Using in vivo EPID images to detect and quantify patient anatomy changes with gradient dose segmented analysis.

PURPOSE: To investigate the utility of gradient dose segmented analysis (GDSA) in combination with in vivo electronic portal imaging device (EPID) images to predict changes in the PTV mean dose for patient cases. Also, we use the GDSA to retrospectively analyze patients treated in our clinic to assess deviations for different treatment sites and use time-series data to observe any day-to-day changes. METHODS: In vivo EPID transit images acquired on the Varian Halcyon were analyzed for simulated errors in a phantom, including gas bubbles, weight loss, patient shifts, and an arm erroneously in the field. GDSA threshold parameters were tuned to maximize the coefficient of determination (R2 ) between GDSA metrics and the change in the PTV mean dose (Dmean ) as estimated in a treatment planning system (TPS). Similarly for a gamma analysis, the gamma criteria were adjusted to maximize R2 between gamma pass rate and the change in the PTV Dmean from the TPS. The predictive accuracy of these models was tested on patient data measuring the mean and standard deviation of the difference in the predicted change in PTV Dmean and the change in PTV Dmean measured in the TPS. This analysis was extended retrospectively for every patient treated over a 23-month period (n = 852 patients) to assess the range of expected deviations that occurred during routine clinical operation, as well as to assess any differences between treatment sites. Grouping patients treated on the same day, a time-series analysis was performed to determine if GDSA metrics could add value in tracking machine behavior over time. RESULTS: For the phantom data, analyzing the errors, except for shifts, and comparing the change in PTV Dmean and GDSA mean, a maximal R2  = 0.90 was found for a dose threshold of 5% and gradient threshold of 3 mm. For the gamma approach a linear fit between the gamma pass rate for change in the PTV Dmean was assessed for different criteria, using the same image data. A maximal, R2  = 0.84 was found for a gamma criteria of 3%/3 mm, 45% lower dose threshold. For patient data, the predictive accuracy of the change in the PTV Dmean using the GDSA approach and the gamma approach was 0.09 ± 0.98 % and - 0.65 ± 2.21%, respectively. Comparing the two approaches the accuracy did not significantly differ (P = 0.38), whereas the precision of the GDSA prediction is significantly less (P < 0.001). The dosimetric impact of shifts was not detectable with either the GDSA or gamma approach. Analysis of all patients treated over 23 months showed that over 95% of fractions treated deviated from the first fraction by 2% or less. Deviations> 2% occurred most frequently for the later fractions of head-and-neck and lung treatments. Additionally, averaging the GDSA mean metric over all patients on a given treatment day showed that changes in the machine output on the order of 1% could be identified. CONCLUSIONS: GDSA of in vivo EPID images is a useful technique for monitoring patient changes during the course of treatment, particularly weight loss and tumor shrinkage. The GDSA mean provides a quantitative estimate of the change in the PTV Dmean , giving a simple, quantitative metric by which to flag patients with clinically meaningful deviations in treatment. Averaging the GDSA metric over all patients treated on a given day and tracking daily variations can also provide a flag for any systematic deviations in treatment due to machine performance.

Automatic classification of tissues on pelvic MRI based on relaxation times and support vector machine.

Tissue segmentation and classification in MRI is a challenging task due to a lack of signal intensity standardization. MRI signal is dependent on the acquisition protocol, the coil profile, the scanner type, etc. While we can compute quantitative physical tissue properties independent of the hardware and the sequence parameters, it is still difficult to leverage these physical properties to segment and classify pelvic tissues. The proposed method integrates quantitative MRI values (T1 and T2 relaxation times and pure synthetic weighted images) and machine learning (Support Vector Machine (SVM)) to segment and classify tissues in the pelvic region, i.e.: fat, muscle, prostate, bone marrow, bladder, and air. Twenty-two men with a mean age of 30±14 years were included in this prospective study. The images were acquired with a 3 Tesla MRI scanner. An inversion recovery-prepared turbo spin echo sequence was used to obtain T1-weighted images at different inversion times with a TR of 14000 ms. A 32-echo spin echo sequence was used to obtain the T2-weighted images at different echo times with a TR of 5000 ms. T1 and T2 relaxation times, synthetic T1- and T2-weighted images and anatomical probabilistic maps were calculated and used as input features of a SVM for segmenting and classifying tissues within the pelvic region. The mean SVM classification accuracy across subjects was calculated for the different tissues: prostate (94.2%), fat (96.9%), muscle (95.8%), bone marrow (91%) and bladder (82.1%) indicating an excellent classification performance. However, the segmentation and classification for air (within the rectum) may not always be successful (mean SVM accuracy 47.5%) due to the lack of air data in the training and testing sets. Our findings suggest that SVM can reliably segment and classify tissues in the pelvic region.

Automatic deformable PET/MRI registration for preclinical studies based on B-splines and non-linear intensity transformation.

PET images deliver functional data, whereas MRI images provide anatomical information. Merging the complementary information from these two modalities is helpful in oncology. Alignment of PET/MRI images requires the use of multi-modal registration methods. Most of existing PET/MRI registration methods have been developed for humans and few works have been performed for small animal images. We proposed an automatic tool allowing PET/MRI registration for pre-clinical study based on a two-level hierarchical approach. First, we applied a non-linear intensity transformation to the PET volume to enhance. The global deformation is modeled by an affine transformation initialized by a principal component analysis. A free-form deformation based on B-splines is then used to describe local deformations. Normalized mutual information is used as voxel-based similarity measure. To validate our method, CT images acquired simultaneously with the PET on tumor-bearing mice were used. Results showed that the proposed algorithm outperformed affine and deformable registration techniques without PET intensity transformation with an average error of 0.72 ± 0.44 mm. The optimization time was reduced by 23% due to the introduction of robust initialization. In this paper, an automatic deformable PET-MRI registration algorithm for small animals is detailed and validated. Graphical abstract ᅟ.