Landmark-based deep multi-instance learning for brain disease diagnosis

By Mingxia Liu, Jun Zhang, Ehsan Adeli, Dinggang Shen. 2017

398 citations recorded by the source corpus.

HighlightsWe developed a novel deep multi‐instance convolutional neural network to automatically learn both local and global representations for MR images.We proposed a landmark‐based image patch extraction approach based on a data‐driven landmark discovery algorithm.We trained the model on ADNI‐1 and tested it on two independent datasets (i.e., ADNI‐2 and MIRIAD). Graphical abstract Figure. No Caption available. Abstract In conventional Magnetic Resonance (MR) image based methods, two stages are often involved to capture brain structural information for disease diagnosis, i.e., 1) manually partitioning each MR image into a number of regions‐of‐interest (ROIs), and 2) extracting pre‐defined features from each ROI for diagnosis with a certain classifier. However, these pre‐defined features often limit the performance of the diagnosis, due to challenges in 1) defining the ROIs and 2) extracting effective disease‐related features. In this paper, we propose a landmark‐based deep multi‐instance learning (LDMIL) framework for brain disease diagnosis. Specifically, we first adopt a data‐driven learning approach to discover disease‐related anatomical landmarks in the brain MR images, along with their nearby image patches. Then, our LDMIL framework learns an end‐to‐end MR image classifier for capturing both the local structural information conveyed by image patches located by landmarks and the global structural information derived from all detected landmarks. We have evaluated our proposed framework on 1526 subjects from three public datasets (i.e., ADNI‐1, ADNI‐2, and MIRIAD), and the experimental results show that our framework can achieve superior performance over state‐of‐the‐art approaches.

Subfields: Computer Vision and Pattern Recognition, Neurology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Neurology

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, background): “Alzheimer’s disease [274] Landmark-based deep multi-instance learning evaluated on 1526 subjects from three public datasets (ADNI-1,”
Accurate brain age prediction with lightweight deep neural networks (2019, background): “, 2017), taking patches (Kamnitsas et al., 2017; Liu et al., 2018) or 2D slices (Bashyam et al.”
Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer’s Disease Diagnosis using Structural MRI (2018, methodology): “Capitalizing on task-oriented, high-nonlinear feature extraction for classiﬁer construction, CNNs have also been applied to developing advanced CAD methods for brain disease diagnosis [31], [32], [33], [34].”
A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis (2019, methodology): “In recent years, Deep Learning (DL) has emerged as the state-of-the-art technique for performing many medical image analysis tasks (Tajbakhsh et al., 2020; Tizhoosh and Pan-tanowitz, 2018; Shen et al., 2017; Litjens et al., 2017; Suzuki, 2017).”
Deep Bayesian Hashing with Center Prior for Multi-modal Neuroimage Retrieval (2020, background): “In practice, it is important to provide physicians with previous cases (with visually similar neuroimages) and their corresponding treatment records to facilitate case-based reasoning and evidence-based medicine in clinical decision making [19], [20].”
Brain MRI analysis for Alzheimer’s disease diagnosis using an ensemble system of deep convolutional neural networks (2018, background): “However, training a classifier independent from the feature extraction process may result in sub-optimal performance due to the possible heterogeneous nature of the classifier and features [72].”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, background): “In recent years, a large amount of work has been published on deep learning based prediction tasks such as brain age prediction [136], [137], [138], Alzheimer’s disease classification and trajectory modeling [139], [140], [141], [142], and schizophrenia classification [143], [144].”