionists’ Technical Manipulation Skills for Robot-Assisted Intravascular PCI Catheterization

Omisore

Duan

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Despite the great proven advantages of imaging techniques in percutaneous coronary interventions (PCIs), the recent rapid increase in the number of PCI procedures exposes both surgical experts and patients to more radiation and orthopedic hazards in the intervention room. While patients are minimally exposed, many appearance of interventionists subject them to frequent exposure of the operational hazards. Despite promoting the use of robot-assisted intravascular PCI in the Cath-Labs, cognitive and technical skills of interventionists' are yet to be explored towards reducing procedure time and minimal exposure of surgeon to operational hazards. In this study, a random forest classification framework is developed for proper identification of technical manipulation skills of surgeons along with underlying motion patterns of the flexible intravascular tools (viz. guidewire and catheter) during PCI catheterization. For this purpose, analysis of interventionists' muscular activities and related hand motion were decoded from physiological signals recorded with sensors. Surface electromyography, electromagnetic, and tactile force signals were acquired concurrently from seven interventionists during specified guidewire movement viz. pull, push, rotate-pull (clockwise rotation with pull), rotate-push (counterclockwise rotation with push), CR (clockwise rotation), and CCR (counterclockwise rotation). While relations were established between force and muscle activities in the surgeon groups using Spearman's Rank-Order statistical method, Wilcoxon test and Kruskal-Wallis one-way ANOVA test were employed to identify intra-group and inter-group differences. From the experimental results obtained, guidewire delivery patterns exhibit stable characteristics with overall classification accuracies of 94.11% based on nineteen features subset from muscle activities and hand motion, followed by 88.01% based on twelve features subset from muscle activities, 71.97% based on seven features subset from hand motion, 84.56% based on ten features subset from part muscle activities and hand motion. Thus, this study shows existence of significant correlation (p < 0.05) between force and muscle activity during intravascular catheterization for PCIs, while comparably high tactile force values were experience in vascular model with plaque or stenosis.

show abstract

“…A recurrent residual network was applied for segmentation and catheter tracking during endovascular aneurysm repair (22). Relatedly, a model based on deep neural networks for guidewire tracking during robotic navigation was proposed (23). Successive localized frames were utilized for tracking; however, the study did not involve the use of X-ray image frames.…”

Section: Introductionmentioning

confidence: 99%

Automatic tool segmentation and tracking during robotic intravascular catheterization for cardiac interventions

Omisore¹,

Duan²,

Du³

et al. 2021

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Cardiovascular diseases resulting from aneurism, thrombosis, and atherosclerosis in the cardiovascular system are major causes of global mortality. Recent treatment methods have been based on catheterization of flexible endovascular tools with imaging guidance. While advances in robotic intravascular catheterization have led to modeling tool navigation approaches with data sensing and feedback, proper adaptation of image-based guidance for robotic navigation requires the development of sensitive segmentation and tracking models without specificity loss. Several methods have been developed to tackle non-uniform illumination, low contrast; however, presence of untargeted body organs commonly found in X-ray frames taken during angiography procedures still presents some major issues to be solved.Methods: In this study, a segmentation method was developed for automatic detection and tracking of guidewire pixels in X-ray angiograms. Image frames were acquired during robotic intravascular catheterization for cardiac interventions. For segmentation, multiscale enhancement filtering was applied on preprocessed X-ray angiograms, while morphological operations and filters were applied to refine the frames for pixel intensity adjustment and vesselness measurement. Minima and maxima extrema of the pixels were obtained to detect guidewire pixels in the X-ray frames. Lastly, morphological operation was applied for guidewire pixel connectivity and tracking in segmented pixels. Method validation was performed on 12 X-ray angiogram sequences which were acquired during in vivo intravascular catheterization trials in rabbits. Results:The study outcomes showed that an overall accuracy of 0.995±0.001 was achieved for segmentation. Tracking performance was characterized with displacement and orientation errors observed as 1.938±2.429 mm and 0.039±0.040°, respectively. Evaluation studies performed against 9 existing methods revealed that this proposed method provides more accurate segmentation with 0.753±0.074 area under curve. Simultaneously, high tracking accuracy of 0.995±0.001 with low displacement and orientation errors of 1.938±2.429 mm and 0.039±0.040°, respectively, were achieved. Also, the method demonstrated higher sensitivity and specificity values compared to the 9 existing methods, with a relatively faster exaction time. Conclusions:The proposed method has the capability to enhance robotic intravascular catheterization during percutaneous coronary interventions (PCIs). Thus, interventionists can be provided with better tool tracking and visualization systems while also reducing their exposure to operational hazards during intravascular catheterization for cardiac interventions.

show abstract

Real-Time Tracking of Guidewire Robot Tips Using Deep Convolutional Neural Networks on Successive Localized Frames

Cited by 14 publications

References 46 publications

A deep learning based dual encoder–decoder framework for anatomical structure segmentation in chest X-ray images

A deep learning based dual encoder–decoder framework for anatomical structure segmentation in chest X-ray images

Exploration of Interventionists’ Technical Manipulation Skills for Robot-Assisted Intravascular PCI Catheterization

Automatic tool segmentation and tracking during robotic intravascular catheterization for cardiac interventions

Contact Info

Product

Resources

About