A review of convolutional neural network architectures and their optimizations

S Cong, Y Zhou - Artificial Intelligence Review, 2023 - Springer
The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …

Bidirectional copy-paste for semi-supervised medical image segmentation

Y Bai, D Chen, Q Li, W Shen… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
In semi-supervised medical image segmentation, there exist empirical mismatch problems
between labeled and unlabeled data distribution. The knowledge learned from the labeled …

[HTML][HTML] Artificial Intelligence in Pancreatic Image Analysis: A Review

W Liu, B Zhang, T Liu, J Jiang, Y Liu - Sensors, 2024 - mdpi.com
Pancreatic cancer is a highly lethal disease with a poor prognosis. Its early diagnosis and
accurate treatment mainly rely on medical imaging, so accurate medical image analysis is …

MedShapeNet – a large-scale dataset of 3D medical shapes for computer vision

J Li, Z Zhou, J Yang, A Pepe, C Gsaxner… - Biomedical …, 2024 - degruyter.com
Objectives The shape is commonly used to describe the objects. State-of-the-art algorithms
in medical imaging are predominantly diverging from computer vision, where voxel grids …

Devil is in the queries: advancing mask transformers for real-world medical image segmentation and out-of-distribution localization

M Yuan, Y **a, H Dong, Z Chen, J Yao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Real-world medical image segmentation has tremendous long-tailed complexity of objects,
among which tail conditions correlate with relatively rare diseases and are clinically …

Squid: Deep feature in-painting for unsupervised anomaly detection

T **ang, Y Zhang, Y Lu, AL Yuille… - Proceedings of the …, 2023 - openaccess.thecvf.com
Radiography imaging protocols focus on particular body regions, therefore producing
images of great similarity and yielding recurrent anatomical structures across patients. To …

Zept: Zero-shot pan-tumor segmentation via query-disentangling and self-prompting

Y Jiang, Z Huang, R Zhang… - Proceedings of the …, 2024 - openaccess.thecvf.com
The long-tailed distribution problem in medical image analysis reflects a high prevalence of
common conditions and a low prevalence of rare ones which poses a significant challenge …

DeepPrognosis: Preoperative prediction of pancreatic cancer survival and surgical margin via comprehensive understanding of dynamic contrast-enhanced CT …

J Yao, Y Shi, K Cao, L Lu, J Lu, Q Song, G **… - Medical image …, 2021 - Elsevier
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers and carries a
dismal prognosis of∼ 10% in five year survival rate. Surgery remains the best option of a …

Effective pancreatic cancer screening on non-contrast CT scans via anatomy-aware transformers

Y **a, J Yao, L Lu, L Huang, G **e, J **ao… - … Image Computing and …, 2021 - Springer
Pancreatic cancer is a relatively uncommon but most deadly cancer. Screening the general
asymptomatic population is not recommended due to the risk that a significant number of …

The felix project: Deep networks to detect pancreatic neoplasms

Y **a, Q Yu, L Chu, S Kawamoto, S Park, F Liu, J Chen… - medRxiv, 2022 - medrxiv.org
Tens of millions of abdominal images are performed with computed tomography (CT) in the
US each year but pancreatic cancers are sometimes not initially detected in these images …