Novel multistage three-dimensional medical image segmentation: methodology and validation

Machine Vision Methods, Natural Language Processing, and Machine Learning Algorithms for Automated Dispersion Plot Analysis and Chemical Identification from Complex Mixtures

Gas-phase trace chemical detection techniques such as ion mobility spectrometry (IMS) and differential mobility spectrometry (DMS) can be used in many settings, such as evaluating the health condition of patients or detecting explosives at airports. These devices separate chemical compounds in a mixture and provide information to identify specific chemical species of interest. Further, these types of devices operate well in both controlled lab environments and in-field applications. Frequently, the commercial versions of these devices are highly tailored for niche applications (e.g., explosives detection) because of the difficulty involved in reconfiguring instrumentation hardware and data analysis software algorithms. In order for researchers to quickly adapt these tools for new purposes and broader panels of chemical targets, it is critical to develop new algorithms and methods for generating libraries of these sensor responses. Microelectromechanical system (MEMS) technology has been used to fabricate DMS devices that miniaturize the platforms for easier deployment; however, concurrent advances in advanced data analytics are lagging. DMS generates complex three-dimensional dispersion plots for both positive and negative ions in a mixture. Although simple spectra of single chemicals are straightforward to interpret (both visually and via algorithms), it is exceedingly challenging to interpret dispersion plots from complex mixtures with many chemical constituents. This study uses image processing and computer vision steps to automatically identify features from DMS dispersion plots. We used the bag-of-words approach adapted from natural language processing and information retrieval to cluster and organize these features. Finally, a support vector machine (SVM) learning algorithm was trained using these features in order to detect and classify specific compounds in these represented conceptualized data outputs. Using this approach, we successfully maintain a high level of correct chemical identification, even when a gas mixture increases in complexity with interfering chemicals present.

Bidirectional local distance measure for comparing segmentations

PURPOSE

To accurately quantify the local difference between two contour surfaces in two- or three-dimensional space, a new, robust point-to-surface distance measure is developed.

METHODS

To evaluate and visualize the local surface differences, point-to-surface distance measures have been utilized. However, previously well-known point-to-surface distance measures have critical shortfalls. Previous distance measures termed "normal distance (ND)," "radial distance," or "minimum distance (MD)" can report erroneous results at certain points where the surfaces under comparison meet certain conditions. These skewed results are due to the monodirectional characteristics of these methods. ComGrad distance was also proposed to overcome asymmetric characteristics of previous point-to-surface distance measures, but their critical incapability of dealing with a fold or concave contours. In this regard, a new distance measure termed the bidirectional local distance (BLD) is proposed which minimizes errors of the previous methods by taking into account the bidirectional characteristics with the forward and backward directions. BLD measure works through three steps which calculate the maximum value between the forward minimum distance (FMinD) and the backward maximum distance (BMaxD) at each point. The first step calculates the FMinD as the minimum distance to the test surface from a point, p(ref) on the reference surface. The second step involves calculating the minimum distances at every point on the test surface to the reference surface. During the last step, the BMaxD is calculated as the maximum distance among the minimum distances found at p(ref) on the reference surface. Tests are performed on two- and three-dimensional artificial contour sets in comparison to MD and ND measure techniques. Three-dimensional tests performed on actual liver and head-and-neck cancer patients.

RESULTS

The proposed BLD measure provides local distances between segmentations, even in situations where ND, MD, or ComGrad measures fail. In particular, the standard deviation measure is not distorted at certain geometries where ND, MD, and ComGrad measures report skewed results.

CONCLUSIONS

The proposed measure provides more reliable statistics on contour comparisons. From the statistics, specific local and global distances can be extracted. Bidirectional local distance is a reliable distance measure in comparing two- or three-dimensional organ segmentations.

Magnetic navigation for thoracic aortic stent-graft deployment using ultrasound image guidance

We propose a system for thoracic aortic stent-graft deployment that employs a magnetic tracking system (MTS) and intraoperative ultrasound (US). A preoperative plan is first performed using a general public utilities-accelerated cardiac modeling method to determine the target position of the stent-graft. During the surgery, an MTS is employed to track sensors embedded in the catheter, cannula, and the US probe, while a fiducial landmark based registration is used to map the patient's coordinate to the image coordinate. The surgical target is tracked in real time via a calibrated intraoperative US image. Under the guidance of the MTS integrated with the real-time US images, the stent-graft can be deployed to the target position without the use of ionizing radiation. This navigation approach was validated using both phantom and animal studies. In the phantom study, we demonstrate a US calibration accuracy of 1.5 ± 0.47 mm, and a deployment error of 1.4 ± 0.16 mm. In the animal study, we performed experiments on five porcine subjects and recorded fiducial, target, and deployment errors of 2.5 ± 0.32, 4.2 ± 0.78, and 2.43 ± 0.69 mm, respectively. These results demonstrate that delivery and deployment of thoracic stent-graft under MTS-guided navigation using US imaging is feasible and appropriate for clinical application.

Spatially adaptive active contours: a semi-automatic tumor segmentation framework

PURPOSE

Tumor segmentation constitutes a crucial step in simulating cancer growth and response to therapy. Incorporation of imaging data individualizes the simulation and assists clinical correlation with the predicted outcome. We adapted snakes to improve tumor segmentation including difficult cases with inherently inhomogeneous structure and poorly defined margins.

METHODS

Snakes are flexible curves, based on the parameter-controlled deformation of an initial user-defined contour toward the boundary of the desired object, through the minimization of a suitable energy function. Although parameter-adjustment can yield fairly good results in homogeneous regions, traditional snakes often fail to provide an accurate segmentation result when both rigid and very elastic behavior is needed simultaneously to delineate the true outline of the tumor. We developed and tested a spatially adaptive active contour technique by introducing local snake bending, to improve traditional snakes performance for segmenting tumors. The key point of our method is the use of adaptable snake parameters, instead of constant ones, to adjust the bending of the curve according to the local edge characteristics. Our algorithm discriminates image regions according to underlying image features, such as gradient magnitude and corner strength. More specifically, it assigns each region a different "localized" set of parameters, one corresponding to a very flexible snake, and the other corresponding to a very rigid one, according to the local image characteristics.

RESULTS

Qualitative results on more than 150 real MR images, as well as quantitative validation based on agreement with an expert clinician's annotations of the true tumor boundaries, demonstrate our approach is highly efficient compared to traditional active contours and region growing. Due to the use of adaptable parameters in the snake evolution process, our approach outperforms the other two methods, and consistently follows an expert's annotations. Statistical tests indicated significant difference between the results produced by our approach and two other algorithms traditional snakes and region growing, while multiple comparison showed that our method consistently outperformed those algorithms, with an average overlap of 89%, over the entire data set, while traditional snakes were at 82.5% and region growing at 59.2%. Furthermore, we performed several tests that demonstrate our method's stability to different initial contours, as well as, to lower resolution images.

CONCLUSION

Our adaptive snake algorithm can spatially adapt to diverse image characteristics, producing outlines that mimic the true tumor boundaries. Results in MR datasets are very close to an expert clinician's intuition about the tumor boundaries.