skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: TU-FG-209-12: Treatment Site and View Recognition in X-Ray Images with Hierarchical Multiclass Recognition Models

Abstract

Purpose: To investigate an approach of automatically recognizing anatomical sites and imaging views (the orientation of the image acquisition) in 2D X-ray images. Methods: A hierarchical (binary tree) multiclass recognition model was developed to recognize the treatment sites and views in x-ray images. From top to bottom of the tree, the treatment sites are grouped hierarchically from more general to more specific. Each node in the hierarchical model was designed to assign images to one of two categories of anatomical sites. The binary image classification function of each node in the hierarchical model is implemented by using a PCA transformation and a support vector machine (SVM) model. The optimal PCA transformation matrices and SVM models are obtained by learning from a set of sample images. Alternatives of the hierarchical model were developed to support three scenarios of site recognition that may happen in radiotherapy clinics, including two or one X-ray images with or without view information. The performance of the approach was tested with images of 120 patients from six treatment sites – brain, head-neck, breast, lung, abdomen and pelvis – with 20 patients per site and two views (AP and RT) per patient. Results: Given two images in knownmore » orthogonal views (AP and RT), the hierarchical model achieved a 99% average F1 score to recognize the six sites. Site specific view recognition models have 100 percent accuracy. The computation time to process a new patient case (preprocessing, site and view recognition) is 0.02 seconds. Conclusion: The proposed hierarchical model of site and view recognition is effective and computationally efficient. It could be useful to automatically and independently confirm the treatment sites and views in daily setup x-ray 2D images. It could also be applied to guide subsequent image processing tasks, e.g. site and view dependent contrast enhancement and image registration. The senior author received research grants from ViewRay Inc. and Varian Medical System.« less

Authors:
; ;  [1]
  1. Washington University in St Louis, St Louis, MO (United States)
Publication Date:
OSTI Identifier:
22654013
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 43; Journal Issue: 6; Other Information: (c) 2016 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; 61 RADIATION PROTECTION AND DOSIMETRY; BIOMEDICAL RADIOGRAPHY; CALCULATION METHODS; IMAGE PROCESSING; MAMMARY GLANDS; PATIENTS; X RADIATION

Citation Formats

Chang, X, Mazur, T, and Yang, D. TU-FG-209-12: Treatment Site and View Recognition in X-Ray Images with Hierarchical Multiclass Recognition Models. United States: N. p., 2016. Web. doi:10.1118/1.4957582.
Chang, X, Mazur, T, & Yang, D. TU-FG-209-12: Treatment Site and View Recognition in X-Ray Images with Hierarchical Multiclass Recognition Models. United States. doi:10.1118/1.4957582.
Chang, X, Mazur, T, and Yang, D. 2016. "TU-FG-209-12: Treatment Site and View Recognition in X-Ray Images with Hierarchical Multiclass Recognition Models". United States. doi:10.1118/1.4957582.
@article{osti_22654013,
title = {TU-FG-209-12: Treatment Site and View Recognition in X-Ray Images with Hierarchical Multiclass Recognition Models},
author = {Chang, X and Mazur, T and Yang, D},
abstractNote = {Purpose: To investigate an approach of automatically recognizing anatomical sites and imaging views (the orientation of the image acquisition) in 2D X-ray images. Methods: A hierarchical (binary tree) multiclass recognition model was developed to recognize the treatment sites and views in x-ray images. From top to bottom of the tree, the treatment sites are grouped hierarchically from more general to more specific. Each node in the hierarchical model was designed to assign images to one of two categories of anatomical sites. The binary image classification function of each node in the hierarchical model is implemented by using a PCA transformation and a support vector machine (SVM) model. The optimal PCA transformation matrices and SVM models are obtained by learning from a set of sample images. Alternatives of the hierarchical model were developed to support three scenarios of site recognition that may happen in radiotherapy clinics, including two or one X-ray images with or without view information. The performance of the approach was tested with images of 120 patients from six treatment sites – brain, head-neck, breast, lung, abdomen and pelvis – with 20 patients per site and two views (AP and RT) per patient. Results: Given two images in known orthogonal views (AP and RT), the hierarchical model achieved a 99% average F1 score to recognize the six sites. Site specific view recognition models have 100 percent accuracy. The computation time to process a new patient case (preprocessing, site and view recognition) is 0.02 seconds. Conclusion: The proposed hierarchical model of site and view recognition is effective and computationally efficient. It could be useful to automatically and independently confirm the treatment sites and views in daily setup x-ray 2D images. It could also be applied to guide subsequent image processing tasks, e.g. site and view dependent contrast enhancement and image registration. The senior author received research grants from ViewRay Inc. and Varian Medical System.},
doi = {10.1118/1.4957582},
journal = {Medical Physics},
number = 6,
volume = 43,
place = {United States},
year = 2016,
month = 6
}
  • Purpose: To investigate the method to automatically recognize the treatment site in the X-Ray portal images. It could be useful to detect potential treatment errors, and to provide guidance to sequential tasks, e.g. automatically verify the patient daily setup. Methods: The portal images were exported from MOSAIQ as DICOM files, and were 1) processed with a threshold based intensity transformation algorithm to enhance contrast, and 2) where then down-sampled (from 1024×768 to 128×96) by using bi-cubic interpolation algorithm. An appearance-based vector space model (VSM) was used to rearrange the images into vectors. A principal component analysis (PCA) method was usedmore » to reduce the vector dimensions. A multi-class support vector machine (SVM), with radial basis function kernel, was used to build the treatment site recognition models. These models were then used to recognize the treatment sites in the portal image. Portal images of 120 patients were included in the study. The images were selected to cover six treatment sites: brain, head and neck, breast, lung, abdomen and pelvis. Each site had images of the twenty patients. Cross-validation experiments were performed to evaluate the performance. Results: MATLAB image processing Toolbox and scikit-learn (a machine learning library in python) were used to implement the proposed method. The average accuracies using the AP and RT images separately were 95% and 94% respectively. The average accuracy using AP and RT images together was 98%. Computation time was ∼0.16 seconds per patient with AP or RT image, ∼0.33 seconds per patient with both of AP and RT images. Conclusion: The proposed method of treatment site recognition is efficient and accurate. It is not sensitive to the differences of image intensity, size and positions of patients in the portal images. It could be useful for the patient safety assurance. The work was partially supported by a research grant from Varian Medical System.« less
  • DBI (diazepam-binding inhibitor) is a putative neuromodulatory peptide isolated from rat brain that acts on ..gamma..-aminobutyric acid-benzodiazepine-Cl/sup -/ ionosphore receptor complex inducing ..beta..-carboline-like effects. The authors used a cDNA probe complementary to DBI mRNA and a specific antibody for rat DBI to study in rat brain how the dynamic state of DBI can be affected after protected (three times a day for 10 days) treatment with diazepam and chlordiazepoxide by oral gavage. Both the content of DBI and DBI mRNA increased in the cerebellum and cerebral cortex but failed to change in the hippocampus and striatum of rats receiving thismore » protracted benzodiazepine treatment. Acute treatment with diazepam did not affect the dynamic state of brain DBI. An antibody was raised against a biologically active octadecaneuropeptide derived from the tryptic digestion of DBI. The combined HPLC/RIA analysis of rat cerebellar extracts carried out with this antibody showed that multiple molecular forms of the octadecaneuropeptide-like reactivity are present and all of them are increased in rats receiving repeated daily injections of diazepam. It is inferred that tolerance to benzodiazepines in associated with an increase in the turnover rate of DBI, which may be responsible for the ..gamma..-aminobutyric acid receptor desensitization that occurs after protracted benzodiazepine administration.« less
  • Purpose: Accurate delineation of organs at risk (OARs) is a precondition for intensity modulated radiation therapy. However, manual delineation of OARs is time consuming and prone to high interobserver variability. Because of image artifacts and low image contrast between different structures, however, the number of available approaches for autosegmentation of structures in the head-neck area is still rather low. In this project, a new approach for automated segmentation of head-neck CT images that combine the robustness of multiatlas-based segmentation with the flexibility of geodesic active contours and the prior knowledge provided by statistical appearance models is presented. Methods: The presentedmore » approach is using an atlas-based segmentation approach in combination with label fusion in order to initialize a segmentation pipeline that is based on using statistical appearance models and geodesic active contours. An anatomically correct approximation of the segmentation result provided by atlas-based segmentation acts as a starting point for an iterative refinement of this approximation. The final segmentation result is based on using model to image registration and geodesic active contours, which are mutually influencing each other. Results: 18 CT images in combination with manually segmented labels of parotid glands and brainstem were used in a leave-one-out cross validation scheme in order to evaluate the presented approach. For this purpose, 50 different statistical appearance models have been created and used for segmentation. Dice coefficient (DC), mean absolute distance and max. Hausdorff distance between the autosegmentation results and expert segmentations were calculated. An average Dice coefficient of DC = 0.81 (right parotid gland), DC = 0.84 (left parotid gland), and DC = 0.86 (brainstem) could be achieved. Conclusions: The presented framework provides accurate segmentation results for three important structures in the head neck area. Compared to a segmentation approach based on using multiple atlases in combination with label fusion, the proposed hybrid approach provided more accurate results within a clinically acceptable amount of time.« less
  • The problem of the quantitative description of multiscale structure in interstellar cloud complexes and gravitational collapse calculations is considered, emphasizing the recognition and characterization of hierarchical fragmentation structure. The response of the two-point correlation function to a variety of analytical models for density structure is discussed for simple clustering of pointlike clouds to more complex models involving clouds with a distribution of sizes and densities and hierarchical substructure. By expressing the density distribution as the superposition of individual clouds, it is shown that the correlation function generates two types of terms: those involving each cloud's density convolved with itself andmore » those involving pairs of different clouds. Major distortion of the correlation function are introduced by the presence of any image features with size scales a significant fraction of the image size. 42 refs.« less
  • Hierarchical carbon encapsulated tin (Sn@C) embedded graphene nanosheet (GN) composites (Sn@C–GNs) have been successfully fabricated via a simple and scalable one-step chemical vapor deposition (CVD) procedure. The GN supported Sn@C core–shell structures consist of a crystalline tin core, which is thoroughly covered by a carbon shell and more interestingly, extra voids are present between the carbon shell and the tin core. Synchrotron spectroscopy confirms that the metallic tin core is free of oxidation and the existence of charge redistribution transfer from tin to the carbonaceous materials of the shell, facilitating their intimate contact by chemical bonding and resultant lattice variation.more » The hybrid electrodes of this material exhibit a highly stable and reversible capacity together with an excellent rate capability, which benefits from the improved electrochemical properties of tin provided by the protective carbon matrix, voids and the flexible GN matrices.« less