Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention最新文献

Current deep learning-based models typically analyze medical images in either 2D or 3D albeit disregarding volumetric information or suffering sub-optimal performance due to the anisotropic resolution of MR data. Furthermore, providing an accurate uncertainty estimation is beneficial to clinicians, as it indicates how confident a model is about its prediction. We propose a novel 2.5D cross-slice attention model that utilizes both global and local information, along with an evidential critical loss, to perform evidential deep learning for the detection in MR images of prostate cancer, one of the most common cancers and a leading cause of cancer-related death in men. We perform extensive experiments with our model on two different datasets and achieve state-of-the-art performance in prostate cancer detection along with improved epistemic uncertainty estimation. The implementation of the model is available at https://github.com/aL3x-O-o-Hung/GLCSA_ECLoss.

We present in this paper a novel approach for 3D/2D intraoperative registration during neurosurgery via cross-modal inverse neural rendering. Our approach separates implicit neural representation into two components, handling anatomical structure preoperatively and appearance intraoperatively. This disentanglement is achieved by controlling a Neural Radiance Field's appearance with a multi-style hypernetwork. Once trained, the implicit neural representation serves as a differentiable rendering engine, which can be used to estimate the surgical camera pose by minimizing the dissimilarity between its rendered images and the target intraoperative image. We tested our method on retrospective patients' data from clinical cases, showing that our method outperforms state-of-the-art while meeting current clinical standards for registration. Code and additional resources can be found at https://maxfehrentz.github.io/style-ngp/.

Diffusion models have been used extensively for high quality image and video generation tasks. In this paper, we propose a novel conditional diffusion model with spatial attention and latent embedding (cDAL) for medical image segmentation. In cDAL, a convolutional neural network (CNN) based discriminator is used at every time-step of the diffusion process to distinguish between the generated labels and the real ones. A spatial attention map is computed based on the features learned by the discriminator to help cDAL generate more accurate segmentation of discriminative regions in an input image. Additionally, we incorporated a random latent embedding into each layer of our model to significantly reduce the number of training and sampling time-steps, thereby making it much faster than other diffusion models for image segmentation. We applied cDAL on 3 publicly available medical image segmentation datasets (MoNuSeg, Chest X-ray and Hippocampus) and observed significant qualitative and quantitative improvements with higher Dice scores and mIoU over the state-of-the-art algorithms. The source code is publicly available at https://github.com/Hejrati/cDAL/.

Neurodevelopment is exceptionally dynamic and critical during infancy, as many neurodevelopmental disorders emerge from abnormal brain development during this stage. Obtaining a full trajectory of neurodevelopment from existing incomplete longitudinal data can enrich our limited understanding of normal early brain development and help identify neurodevelopmental disorders. Although many regression models and deep learning methods have been proposed for longitudinal prediction based on incomplete datasets, they have two major drawbacks. First, regression models suffered from the strict requirements of input and output time points, which is less useful in practical scenarios. Second, although existing deep learning methods could predict cortical development at multiple ages, they predicted missing data independently with each available scan, yielding inconsistent predictions for a target time point given multiple inputs, which ignores longitudinal dependencies and introduces ambiguity in practical applications. To this end, we emphasize temporal consistency and develop a novel, flexible framework named longitudinally consistent triplet disentanglement autoencoder to predict an individualized longitudinal cortical developmental trajectory based on each available input by encouraging the similarity among trajectories with a dynamic time-warping loss. Specifically, to achieve individualized prediction, we employ a surfaced-based autoencoder, which decomposes the encoded latent features into identity-related and age-related features with an age estimation task and identity similarity loss as supervisions. These identity-related features are further combined with age conditions in the latent space to generate longitudinal developmental trajectories with the decoder. Experiments on predicting longitudinal infant cortical property maps validate the superior longitudinal consistency and exactness of our results compared to baselines'.

The cerebellum (i.e., little brain) plays an important role in motion and balances control abilities, despite its much smaller size and deeper sulci compared to the cerebrum. Previous cerebellum studies mainly relied on and focused on conventional volumetric analysis, which ignores the extremely deep and highly convoluted nature of the cerebellar cortex. To better reveal localized functional and structural changes, we propose cortical surface-based analysis of the cerebellar cortex. Specifically, we first reconstruct the cerebellar cortical surfaces to represent and characterize the highly folded cerebellar cortex in a geometrically accurate and topologically correct manner. Then, we propose a novel method to automatically parcellate the cerebellar cortical surface into anatomically meaningful regions by a weakly supervised graph convolutional neural network. Instead of relying on registration or requiring mapping the cerebellar surface to a sphere, which are either inaccurate or have large geometric distortions due to the deep cerebellar sulci, our learning-based model directly deals with the original cerebellar cortical surface by decomposing this challenging task into two steps. First, we learn the effective representation of the cerebellar cortical surface patches with a contrastive self-learning framework. Then, we map the learned representations to parcellation labels. We have validated our method using data from the Baby Connectome Project and the experimental results demonstrate its superior effectiveness and accuracy, compared to existing methods.

Multiple imaging modalities are often used for disease diagnosis, prediction, or population-based analyses. However, not all modalities might be available due to cost, different study designs, or changes in imaging technology. If the differences between the types of imaging are small, data harmonization approaches can be used; for larger changes, direct image synthesis approaches have been explored. In this paper, we develop an approach based on multi-modal metric learning to synthesize images of diverse modalities. We use metric learning via multi-modal image retrieval, resulting in embeddings that can relate images of different modalities. Given a large image database, the learned image embeddings allow us to use k-nearest neighbor (k-NN) regression for image synthesis. Our driving medical problem is knee osteoarthritis (KOA), but our developed method is general after proper image alignment. We test our approach by synthesizing cartilage thickness maps obtained from 3D magnetic resonance (MR) images using 2D radiographs. Our experiments show that the proposed method outperforms direct image synthesis and that the synthesized thickness maps retain information relevant to downstream tasks such as progression prediction and Kellgren-Lawrence grading (KLG). Our results suggest that retrieval approaches can be used to obtain high-quality and meaningful image synthesis results given large image databases.

Pruning has emerged as a powerful technique for compressing deep neural networks, reducing memory usage and inference time without significantly affecting overall performance. However, the nuanced ways in which pruning impacts model behavior are not well understood, particularly for long-tailed, multi-label datasets commonly found in clinical settings. This knowledge gap could have dangerous implications when deploying a pruned model for diagnosis, where unexpected model behavior could impact patient well-being. To fill this gap, we perform the first analysis of pruning's effect on neural networks trained to diagnose thorax diseases from chest X-rays (CXRs). On two large CXR datasets, we examine which diseases are most affected by pruning and characterize class "forgettability" based on disease frequency and co-occurrence behavior. Further, we identify individual CXRs where uncompressed and heavily pruned models disagree, known as pruning-identified exemplars (PIEs), and conduct a human reader study to evaluate their unifying qualities. We find that radiologists perceive PIEs as having more label noise, lower image quality, and higher diagnosis difficulty. This work represents a first step toward understanding the impact of pruning on model behavior in deep long-tailed, multi-label medical image classification. All code, model weights, and data access instructions can be found at https://github.com/VITA-Group/PruneCXR.

Exploring the relationship between the cognitive ability and infant cortical structural and functional development is critically important to advance our understanding of early brain development, which, however, is very challenging due to the complex and dynamic brain development in early postnatal stages. Conventional approaches typically use either the structural MRI or resting-state functional MRI and rely on the region-level features or inter-region connectivity features after cortical parcellation for predicting cognitive scores. However, these methods have two major issues: 1) spatial information loss, which discards the critical fine-grained spatial patterns containing rich information related to cognitive development; 2) modality information loss, which ignores the complementary information and the interaction between the structural and functional images. To address these issues, we unprecedentedly invent a novel framework, namely cortical surface-based multimodal learning framework (CSML), to leverage fine-grained multimodal features for cognition development prediction. First, we introduce the fine-grained surface-based data representation to capture spatially detailed structural and functional information. Then, a dual-branch network is proposed to extract the discriminative features for each modality respectively and further captures the modality-shared and complementary information with a disentanglement strategy. Finally, an age-guided cognition prediction module is developed based on the prior that the cognition develops along with age. We validate our method on an infant multimodal MRI dataset with 318 scans. Compared to state-of-the-art methods, our method consistently achieves superior performances, and for the first time suggests crucial regions and features for cognition development hidden in the fine-grained spatial details of cortical structure and function.

Multi-class cell segmentation in high-resolution Giga-pixel whole slide images (WSI) is critical for various clinical applications. Training such an AI model typically requires labor-intensive pixel-wise manual annotation from experienced domain experts (e.g., pathologists). Moreover, such annotation is error-prone when differentiating fine-grained cell types (e.g., podocyte and mesangial cells) via the naked human eye. In this study, we assess the feasibility of democratizing pathological AI deployment by only using lay annotators (annotators without medical domain knowledge). The contribution of this paper is threefold: (1) We proposed a molecular-empowered learning scheme for multi-class cell segmentation using partial labels from lay annotators; (2) The proposed method integrated Giga-pixel level molecular-morphology cross-modality registration, molecular-informed annotation, and molecular-oriented segmentation model, so as to achieve significantly superior performance via 3 lay annotators as compared with 2 experienced pathologists; (3) A deep corrective learning (learning with imperfect label) method is proposed to further improve the segmentation performance using partially annotated noisy data. From the experimental results, our learning method achieved F1 = 0.8496 using molecular-informed annotations from lay annotators, which is better than conventional morphology-based annotations (F1 = 0.7015) from experienced pathologists. Our method democratizes the development of a pathological segmentation deep model to the lay annotator level, which consequently scales up the learning process similar to a non-medical computer vision task. The official implementation and cell annotations are publicly available at https://github.com/hrlblab/MolecularEL.

Cochlear implants (CIs) are neuroprosthetics that can provide a sense of sound to people with severe-to-profound hearing loss. A CI contains an electrode array (EA) that is threaded into the cochlea during surgery. Recent studies have shown that hearing outcomes are correlated with EA placement. An image-guided cochlear implant programming technique is based on this correlation and utilizes the EA location with respect to the intracochlear anatomy to help audiologists adjust the CI settings to improve hearing. Automated methods to localize EA in postoperative CT images are of great interest for large-scale studies and for translation into the clinical workflow. In this work, we propose a unified deep-learning-based framework for automated EA localization. It consists of a multi-task network and a series of postprocessing algorithms to localize various types of EAs. The evaluation on a dataset with 27 cadaveric samples shows that its localization error is slightly smaller than the state-of-the-art method. Another evaluation on a large-scale clinical dataset containing 561 cases across two institutions demonstrates a significant improvement in robustness compared to the state-of-the-art method. This suggests that this technique could be integrated into the clinical workflow and provide audiologists with information that facilitates the programming of the implant leading to improved patient care.