Search

Injuries of the spine, and its posterior elements in particular, are a common occurrence in trauma patients, with potentially devastating consequences. Computer-aided detection (CADe) could assist in the detection and classification of spine fractures. Furthermore, CAD could help assess the stability and chronicity of fractures, as well as facilitate research into optimization of treatment paradigms. In this work, we apply deep convolutional networks (ConvNets) for the automated detection of posterior element fractures of the spine. First, the vertebra bodies of the spine with its posterior elements are segmented in spine CT using multi-atlas label fusion. Then, edge maps of the posterior elements are computed. These edge maps serve as candidate regions for predicting a set of probabilities for fractures along the image edges using ConvNets in a 2.5D fashion (three orthogonal patches in axial, coronal and sagittal planes). We explore three different methods for training the ConvNet using 2.5D patches along the edge maps of 'positive', i.e. fractured posterior-elements and 'negative', i.e. non-fractured elements. An experienced radiologist retrospectively marked the location of 55 displaced posterior-element fractures in 18 trauma patients. We randomly split the data into training and testing cases. In testing, we achieve an area-under-the-curve of 0.857. This corresponds to 71% or 81% sensitivities at 5 or 10 false-positives per patient, respectively. Analysis of our set of trauma patients demonstrates the feasibility of detecting posterior-element fractures in spine CT images using computer vision techniques such as deep convolutional networks.

Injuries of the spine, and its posterior elements in particular, are a common occurrence in trauma patients, with potentially devastating consequences. Computer-aided detection (CADe) could assist in the detection and classification of spine fractures. Furthermore, CAD could help assess the stability and chronicity of fractures, as well as facilitate research into optimization of treatment paradigms. In this work, we apply deep convolutional networks (ConvNets) for the automated detection of posterior element fractures of the spine. First, the vertebra bodies of the spine with its posterior elements are segmented in spine CT using multi-atlas label fusion. Then, edge maps of the posterior elements are computed. These edge maps serve as candidate regions for predicting a set of probabilities for fractures along the image edges using ConvNets in a 2.5D fashion (three orthogonal patches in axial, coronal and sagittal planes). We explore three different methods for training the ConvNet using 2.5D patches along the edge maps of 'positive', i.e. fractured posterior-elements and 'negative', i.e. non-fractured elements. An experienced radiologist retrospectively marked the location of 55 displaced posterior-element fractures in 18 trauma patients. We randomly split the data into training and testing cases. In testing, we achieve an area-under-the-curve of 0.857. This corresponds to 71% or 81% sensitivities at 5 or 10 false-positives per patient, respectively. Analysis of our set of trauma patients demonstrates the feasibility of detecting posterior-element fractures in spine CT images using computer vision techniques such as deep convolutional networks.

Automated detection of sclerotic metastases (bone lesions) in Computed Tomography (CT) images has potential to be an important tool in clinical practice and research. State-of-the-art methods show performance of 79 % sensitivity or truepositive (TP) rate, at 10 false-positives (FP) per volume. We design a two-tiered coarse-to-fine cascade framework to first operate a highly sensitive candidate generation system at a maximum sensitivity of ∼92% but with high FP level (∼50 per patient). Regions of interest (ROI) for lesion candidates are generated in this step and function as input for the second tier. In the second tier we generate N 2D views, via scale, random translations, and rotations with respect to each ROI centroid coordinates. These random views are used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign individual probabilities for a new set of N random views that are averaged at each ROI to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. We validate the approach on CT images of 59 patients (49 with sclerotic metastases and 10 normal controls). The proposed method reduces the number of FP/vol.from 4 to 1.2, 7 to 3, and 12 to 9.5 when comparing a sensitivity rates of 60, 70, and 80% respectively in testing. The Area-Under-the-Curve (AUC) is 0.834. The results show marked improvement upon previous work.

Automated detection of sclerotic metastases (bone lesions) in Computed Tomography (CT) images has potential to be an important tool in clinical practice and research. State-of-the-art methods show performance of 79 % sensitivity or truepositive (TP) rate, at 10 false-positives (FP) per volume. We design a two-tiered coarse-to-fine cascade framework to first operate a highly sensitive candidate generation system at a maximum sensitivity of ∼92% but with high FP level (∼50 per patient). Regions of interest (ROI) for lesion candidates are generated in this step and function as input for the second tier. In the second tier we generate N 2D views, via scale, random translations, and rotations with respect to each ROI centroid coordinates. These random views are used to train a deep Convolutional Neural Network (CNN) classifier. In testing, the CNN is employed to assign individual probabilities for a new set of N random views that are averaged at each ROI to compute a final per-candidate classification probability. This second tier behaves as a highly selective process to reject difficult false positives while preserving high sensitivities. We validate the approach on CT images of 59 patients (49 with sclerotic metastases and 10 normal controls). The proposed method reduces the number of FP/vol.from 4 to 1.2, 7 to 3, and 12 to 9.5 when comparing a sensitivity rates of 60, 70, and 80% respectively in testing. The Area-Under-the-Curve (AUC) is 0.834. The results show marked improvement upon previous work.

Gene therapy represents an attractive strategy for the non-invasive treatment of prostate cancer, where current clinical interventions show limited efficacy. Here, we evaluate the use of the insect virus, baculovirus (BV), as a novel vector for human prostate cancer gene therapy. Since prostate tumours represent a heterogeneous environment, a therapeutic approach that achieves long-term regression must be capable of targeting multiple transformed cell populations. Furthermore, discrimination in the targeting of malignant compared to non-malignant cells would have value in minimising side effects. We employed a number of prostate cancer models to analyse the potential for BV to achieve these goals. In vitro, both traditional prostate cell lines as well as primary epithelial or stromal cells derived from patient prostate biopsies, in two-or three-dimensional cultures, were used. We also evaluated BV in vivo in murine prostate cancer xenograft models. BV was capable of preferentially transducing invasive malignant prostate cancer cell lines compared to early stage cancers and non-malignant samples, a restriction that was not a function of nuclear import. Of more clinical relevance, primary patient-derived prostate cancer cells were also efficiently transduced by BV, with robust rates observed in epithelial cells of basal phenotype, which expressed BV-encoded transgenes faster than epithelial cells of a more differentiated, luminal phenotype. Maximum transduction capacity was observed in stromal cells. BV was able to penetrate through three-dimensional structures, including in vitro spheroids and in vivo orthotopic xenografts. BV vectors containing a nitroreductase transgene in a gene-directed enzyme pro-drug therapy approach were capable of efficiently killing malignant prostate targets following administration of the pro-drug, CB1954. Thus, BV is capable of transducing a large proportion of prostate cell types within a heterogeneous 3-D prostate tumour, can facilitate