Machine learning in medical imaging. MLMI (Workshop)最新文献

Skull segmentation from three-dimensional (3D) cone-beam computed tomography (CBCT) images is critical for the diagnosis and treatment planning of the patients with craniomaxillofacial (CMF) deformities. Convolutional neural network (CNN)-based methods are currently dominating volumetric image segmentation, but these methods suffer from the limited GPU memory and the large image size (e.g., 512 × 512 × 448). Typical ad-hoc strategies, such as down-sampling or patch cropping, will degrade segmentation accuracy due to insufficient capturing of local fine details or global contextual information. Other methods such as Global-Local Networks (GLNet) are focusing on the improvement of neural networks, aiming to combine the local details and the global contextual information in a GPU memory-efficient manner. However, all these methods are operating on regular grids, which are computationally inefficient for volumetric image segmentation. In this work, we propose a novel VoxelRend-based network (VR-U-Net) by combining a memory-efficient variant of 3D U-Net with a voxel-based rendering (VoxelRend) module that refines local details via voxel-based predictions on non-regular grids. Establishing on relatively coarse feature maps, the VoxelRend module achieves significant improvement of segmentation accuracy with a fraction of GPU memory consumption. We evaluate our proposed VR-U-Net in the skull segmentation task on a high-resolution CBCT dataset collected from local hospitals. Experimental results show that the proposed VR-U-Net yields high-quality segmentation results in a memory-efficient manner, highlighting the practical value of our method.

Accurate bone segmentation and landmark detection are two essential preparation tasks in computer-aided surgical planning for patients with craniomaxillofacial (CMF) deformities. Surgeons typically have to complete the two tasks manually, spending ~12 hours for each set of CBCT or ~5 hours for CT. To tackle these problems, we propose a multi-stage coarse-to-fine CNN-based framework, called SkullEngine, for high-resolution segmentation and large-scale landmark detection through a collaborative, integrated, and scalable JSD model and three segmentation and landmark detection refinement models. We evaluated our framework on a clinical dataset consisting of 170 CBCT/CT images for the task of segmenting 2 bones (midface and mandible) and detecting 175 clinically common landmarks on bones, teeth, and soft tissues. Experimental results show that SkullEngine significantly improves segmentation quality, especially in regions where the bone is thin. In addition, SkullEngine also efficiently and accurately detect all of the 175 landmarks. Both tasks were completed simultaneously within 3 minutes regardless of CBCT or CT with high segmentation quality. Currently, SkullEngine has been integrated into a clinical workflow to further evaluate its clinical efficiency.

Visual explanation methods have an important role in the prognosis of the patients where the annotated data is limited or unavailable. There have been several attempts to use gradient-based attribution methods to localize pathology from medical scans without using segmentation labels. This research direction has been impeded by the lack of robustness and reliability. These methods are highly sensitive to the network parameters. In this study, we introduce a robust visual explanation method to address this problem for medical applications. We provide an innovative visual explanation algorithm for general purpose and as an example application we demonstrate its effectiveness for quantifying lesions in the lungs caused by the Covid-19 with high accuracy and robustness without using dense segmentation labels. This approach overcomes the drawbacks of commonly used Grad-CAM and its extended versions. The premise behind our proposed strategy is that the information flow is minimized while ensuring the classifier prediction stays similar. Our findings indicate that the bottleneck condition provides a more stable severity estimation than the similar attribution methods. The source code will be publicly available upon publication.

Inpainting lesions is an important preprocessing task for algorithms analyzing brain MRIs of multiple sclerosis (MS) patients, such as tissue segmentation and cortical surface reconstruction. We propose a new deep learning approach for this task. Unlike existing inpainting approaches which ignore the lesion areas of the input image, we leverage the edge information around the lesions as a prior to help the inpainting process. Thus, the input of this network includes the T1-w image, lesion mask and the edge map computed from the T1-w image, and the output is the lesion-free image. The introduction of the edge prior is based on our observation that the edge detection results of the MRI scans will usually contain the contour of white matter (WM) and grey matter (GM), even though some undesired edges appear near the lesions. Instead of losing all the information around the neighborhood of lesions, our approach preserves the local tissue shape (brain/WM/GM) with the guidance of the input edges. The qualitative results show that our pipeline inpaints the lesion areas in a realistic and shape-consistent way. Our quantitative evaluation shows that our approach outperforms the existing state-of-the-art inpainting methods in both image-based metrics and in FreeSurfer segmentation accuracy. Furthermore, our approach demonstrates robustness to inaccurate lesion mask inputs. This is important for practical usability, because it allows for a generous over-segmentation of lesions instead of requiring precise boundaries, while still yielding accurate results.

Extensive studies focus on analyzing human brain functional connectivity from a network perspective, in which each network contains complex graph structures. Based on resting-state functional MRI (rs-fMRI) data, graph convolutional networks (GCNs) enable comprehensive mapping of brain functional connectivity (FC) patterns to depict brain activities. However, existing studies usually characterize static properties of the FC patterns, ignoring the time-varying dynamic information. In addition, previous GCN methods generally use fixed group-level (e.g., patients or controls) representation of FC networks, and thus, cannot capture subject-level FC specificity. To this end, we propose a Temporal-Adaptive GCN (TAGCN) framework that can not only take advantage of both spatial and temporal information using resting-state FC patterns and time-series but also explicitly characterize subject-level specificity of FC patterns. Specifically, we first segment each ROI-based time-series into multiple overlapping windows, then employ an adaptive GCN to mine topological information. We further model the temporal patterns for each ROI along time to learn the periodic brain status changes. Experimental results on 533 major depressive disorder (MDD) and health control (HC) subjects demonstrate that the proposed TAGCN outperforms several state-of-the-art methods in MDD vs. HC classification, and also can be used to capture dynamic FC alterations and learn valid graph representations.