Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across various out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms on three test sets. In addition, we also evaluated pre-existing AI frameworks--which, differing from algorithms, are more flexible and can support different algorithms--including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

Advancing Brain Imaging Analysis Step-by-step via Progressive Self-paced Learning

Recent advancements in deep learning have shifted the development of brain imaging analysis. However, several challenges remain, such as heterogeneity, individual variations, and the contradiction between the high dimensionality and small size of brain imaging datasets. These issues complicate the learning process, preventing models from capturing intrinsic, meaningful patterns and potentially leading to suboptimal performance due to biases and overfitting. Curriculum learning (CL) presents a promising solution by organizing training examples from simple to complex, mimicking the human learning process, and potentially fostering the development of more robust and accurate models. Despite its potential, the inherent limitations posed by small initial training datasets present significant challenges, including overfitting and poor generalization. In this paper, we introduce the Progressive Self-Paced Distillation (PSPD) framework, employing an adaptive and progressive pacing and distillation mechanism. This allows for dynamic curriculum adjustments based on the states of both past and present models. The past model serves as a teacher, guiding the current model with gradually refined curriculum knowledge and helping prevent the loss of previously acquired knowledge. We validate PSPD's efficacy and adaptability across various convolutional neural networks using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, underscoring its superiority in enhancing model performance and generalization capabilities. The source code for this approach will be released at https://github.com/Hrychen7/PSPD.

Centerline Boundary Dice Loss for Vascular Segmentation

Vascular segmentation in medical imaging plays a crucial role in analysing morphological and functional assessments. Traditional methods, like the centerline Dice (clDice) loss, ensure topology preservation but falter in capturing geometric details, especially under translation and deformation. The combination of clDice with traditional Dice loss can lead to diameter imbalance, favoring larger vessels. Addressing these challenges, we introduce the centerline boundary Dice (cbDice) loss function, which harmonizes topological integrity and geometric nuances, ensuring consistent segmentation across various vessel sizes. cbDice enriches the clDice approach by including boundary-aware aspects, thereby improving geometric detail recognition. It matches the performance of the boundary difference over union (B-DoU) loss through a mask-distance-based approach, enhancing traslation sensitivity. Crucially, cbDice incorporates radius information from vascular skeletons, enabling uniform adaptation to vascular diameter changes and maintaining balance in branch growth and fracture impacts. Furthermore, we conducted a theoretical analysis of clDice variants (cl-X-Dice). We validated cbDice's efficacy on three diverse vascular segmentation datasets, encompassing both 2D and 3D, and binary and multi-class segmentation. Particularly, the method integrated with cbDice demonstrated outstanding performance on the MICCAI 2023 TopCoW Challenge dataset. Our code is made publicly available at: https://github.com/PengchengShi1220/cbDice.

Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA

The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset and invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. TopCoW dataset was the first public dataset with voxel-level annotations for CoW's 13 vessel components, made possible by virtual-reality (VR) technology. It was also the first dataset with paired MRA and CTA from the same patients. TopCoW challenge aimed to tackle the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant's topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically.

A Chebyshev Confidence Guided Source-Free Domain Adaptation Framework for Medical Image Segmentation

Source-free domain adaptation (SFDA) aims to adapt models trained on a labeled source domain to an unlabeled target domain without the access to source data. In medical imaging scenarios, the practical significance of SFDA methods has been emphasized due to privacy concerns. Recent State-of-the-art SFDA methods primarily rely on self-training based on pseudo-labels (PLs). Unfortunately, PLs suffer from accuracy deterioration caused by domain shift, and thus limit the effectiveness of the adaptation process. To address this issue, we propose a Chebyshev confidence guided SFDA framework to accurately assess the reliability of PLs and generate self-improving PLs for self-training. The Chebyshev confidence is estimated by calculating probability lower bound of the PL confidence, given the prediction and the corresponding uncertainty. Leveraging the Chebyshev confidence, we introduce two confidence-guided denoising methods: direct denoising and prototypical denoising. Additionally, we propose a novel teacher-student joint training scheme (TJTS) that incorporates a confidence weighting module to improve PLs iteratively. The TJTS, in collaboration with the denoising methods, effectively prevents the propagation of noise and enhances the accuracy of PLs. Extensive experiments in diverse domain scenarios validate the effectiveness of our proposed framework and establish its superiority over state-of-the-art SFDA methods. Our paper contributes to the field of SFDA by providing a novel approach for precisely estimating the reliability of pseudo-labels and a framework for obtaining high-quality PLs, resulting in improved adaptation performance.

NexToU: Efficient Topology-Aware U-Net for Medical Image Segmentation

Convolutional neural networks (CNN) and Transformer variants have emerged as the leading medical image segmentation backbones. Nonetheless, due to their limitations in either preserving global image context or efficiently processing irregular shapes in visual objects, these backbones struggle to effectively integrate information from diverse anatomical regions and reduce inter-individual variability, particularly for the vasculature. Motivated by the successful breakthroughs of graph neural networks (GNN) in capturing topological properties and non-Euclidean relationships across various fields, we propose NexToU, a novel hybrid architecture for medical image segmentation. NexToU comprises improved Pool GNN and Swin GNN modules from Vision GNN (ViG) for learning both global and local topological representations while minimizing computational costs. To address the containment and exclusion relationships among various anatomical structures, we reformulate the topological interaction (TI) module based on the nature of binary trees, rapidly encoding the topological constraints into NexToU. Extensive experiments conducted on three datasets (including distinct imaging dimensions, disease types, and imaging modalities) demonstrate that our method consistently outperforms other state-of-the-art (SOTA) architectures. All the code is publicly available at https://github.com/PengchengShi1220/NexToU.

DECOR-NET: A COVID-19 Lung Infection Segmentation Network Improved by Emphasizing Low-level Features and Decorrelating Features

Since 2019, coronavirus Disease 2019 (COVID-19) has been widely spread and posed a serious threat to public health. Chest Computed Tomography (CT) holds great potential for screening and diagnosis of this disease. The segmentation of COVID-19 CT imaging can achieves quantitative evaluation of infections and tracks disease progression. COVID-19 infections are characterized by high heterogeneity and unclear boundaries, so capturing low-level features such as texture and intensity is critical for segmentation. However, segmentation networks that emphasize low-level features are still lacking. In this work, we propose a DECOR-Net capable of capturing more decorrelated low-level features. The channel re-weighting strategy is applied to obtain plenty of low-level features and the dependencies between channels are reduced by proposed decorrelation loss. Experiments show that DECOR-Net outperforms other cutting-edge methods and surpasses the baseline by 5.1% and 4.9% in terms of Dice coefficient and intersection over union. Moreover, the proposed decorrelation loss can improve the performance constantly under different settings. The Code is available at https://github.com/jiesihu/DECOR-Net.git.

Accelerating Diffusion Models via Pre-segmentation Diffusion Sampling for Medical Image Segmentation

Based on the Denoising Diffusion Probabilistic Model (DDPM), medical image segmentation can be described as a conditional image generation task, which allows to compute pixel-wise uncertainty maps of the segmentation and allows an implicit ensemble of segmentations to boost the segmentation performance. However, DDPM requires many iterative denoising steps to generate segmentations from Gaussian noise, resulting in extremely inefficient inference. To mitigate the issue, we propose a principled acceleration strategy, called pre-segmentation diffusion sampling DDPM (PD-DDPM), which is specially used for medical image segmentation. The key idea is to obtain pre-segmentation results based on a separately trained segmentation network, and construct noise predictions (non-Gaussian distribution) according to the forward diffusion rule. We can then start with noisy predictions and use fewer reverse steps to generate segmentation results. Experiments show that PD-DDPM yields better segmentation results over representative baseline methods even if the number of reverse steps is significantly reduced. Moreover, PD-DDPM is orthogonal to existing advanced segmentation models, which can be combined to further improve the segmentation performance.

Multi-modal Dynamic Graph Network: Coupling Structural and Functional Connectome for Disease Diagnosis and Classification

Multi-modal neuroimaging technology has greatlly facilitated the efficiency and diagnosis accuracy, which provides complementary information in discovering objective disease biomarkers. Conventional deep learning methods, e.g. convolutional neural networks, overlook relationships between nodes and fail to capture topological properties in graphs. Graph neural networks have been proven to be of great importance in modeling brain connectome networks and relating disease-specific patterns. However, most existing graph methods explicitly require known graph structures, which are not available in the sophisticated brain system. Especially in heterogeneous multi-modal brain networks, there exists a great challenge to model interactions among brain regions in consideration of inter-modal dependencies. In this study, we propose a Multi-modal Dynamic Graph Convolution Network (MDGCN) for structural and functional brain network learning. Our method benefits from modeling inter-modal representations and relating attentive multi-model associations into dynamic graphs with a compositional correspondence matrix. Moreover, a bilateral graph convolution layer is proposed to aggregate multi-modal representations in terms of multi-modal associations. Extensive experiments on three datasets demonstrate the superiority of our proposed method in terms of disease classification, with the accuracy of 90.4%, 85.9% and 98.3% in predicting Mild Cognitive Impairment (MCI), Parkinson's disease (PD), and schizophrenia (SCHZ) respectively. Furthermore, our statistical evaluations on the correspondence matrix exhibit a high correspondence with previous evidence of biomarkers.

Estimating Brain Age with Global and Local Dependencies

The brain age has been proven to be a phenotype of relevance to cognitive performance and brain disease. Achieving accurate brain age prediction is an essential prerequisite for optimizing the predicted brain-age difference as a biomarker. As a comprehensive biological characteristic, the brain age is hard to be exploited accurately with models using feature engineering and local processing such as local convolution and recurrent operations that process one local neighborhood at a time. Instead, Vision Transformers learn global attentive interaction of patch tokens, introducing less inductive bias and modeling long-range dependencies. In terms of this, we proposed a novel network for learning brain age interpreting with global and local dependencies, where the corresponding representations are captured by Successive Permuted Transformer (SPT) and convolution blocks. The SPT brings computation efficiency and locates the 3D spatial information indirectly via continuously encoding 2D slices from different views. Finally, we collect a large cohort of 22645 subjects with ages ranging from 14 to 97 and our network performed the best among a series of deep learning methods, yielding a mean absolute error (MAE) of 2.855 in validation set, and 2.911 in an independent test set.