This was published as an extended abstract in MIDL 2019 [arXiv:1907.08612]. An alpha version of the code is available at https://github.com/dscarmo/e2dhipseg. More experiments on improvements to the method and code are ongoing. Future updates are to be expected. A new, more complete paper is published in arXiv:2001.05058
Hippocampus segmentation plays a key role in diagnosing various brain disorders such as Alzheimer's disease, epilepsy, multiple sclerosis, cancer, depression and others. Nowadays, segmentation is still mainly performed manually by specialists. Segmentation done by experts is considered to be a gold-standard when evaluating automated methods, buts it is a time consuming and arduos task, requiring specialized personnel. In recent years, efforts have been made to achieve reliable automated segmentation. For years the best performing authomatic methods were multi atlas based with around 80-85% Dice coefficient and very time consuming, but machine learning methods are recently rising with promising time and accuracy performance. A method for volumetric hippocampus segmentation is presented, based on the consensus of tri-planar U-Net inspired fully convolutional networks (FCNNs), with some modifications, including residual connections, VGG weight transfers, batch normalization and a patch extraction technique employing data from neighbor patches. A study on the impact of our modifications to the classical U-Net architecture was performed. Our method achieves cutting edge performance in our dataset, with around 96% volumetric Dice accuracy in our test data. In a public validation dataset, HARP, we achieve 87.48% DICE. GPU execution time is in the order of seconds per volume, and source code is publicly available. Also, masks are shown to be similar to other recent state-of-the-art hippocampus segmentation methods in a third dataset, without manual annotations.
UNICAMP（坎皮纳斯州立大学）；School of Electrical and Computer Engineering, UNICAMP（坎皮纳斯州立大学电气与计算机工程学院）；Faculty of Medical Sciences, UNICAMP（坎皮纳斯州立大学医学科学学院）
Hippocampus segmentation on magnetic resonance imaging is of key importance for the diagnosis, treatment decision and investigation of neuropsychiatric disorders. Automatic segmentation is an active research field, with many recent models using deep learning. Most current state-of-the art hippocampus segmentation methods train their methods on healthy or Alzheimer's disease patients from public datasets. This raises the question whether these methods are capable of recognizing the hippocampus on a different domain, that of epilepsy patients with hippocampus resection. In this paper we present …
Limited amount of labelled training data are a common problem in medical imaging. This makes it difficult to train a well-generalised model and therefore often leads to failure in unknown domains. Hippocampus segmentation from magnetic resonance imaging (MRI) scans is critical for the diagnosis and treatment of neuropsychatric disorders. Domain differences in contrast or shape can significantly affect segmentation. We address this issue by disentangling a T1-weighted MRI image into its content and domain. This separation enables us to perform a domain transfer and thus convert data from new so…
Shahid Beheshti University of Medical Sciences（沙希德·贝赫什提医科大学）；Khazar University（哈扎尔大学）
Background: Alzheimers disease is a progressive neurodegenerative disorder and the main cause of dementia in aging. Hippocampus is prone to changes in the early stages of Alzheimers disease. Detection and observation of the hippocampus changes using magnetic resonance imaging (MRI) before the onset of Alzheimers disease leads to the faster preventive and therapeutic measures. Objective: The aim of this study was the segmentation of the hippocampus in magnetic resonance (MR) images of Alzheimers patients using deep machine learning method. Methods: U-Net architecture of convolutional neural net…
In clinical settings, where acquisition conditions and patient populations change over time, continual learning is key for ensuring the safe use of deep neural networks. Yet most existing work focuses on convolutional architectures and image classification. Instead, radiologists prefer to work with segmentation models that outline specific regions-of-interest, for which Transformer-based architectures are gaining traction. The self-attention mechanism of Transformers could potentially mitigate catastrophic forgetting, opening the way for more robust medical image segmentation. In this work, we…
Tissue loss in the hippocampi has been heavily correlated with the progression of Alzheimer's Disease (AD). The shape and structure of the hippocampus are important factors in terms of early AD diagnosis and prognosis by clinicians. However, manual segmentation of such subcortical structures in MR studies is a challenging and subjective task. In this paper, we investigate variants of the well known 3D U-Net, a type of convolution neural network (CNN) for semantic segmentation tasks. We propose an alternative form of the 3D U-Net, which uses dilated convolutions and deep supervision to incorpor…
The automatic assessment of hippocampus volume is an important tool in the study of several neurodegenerative diseases such as Alzheimer's disease. Specifically, the measurement of hippocampus subfields properties is of great interest since it can show earlier pathological changes in the brain. However, segmentation of these subfields is very difficult due to their complex structure and for the need of high-resolution magnetic resonance images manually labeled. In this work, we present a novel pipeline for automatic hippocampus subfield segmentation based on a deeply supervised convolutional n…
Segmentation of brain structures in a large dataset of magnetic resonance images (MRI) necessitates automatic segmentation instead of manual tracing. Automatic segmentation methods provide a much-needed alternative to manual segmentation which is both labor intensive and time-consuming. Among brain structures, the hippocampus presents a challenging segmentation task due to its irregular shape, small size, and unclear edges. In this work, we use T1-weighted MRI of 426 subjects to validate the approach and compare three automatic segmentation methods: FreeSurfer, LocalInfo, and ABSS. Four evalua…
Face segmentation is the task of densely labeling pixels on the face according to their semantics. While current methods place an emphasis on developing sophisticated architectures, use conditional random fields for smoothness, or rather employ adversarial training, we follow an alternative path towards robust face segmentation and parsing. Occlusions, along with other parts of the face, have a proper structure that needs to be propagated in the model during training. Unlike state-of-the-art methods that treat face segmentation as an independent pixel prediction problem, we argue instead that …
From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation
Department of Software Convergence, Seoul Women's University, Seoul, Republic of Korea（首尔女性大学软件融合系）；Department of Pediatric Neurosurgery, Craniofacial Reforming and Reconstruction Clinic, Yonsei University College of Medicine, Seoul, Republic of Korea（延世大学医学院小儿神经外科及颅面整复与重建诊所）
University of Toronto（多伦多大学）；Sunnybrook Research Institute（桑尼布鲁克研究所）；Western University（西部大学）
Deep artificial neural networks (DNNs) have moved to the forefront of medical image analysis due to their success in classification, segmentation, and detection challenges. A principal challenge in large-scale deployment of DNNs in neuroimage analysis is the potential for shifts in signal-to-noise ratio, contrast, resolution, and presence of artifacts from site to site due to variances in scanners and acquisition protocols. DNNs are famously susceptible to these distribution shifts in computer vision. Currently, there are no benchmarking platforms or frameworks to assess the robustness of new …
A kinetic approach to consensus-based segmentation of biomedical images
University of Pavia（帕维亚大学）；INFN, Istituto Nazionale di Fisica Nucleare（国家核物理研究所）；Euler Institute, USI（瑞士意大利语区大学欧拉研究所）；IRCCS Mondino Foundation（IRCCS蒙迪诺基金会）
本文提出有界置信度一致性模型的动力学版本，结合 Fokker–Planck 近似与直接模拟 Monte Carlo 进行参数识别，并通过分割掩码损失优化二维生物医学灰度图像分割。
Philips Research North America（飞利浦北美研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）
Accurate, real-time segmentation of vessel structures in ultrasound image sequences can aid in the measurement of lumen diameters and assessment of vascular diseases. This, however, remains a challenging task, particularly for extremely small vessels that are difficult to visualize. We propose to leverage the rich spatiotemporal context available in ultrasound to improve segmentation of small-scale lower-extremity arterial vasculature. We describe efficient deep learning methods that incorporate temporal, spatial, and feature-aware contextual embeddings at multiple resolution scales while join…
Stable deep neural network architectures for mitochondria segmentation on electron microscopy volumes
University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））；Donostia International Physics Center (DIPC)（多诺斯蒂亚国际物理中心（DIPC））；Universidad Carlos III de Madrid（马德里卡洛斯三世大学）；Instituto de Investigación Sanitaria Gregorio Marañón（格雷戈里奥·马拉尼翁健康研究所）；Ikerbasque, Basque Foundation for Science（巴斯克科学基金会（Ikerbasque））
Florida Atlantic University（佛罗里达大西洋大学）；University of Technology（理工大学）；Babylon Health Directorate（巴比伦卫生局）
Traumatic brain injuries could cause intracranial hemorrhage (ICH). ICH could lead to disability or death if it is not accurately diagnosed and treated in a time-sensitive procedure. The current clinical protocol to diagnose ICH is examining Computerized Tomography (CT) scans by radiologists to detect ICH and localize its regions. However, this process relies heavily on the availability of an experienced radiologist. In this paper, we designed a study protocol to collect a dataset of 82 CT scans of subjects with traumatic brain injury. Later, the ICH regions were manually delineated in each sl…
The bottleneck of convolutional neural networks (CNN) for medical imaging is the number of annotated data required for training. Manual segmentation is considered to be the "gold-standard". However, medical imaging datasets with expert manual segmentation are scarce as this step is time-consuming and expensive. We propose in this work the use of what we refer to as silver standard masks for data augmentation in deep-learning-based skull-stripping also known as brain extraction. We generated the silver standard masks using the consensus algorithm Simultaneous Truth and Performance Level Estimat…
