Peter Brotchie

ORCID: 0000-0003-2313-9067
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Radiomics and Machine Learning in Medical Imaging
  • AI in cancer detection
  • Radiology practices and education
  • Visual perception and processing mechanisms
  • Neural dynamics and brain function
  • Artificial Intelligence in Healthcare and Education
  • Radiation Dose and Imaging
  • Genetics and Neurodevelopmental Disorders
  • Advanced MRI Techniques and Applications
  • Motor Control and Adaptation
  • Advanced X-ray and CT Imaging
  • Acute Ischemic Stroke Management
  • Advanced Neuroimaging Techniques and Applications
  • Spatial Neglect and Hemispheric Dysfunction
  • COVID-19 diagnosis using AI
  • Photoacoustic and Ultrasonic Imaging
  • Spatial Cognition and Navigation
  • Bone and Joint Diseases
  • Autism Spectrum Disorder Research
  • Cerebrovascular and Carotid Artery Diseases
  • RNA regulation and disease
  • Ophthalmology and Eye Disorders
  • Genomic variations and chromosomal abnormalities
  • Neurological disorders and treatments
  • Functional Brain Connectivity Studies

St Vincent's Hospital
2014-2024

St Vincent's Health
2021-2023

Royal Hobart Hospital
2023

Metro South Health
2023

Sir Charles Gairdner Hospital
2023

American Nephrology Nurses Association
2021-2022

Barwon Health
2021

St. Vincent's Hospital
2014

Saint Vincent's Catholic Medical Center
2014

St. Vincent's Birmingham
1995-2014

BackgroundChest x-rays are widely used in clinical practice; however, interpretation can be hindered by human error and a lack of experienced thoracic radiologists. Deep learning has the potential to improve accuracy chest x-ray interpretation. We therefore aimed assess radiologists with without assistance deep-learning model.MethodsIn this retrospective study, model was trained on 821 681 images (284 649 patients) from five data sets Australia, Europe, USA. 2568 enriched cases adult...

10.1016/s2589-7500(21)00106-0 article EN cc-by The Lancet Digital Health 2021-07-01

In order to examine the role of basal ganglia (BG) in regulation basic movement parameters, we recorded extracellularly from pallidal neurons conscious monkeys during performance a sequential wrist task which was composed series holds and ballistic jumps. The sequence predictable had be performed within specified time restraints. We activity 297 whose discharges were related task. included only movements at or about joint by prior examination outside behavioural paradigm. Each neuron...

10.1093/brain/114.4.1667 article EN Brain 1991-01-01

In order to study the role of basal ganglia (BG) in cognitive aspects movement, we recorded extracellularly from pallidal neurons conscious monkeys while they performed a sequential wrist movement task consisting series holds and ballistic jumps. The sequence had be within specified time restraints was predictable. We activity 297 whose discharges were related task. movement-related response found influenced by contextual setting degree difficulty subgroup 82 with clear first movement....

10.1093/brain/114.4.1685 article EN Brain 1991-01-01

Artificial intelligence (AI) readers of mammograms compare favourably to individual radiologists in detecting breast cancer. However, AI cannot perform at the level multi-reader systems used by screening programs countries such as Australia, Sweden, and UK. Therefore, implementation demands human-AI collaboration. Here, we use a large, high-quality retrospective mammography dataset from Victoria, Australia conduct detailed simulations five potential AI-integrated pathways, examine...

10.1038/s41467-024-51725-8 article EN cc-by-nc-nd Nature Communications 2024-08-30

Distal medium vessel occlusions (DMVOs) are increasingly considered for endovascular thrombectomy but difficult to detect on computed tomography angiography (CTA). We aimed determine whether time-to-maximum of tissue residue function (Tmax) maps, derived from CT perfusion, can be used as a triage screening tool accurately and rapidly identify patients with DMVOs.Consecutive code stroke who underwent multimodal were screened retrospectively. Two experienced readers evaluated all patients’...

10.1161/strokeaha.120.032941 article EN public-domain Stroke 2021-07-08

Supplemental material is available for this article.Keywords: Mammography, Screening, Convolutional Neural Network (CNN) Published under a CC BY 4.0 license. See also the commentary by Cadrin-Chênevert in issue.

10.1148/ryai.220072 article EN Radiology Artificial Intelligence 2022-12-21

A neurodegenerative disorder, fragile X‐associated tremor/ataxia syndrome (FXTAS), occurs in some older men carrying a small CGG repeat expansion (pre‐mutation) the FMR1 gene. We surveyed sample of pre‐mutation males to estimate prevalence and spectrum neurological involvement. Twelve aged 50–82 years 11 age‐matched normal controls ascertained an unbiased manner were included assessment that also used standard scales for tremor (Clinical Rating Scale Tremor), ataxia (International...

10.1111/j.1399-0004.2005.00425.x article EN Clinical Genetics 2005-02-22

Abstract Some carriers of a “premutation” allele the FMR1 gene develop late‐onset tremor/ataxia. We conducted magnetic resonance imaging volumetric study in an unselected sample eight older male premutation carriers. Volumetric measures, including total brain volume, and volumes cerebrum, cerebellum, cerebral cortex all were significantly reduced compared with similar data from 21 age‐matched normal controls. Total related to number CGG repeats gene. Moreover, increased hippocampal volume...

10.1002/ana.20542 article EN Annals of Neurology 2005-07-27

This study aims to evaluate deep learning (DL)-based artificial intelligence (AI) techniques for detecting the presence of breast cancer on a digital mammogram image.We evaluated several DL-based AI that employ different approaches and backbone DL models tested effect performance using data-processing strategies set mammographic images with annotations pathologically proven cancer.Our evaluation uses area under curve (AUC) accuracy (ACC) measurement. The best result, based 349 test cases...

10.1111/1754-9485.13278 article EN Journal of Medical Imaging and Radiation Oncology 2021-07-01

Non-contrast computed tomography of the brain (NCCTB) is commonly used to detect intracranial pathology but subject interpretation errors. Machine learning can augment clinical decision-making and improve NCCTB scan interpretation. This retrospective detection accuracy study assessed performance radiologists assisted by a deep model compared standalone with that unassisted radiologists.

10.1007/s00330-023-10074-8 article EN cc-by European Radiology 2023-08-22

Detecting intracranial distal arterial occlusions on CTA is challenging but increasingly relevant to clinical decision-making. Our purpose was determine whether the use of CTP-derived time-to-maximum tissue residue function maps improves diagnostic performance for detecting these occlusions.Seventy consecutive patients with a occlusion and 70 randomly selected controls who underwent multimodal CT CTP suspected acute ischemic stroke were included in this retrospective study. Four readers...

10.3174/ajnr.a6891 article EN cc-by American Journal of Neuroradiology 2021-01-01

Abstract Background Intraoperative cholangiography (IOC) is a contrast-enhanced X-ray acquired during laparoscopic cholecystectomy. IOC images the biliary tree whereby filling defects, anatomical anomalies and duct injuries can be identified. In Australia, are performed in over 81% of cholecystectomies compared with 20 to 30% internationally (Welfare AIoHa Australian Atlas Healthcare Variation, 2017). this study, we aim train artificial intelligence (AI) algorithms interpret anatomy...

10.1007/s00464-024-10768-0 article EN cc-by Surgical Endoscopy 2024-04-01

Abstract Prostate cancer (PCa) is the second most frequent type of found in men worldwide, with around one nine being diagnosed PCa within their lifetime. often shows no symptoms its early stages and diagnosis techniques are either invasive, resource intensive, or has low efficacy, making widespread detection onerous. Inspired by recent success deep convolutional neural networks (CNN) computer aided (CADe), we propose a new CNN based framework for incidental clinically significant prostate...

10.1038/s41598-021-86972-y article EN cc-by Scientific Reports 2021-04-12

To evaluate the ability of a commercially available comprehensive chest radiography deep convolutional neural network (DCNN) to detect simple and tension pneumothorax, as stratified by following subgroups: presence an intercostal drain; rib, clavicular, scapular or humeral fractures rib resections; subcutaneous emphysema erect versus non-erect positioning. The hypothesis was that performance would not differ significantly in each these subgroups when compared with overall test dataset.A...

10.1136/bmjopen-2021-053024 article EN cc-by-nc BMJ Open 2021-12-01

Background : Mammographic (or breast) density is an established risk factor for breast cancer. There are a variety of approaches to measurement including quantitative, semi-automated and automated approaches. We present new measure, AutoCumulus, learnt from applying deep learning measures. Methods: used mammograms 9,057 population-screened women in the BRAIx study which measurements mammographic had been made by experienced readers using CUMULUS software. The dataset was split into training,...

10.1101/2024.02.01.24302158 preprint EN cc-by-nc-nd medRxiv (Cold Spring Harbor Laboratory) 2024-02-03
Coming Soon ...