Online updating of context‐aware landmark detectors for prostate localization in daily treatment CT images

Abstract

Purpose: In image guided radiation therapy, it is crucial to fast and accurately localize the prostate in the daily treatment images. To this end, the authors propose an online update scheme for landmarkguided prostate segmentation, which can fully exploit valuable patient-specific information contained in the previous treatment images and can achieve improved performance in landmark detection and prostate segmentation. Methods: To localize the prostate in the daily treatment images, the authors first automatically detect six anatomical landmarks on the prostate boundary by adopting a context-aware landmark detection method. Specifically, in this method, a two-layer regression forest is trained as a detector for each target landmark. Once all the newly detected landmarks from new treatment images are reviewed or adjusted (if necessary) by clinicians, they are further included into the training pool as new patient-specific information to update all the two-layer regression forests for the next treatment day. As more and more treatment images of the current patient are acquired, the two-layer regression forests can be continually updated by incorporating the patient-specific information into the training procedure. After all target landmarks are detected, a multiatlas random sample consensus (multiatlas RANSAC) method is used to segment the entire prostate by fusing multiple previously segmented prostates of the current patient after they are aligned to the current treatment image. Subsequently, the segmented prostate of the current treatment image is again reviewed (or even adjusted if needed) by clinicians before including it as a new shape example into the prostate shape dataset for helping localize the entire prostate in the next treatment image. Results: The experimental results on 330 images of 24 patients show the effectiveness of the authors' proposed online update scheme in improving the accuracies of both landmark detection and prostate segmentation. Besides, compared to the other state-of-the-art prostate segmentation methods, the authors' method achieves the best performance. Conclusions: By appropriate use of valuable patient-specific information contained in the previous treatment images, the authors' proposed online update scheme can obtain satisfactory results for both landmark detection and prostate segmentation. C 2015 American Association of Physicists in Medicine. [http://dx

Context-Aware Medical Systems within Healthcare Environments: A Systematic Scoping Review to Identify Subdomains and Significant Medical Contexts

“…Another application of context awareness in disease management is the system by Dai et al, who improved prostate segmentation during image-guided radiation therapy using patient-specific contexts obtained from their prior images. The system was tested on 24 patients, and they found that using prior personalized image data led to improved prostate segmentation accuracy, as defined by the dice ratio and average surface distance [30]. As disease management is quite specific to the condition of interest and the patient's ability to follow what are often complex guidelines, context-aware disease management systems have the potential to improve patient health by helping them complete the necessary daily tasks required to manage their disease.…”

“…Many papers have relied on machine learning methods, which would require the inputted data to be similar when using interoperable data across systems [23,30]. That being said, manual labelling of training data to generate significantly large high-quality datasets to create models that predict new contexts may not be practical at scale or when trying to infer many everyday contexts.…”

Attaining Human-Level Performance with Atlas Location Autocontext for Anatomical Landmark Detection in 3D CT Data

“…As our baseline for comparison, we follow the decision forest approach of Dabbah et al [4] for which we have a mature C++ implementation. Until the recent popular adoption of CNN solutions, decision forests and their variants were the gold standard for the task of anatomical landmark detection [18,27,27,5,10,12,40,39]. In brief, a decision forest is trained to perform voxelwise classification across n + 1 classes, where there are n landmarks and 1 background class.…”