Localization and Segmentation of 3D Intervertebral Discs in MR Images by Data Driven Estimation

This paper addresses the problem of fully-automatic localization and segmentation of 3D intervertebral discs (IVDs) from MR images. Our method contains two steps, where we first localize the center of each IVD, and then segment IVDs by classifying image pixels around each disc center as foreground (disc) or background. The disc localization is done by estimating the image displacements from a set of randomly sampled 3D image patches to the disc center. The image displacements are estimated by jointly optimizing the training and test displacement values in a data-driven way, where we take into consideration both the training data and the geometric constraint on the test image. After the disc centers are localized, we segment the discs by classifying image pixels around disc centers as background or foreground. The classification is done in a similar data-driven approach as we used for localization, but in this segmentation case we are aiming to estimate the foreground/background probability of each pixel instead of the image displacements. In addition, an extra neighborhood smooth constraint is introduced to enforce the local smoothness of the label field. Our method is validated on 3D T2-weighted turbo spin echo MR images of 35 patients from two different studies. Experiments show that compared to state of the art, our method achieves better or comparable results. Specifically, we achieve for localization a mean error of 1.6-2.0 mm, and for segmentation a mean Dice metric of 85%-88% and a mean surface distance of 1.3-1.4 mm.

Consensus and differences in primary radiotherapy for localized and locally advanced prostate cancer in Switzerland: A survey on patterns of practice

INTRODUCTION External beam radiotherapy (EBRT), with or without androgen deprivation therapy (ADT), is an established treatment option for nonmetastatic prostate cancer. Despite high-level evidence from several randomized trials, risk group stratification and treatment recommendations vary due to contradictory or inconclusive data, particularly with regard to EBRT dose prescription and ADT duration. Our aim was to investigate current patterns of practice in primary EBRT for prostate cancer in Switzerland. MATERIALS AND METHODS Treatment recommendations on EBRT and ADT for localized and locally advanced prostate cancer were collected from 23 Swiss radiation oncology centers. Written recommendations were converted into center-specific decision trees, and analyzed for consensus and differences using a dedicated software tool. Additionally, specific radiotherapy planning and delivery techniques from the participating centers were assessed. RESULTS The most commonly prescribed radiation dose was 78 Gy (range 70-80 Gy) across all risk groups. ADT was recommended for intermediate-risk patients for 6 months in over 80 % of the centers, and for high-risk patients for 2 or 3 years in over 90 % of centers. For recommendations on combined EBRT and ADT treatment, consensus levels did not exceed 39 % in any clinical scenario. Arc-based intensity-modulated radiotherapy (IMRT) is implemented for routine prostate cancer radiotherapy by 96 % of the centers. CONCLUSION Among Swiss radiation oncology centers, considerable ranges of radiotherapy dose and ADT duration are routinely offered for localized and locally advanced prostate cancer. In the vast majority of cases, doses and durations are within the range of those described in current evidence-based guidelines.