Track topics on Twitter Track topics that are important to you
Fully Convolutional Networks (FCNs) have emerged as powerful segmentation models but are usually designed manually, which requires extensive time and can result in large and complex architectures. There is a growing interest to automatically design efficient architectures that can accurately segment 3D medical images. However, most approaches either do not fully exploit volumetric information or do not optimize the model's size. To address these problems, we propose a self-adaptive 2D-3D ensemble of FCNs called AdaEn-Net for 3D medical image segmentation that incorporates volumetric data and adapts to a particular dataset by optimizing both the model's performance and size. The AdaEn-Net consists of a 2D FCN that extracts intra-slice information and a 3D FCN that exploits inter-slice information. The architecture and hyperparameters of the 2D and 3D architectures are found through a multiobjective evolutionary based algorithm that maximizes the expected segmentation accuracy and minimizes the number of parameters in the network. The main contribution of this work is a model that fully exploits volumetric information and automatically searches for a high-performing and efficient architecture. The AdaEn-Net was evaluated for prostate segmentation on the PROMISE12 Grand Challenge and for cardiac segmentation on the MICCAI ACDC challenge. In the first challenge, the AdaEn-Net ranks 9 out of 297 submissions and surpasses the performance of an automatically-generated segmentation network while producing an architecture with 13× fewer parameters. In the second challenge, the proposed model is ranked within the top 8 submissions and outperforms an architecture designed with reinforcement learning while having 1.25× fewer parameters.
This article was published in the following journal.
Name: Neural networks : the official journal of the International Neural Network Society
Convolutional neural networks (CNNs) play an important role in the field of medical image segmentation. Among many kinds of CNNs, the U-net architecture is one of the most famous fully convolutional n...
Precise 3D segmentation of infant brain tissues is an essential step towards comprehensive volumetric studies and quantitative analysis of early brain development. However, computing such segmentation...
Medical image synthesis can simulate a target modality of interest based on existing modalities and has the potential to save scanning time while contributing to efficient data collection. This study ...
To automatically and efficiently segment the lesion area of the colonoscopy polyp image, a polyp segmentation method has been presented.
Establishing a solid theoretical foundation for structured deep neural networks is greatly desired due to the successful applications of deep learning in various practical domains. This paper aims at ...
This study focuses on the difficulties of maintaining optimal psychological health and quality of life for caregivers in adult psychiatry while they play an important role in helping patie...
We aim to experiment and implement various deep learning architectures in order to achieve human-level accuracy in Computer-aided diagnosis (CAD) systems. In particular, we are interested ...
Within this study patient data are collected from different imaging and motion monitoring devices that will be used to develop and test strategies for image-guided adaptive radiotherapy in...
This project aims to use artificial intelligence (image discrimination) algorithms, specifically convolutional neural networks (CNNs) for scanning chest radiographs in the emergency depart...
Patients with primary head and neck squamous cell carcinoma (HNSCC) planned for treatment with radiotherapy with or without chemotherapy in curative setting will be treated with an adaptiv...
The use of COMPUTER COMMUNICATION NETWORKS to store and transmit medical PRESCRIPTIONS.
A method of delineating blood vessels by subtracting a tissue background image from an image of tissue plus intravascular contrast material that attenuates the X-ray photons. The background image is determined from a digitized image taken a few moments before injection of the contrast material. The resulting angiogram is a high-contrast image of the vessel. This subtraction technique allows extraction of a high-intensity signal from the superimposed background information. The image is thus the result of the differential absorption of X-rays by different tissues.
A health care system which combines physicians, hospitals, and other medical services with a health plan to provide the complete spectrum of medical care for its customers. In a fully integrated system, the three key elements - physicians, hospital, and health plan membership - are in balance in terms of matching medical resources with the needs of purchasers and patients. (Coddington et al., Integrated Health Care: Reorganizing the Physician, Hospital and Health Plan Relationship, 1994, p7)
Disorders having the presence of physical symptoms that suggest a general medical condition but that are not fully explained by a general medical condition, by the direct effects of a substance, or by another mental disorder. The symptoms must cause clinically significant distress or impairment in social, occupational, or other areas of functioning. In contrast to FACTITIOUS DISORDERS and MALINGERING, the physical symptoms are not under voluntary control. (APA, DSM-IV)
The production of an image obtained by cameras that detect the radioactive emissions of an injected radionuclide as it has distributed differentially throughout tissues in the body. The image obtained from a moving detector is called a scan, while the image obtained from a stationary camera device is called a scintiphotograph.