Advances in medical image analysis with vision transformers: a comprehensive review

R Azad, A Kazerouni, M Heidari, EK Aghdam… - Medical Image …, 2024 - Elsevier
The remarkable performance of the Transformer architecture in natural language processing
has recently also triggered broad interest in Computer Vision. Among other merits …

A vertebral segmentation dataset with fracture grading

MT Löffler, A Sekuboyina, A Jacob, AL Grau… - Radiology: Artificial …, 2020 - pubs.rsna.org
Keywords: CT, Computer Aided Diagnosis (CAD), Computer Applications-General
(Informatics), Convolutional Neural Network (CNN), Diagnosis, Neural Networks …

Cutting-edge 3D medical image segmentation methods in 2020: Are happy families all alike?

J Ma - arxiv preprint arxiv:2101.00232, 2021 - arxiv.org
Segmentation is one of the most important and popular tasks in medical image analysis,
which plays a critical role in disease diagnosis, surgical planning, and prognosis evaluation …

A computed tomography vertebral segmentation dataset with anatomical variations and multi-vendor scanner data

H Liebl, D Schinz, A Sekuboyina, L Malagutti… - Scientific data, 2021 - nature.com
With the advent of deep learning algorithms, fully automated radiological image analysis is
within reach. In spine imaging, several atlas-and shape-based as well as deep learning …

Localization and edge-based segmentation of lumbar spine vertebrae to identify the deformities using deep learning models

M Mushtaq, MU Akram, NS Alghamdi, J Fatima… - Sensors, 2022 - mdpi.com
The lumbar spine plays a very important role in our load transfer and mobility. Vertebrae
localization and segmentation are useful in detecting spinal deformities and fractures …

CTSpine1K: a large-scale dataset for spinal vertebrae segmentation in computed tomography

Y Deng, C Wang, Y Hui, Q Li, J Li, S Luo, M Sun… - arxiv preprint arxiv …, 2021 - arxiv.org
Spine-related diseases have high morbidity and cause a huge burden of social cost. Spine
imaging is an essential tool for noninvasively visualizing and assessing spinal pathology …

Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the DICE coefficient

F Kofler, I Ezhov, F Isensee, F Balsiger… - arxiv preprint arxiv …, 2021 - arxiv.org
Metrics optimized in complex machine learning tasks are often selected in an ad-hoc
manner. It is unknown how they align with human expert perception. We explore the …

Domain generalizer: A few-shot meta learning framework for domain generalization in medical imaging

P Khandelwal, P Yushkevich - … MICCAI Workshop, DART 2020, and First …, 2020 - Springer
Deep learning models perform best when tested on target (test) data domains whose
distribution is similar to the set of source (train) domains. However, model generalization can …

Opportunistic osteoporosis screening reveals low bone density in patients with screw loosening after lumbar semi-rigid instrumentation: a case-control study

MT Löffler, N Sollmann, E Burian, A Bayat… - Frontiers in …, 2021 - frontiersin.org
Objective Decreased bone mineral density (BMD) impairs screw purchase in trabecular
bone and can cause screw loosening following spinal instrumentation. Existing computed …

Vertebral deformity measurements at MRI, CT, and radiography using deep learning

A Suri, BC Jones, G Ng, N Anabaraonye… - Radiology: Artificial …, 2021 - pubs.rsna.org
Purpose To construct and evaluate the efficacy of a deep learning system to rapidly and
automatically locate six vertebral landmarks, which are used to measure vertebral body …