T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging
20
Citation
77
Reference
10
Related Paper
Citation Trend
Abstract:
Lesion segmentation in medical imaging has been an important topic in clinical research. Researchers have proposed various detection and segmentation algorithms to address this task. Recently, deep learning-based approaches have significantly improved the performance over conventional methods. However, most state-of-the-art deep learning methods require the manual design of multiple network components and training strategies. In this paper, we propose a new automated machine learning algorithm, T-AutoML, which not only searches for the best neural architecture, but also finds the best combination of hyper-parameters and data augmentation strategies simultaneously. The proposed method utilizes the modern transformer model, which is introduced to adapt to the dynamic length of the search space embedding and can significantly improve the ability of the search. We validate T-AutoML on several large-scale public lesion segmentation data-sets and achieve state-of-the-art performance.The embedding problem for Markov chains is a famous problem in probability theory and only partial results are available up till now. In this paper, we propose a variant of the embedding problem called the reversible embedding problem which has a deep physical and biochemical background and provide a complete solution to this new problem. We prove that the reversible embedding of a stochastic matrix, if it exists, must be unique. Moreover, we obtain the sufficient and necessary conditions for the existence of the reversible embedding and provide an effective method to compute the reversible embedding. Some examples are also given to illustrate the main results of this paper.
Matrix (chemical analysis)
Cite
Citations (1)
Neural networks have progressively used at a surprising rate now a days. Deep neural networks are majorly used machine learning models in different areas, from analysis of image to natural language processing (NLP) and broadly conveyed in scholarly community and industry. These progresses to have enormous possibilities for medical imaging, analysis of medical data, medical diagnostics. This paper illustrates a thorough literature review of deep learning techniques. This paper illustrates brief discussion about current deep learning architectures used for medical imaging and magnetic resonance imaging (MRI) for image classification, detection, segmentation, registration, etc. This review mainly focuses on the applications of deep learning methods in medical diagnosis that uses MRI modality along with the recent developments and various challenges in deep learning related to analysis of medical images.
Modality (human–computer interaction)
Deep Neural Networks
Cite
Citations (8)
Medical imaging technology plays an important role in the detection, diagnosis and treatment of diseases. Due to the instability of human expert experience, machine learning technology is expected to assist researchers and physicians to improve the accuracy of imaging diagnosis and reduce the imbalance of medical resources. This article systematically summarizes some methods of deep learning technology, introduces the application research of deep learning technology in medical imaging, and discusses the limitations of deep learning technology in medical imaging. Key words: Artificial Intelligence, Deep Learning, Medical Imaging, big data
Imaging technology
Cite
Citations (3)
Cite
Citations (164)
The development of computer hardware allows rapid accumulation of medical imaging data. Deep learning has shown great potential in medical imaging data analysis and establish a new area of machine learning. The commonly used deep learning models were firstly introduced in the paper, and then, summarized with the application of deep learning in the detection, classification, diagnosis, segmentation, identification of medical imaging. The application of deep learning in oral and maxillofacial radiology and other discipline of stomatology was proposed. At the end, the paper discussed the problems of deep learning in medical imaging research.计算机硬件的发展让影像学数据得以迅速积累，深度学习作为机器学习的新兴内容，在影像学数据分析方面表现出较大潜力。本综述首先介绍了基于神经网络的深度学习发展及内容；然后分别从检测分类与诊断、图像分割、识别与标记等研究方向具体介绍深度学习研究进展及在口腔颌面医学影像中的应用；最后对深度学习在医学影像研究中存在的问题予以讨论。.
Deep Neural Networks
Identification
Cite
Citations (7)
The rapid accumulation of various medical Imaging data has brought great challenges to radiologists and clinicians who diagnose disease through traditional medical Imaging analysis methods. Deep learning, especially deep convolutional neural networks, can learn automatically latent disease features from medical imaging big data. Therefore, in recent years, deep learning based medical imaging analysis became a research hotspot in the academia. This article surveys applications in area of medical imaging analysis based on deep learning. Firstly the brief characteristics of medical imaging analysis are given; basic principles of deep learning models, especially various popular neural networks in deep learning algorithms are briefly introduced. Secondly, applications in area of medical imaging analysis are systematically reviewed. More importantly, latent challenges and future research directions are summarized.
Cite
Citations (0)
Abstract: Deep fake is a rapidly growing concern in society, and it has become a significant challenge to detect such manipulated media. Deep fake detection involves identifying whether a media file is authentic or generated using deep learning algorithms. In this project, we propose a deep learning-based approach for detecting deep fakes in videos. We use the Deep fake Detection Challenge dataset, which consists of real and Deep fake videos, to train and evaluate our deep learning model. We employ a Convolutional Neural Network (CNN) architecture for our implementation, which has shown great potential in previous studies. We pre-process the dataset using several techniques such as resizing, normalization, and data augmentation to enhance the quality of the input data. Our proposed model achieves high detection accuracy of 97.5% on the Deep fake Detection Challenge dataset, demonstrating the effectiveness of the proposed approach for deep fake detection. Our approach has the potential to be used in real-world scenarios to detect deep fakes, helping to mitigate the risks posed by deep fakes to individuals and society. The proposed methodology can also be extended to detect in other types of media, such as images and audio, providing a comprehensive solution for deep fake detection.
Deep Neural Networks
Normalization
Cite
Citations (2)
Embedding and visualizing large-scale high-dimensional data in a two-dimensional space is an important problem since such visualization can reveal deep insights out of complex data. Most of the existing embedding approaches, however, run on an excessively high precision, ignoring the fact that at the end, embedding outputs are converted into coarse-grained discrete pixel coordinates in a screen space. Motivated by such an observation and directly considering pixel coordinates in an embedding optimization process, we accelerate Barnes-Hut tree-based t-distributed stochastic neighbor embedding (BH-SNE), known as a state-of-the-art 2D embedding method, and propose a novel method called PixelSNE, a highly-efficient, screen resolution-driven 2D embedding method with a linear computational complexity in terms of the number of data items. Our experimental results show the significantly fast running time of PixelSNE by a large margin against BH-SNE, while maintaining the minimal degradation in the embedding quality. Finally, the source code of our method is publicly available at https://github.com/awesome-davian/PixelSNE
Cite
Citations (5)
Given a Brownian motion $B_t$ and a general target law $μ$ (not necessarily centered or even integrable) we show how to construct an embedding of $μ$ in $B$. This embedding is an extension of an embedding due to Perkins, and is optimal in the sense that it simultaneously minimises the distribution of the maximum and maximises the distribution of the minimum among all embeddings of $μ$. The embedding is then applied to regular diffusions, and used to characterise the target laws for which a $H^p$-embedding may be found.
Cite
Citations (1)