Fiducial Marker Detection Research Articles

Artificial intelligence-based framework in evaluating intrafraction motion for liver cancer robotic stereotactic body radiation therapy with fiducial tracking.

This study aimed to design a fully automated framework to evaluate intrafraction motion using orthogonal x-ray images from CyberKnife. The proposed framework includes three modules: (a) automated fiducial marker detection, (b) three-dimensional (3D) position reconstruction, and (c) intrafraction motion evaluation. A total of 5927 images from real patients treated with CyberKnife fiducial tracking were collected. The ground truth was established by labeling coarse bounding boxes manually, and binary mask images were then obtained by applying a binary threshold and filter. These images and labels were used to train a detection model using a fully convolutional network (fCN). The output of the detection model can be used to reconstruct the 3D positions of the fiducial markers and then evaluate the intrafraction motion via a rigid transformation. For a patient test, the motion amplitudes, rotations, and fiducial cohort deformations were calculated used the developed framework for 13 patients with a total of 52 fractions. The precision and recall of the fiducial marker detection model were 98.6% and 95.6%, respectively, showing high model performance. The mean (±SD) centroid error between the predicted fiducial markers and the ground truth was 0.25±0.47 pixels on the test data. For intrafraction motion evaluation, the mean (±SD) translations in the superior-posterior (SI), left-right (LR), and anterior-posterior (AP) directions were 13.1±2.2mm, 2.0±0.4mm, and 5.2±1.4mm, respectively, and the mean (±SD) rotations in the roll, pitch and yaw directions were 2.9±1.5°, 2.5±1.5°, and 3.1±2.2°. Seventy-one percent of the fractions had rotations larger than the system limitations. With rotation correction during rigid registration, only 2 of the 52 fractions had residual errors larger than 2mm in any direction, while without rotation correction, the probability of large residual errors increased to 46.2%. We developed a framework with high performance and accuracy for automatic fiducial marker detection, which can be used to evaluate intrafraction motion using orthogonal x-ray images from CyberKnife. For liver patients, most fractions have fiducial cohort rotations larger than the system limitations; however, the fiducial cohort deformation is small, especially for the scenario with rotation correction.

A Generative Adversarial Network (GAN)-based Approach for Automatic Fiducial Marker Detection in MR Radiotherapy Simulation Images

To design and evaluate a robust method for the automatic detection of fiducial markers (FMs) in MR simulation images used for prostate cancer radiotherapy planning. MR-only simulation continues to see expanded use due to the benefits of eliminating CT from standard MR/CT radiotherapy planning workflows, including reduced registration uncertainties, cost, and time. Standard x-ray-based IGRT treatments that use FMs for patient alignment pose a challenge for MR-only simulation, where FMs appear as small and often difficult to detect signal voids. In practice, multiple MR sequences with varying echo times and manual interaction are often required to distinguish FMs. Such methods are vulnerable to patient motion and require increased clinician effort. In this work we present an automatic FM detection method requiring a single standard GRE-based MR sequence. 21 prostate cancer patients who each had three FMs implanted prior to CT simulation and MR imaging were retrospectively selected for this study. Contrast enhanced T1 VIBE images were used in this study. Ground truth FM contours were manually defined on the patients’ CT and corresponding MR images. The cohort was divided into five groups, with one group held out for testing and the other four used for training in a five-fold cross validation approach. The MR images and FM contours (converted to labeled binary masks) from the training sets were used to train a Generative Adversarial Network (GAN) with the pix2pix image-to-image translation package. Trained models take an input MR image and output an image with suspected FM pixels labeled. The final three FM contours for each patient were defined as the three largest clustered objects in the labeled volume. Successful FM identification was defined based on the DICE coefficient of the automatically detected and ground truth FM contours. The Fiducial Registration Error (FRE) between the automatically detected and ground truth FM locations were calculated. FMs were correctly identified in 97% of tested cases (Table 1). All implanted FMs were correctly identified in 19/21 of the tested patients. The two incorrect FM identifications occurred with a marker implanted at the prostate/rectal wall interface and urethra. The mean FRE difference in the Anterior-Posterior, Left-Right and Superior-Inferior directions was 0.3 ± 0.7, 0.7 ± 1.4 and 0.8 ± 1.1 mm respectively. We developed a GAN-based approach to automatic FM detection in MR simulation images, and used it to demonstrate the feasibility of detecting FMs with a single standard MR sequence. Future work will involve testing the model on a larger cohort of patients and further investigating potential sources of FM misidentification, including calcifications and proximity to tissue interfaces.Abstract 189; Table 1Group 1 (Patient 1-4)Group 2 (Patient 5-8)Group 3 (Patient 9-12)Group 4 (Patient 13-17)Group 5 (Patient 18-21)% FM Detection accuracy1001001009292ΔFRE Magnitude (mm)1.4 ± 1.90.7 ± 11 ± 1.61.5 ± 1.81.6 ± 2.6 Open table in a new tab

Visualization of gold fiducial markers in the prostate using phase-cycled bSSFP imaging for MRI-only radiotherapy

In this work, we present a new method for visualization of fiducial markers (FMs) in the prostate for MRI-only radiotherapy with a positive contrast directly at the MR console. The method is based on high bandwidth phase-cycled balanced steady-state free precession (bSSFP) sequence, which is available on many clinical scanners, does not require any additional post-processing or software, and has a higher signal-to-noise (SNR) compared to conventional gradient-echo (GE) imaging. Complex phase-cycled bSSFP data is acquired with different RF phase increment settings such that the manifestation of the artifacts around FMs in the acquired complex images is different for each dynamic acquisition and depends on the RF phase increment used.First, we performed numerical simulations to investigate the complex-valued phase-cycled bSSFP signal in the presence of a gold FM, and to investigate the relation of the true physical location of the FM with the geometrical manifestation of the artifacts. Next, to validate the simulations, we performed phantoms and in vivo studies and compared the experimentally obtained artifacts with those predicted in simulations. The accuracy of the method was assessed by comparing the distances between the FM’s centers and the center of mass of FMs system measured using phase-cycled bSSFP MR images and using reference CT (or MRI-only) images.The results show accurate (within 1 mm) matching of FMs localization between CT and MR images on five patients, proving the feasibility of in vivo FMs detection on MR images only. The FMs show a positive contrast with respect to the prostate background on real/imaginary phase-cycled bSSFP images, which was confirmed by simulations.The proposed method facilitates robust FMs visualization with positive contrast directly at the MR console, allowing RT technicians to obtain immediate feedback on the anticipated feasibility of accurate FMs localization while the patient is being scanned.

Automated fiducial marker detection and fiducial point localization in CT images for lung biopsy image-guided surgery systems.

In the lung biopsy image-guided surgery systems, the fiducial markers are used for point-based registration of the patient space to the CT image space. Fiducial marker detection and fiducial point localization in CT images have great influence on the accuracy of registration and guidance. This study proposes a fiducial marker detection approach based on the features of marker image slice sequences and a fiducial point localization approach according to marker projection images, without depending on the priori-knowledge of the marker default parameters provided by the manufacturers. The accuracy of our method was validated based on a CT image dataset of 24 patients. The experimental results showed that all 144 markers of 24 patients were correctly detected, and the fiducial points were localized with the average error of 0.35 mm. In addition, the localization accuracy of the proposed method was improved by an average of 12.5% compared with the accuracy of the previous method using the marker default parameters provided by the manufacturers. Thus, the study demonstrated that the proposed detection and localization methods are accurate and robust, which is quite encouraging to meet the requirement of future clinical applications in the image guided lung biopsy and surgery systems.

Assessment of the accuracy of truebeam intrafraction motion review (IMR) system for prostate treatment guidance.

Intrafraction motion review (IMR), a real-time 2D, motion management feature of the Varian Truebeam™ incorporates triggered imaging, automatic fiducial marker detection and automatic beam hold. With the increasing adoption of high dose per fraction stereotactic body radiotherapy (SBRT) this system provides a potential means to ensure treatment accuracy. The goal of this study was therefore to investigate and quantify key performance characteristics of IMR for prostate treatment guidance. Phantom experiments were performed with a custom Computerized Imaging Reference Systems, Inc (CIRS) pelvis phantom with implanted gold seeds and the Hexamotion™ 5D motion platform. The system accuracy was assessed statically and under typical prostate motion trajectories. The IMR functionality and marker detectability was tested under different anatomical conditions and with different imaging acquisition modes. Imaging dose for triggered imaging modes was determined using an ionisation chamber based on IPEMB dose calibration protocol for kV energies. For zero displacement, the IMR demonstrated submillimeter agreement with the known position. Similarly, dynamic motion differences between the IMR reported position and 2D trajectory displacement were within 1mm. Static displacement in the anterior direction was reported by IMR as sinusoidal motion on the x-axis (kV angle). The 2D nature of IMR limits the ability to detect motion out of the plane of the kV image detector. Using typical clinical imaging settings, imaging dose determined at the patient surface was 2.58mGy/frame and the corresponding IMR displayed dose was 2.63mGy/frame. The methodology used was able to quantify the accuracy of the IMR system. The IMR was able to accurately and consistently report fiducial positions within the limitations inherent of a 2D system. IMR is fully integrated with the Truebeam system with an easy to use and efficient workflow and is clinically beneficial especially within the context of SBRT.

Detecting Square Markers in Underwater Environments

Augmented reality can be deployed in various application domains, such as enhancing human vision, manufacturing, medicine, military, entertainment, and archeology. One of the least explored areas is the underwater environment. The main benefit of augmented reality in these environments is that it can help divers navigate to points of interest or present interesting information about archaeological and touristic sites (e.g., ruins of buildings, shipwrecks). However, the harsh sea environment affects computer vision algorithms and complicates the detection of objects, which is essential for augmented reality. This paper presents a new algorithm for the detection of fiducial markers that is tailored to underwater environments. It also proposes a method that generates synthetic images with such markers in these environments. This new detector is compared with existing solutions using synthetic images and images taken in the real world, showing that it performs better than other detectors: it finds more markers than faster algorithms and runs faster than robust algorithms that detect the same amount of markers.

Development of marker-based augmented reality system for object detection in an optimum latency time

Augmented reality is an emerging technique to monitor real-time environment to take a decision based on the collected data. With the advancement in the concept of augmented reality and rapid development of robots, there is a need to develop a system or a method to reduce the latency in the most challenging conditions. Although, now some applications are using marker less augmented reality technique due to complications in object detection and tracking in Boston dynamics (robotics) and real-time application we relied on fiducial marker based system. This paper mainly proposes an AR system which explains a guideline to detect the fiducial marker by an object (unidirectional movement) at minimum latency time. In this experiment, fiducial marker detection and position orientation with respect to the camera has been processed by 'Aforge.NET Framework' in combination with C# language and pose estimation. We designed machine marker detection algorithm and mathematics equation which compute the latency time in different challenging conditions lux, distance frame per second of camera in an optimum latency time.

Performance of gimbal-based dynamic tumor tracking for treating liver carcinoma

BackgroundSince the introduction of tumor tracking in radiotherapy, it is possible to ensure a precise irradiation of moving targets. To follow the tumor movement, most systems rely on the detection of implanted markers and correlation models between the internal and external patient movement. This study reports the clinical workflow and first results of the dynamic tumor tracking (DTT) performance for patients with liver carcinoma at the Vero SBRT system of the University Hospital Erlangen regarding the detection of the internal marker and the changes of the determined correlation models.MethodsSo far 13 liver patients were treated with DTT. For each patient, two fiducial markers (FM), which are monitored with X-rays during treatment, were implanted in the vicinity of the tumor. All patients received a fraction dose of 4–6 Gy with 8 to 12 fractions. Treatment and patient data is evaluated by processing the acquired log-files of the DTT treatment. Based on this, the marker detection and the changes of the correlation model between the internal and external movement is investigated.ResultsThe median treatment time was 19:42 min. During treatment a median of 173 X-ray stereoscopic images were acquired. The marker detection was successful in 64.6% of the images. The FM detection is independent of the relative angle between the marker and the imager, but shows a dependency on the average intensity surrounding the FM position within the kV images. The number of correlation models needed during treatment increases in the presence of baseline shifts. The comparison of the correlation models shows large differences in the internal-external correlation between the different models acquired for one patient.ConclusionThirteen liver patients were treated with DTT at the Vero SBRT system and the marker detection was analyzed. Furthermore, the importance of regularly monitoring the internal target motion could be shown, since the correlation between the internal and external motion changes considerably over the course of the treatment.

AuTom-dualx: a toolkit for fully automatic fiducial marker-based alignment of dual-axis tilt series with simultaneous reconstruction.

MotivationDual-axis electron tomography is an important 3 D macro-molecular structure reconstruction technology, which can reduce artifacts and suppress the effect of missing wedge. However, the fully automatic data process for dual-axis electron tomography still remains a challenge due to three difficulties: (i) how to track the mass of fiducial markers automatically; (ii) how to integrate the information from the two different tilt series; and (iii) how to cope with the inconsistency between the two different tilt series.ResultsHere we develop a toolkit for fully automatic alignment of dual-axis electron tomography, with a simultaneous reconstruction procedure. The proposed toolkit and its workflow carries out the following solutions: (i) fully automatic detection and tracking of fiducial markers under large-field datasets; (ii) automatic combination of two different tilt series and global calibration of projection parameters; and (iii) inconsistency correction based on distortion correction parameters and the consequently simultaneous reconstruction. With all of these features, the presented toolkit can achieve accurate alignment and reconstruction simultaneously and conveniently under a single global coordinate system.Availability and implementationThe toolkit AuTom-dualx (alignment module dualxmauto and reconstruction module ) are accessible for general application at http://ear.ict.ac.cn, and the key source code is freely available under request.Supplementary information Supplementary data are available at Bioinformatics online.

EP-2030: Examination of the automatic fiducial marker detection on the Vero system

EP-2030: Examination of the automatic fiducial marker detection on the Vero system

Detection of Spherical Gold Fiducials in kV X-Ray Images Using Intensity-Estimation-Based Method

Fiducial marker detection algorithms in kilovoltage x-ray images using physical characteristics of transmission x-ray have been proposed. It, however, has been suggested recently that factors besides transmission x-ray affect x-ray images. The purpose of this study was to develop a new fiducial detection algorithm using fiducial intensity estimation based on physical characteristics of x-ray images with gold fiducials. First, x-ray images of a fiducial on a water-equivalent phantom were acquired. It was observed that the ratio of background to fiducial intensity in the images decreased as phantom thickness increased. Based on the negative correlation, we identified a function for estimating fiducial intensity that consists of background intensity and the amount of scattered radiation by the other x-ray source of an orthogonal imaging system and a treatment beam. Then, we developed an algorithm that extracts fiducial candidates using the estimation function. Its performance was measured using x-ray images which had 3824 fiducials altogether. The average number of false-positive detection of the proposed algorithm in single image was one-tenth of an algorithm considering only transmission x-ray. The proposed algorithm detected 99.5% of all fiducials under an error of 1.0 mm, while the other algorithm detected 94.7% or less (Clinical trial number: UMIN000005324).

An efficient visual fiducial localisation system

With use cases that range from external localisation of single robots or robotic swarms to self-localisation in marker-augmented environments and simplifying perception by tagging objects in a robot's surrounding, fiducial markers have a wide field of application in the robotic world. We propose a new family of circular markers which allow for both computationally efficient detection, tracking and identification and full 6D position estimation. At the core of the proposed approach lies the separation of the detection and identification steps, with the former using computationally efficient circular marker detection and the latter utilising an open-ended 'necklace encoding', allowing scalability to a large number of individual markers. While the proposed algorithm achieves similar accuracy to other state-of-the-art methods, its experimental evaluation in realistic conditions demonstrates that it can detect markers from larger distances while being up to two orders of magnitude faster than other state-of-the art fiducial marker detection methods. In addition, the entire system is available as an open-source package at https://github.com/LCAS/whycon.

Evaluation of an automatic MR-based gold fiducial marker localisation method for MR-only prostate radiotherapy

An MR-only radiotherapy planning (RTP) workflow would reduce the cost, radiation exposure and uncertainties introduced by CT-MRI registrations. In the case of prostate treatment, one of the remaining challenges currently holding back the implementation of an RTP workflow is the MR-based localisation of intraprostatic gold fiducial markers (FMs), which is crucial for accurate patient positioning.Currently, MR-based FM localisation is clinically performed manually. This is sub-optimal, as manual interaction increases the workload. Attempts to perform automatic FM detection often rely on being able to detect signal voids induced by the FMs in magnitude images. However, signal voids may not always be sufficiently specific, hampering accurate and robust automatic FM localisation.Here, we present an approach that aims at automatic MR-based FM localisation. This method is based on template matching using a library of simulated complex-valued templates, and exploiting the behaviour of the complex MR signal in the vicinity of the FM. Clinical evaluation was performed on seventeen prostate cancer patients undergoing external beam radiotherapy treatment. Automatic MR-based FM localisation was compared to manual MR-based and semi-automatic CT-based localisation (the current gold standard) in terms of detection rate and the spatial accuracy and precision of localisation. The proposed method correctly detected all three FMs in 15/17 patients. The spatial accuracy (mean) and precision (STD) were 0.9 mm and 0.5 mm respectively, which is below the voxel size of mm3 and comparable to MR-based manual localisation. FM localisation failed (3/51 FMs) in the presence of bleeding or calcifications in the direct vicinity of the FM.The method was found to be spatially accurate and precise, which is essential for clinical use. To overcome any missed detection, we envision the use of the proposed method along with verification by an observer. This will result in a semi-automatic workflow facilitating the introduction of an MR-only workflow.

Efficacy of butylscopolamine in obtaining clear MR image for intensity-modulated radiotherapy for prostate cancer.

The use of butylscopolamine in magnetic resonance imaging (MRI) of the prostate is controversial in the context of diagnostic imaging where local invasion and the presence of metastases are evaluated. However, in radiation oncology, MRI is performed as part of the simulation process, and the objectives differ to the diagnostic setting. MRI is primarily used for accurate target delineation; hence, the use of an agent to reduce intestinal peristalsis and increase image quality may be beneficial. The impact of butylscopolamine on MRI for radiation oncology purposes has not previously been described. The aim of this study was to evaluate the efficacy of butylscopolamine in MRI acquired for radiation oncology simulation of the prostate. In total, 67 patients were enrolled in this study. Thirty-five patients received intramuscular injection of butylscopolamine (group A) and 32 patients did not (group B). Visualization of the prostate outline and detection of fiducial gold markers (GMs) in the prostate were evaluated on MRI. Two blinded radiation oncologists (ROs) and one radiation technologist (RT) scored the image quality of the detection of prostate outline and recognition of GMs in the prostate on a scale of 1-5 (1=poor; 5=excellent), and the results were evaluated using Mann-Whitney U test and p<0.05 was considered as statistically significant. On MRI, group A was statistically superior to group B in terms of fiducial marker detection by two ROs (p<0.01). However, there was no significant difference in RT scoring. Furthermore, on MRI, group A was statistically superior to group B in terms of the detection of the prostate outline by an RT. Butylscopolamine is effective with respect to detection of the prostate outline and GM recognition (without endorectal coil). The addition of butylscopolamine is simple and cost efficient. We recommend the use of butylscopolamine routinely to obtain good MR images, particularly in the detection of GMs.

Development of semi-automatic procedure for detection and tracking of fiducial markers for orofacial kinematics during natural feeding.

Feeding is a highly complex, essential behavior for survival in all species. Characterization of feeding behaviors has implications in basic science and translational medicine. We have been developing methods to study feeding behaviors using high speed videofluoroscopy (XROMM) in rats while self-feeding radiopaque flavored kibble. The rat is a popular model in translational medicine; however, it has not been studied using this methodology. Towards this goal, we surgically implanted radiopaque fiducial markers into the skull, mandible, and tongue of rats to enable motion tracking. We are developing computer vision tools to extract kinematics and behavioral features from XROMM videos to overcome barriers of current analysis methods. By understanding feeding dynamics, we will gain basic scientific knowledge and translational insights for feeding disorders caused by neurological conditions such as ALS, Parkinson's disease, and stroke.

Prostate fiducial marker detection with the use of multi-parametric magnetic resonance imaging

Abstract Background and purpose The introduction of a magnetic resonance (MR)-only workflow in radiotherapy requires that fiducial markers, used for position verification, can be detected on MR images. Here we evaluate a model for marker detection in prostate cancer patients by combining information from our hospital standard multi-parametric (mp-) MRI protocol (T1-weighted – T1w, T2-weighted – T2w, B 0 ) with dedicated sequences (balanced steady-state free precession sequence – bTFE, susceptibility weighted imaging – SWI). Materials and methods Thirty two patients scheduled for external-beam radiotherapy received a mp-MRI and computed-tomography; the latter was used as ground truth location of the markers. A logistic regression model was implemented for marker detection by combining features from all imaging sequences. The performance of the individual and combined sequences was assessed by determining true and false positive detections. Results The combination of different sequences (mp-MRI) resulted in a better performance than the best imaging sequence alone (bTFE). Combining mp-MRI+bTFE resulted in good accuracy and a true positive detection rate of 0.94. Conclusions The standard mp-MRI provides valuable information to detect fiducial markers. The combination of different sequences outperforms the use of a single dedicated sequence. We recommend the addition of a bTFE to the standard mp-MRI protocol to improve fiducial marker detection.

Comparison of fiducial marker detection and object interaction in activities of daily living utilising a wearable vision sensor

SummaryThis paper presents a comparison between algorithms (Oriented FAST and Rotated BRIEF (ORB) and Aruco) for the detection of fiducial markers placed throughout a smart environment. A series of activities of daily living (ADL) were conducted while monitoring a first‐person perspective of the situation; this was achieved through the usage of the Google Glass platform. Fiducial markers were employed, as a means to assist with the detection of specific objects of interest, within the environment. Each marker was assigned unique Identification (ID) and was used to identify the object. Three activities were performed by a participant within the environment. On subsequent trials of the solution, lighting conditions were modified to assess fiducial marker detection rates on a frame‐by‐frame basis. This paper presents the results from this investigation, detailing performance measure for each object detected under various lighting conditions, motion blur and distance from the objects. An intelligent system was developed to specifically consider distance estimation in order to aid with the filtering out of false interactions. A linear filtering method was applied along with a fuzzy membership function to estimate the degree of user interaction, which assists in removing false positives generated by the occupant. The intelligent system returns an average precision, recall and an F‐Measure of 0.99, 0.62 and 0.49, respectively. Copyright © 2016 John Wiley &amp; Sons, Ltd.

Comparison of the MRI sequences in ideal fiducial maker-based radiotherapy for prostate cancer

Introduction Contouring the prostate using CT alone is difficult. MRI is used in registration of CT and MRI using fiducial markers. However, visualization of the marker itself can be difficult in MRI. Purpose The aim of this study was to determine the optimal MRI pulse sequence to define the marker, as well as the prostate gland, by comparing five sequences. Methods and materials A total of 21 consecutive patients with prostate cancer were enrolled. We obtained five sequences of T1-weighted spin-echo ([TR]/[TE]): (607/12) (T1WI), T2-weighted fast spin-echo (3000/80) (T2WI), T2∗-2D-weighted gradient echo (4000/80) (T2∗2D), T2∗-3D-weighted gradient echo [TR/TE1/deltaTE](37/14/7.3) (T2∗3D), and contrast-enhanced T1-weighted spin-echo (607/12) (CE-T1WI). A qualitative image analysis of the sequence was also performed by three observers. These observers subjectively scored all images according to the following five evaluation items: definition of the outline of the prostate; apex vs. soft tissue; base vs. bladder; base vs. seminal vesicle; and gold fiducial marker detection. A score of 1–3 (1 = poor, 2 = moderate, 3 = good) was assigned to all items. A higher score was regarded to indicate better visualization. Results T2∗2D and T2∗3D were strongly superior to other sequences and significantly superior in terms of fiducial marker definition. T2∗3D was slightly superior to T2∗3D, but this difference was not significant. Conclusion We recommend that a T2∗3D examination is initially performed, followed by a T2∗2D sequence if necessary. Contouring the prostate using CT alone is difficult. MRI is used in registration of CT and MRI using fiducial markers. However, visualization of the marker itself can be difficult in MRI. The aim of this study was to determine the optimal MRI pulse sequence to define the marker, as well as the prostate gland, by comparing five sequences. A total of 21 consecutive patients with prostate cancer were enrolled. We obtained five sequences of T1-weighted spin-echo ([TR]/[TE]): (607/12) (T1WI), T2-weighted fast spin-echo (3000/80) (T2WI), T2∗-2D-weighted gradient echo (4000/80) (T2∗2D), T2∗-3D-weighted gradient echo [TR/TE1/deltaTE](37/14/7.3) (T2∗3D), and contrast-enhanced T1-weighted spin-echo (607/12) (CE-T1WI). A qualitative image analysis of the sequence was also performed by three observers. These observers subjectively scored all images according to the following five evaluation items: definition of the outline of the prostate; apex vs. soft tissue; base vs. bladder; base vs. seminal vesicle; and gold fiducial marker detection. A score of 1–3 (1 = poor, 2 = moderate, 3 = good) was assigned to all items. A higher score was regarded to indicate better visualization. T2∗2D and T2∗3D were strongly superior to other sequences and significantly superior in terms of fiducial marker definition. T2∗3D was slightly superior to T2∗3D, but this difference was not significant. We recommend that a T2∗3D examination is initially performed, followed by a T2∗2D sequence if necessary.

MRI-alone radiation therapy planning for prostate cancer: Automatic fiducial marker detection.

The feasibility of radiation therapy treatment planning using substitute computed tomography (sCT) generated from magnetic resonance images (MRIs) has been demonstrated by a number of research groups. One challenge with an MRI-alone workflow is the accurate identification of intraprostatic gold fiducial markers, which are frequently used for prostate localization prior to each dose delivery fraction. This paper investigates a template-matching approach for the detection of these seeds in MRI. Two different gradient echo T1 and T2* weighted MRI sequences were acquired from fifteen prostate cancer patients and evaluated for seed detection. For training, seed templates from manual contours were selected in a spectral clustering manifold learning framework. This aids in clustering "similar" gold fiducial markers together. The marker with the minimum distance to a cluster centroid was selected as the representative template of that cluster during training. During testing, Gaussian mixture modeling followed by a Markovian model was used in automatic detection of the probable candidates. The probable candidates were rigidly registered to the templates identified from spectral clustering, and a similarity metric is computed for ranking and detection. A fiducial detection accuracy of 95% was obtained compared to manual observations. Expert radiation therapist observers were able to correctly identify all three implanted seeds on 11 of the 15 scans (the proposed method correctly identified all seeds on 10 of the 15). An novel automatic framework for gold fiducial marker detection in MRI is proposed and evaluated with detection accuracies comparable to manual detection. When radiation therapists are unable to determine the seed location in MRI, they refer back to the planning CT (only available in the existing clinical framework); similarly, an automatic quality control is built into the automatic software to ensure that all gold seeds are either correctly detected or a warning is raised for further manual intervention.

Marker Detection in Electron Tomography: A Comparative Study.

We conducted a comparative study of three widely used algorithms for the detection of fiducial markers in electron microscopy images. The algorithms were applied to four datasets from different sources. For the purpose of obtaining comparable results, we introduced figures of merit and implemented all three algorithms in a unified code base to exclude software-specific differences. The application of the algorithms revealed that none of the three algorithms is superior to the others in all cases. This leads to the conclusion that the choice of a marker detection algorithm highly depends on the properties of the dataset to be analyzed, even within the narrowed domain of electron tomography.