This paper shows how to significantly accelerate cone-beam CT reconstruction and 3D deformable image registration using the stream-processing model. We describe data-parallel designs for the Feldkamp, Davis and Kress (FDK) reconstruction algorithm, and the demons deformable registration algorithm, suitable for use on a commodity graphics processing unit. The streaming versions of these algorithms are implemented using the Brook programming environment and executed on an NVidia 8800 GPU. Performance results using CT data of a preserved swine lung indicate that the GPU-based implementations of the FDK and demons algorithms achieve a substantial speedup--up to 80 times for FDK and 70 times for demons when compared to an optimized reference implementation on a 2.8 GHz Intel processor. In addition, the accuracy of the GPU-based implementations was found to be excellent. Compared with CPU-based implementations, the RMS differences were less than 0.1 Hounsfield unit for reconstruction and less than 0.1 mm for deformable registration.

Purpose The use of intensity-modulated radiation therapy (IMRT) in the treatment of soft tissue sarcoma (STS) of the extremity is increasing, but no large-scale direct comparison has been reported between conventional external-beam radiation therapy (EBRT) and IMRT. Methods Between January 1996 and December 2010, 319 consecutive adult patients with primary nonmetastatic extremity STS were treated with limb-sparing surgery and adjuvant radiotherapy (RT) at a single institution. Conventional EBRT was used in 154 patients and IMRT in 165 with similar dosing schedules. Median follow-up time for the cohort was 58 months. Results Treatment groups were comparable in terms of tumor location, histology, tumor size, depth, and use of chemotherapy. Patients treated with IMRT were older (P = .08), had more high-grade lesions (P = .05), close (< 1 mm) or positive margins (P = .04), preoperative radiation (P < .001), and nerve manipulation (P = .04). Median follow-up was 90 months for patients treated with conventional EBRT and 42 months for patients treated with IMRT. On multivariable analysis adjusting for patient age and tumor size, IMRT retained significance as an independent predictor of reduced LR (hazard ratio = 0.46; 95% CI, 0.24 to 0.89; P = .02). Conclusion Despite a preponderance of higher-risk features (especially close/positive margin) in the IMRT group, IMRT was associated with significantly reduced local recurrence compared with conventional EBRT for primary STS of the extremity.

No abstract

Stereotactic body radiation therapy (SBRT) has demonstrated high local control rates in early stage non-small cell lung cancer patients who are not ideal surgical candidates. However, distant failure after SBRT is still common. For patients at high risk of early distant failure after SBRT treatment, additional systemic therapy may reduce the risk of distant relapse and improve overall survival. Therefore, a strategy that can correctly stratify patients at high risk of failure is needed. The field of radiomics holds great potential in predicting treatment outcomes by using high-throughput extraction of quantitative imaging features. The construction of predictive models in radiomics is typically based on a single objective such as overall accuracy or the area under the curve (AUC). However, because of imbalanced positive and negative events in the training datasets, a single objective may not be ideal to guide model construction. To overcome these limitations, we propose a multi-objective radiomics model that simultaneously considers sensitivity and specificity as objective functions. To design a more accurate and reliable model, an iterative multi-objective immune algorithm (IMIA) was proposed to optimize these objective functions. The multi-objective radiomics model is more sensitive than the single-objective model, while maintaining the same levels of specificity and AUC. The IMIA performs better than the traditional immune-inspired multi-objective algorithm.

No abstract