Premal Amrishkumar Patel

Premal Amrishkumar Patel

Auto-generated profile, based on publicly available information

Premal Amrishkumar Patel

Interventional Radiology, Radiology Department, Great Ormond Street Hospital for Children, London, UK

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 January 2018 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Open access
GWGuotai Wang
Guotai Wang
WLWenqi Li
Wenqi Li
MZMaria A. Zuluaga
Maria A. Zuluaga
RPRosalind Pratt
Rosalind Pratt
PPPremal A. Patel
Premal A. Patel
TVTom Vercauteren
Tom Vercauteren
Convolutional neural networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the lack of image-specific adaptation and the lack of generalizability to previously unseen object classes (a.k.a. zero-shot learning). To address these problems, we propose a novel deep learning-based interactive segmentation framework by incorporating CNNs into a bounding box and scribble-based segmentation pipeline. We propose image-specific fine tuning to make a CNN model adaptive to a specific test image, which can be either unsupervised (without additional user interactions) or supervised (with additional scribbles). We also propose a weighted loss function considering network and interaction-based uncertainty for the fine tuning. We applied this framework to two applications: 2-D segmentation of multiple organs from fetal magnetic resonance (MR) slices, where only two types of these organs were annotated for training and 3-D segmentation of brain tumor core (excluding edema) and whole brain tumor (including edema) from different MR sequences, where only the tumor core in one MR sequence was annotated for training. Experimental results show that: 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.

1 June 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
GWGuotai Wang
Guotai Wang
MZMaria A. Zuluaga
Maria A. Zuluaga
WLWenqi Li
Wenqi Li
RPRosalind Pratt
Rosalind Pratt
PPPremal A. Patel
Premal A. Patel
TVTom Vercauteren
Tom Vercauteren
Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.

1 June 2013 in Bone & Joint Research
Verified
Journal Article
Open access
RPR. A. Patel
R. A. Patel
RWR. F. Wilson
R. F. Wilson
PPP. A. Patel
P. A. Patel
RPR. M. Palmer
R. M. Palmer
Objectives: To review the systemic impact of smoking on bone healing as evidenced within the orthopaedic literature. Methods: A protocol was established and studies were sourced from five electronic databases. Screening, data abstraction and quality assessment was conducted by two review authors. Prospective and retrospective clinical studies were included. The primary outcome measures were based on clinical and/or radiological indicators of bone healing. This review specifically focused on non-spinal orthopaedic studies. Results: Nine tibia studies and eight other orthopaedic studies were considered for systematic review. Of these 17 studies, 13 concluded that smoking negatively influenced bone healing. Conclusions: Smoking has a negative effect on bone healing, in terms of delayed union, nonunion and more complications.

13 May 2014 in Pediatric Radiology
Verified
Journal Article
Closed access
PDF file
FGFernando M. Gómez
Fernando M. Gómez
PPPremal A. Patel
Premal A. Patel
SSSamuel Stuart
Samuel Stuart
DRDerek J. Roebuck
Derek J. Roebuck

7 January 2021 in CVIR Endovascular
Verified
Journal Article
Open access
PDF file
PPPremal Amrishkumar Patel
Premal Amrishkumar Patel
ACAnne Marie Cahill
Anne Marie Cahill
Paediatric hypertension, defined as systolic blood pressure > 95th percentile for age, sex and height is often incidentally diagnosed. Renovascular hypertension (RVH) is responsible for 5–25% of hypertension in children. Renal artery stenosis and middle aortic syndrome can both can be associated with various conditions such as fibromuscular dysplasia, Williams syndrome & Neurofibromatosis type 1. This paper discusses the approaches to diagnosis and interventional management and outcomes of renovascular hypertension in children. Angiography is considered the gold standard in establishing the diagnosis of renovascular disease in children. Angioplasty is beneficial in the majority of patients and generally repeated angioplasty is considered more appropriate than stenting. Surgical options should first be considered before placing a stent unless there is an emergent requirement. Given the established safety and success of endovascular intervention, at most institutions it remains the preferred treatment option.

1 August 2013 in Journal of Vascular and Interventional Radiology
Verified
Journal Article
Closed access
PPPremal A. Patel
Premal A. Patel
LILiam Ingram
Liam Ingram
IWIain D.C. Wilson
Iain D.C. Wilson
DBDavid J. Breen
David J. Breen