Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin

Abstract

Lacunes of presumed vascular origin (lacunes) are associated with an increased risk of stroke, gait impairment, and dementia and are a primary imaging feature of the small vessel disease. Quantification of lacunes may be of great importance to elucidate the mechanisms behind neuro-degenerative disorders and is recommended as part of study standards for small vessel disease research. However, due to the different appearance of lacunes in various brain regions and the existence of other similar-looking structures, such as perivascular spaces, manual annotation is a difficult, elaborative and subjective task, which can potentially be greatly improved by reliable and consistent computer-aided detection (CAD) routines.In this paper, we propose an automated two-stage method using deep convolutional neural networks (CNN). We show that this method has good performance and can considerably benefit readers. We first use a fully convolutional neural network to detect initial candidates. In the second step, we employ a 3D CNN as a false positive reduction tool. As the location information is important to the analysis of candidate structures, we further equip the network with contextual information using multi-scale analysis and integration of explicit location features. We trained, validated and tested our networks on a large dataset of 1075 cases obtained from two different studies. Subsequently, we conducted an observer study with four trained observers and compared our method with them using a free-response operating characteristic analysis. Shown on a test set of 111 cases, the resulting CAD system exhibits performance similar to the trained human observers and achieves a sensitivity of 0.974 with 0.13 false positives per slice. A feasibility study also showed that a trained human observer would considerably benefit once aided by the CAD system.

Multi-branch convolutional neural network for multiple sclerosis lesion segmentation

“…To deal with this problem, we proposed a whole-brain slice-based approach. Compared with patch-based methods (Valverde et al, 2017;Ghafoorian et al, 2017), we have shown that our model has better performance for most measures, as seen in Table 2. Although the CNN proposed by Valverde et al (2017) had the highest DSC value among all, our method showed better performance regarding the LTPR and LFPR, which indicates that our model is robust in identifying the correct location of lesions.…”

Deep Learning for Medical Image Analysis: Applications to Computed Tomography and Magnetic Resonance Imaging

“…In a study by Ghafoorian et al, a CNN model was trained to detect lacunes from T1 and FLAIR brain MRI patches that are closely related to neurodegenerative disorders [17]. By changing the fully-connected layers of the trained patch-based model to convolution layers, they could effectively create a lacunes probability map of the whole brain MRIs.…”

Single‐shot T2 mapping using overlapping‐echo detachment planar imaging and a deep convolutional neural network

“…Deep learning, a family of algorithms for efficiently learning complicated dependencies of outputs on input data and propagating a training dataset through several layers of hidden units, have shown explosive popularity in recent years with the availability of powerful graphics processing units (GPUs) . Deep neural network (DNN) architectures, convolutional neural network (CNN) in particular, are finding more and more applications in medical imaging analysis for various problems including classification, detection and segmentation . It has already been demonstrated that CNN outperforms sparsity‐based methods in super‐resolution reconstruction …”