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

Lewy Body Disease (LBD) is a common but understudied dementia that poses a significant public health burden. It shares similar clinical signs with Alzheimer's disease (AD), with both conditions progressing through stages of normal cognition, mild cognitive impairment, and dementia. A major obstacle in LBD diagnosis is data scarcity, which limits the effectiveness of deep learning models. In contrast, AD datasets are more abundant, offering a potential avenue for knowledge transfer. However, LBD and AD data are typically collected from different sites using varied machines and protocols, resulting in a distinct domain shift. To effectively leverage AD data while mitigating domain shift, we propose a Transferability Aware Transformer (TAT) that adapts knowledge from AD to enhance LBD diagnosis. Our method utilizes structural connectivity (SC) derived from structural MRI as training data. Built on the attention mechanism, TAT assigns high weights to disease-transferable features while suppressing domain-specific ones, effectively reducing domain shift and improving diagnostic accuracy on limited LBD data. The experimental results demonstrate the effectiveness of TAT. Our work serves as the first to explore domain adaptation from AD to LBD study under data scarcity and domain shift scenarios, providing a promising framework for domain-adaptive diagnosis of rare diseases.

Preclinical imaging studies are vital to the research, development, and evaluation of new medical therapies. Images acquired during these studies often have high in-plane resolution but low through-plane resolution, resulting in highly anisotropic volumes that hamper downstream volumetric analysis. Additionally, since there are no image acquisition standards across studies, training data for conventional supervised super-resolution (SR) methods is limited. In this work, we compare two SR methods that do not require additional training data. The first is ECLARE, a self-SR approach that creates its own training data from in-plane patches drawn from the anisotropic volume. The second is Biplanar Denoising diffusion null space model (DDNM) Averaging (BiDA), a proposed method leveraging two independently pre-trained denoising diffusion probabilistic models and the DDNM posterior sampling technique. We evaluate both methods first on rat data at two scale factors (2.5× and .5×) and compare signal recovery and downstream task performance. We further evaluate these methods on a different species (mice) to measure their generalizability. Both methods experimentally resulted in good signal recovery performance, but only the images super-resolved by BiDA were accurately skullstripped downstream. Although both methods performed well on the in-domain rat data, BiDA did not fully generalize to the out-of-domain mouse data.

Radiographic knee alignment (KA) measurement is important for predicting joint health and surgical outcomes after total knee replacement. Traditional methods for KA measurements are manual, time-consuming and require long-leg radiographs. This study proposes a deep learning-based method to measure KA in anteroposterior knee radiographs via automatically localized knee anatomical landmarks. Our method builds on hourglass networks and incorporates an attention gate structure to enhance robustness and focus on key anatomical features. To our knowledge, this is the first deep learning-based method to localize over 100 knee anatomical landmarks to fully outline the knee shape while integrating KA measurements on both pre-operative and post-operative images. It provides highly accurate and reliable anatomical varus/valgus KA measurements using the anatomical tibiofemoral angle, achieving mean absolute differences ~1° when compared to clinical ground truth measurements. Agreement between automated and clinical measurements was excellent pre-operatively (intra-class correlation coefficient (ICC) = 0.97) and good post-operatively (ICC = 0.86). Our findings demonstrate that KA assessment can be automated with high accuracy, creating opportunities for digitally enhanced clinical workflows.

Embodied AI (E-AI) in the form of intelligent surgical robotics and other agents is calling for data platforms to facilitate its development and deployment. In this work, we present a cross-platform multimodal data recording and streaming software, MUTUAL, successfully deployed on two clinical studies, along with its ROS 2 distributed adaptation, MUTUAL-ROS 2. We describe and compare the two implementations of MUTUAL through their recording performance under different settings. MUTUAL offers robust recording performance at target configurations for multiple modalities, including video, audio, and live expert commentary. While this recording performance is not matched by MUTUAL-ROS 2, we demonstrate its advantages related to real-time streaming capabilities for AI inference and more horizontal scalability, key aspects for E-AI systems in the operating room. Our findings demonstrate that the baseline MUTUAL is well-suited for data curation and offline analysis, whereas MUTUAL-ROS 2, should match the recording reliability of the baseline system under a fully distributed manner where modalities are handled independently by edge computing devices. These insights are critical for advancing the integration of E-AI in surgical practice, ensuring that data infrastructure can support both robust recording and real-time processing needs.

Despite the strong prediction power of deep learning models, their interpretability remains an important concern. Disentanglement models increase interpretability by decomposing the latent space into interpretable subspaces. In this paper, we propose the first disentanglement method for pathology images. We focus on the task of detecting tumor-infiltrating lymphocytes (TIL). We propose different ideas including cascading disentanglement, novel architecture, and reconstruction branches. We achieve superior performance on complex pathology images, thus improving the interpretability and even generalization power of TIL detection deep learning models. Our codes are available at https://github.com/Shauqi/SS-cVAE.

During a fetal ultrasound scan, a sonographer will zoom in and zoom out as they attempt to get clearer images of the anatomical structures of interest. This paper explores how to use this zoom information which is an under-utilised piece of information that is extractable from fetal ultrasound images. We explore associating zooming patterns to specific structures. The presence of such patterns would indicate that each individual anatomical structure has a unique signature associated with it, thereby allowing for classification of fetal ultrasound clips without directly reading the actual fetal ultrasound images in a convolutional neural network.

The robustness of supervised deep learning-based medical image classification is significantly undermined by label noise in the training data. Although several methods have been proposed to enhance classification performance in the presence of noisy labels, they face some challenges: 1) a struggle with class-imbalanced datasets, leading to the frequent overlooking of minority classes as noisy samples; 2) a singular focus on maximizing performance using noisy datasets, without incorporating experts-in-the-loop for actively cleaning the noisy labels. To mitigate these challenges, we propose a two-phase approach that combines Learning with Noisy Labels (LNL) and active learning. This approach not only improves the robustness of medical image classification in the presence of noisy labels but also iteratively improves the quality of the dataset by relabeling the important incorrect labels, under a limited annotation budget. Furthermore, we introduce a novel Variance of Gradients approach in the LNL phase, which complements the loss-based sample selection by also sampling under-represented examples. Using two imbalanced noisy medical classification datasets, we demonstrate that our proposed technique is superior to its predecessors at handling class imbalance by not misidentifying clean samples from minority classes as mostly noisy samples. Code available at: https://github.com/Bidur-Khanal/imbalanced-medical-active-label-cleaning.git.

Subtype and Stage Inference (SuStaIn) is a useful Event-based Model for capturing both the temporal and the phenotypical patterns for any progressive disorders, which is essential for understanding the heterogeneous nature of such diseases. However, this model cannot capture subtypes with different progression rates with respect to predefined biomarkers with fixed events prior to inference. Therefore, we propose an adaptive algorithm for learning subtype-specific events while making subtype and stage inference. We use simulation to demonstrate the improvement with respect to various performance metrics. Finally, we provide snapshots of different levels of biomarker abnormality within different subtypes on Alzheimer's Disease (AD) data to demonstrate the effectiveness of our algorithm.

Supervised methods for 3D anatomy segmentation demonstrate superior performance but are often limited by the availability of annotated data. This limitation has led to a growing interest in self-supervised approaches in tandem with the abundance of available unannotated data. Slice propagation has emerged as a self-supervised approach that leverages slice registration as a self-supervised task to achieve full anatomy segmentation with minimal supervision. This approach significantly reduces the need for domain expertise, time, and the cost associated with building fully annotated datasets required for training segmentation networks. However, this shift toward reduced supervision via deterministic networks raises concerns about the trustworthiness and reliability of predictions, especially when compared with more accurate supervised approaches. To address this concern, we propose integrating calibrated uncertainty quantification (UQ) into slice propagation methods, which would provide insights into the model's predictive reliability and confidence levels. Incorporating uncertainty measures enhances user confidence in self-supervised approaches, thereby improving their practical applicability. We conducted experiments on three datasets for 3D abdominal segmentation using five UQ methods. The results illustrate that incorporating UQ improves not only model trustworthiness but also segmentation accuracy. Furthermore, our analysis reveals various failure modes of slice propagation methods that might not be immediately apparent to end-users. This study opens up new research avenues to improve the accuracy and trustworthiness of slice propagation methods.

Neuroimage modalities acquired by longitudinal studies often provide complementary information regarding disease progression. For example, amyloid PET visualizes the build-up of amyloid plaques that appear in earlier stages of Alzheimer's disease (AD), while structural MRIs depict brain atrophy appearing in the later stages of the disease. To accurately model multi-modal longitudinal data, we propose an interpretable self-supervised model called Self-Organized Multi-Modal Longitudinal Maps (SOM2LM). SOM2LM encodes each modality as a 2D self-organizing map (SOM) so that one dimension of each modality-specific SOMs corresponds to disease abnormality. The model also regularizes across modalities to depict their temporal order of capturing abnormality. When applied to longitudinal T1w MRIs and amyloid PET of the Alzheimer's Disease Neuroimaging Initiative (ADNI, N=741), SOM2LM generates interpretable latent spaces that characterize disease abnormality. When compared to state-of-art models, it achieves higher accuracy for the downstream tasks of cross-modality prediction of amyloid status from T1w-MRI and joint-modality prediction of individuals with mild cognitive impairment converting to AD using both MRI and amyloid PET. The code is available at https://github.com/ouyangjiahong/longitudinal-som-multi-modality.