Automated Lung Segmentation and Image Quality Assessment for Clinical 3D/4D Computed Tomography

A review of automatic lung tumour segmentation in the era of 4DCT

Aim

To review the literature on auto-contouring methods of lung tumour volumes on four-dimensional computed tomography (4DCT).

Background

Manual delineation of lung tumour on 4DCT has been the gold standard in clinical practice. However, it is resource intensive due to the high volume of data which results in longer contouring duration and uncertainties in defining target. Auto-contouring may present as an attractive alternative by decreasing manual inputs required, thus improving the contouring process. This review aims to assess the accuracy, variability and contouring duration of automatic contouring compared with manual contouring in lung cancer on 4DCT datasets.

Materials and methods

A search and review of literature were conducted to identify studies regarding lung tumour contouring on 4DCT. Manual and auto-contours were assessed and compared based on accuracy, variability and contouring duration.

Results

Thirteen studies were included in this review and their results were compared. Accuracy of auto-contours was found to be comparable to manual contours. Auto-contouring resulted in lesser inter-observer variation when compared to manual contouring, however there was no significant reduction in intra-observer variability. Additionally, contouring duration was reduced with auto-contouring although long computation time could present as a bottleneck.

Conclusion

Auto-contouring is reliable and efficient, producing accurate contours with better consistency compared to manual contours. However, manual inputs would still be required both before and after auto-propagation.

Characterization of optical-surface-imaging-based spirometry for respiratory surrogating in radiotherapy

PURPOSE

To provide a comprehensive characterization of a novel respiratory surrogate that uses optical surface imaging (OSI) for accurate tidal volume (TV) measurement, dynamic airflow (TV') calculation, and quantitative breathing pattern (BP) estimation during free breathing (FB), belly breathing (BB), chest breathing (CB), and breath hold (BH).

METHODS

Optical surface imaging, which captures all respiration-induced torso surface motion, was applied to measure respiratory TV, TV', and BP in three common breathing patterns. Eleven healthy volunteers participated in breathing experiments with concurrent OSI-based and conventional spirometric measurements under an institutional review board approved protocol. This OSI-based technique measures dynamic TV from torso volume change (ΔVtorso = TV) in reference to full exhalation and airflow (TV' = dTV/dt). Volume conservation, excluding exchanging air, was applied for OSI-based measurements under negligible pleural pressure variation in FB, BB, and CB. To demonstrate volume conservation, a constant TV was measured during BH while the chest and belly are moving ("pretended" respiration). To assess the accuracy of OSI-based spirometry, a conventional spirometer was used as the standard for both TV and TV'. Using OSI, BP was measured as BP(OSI) = ΔVchest/ΔVtorso and BP can be visualized using BP(SHI) = SHIchest/(SHIchest + SHIbelly), where surface height index (SHI) is defined as the mean vertical distance within a region of interest on the torso surface. A software tool was developed for OSI image processing, volume calculation, and BP visualization, and another tool was implemented for data acquisition using a Bernoulli-type spirometer.

RESULTS

The accuracy of the OSI-based spirometry is -21 ± 33 cm(3) or -3.5% ± 6.3% averaged from 11 volunteers with 76 ± 28 breathing cycles on average in FB. Breathing variations between two separate acquisitions with approximate 30-min intervals are substantial: -1% ± 34% (ranging from -64% to 40%) in TV, 4% ± 20% (ranging from -50% to 26%) in breathing period (T), and -1% ± 34% (ranging from -49% to 44%) in BP. The airflow accuracy and variation (between two exercises) are -1 ± 54 cm(3)/s and -5% ± 30%, respectively. The slope of linear regression between OSI-TV and spirometric TV is 0.93 (R(2) = 0.95) for FB, 0.96 (R(2) = 0.98) for BB, and 0.95 (R(2) = 0.95) for CB. The correlation between the two spirometric measurements is 0.98 ± 0.01. BP increases from BB, FB to CB, while TV increases from FB, BB, to CB. Under BH, 4% volume variation (range) on average was observed.

CONCLUSIONS

The OSI-based technique provides an accurate measurement of tidal volume, airflow rate, and breathing pattern; all affect internal organ motion. This technique can be applied to various breathing patterns, including FB, BB, and CB. Substantial breathing irregularities and irreproducibility were observed and quantified with the OSI-based technique. These breathing parameters are useful to quantify breathing conditions, which could be used for effective tumor motion predictions.

Novel and powerful 3D adaptive crisp active contour method applied in the segmentation of CT lung images

The World Health Organization estimates that 300 million people have asthma, 210 million people have Chronic Obstructive Pulmonary Disease (COPD), and, according to WHO, COPD will become the third major cause of death worldwide in 2030. Computational Vision systems are commonly used in pulmonology to address the task of image segmentation, which is essential for accurate medical diagnoses. Segmentation defines the regions of the lungs in CT images of the thorax that must be further analyzed by the system or by a specialist physician. This work proposes a novel and powerful technique named 3D Adaptive Crisp Active Contour Method (3D ACACM) for the segmentation of CT lung images. The method starts with a sphere within the lung to be segmented that is deformed by forces acting on it towards the lung borders. This process is performed iteratively in order to minimize an energy function associated with the 3D deformable model used. In the experimental assessment, the 3D ACACM is compared against three approaches commonly used in this field: the automatic 3D Region Growing, the level-set algorithm based on coherent propagation and the semi-automatic segmentation by an expert using the 3D OsiriX toolbox. When applied to 40 CT scans of the chest the 3D ACACM had an average F-measure of 99.22%, revealing its superiority and competency to segment lungs in CT images.

A Novel Respiratory Motion Perturbation Model Adaptable to Patient Breathing Irregularities

PURPOSE

To develop a physical, adaptive motion perturbation model to predict tumor motion using feedback from dynamic measurement of breathing conditions to compensate for breathing irregularities.

METHODS AND MATERIALS

A novel respiratory motion perturbation (RMP) model was developed to predict tumor motion variations caused by breathing irregularities. This model contained 2 terms: the initial tumor motion trajectory, measured from 4-dimensional computed tomography (4DCT) images, and motion perturbation, calculated from breathing variations in tidal volume (TV) and breathing pattern (BP). The motion perturbation was derived from the patient-specific anatomy, tumor-specific location, and time-dependent breathing variations. Ten patients were studied, and 2 amplitude-binned 4DCT images for each patient were acquired within 2 weeks. The motion trajectories of 40 corresponding bifurcation points in both 4DCT images of each patient were obtained using deformable image registration. An in-house 4D data processing toolbox was developed to calculate the TV and BP as functions of the breathing phase. The motion was predicted from the simulation 4DCT scan to the treatment 4DCT scan, and vice versa, resulting in 800 predictions. For comparison, noncorrected motion differences and the predictions from a published 5-dimensional model were used.

RESULTS

The average motion range in the superoinferior direction was 9.4 ± 4.4 mm, the average ΔTV ranged from 10 to 248 mm³ (-26% to 61%), and the ΔBP ranged from 0 to 0.2 (-71% to 333%) between the 2 4DCT scans. The mean noncorrected motion difference was 2.0 ± 2.8 mm between 2 4DCT motion trajectories. After applying the RMP model, the mean motion difference was reduced significantly to 1.2 ± 1.8 mm (P=.0018), a 40% improvement, similar to the 1.2 ± 1.8 mm (P=.72) predicted with the 5-dimensional model.

CONCLUSIONS

A novel physical RMP model was developed with an average accuracy of 1.2 ± 1.8 mm for interfraction motion prediction, similar to that of a published lung motion model. This physical RMP was analytically derived and is able to adapt to breathing irregularities. Further improvement of this RMP model is under investigation.

Robust breathing signal extraction from cone beam CT projections based on adaptive and global optimization techniques

We present a study of extracting respiratory signals from cone beam computed tomography (CBCT) projections within the framework of the Amsterdam Shroud (AS) technique. Acquired prior to the radiotherapy treatment, CBCT projections were preprocessed for contrast enhancement by converting the original intensity images to attenuation images with which the AS image was created. An adaptive robust z-normalization filtering was applied to further augment the weak oscillating structures locally. From the enhanced AS image, the respiratory signal was extracted using a two-step optimization approach to effectively reveal the large-scale regularity of the breathing signals. CBCT projection images from five patients acquired with the Varian Onboard Imager on the Clinac iX System Linear Accelerator (Varian Medical Systems, Palo Alto, CA) were employed to assess the proposed technique. Stable breathing signals can be reliably extracted using the proposed algorithm. Reference waveforms obtained using an air bellows belt (Philips Medical Systems, Cleveland, OH) were exported and compared to those with the AS based signals. The average errors for the enrolled patients between the estimated breath per minute (bpm) and the reference waveform bpm can be as low as -0.07 with the standard deviation 1.58. The new algorithm outperformed the original AS technique for all patients by 8.5% to 30%. The impact of gantry rotation on the breathing signal was assessed with data acquired with a Quasar phantom (Modus Medical Devices Inc., London, Canada) and found to be minimal on the signal frequency. The new technique developed in this work will provide a practical solution to rendering markerless breathing signal using the CBCT projections for thoracic and abdominal patients.

Automatic assessment of average diaphragm motion trajectory from 4DCT images through machine learning

To automatically estimate average diaphragm motion trajectory (ADMT) based on four-dimensional computed tomography (4DCT), facilitating clinical assessment of respiratory motion and motion variation and retrospective motion study. We have developed an effective motion extraction approach and a machine-learning-based algorithm to estimate the ADMT. Eleven patients with 22 sets of 4DCT images (4DCT1 at simulation and 4DCT2 at treatment) were studied. After automatically segmenting the lungs, the differential volume-per-slice (dVPS) curves of the left and right lungs were calculated as a function of slice number for each phase with respective to the full-exhalation. After 5-slice moving average was performed, the discrete cosine transform (DCT) was applied to analyze the dVPS curves in frequency domain. The dimensionality of the spectrum data was reduced by using several lowest frequency coefficients (f_v) to account for most of the spectrum energy (Σf_v²). Multiple linear regression (MLR) method was then applied to determine the weights of these frequencies by fitting the ground truth-the measured ADMT, which are represented by three pivot points of the diaphragm on each side. The 'leave-one-out' cross validation method was employed to analyze the statistical performance of the prediction results in three image sets: 4DCT1, 4DCT2, and 4DCT1 + 4DCT2. Seven lowest frequencies in DCT domain were found to be sufficient to approximate the patient dVPS curves (R = 91%-96% in MLR fitting). The mean error in the predicted ADMT using leave-one-out method was 0.3 ± 1.9 mm for the left-side diaphragm and 0.0 ± 1.4 mm for the right-side diaphragm. The prediction error is lower in 4DCT2 than 4DCT1, and is the lowest in 4DCT1 and 4DCT2 combined. This frequency-analysis-based machine learning technique was employed to predict the ADMT automatically with an acceptable error (0.2 ± 1.6 mm). This volumetric approach is not affected by the presence of the lung tumors, providing an automatic robust tool to evaluate diaphragm motion.