A5004908094- AI in cancer detection
- Advanced Neural Network Applications
- Medical Image Segmentation Techniques
- COVID-19 diagnosis using AI
- Lung Cancer Diagnosis and Treatment
- Phonocardiography and Auscultation Techniques
- Colorectal Cancer Screening and Detection
- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
Sichuan University
2022-2023
Shandong Institute of Business and Technology
2022-2023
West China Medical Center of Sichuan University
2022
The Fourth People's Hospital
2022
Pneumoconiosis staging has been a very challenging task, both for certified radiologists and computer-aided detection algorithms. Although deep learning shown proven advantages in the of pneumoconiosis, it remains pneumoconiosis due to stage ambiguity noisy samples caused by misdiagnosis when they are used training models. In this article, we propose fully paradigm that comprises segmentation procedure procedure. The extracts lung fields chest radiographs through an Asymmetric...
Abstract Medical image segmentation is a key step in medical analysis. The small differences the background and foreground of images size most data sets make difficult. This paper uses global‐local training strategy to train network. In global structure, ResNest used as backbone network, parallel decoders are added aggregate features, well gated axial attention adapt datasets. local extraction details accomplished by dividing into equal patches same size. To evaluate performance model,...
The convolutional neural network, as the backbone network for medical image segmentation, has shown good performance in past years. However, its drawbacks cannot be ignored, namely, networks focus on local regions and are difficult to model global contextual information. For this reason, transformer, which is used text processing, was introduced into field of thanks expertise modelling relationships, accuracy segmentation further improved. transformer-based structure requires a certain...
Pneumoconiosis staging has been a challenging task for deep neural networks due to the stage ambiguity in early pneumoconiosis. In this article, we propose log-normal label distribution learning method named DLN-LDL pneumo-coniosis by exploring intrinsic pat-terns of effectively prevents network from overfitting features ambiguous chest radiographs that are irrelevant which they belong replacing one-hot labels with log-normally distributed vectors. The experiments on our collected...