Radiology - Research Publications

Permanent URI for this collection

http://hdl.handle.net/11343/196

Filters

2014 - 2019 1 2020 - 2021 1
Reset filters

Settings
Statistics
Citations
Author: Sutherland, Thomas × Author: Brotchie, Peter × Type: Journal Article ×

Search Results

Now showing 1 - 2 of 2
  • Item
    Thumbnail Image
    Incidental detection of prostate cancer with computed tomography scans
    Korevaar, S ; Tennakoon, R ; Page, M ; Brotchie, P ; Thangarajah, J ; Florescu, C ; Sutherland, T ; Kam, NM ; Bab-Hadiashar, A (NATURE PORTFOLIO, 2021-04-12)
    Prostate cancer (PCa) is the second most frequent type of cancer found in men worldwide, with around one in nine men being diagnosed with PCa within their lifetime. PCa often shows no symptoms in its early stages and its diagnosis techniques are either invasive, resource intensive, or has low efficacy, making widespread early detection onerous. Inspired by the recent success of deep convolutional neural networks (CNN) in computer aided detection (CADe), we propose a new CNN based framework for incidental detection of clinically significant prostate cancer (csPCa) in patients who had a CT scan of the abdomen/pelvis for other reasons. While CT is generally considered insufficient to diagnose PCa due to its inferior soft tissue characterisation, our evaluations on a relatively large dataset consisting of 139 clinically significant PCa patients and 432 controls show that the proposed deep neural network pipeline can detect csPCa patients at a level that is suitable for incidental detection. The proposed pipeline achieved an area under the receiver operating characteristic curve (ROC-AUC) of 0.88 (95% Confidence Interval: 0.86-0.90) at patient level csPCa detection on CT, significantly higher than the AUCs achieved by two radiologists (0.61 and 0.70) on the same task.
  • Item
    Thumbnail Image
    Magnetic resonance imaging of meningiomas: a pictorial review
    Watts, J ; Box, G ; Galvin, A ; Brotchie, P ; Trost, N ; Sutherland, T (SPRINGER HEIDELBERG, 2014-02)
    UNLABELLED: Meningiomas are the most common non-glial tumour of the central nervous system (CNS). There are a number of characteristic imaging features of meningiomas on magnetic resonance imaging (MRI) that allow an accurate diagnosis, however there are a number of atypical features that may be diagnostically challenging. Furthermore, a number of other neoplastic and non-neoplastic conditions may mimic meningiomas. This pictorial review discusses the typical and atypical MRI features of meningiomas and their mimics. TEACHING POINTS: There are several characteristic features of meningiomas on MRI that allow an accurate diagnosis Some meningiomas may display atypical imaging characteristics that may be diagnostically challenging Routine MRI sequences do not reliably distinguish between benign and malignant meningiomas Spectroscopy and diffusion tensor imaging may be useful in the diagnosis of malignant meningiomas A number of conditions may mimic meningiomas; however, they may have additional differentiating features.