Search

We present a novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research. In total, we recorded 6 hours of traffic scenarios at 10–100 Hz using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras, a Velodyne 3D laser scanner and a high-precision GPS/IMU inertial navigation system. The scenarios are diverse, capturing real-world traffic situations, and range from freeways over rural areas to inner-city scenes with many static and dynamic objects. Our data is calibrated, synchronized and timestamped, and we provide the rectified and raw image sequences. Our dataset also contains object labels in the form of 3D tracklets, and we provide online benchmarks for stereo, optical flow, object detection and other tasks. This paper describes our recording platform, the data format and the utilities that we provide. [ABSTRACT FROM AUTHOR]

Background: The standard treatment of high grade gliomas (HGG) involves maximal neuro-surgical debulking, followed by post-operative radiotherapy, with or without concurrent chemotherapy, depending on histologic grade. Despite this aggressive strategy, there are few long-term survivors. Proton magnetic resonance spectroscopy (MRS) is a non-invasive imaging method that can monitor metabolic changes in brain tumours. To date there is little data concerning the prognostic significance of the evolving spectral alterations during a course of radiotherapy. Materials: We report herein a prospective study of patients with HGGs undergoing post-operative radiotherapy. Fourteen consecutively eligible patients with a confirmed histologic diagnosis of malignant glioma and completion of all required MRS imaging were included in this study. All patients had MRS imaging prior to radiotherapy, at week 4 of radiotherapy, and 2 months post-treatment. T1 and T2 weighted images as well as post-gadolinium multi-voxel proton MRS images were obtained. Normalized (tumour metabolite/normal brain metabolite) levels of choline, NAA, creatine, lipid and lactate were calculated. Kaplan-Meier (KM) curves of progression-free and overall survival were constructed based on the evolving patterns of metabolite changes over the course of the images. Results: The mean tumour choline/NAA ratio decreased over the course of therapy, with a reduction observed between the baseline and post-radiotherapy studies (1.91 vs. 1.29, P=0.049). A similar decrease was identified with the mean normalized choline ratio, with a highly significant difference observed between the baseline and post-radiation images (1.61 vs. 0.96, P=0.001). Patients who exhibited more than 40% decrease in normalized choline between the week 4 and post-radiotherapy studies were associated with unfavourable survival (logrank test, P=0.003) and disease progression (logrank test, P=0.012). The Lactate/NAA ratio and the 4th week of radiotherapy and the change in normalized choline/creatine between baseline and week 4 of radiotherapy were also predictive of outcome suggesting the possibility of adaptive, response-based radiation treatment. Patients with two or more poor prognostic MRS indices had a significantly shorter progression-free survival compared with those with zero or one poor indices, with 15% and 68% at 1 year, respectively (logrank test, P=0.045). Conclusion: The evolving pattern of spectral changes over the course of radiotherapy, in particular those associated with choline-containing compounds, appears to be prognostic of tumour response and outcome. Based on our data, a decision point may exist in the mid course of radical radiotherapy, at which time consideration of the choline levels could indicate the extent of radiotherapeutic response, thus allowing for individualized treatment modification. [ABSTRACT FROM AUTHOR]