Hui Xue

Sarah M. Hooper, Hui Xue

Biomedical imaging modalities often produce high-resolution, multi-dimensional images that pose computational challenges for deep neural networks. These computational challenges are compounded when training transformers due to the self-attention operator, which scales quadratically with context length. Recent developments in long-context models have potential to alleviate these difficulties and enable more efficient application of transformers to large biomedical images, although a systematic evaluation on this topic is lacking. In this study, we investigate the impact of context length on biomedical image analysis and we evaluate the performance of recently proposed long-context models. We first curate a suite of biomedical imaging datasets, including 2D and 3D data for segmentation, denoising, and classification tasks. We then analyze the impact of context length on network performance using the Vision Transformer and Swin Transformer by varying patch size and attention window size. Our findings reveal a strong relationship between context length and performance, particularly for pixel-level prediction tasks. Finally, we show that recent long-context models demonstrate significant improvements in efficiency while maintaining comparable performance, though we highlight where gaps remain. This work underscores the potential and challenges of using long-context models in biomedical imaging.

Pengfei Fang, Yongchun Qin, Hui Xue

Few-shot Class-Incremental Learning (FSCIL) addresses the challenges of evolving data distributions and the difficulty of data acquisition in real-world scenarios. To counteract the catastrophic forgetting typically encountered in FSCIL, knowledge distillation is employed as a way to maintain the knowledge from learned data distribution. Recognizing the limitations of generating discriminative feature representations in a few-shot context, our approach incorporates structural information between samples into knowledge distillation. This structural information serves as a remedy for the low quality of features. Diverging from traditional structured distillation methods that compute sample similarity, we introduce the Displacement Knowledge Distillation (DKD) method. DKD utilizes displacement rather than similarity between samples, incorporating both distance and angular information to significantly enhance the information density retained through knowledge distillation. Observing performance disparities in feature distribution between base and novel classes, we propose the Dual Distillation Network (DDNet). This network applies traditional knowledge distillation to base classes and DKD to novel classes, challenging the conventional integration of novel classes with base classes. Additionally, we implement an instance-aware sample selector during inference to dynamically adjust dual branch weights, thereby leveraging the complementary strengths of each approach. Extensive testing on three benchmarks demonstrates that DDNet achieves state-of-the-art results. Moreover, through rigorous experimentation and comparison, we establish the robustness and general applicability of our proposed DKD method.

Yi Zhang, Yidong Zhao, Hui Xue et al.

Image registration is essential for medical image applications where alignment of voxels across multiple images is needed for qualitative or quantitative analysis. With recent advancements in deep neural networks and parallel computing, deep learning-based medical image registration methods become competitive with their flexible modelling and fast inference capabilities. However, compared to traditional optimization-based registration methods, the speed advantage may come at the cost of registration performance at inference time. Besides, deep neural networks ideally demand large training datasets while optimization-based methods are training-free. To improve registration accuracy and data efficiency, we propose a novel image registration method, termed Recurrent Inference Image Registration (RIIR) network. RIIR is formulated as a meta-learning solver to the registration problem in an iterative manner. RIIR addresses the accuracy and data efficiency issues, by learning the update rule of optimization, with implicit regularization combined with explicit gradient input. We evaluated RIIR extensively on brain MRI and quantitative cardiac MRI datasets, in terms of both registration accuracy and training data efficiency. Our experiments showed that RIIR outperformed a range of deep learning-based methods, even with only $5\%$ of the training data, demonstrating high data efficiency. Key findings from our ablation studies highlighted the important added value of the hidden states introduced in the recurrent inference framework for meta-learning. Our proposed RIIR offers a highly data-efficient framework for deep learning-based medical image registration.

Hui Xue, Jessica Artico, Marianna Fontana et al.

Purpose: To develop a convolutional neural network (CNN) solution for robust landmark detection in cardiac MR images. Methods: This retrospective study included cine, LGE and T1 mapping scans from two hospitals. The training set included 2,329 patients and 34,019 images. A hold-out test set included 531 patients and 7,723 images. CNN models were developed to detect two mitral valve plane and apical points on long-axis (LAX) images. On short-axis (SAX) images, anterior and posterior RV insertion points and LV center were detected. Model outputs were compared to manual labels by two operators for accuracy with a t-test for statistical significance. The trained model was deployed to MR scanners. Results: For the LAX images, success detection was 99.8% for cine, 99.4% for LGE. For the SAX, success rate was 96.6%, 97.6% and 98.9% for cine, LGE and T1-mapping. The L2 distances between model and manual labels were 2 to 3.5 mm, indicating close agreement between model landmarks to manual labels. No significant differences were found for the anterior RV insertion angle and LV length by the models and operators for all views and imaging sequences. Model inference on MR scanner took 610ms/5.6s on GPU/CPU, respectively, for a typical cardiac cine series. Conclusions: This study developed, validated and deployed a CNN solution for robust landmark detection in both long and short-axis CMR images for cine, LGE and T1 mapping sequences, with the accuracy comparable to the inter-operator variation.

Hui Xue, Rhodri Davies, Louis AE Brown et al.

Recent development of quantitative myocardial blood flow (MBF) mapping allows direct evaluation of absolute myocardial perfusion, by computing pixel-wise flow maps. Clinical studies suggest quantitative evaluation would be more desirable for objectivity and efficiency. Objective assessment can be further facilitated by segmenting the myocardium and automatically generating reports following the AHA model. This will free user interaction for analysis and lead to a 'one-click' solution to improve workflow. This paper proposes a deep neural network based computational workflow for inline myocardial perfusion analysis. Adenosine stress and rest perfusion scans were acquired from three hospitals. Training set included N=1,825 perfusion series from 1,034 patients. Independent test set included 200 scans from 105 patients. Data were consecutively acquired at each site. A convolution neural net (CNN) model was trained to provide segmentation for LV cavity, myocardium and right ventricular by processing incoming 2D+T perfusion Gd series. Model outputs were compared to manual ground-truth for accuracy of segmentation and flow measures derived on global and per-sector basis. The trained models were integrated onto MR scanners for effective inference. Segmentation accuracy and myocardial flow measures were compared between CNN models and manual ground-truth. The mean Dice ratio of CNN derived myocardium was 0.93 +/- 0.04. Both global flow and per-sector values showed no significant difference, compared to manual results. The AHA 16 segment model was automatically generated and reported on the MR scanner. As a result, the fully automated analysis of perfusion flow mapping was achieved. This solution was integrated on the MR scanner, enabling 'one-click' analysis and reporting of myocardial blood flow.

Hui Xue, Ethan Tseng, Kristopher D Knott et al.

Quantification of myocardial perfusion has the potential to improve detection of regional and global flow reduction. Significant effort has been made to automate the workflow, where one essential step is the arterial input function (AIF) extraction. Since failure here invalidates quantification, high accuracy is required. For this purpose, this study presents a robust AIF detection method using the convolutional neural net (CNN) model. CNN models were trained by assembling 25,027 scans (N=12,984 patients) from three hospitals, seven scanners. A test set of 5,721 scans (N=2,805 patients) evaluated model performance. The 2D+T AIF time series was inputted into CNN. Two variations were investigated: a) Two Classes (2CS) for background and foreground (LV mask); b) Three Classes (3CS) for background, foreground LV and RV. Final model was deployed on MR scanners via the Gadgetron InlineAI. Model loading time on MR scanner was ~340ms and applying it took ~180ms. The 3CS model successfully detect LV for 99.98% of all test cases (1 failed out of 5,721 cases). The mean Dice ratio for 3CS was 0.87+/-0.08 with 92.0% of all test cases having Dice ratio >0.75, while the 2CS model gave lower Dice of 0.82+/-0.22 (P<1e-5). Extracted AIF signals using CNN were further compared to manual ground-truth for foot-time, peak-time, first-pass duration, peak value and area-under-curve. No significant differences were found for all features (P>0.2). This study proposed, validated, and deployed a robust CNN solution to detect the LV for the extraction of the AIF signal used in fully automated perfusion flow mapping. A very large data cohort was assembled and resulting models were deployed to MR scanners for fully inline AI in clinical hospitals.