Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


John D. Thompson has a total of 76 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Approaches to Automatic Classification, Detection and Segmentation of Breast Arterial Calcification Using Deep Learning

    by Dominic Maguire, John D. Thompson, Sunil Vadera, Katy Szczepura

    Objective: Cardiovascular disease (CVD) is the leading cause of premature death in the United Kingdom with one type, coronary artery disease, killing more than two times as many women as breast cancer. Recently, researchers have noted that breast arterial calcification (BAC), which is regularly observed as an incidental finding on mammograms, could be used to risk‐stratify women for CVD. However, identifying BAC is known to be a tedious, expensive and time‐consuming process. Thus, this paper investigates deep learning models for BAC classification, object detection and segmentation. Methodology: A data set, annotated under the guidance of two consultant radiologists, was created using data augmentation. This was used to evaluate several alternative deep learning models. Results: A modified ResNet22 classification network achieved a test accuracy of 80%, indicating that this method could be used as a flag for the presence or absence of BAC. We also used this network for feature extraction in a YOLOv4 BAC object detection network. Despite improving on a recent similar study, this latter network performed poorly with very low average precision scores at several thresholds. More promising was our DeepLabv3+‐based BAC segmentation network, which reached similar high global accuracy scores to three recent studies and a BFScore of over 70% specifically for BAC. It also performed satisfactorily on an unseen data set. Conclusions: These results show the potential for using classification and segmentation models as part of a pipeline for detecting BAC.


  • Open Access

    The impact of technical and environmental conditions on the quality assessment in mammography

    by S. Papathanasiou, K. Szczepura, J.D. Thompson

  • Open Access

    The Effect of Antihypertensive Agents on Dental Implant Stability, Osseointegration and Survival Outcomes: A Systematic Review

    by Dary Jones, Rabia S. Khan, John D. Thompson, Cemal Ucer, Simon Wright

    Antihypertensive agents are commonly prescribed to manage hypertension and are known to be beneficial for bone formation and remodeling. The aim of this systematic review was to assess the impact that antihypertensive agents have on dental implant stability, osseointegration, and survival outcomes. A review of the literature was conducted using articles from 11 data sources. PRISMA guidelines were followed, and a PICO question was constructed. The search string “Antihypertensive* AND dental implant* AND (osseointegration OR stability OR survival OR success OR failure)” was used for all data sources where possible. The Critical Appraisal Skills Programme (CASP) was used for study appraisal, including the risk of bias. The search resulted in 7726 articles. After selection according to eligibility criteria, seven articles were obtained (one randomized control trial, two prospective cohort studies, three retrospective cohort studies, and a case control study). Five papers investigated the effects of antihypertensive agents on primary stability, but there were discrepancies in the method of assessment. Inhibition of the renin–angiotensin–aldosterone system was linked to higher primary stability. Secondary stability was usually higher than primary stability, but it is unknown if antihypertensive agents caused this. Survival outcomes were increased with certain antihypertensive agents. It is possible that inhibition of the renin–angiotensin–aldosterone system may lead to greater bone mineral density, improved primary stability, and improved survival outcomes although the effects on osseointegration are unknown. However, more research is needed to confirm this theory.


  • Open Access

    A comparison of perceived image quality between computer display monitors and augmented reality smart glasses

    by A. England, J. Thompson, S. Dorey, S. Al-Islam, M. Long, C. Maiorino, M.F. McEntee


  • Predicting the role of touchless technologies within diagnostic radiography: Results of an international survey

    by A. England, J.D. Thompson, E. Littler, J. Tugwell-Allsup, E. Edwards


  • Predictors of radiation dose for uterine artery embolisation are angiography system-dependent

    by Don J Nocum, John Robinson, Mark Halaki, Magnus Båth, John D Thompson, Nadine Thompson, Michelle Moscova, Eisen Liang, Nejc Mekiš, Warren Reed

    This study sought to achieve radiation dose reductions for patients receiving uterine artery embolisation (UAE) by evaluating radiation dose measurements for the preceding generation (Allura) and upgraded (Azurion) angiography system. Previous UAE regression models in the literature could not be applied to this centre’s practice due to being based on different angiography systems and radiation dose predictor variables. The aims of this study were to establish whether radiation dose is reduced with the upgraded angiography system and to develop a regression model to determine predictors of radiation dose specific to the upgraded angiography system. A comparison between Group I (Allura, n = 95) and Group II (Azurion, n = 95) demonstrated a significant reduction in kerma-area product (KAP) and Ka, r (reference air kerma) by 63% (143.2 Gy cm2 vs 52.9 Gy cm2; P < 0.001, d = 0.8) and 67% (0.6 Gy vs 0.2 Gy; P < 0.001, d = 0.8), respectively. The multivariable linear regression (MLR) model identified the UAE radiation dose predictors for KAP on the upgraded angiography system as total fluoroscopy dose, Ka, r, and total uterus volume. The predictive accuracy of the MLR model was assessed using a Bland-Altman plot. The mean difference was 0.39 Gy cm2 and the limits of agreement were +28.49 and −27.71 Gy cm2, and thus illustrated no proportional bias. The resultant MLR model was considered system-dependent and validated the upgraded angiography system and its advance capabilities to significantly reduce radiation dose. Interventional radiologist and interventional radiographer familiarisation of the system’s features and the implementation of the newly established MLR model would further facilitate dose optimisation for all centres performing UAE procedures using the upgraded angiography system.


  • Open Access

    3D Guided Dental Implant Placement: Impact on Surgical Accuracy and Collateral Damage to the Inferior Alveolar Nerve

    by Amit Mistry, Cemal Ucer, John D. Thompson, Rabia Sannam Khan, Emina Karahmet, Farooq Sher

    An increase in the number of implants placed has led to a corresponding increase in the number of complications reported. The complications can vary from restorative complications due to poor placement to damage to collateral structures such as nerves and adjacent teeth. A large majority of these complications can be avoided if the implant has been placed accurately in the optimal position. Therefore, the aim of this in vitro pilot study was to investigate the effect of freehand (FH) and fully guided (FG) surgery on the accuracy of implants placed in close proximity to vital structures such as the inferior alveolar nerve (IAN). Cone-beam computed tomography (CBCT) and intraoral scans of six patients who have had previous dental implants in the posterior mandible were used in this study. The ideal implant position was planned. FG surgical guides were manufactured for each case. In this study, the three-dimensional 3D printed resin models of each of the cases were produced and the implants placed using FG and FH methods on the respective models. The outcome variables of the study, angular deviations were calculated and the distance to the IAN was measured. The mean deviations for the planned position observed were 1.10 mm coronally, 1.88 mm apically with up to 6.3 degrees’ angular deviation for FH surgery. For FG surgical technique the mean deviation was found to be at 0.35 mm coronally, 0.43 mm apically with 0.78 degrees angularly respectively. The maximum deviation from the planned position for the apex of the implant to the IAN was 2.55 mm using FH and 0.63 mm FG. This bench study, within its limitations, demonstrated surgically acceptable accuracy for both FH and FG techniques that would allow safe placement of implants to vital structures such as the IAN when a safety zone of 3 mm is allowed. Nevertheless, a better margin of error was observed for FG surgery with respect to the angular deviation and controlling the distance of the implant to the IAN using R2 Gate® system.