Search

State-of-the-art deep learning-based registration methods employ three different learning strategies: supervised learning, which requires costly manual annotations, unsupervised learning, which heavily relies on hand-crafted similarity metrics designed by domain experts, or learning from synthetic data, which introduces a domain shift. To overcome the limitations of these strategies, we propose a novel self-supervised learning paradigm for unsupervised registration, relying on self-training. Our idea is based on two key insights. Feature-based differentiable optimizers 1) perform reasonable registration even from random features and 2) stabilize the training of the preceding feature extraction network on noisy labels. Consequently, we propose cyclical self-training, where pseudo labels are initialized as the displacement fields inferred from random features and cyclically updated based on more and more expressive features from the learning feature extractor, yielding a self-reinforcement effect. We evaluate the method for abdomen and lung registration, consistently surpassing metric-based supervision and outperforming diverse state-of-the-art competitors. Source code is available at https://github.com/multimodallearning/reg-cyclical-self-train., Comment: accepted at MICCAI 2023

Affine registration is indispensable in a comprehensive medical image registration pipeline. However, only a few studies focus on fast and robust affine registration algorithms. Most of these studies utilize convolutional neural networks (CNNs) to learn joint affine and non-parametric registration, while the standalone performance of the affine subnetwork is less explored. Moreover, existing CNN-based affine registration approaches focus either on the local misalignment or the global orientation and position of the input to predict the affine transformation matrix, which are sensitive to spatial initialization and exhibit limited generalizability apart from the training dataset. In this paper, we present a fast and robust learning-based algorithm, Coarse-to-Fine Vision Transformer (C2FViT), for 3D affine medical image registration. Our method naturally leverages the global connectivity and locality of the convolutional vision transformer and the multi-resolution strategy to learn the global affine registration. We evaluate our method on 3D brain atlas registration and template-matching normalization. Comprehensive results demonstrate that our method is superior to the existing CNNs-based affine registration methods in terms of registration accuracy, robustness and generalizability while preserving the runtime advantage of the learning-based methods. The source code is available at https://github.com/cwmok/C2FViT., Accepted by CVPR2022

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Registration of pre-operative and post-recurrence brain images is often needed to evaluate the effectiveness of brain gliomas treatment. While recent deep learning-based deformable registration methods have achieved remarkable success with healthy brain images, most of them would be unable to accurately align images with pathologies due to the absent correspondences in the reference image. In this paper, we propose a deep learning-based deformable registration method that jointly estimates regions with absent correspondence and bidirectional deformation fields. A forward-backward consistency constraint is used to aid in the localization of the resection and recurrence region from voxels with absence correspondences in the two images. Results on 3D clinical data from the BraTS-Reg challenge demonstrate our method can improve image alignment compared to traditional and deep learning-based registration approaches with or without cost function masking strategy. The source code is available at https://github.com/cwmok/DIRAC., Comment: Accepted by MICCAI2022

Recent deep learning-based methods have shown promising results and runtime advantages in deformable image registration. However, analyzing the effects of hyperparameters and searching for optimal regularization parameters prove to be too prohibitive in deep learning-based methods. This is because it involves training a substantial number of separate models with distinct hyperparameter values. In this paper, we propose a conditional image registration method and a new self-supervised learning paradigm for deep deformable image registration. By learning the conditional features that are correlated with the regularization hyperparameter, we demonstrate that optimal solutions with arbitrary hyperparameters can be captured by a single deep convolutional neural network. In addition, the smoothness of the resulting deformation field can be manipulated with arbitrary strength of smoothness regularization during inference. Extensive experiments on a large-scale brain MRI dataset show that our proposed method enables the precise control of the smoothness of the deformation field without sacrificing the runtime advantage or registration accuracy., Comment: Early accepted by MICCAI2021

Supplemental material, sj-pdf-1-aim-10.1177_0964528420920285 for Economic evaluation alongside a randomised controlled trial to assess the effectiveness and cost-effectiveness of acupuncture in the management of chemotherapy-induced peripheral neuropathy by Alex Molassiotis, Bryony Dawkins, Roberta Longo, Lorna KP Suen, Hui Lin Cheng, Tony Mok, Claire T Hulme and Winnie Yeo: KAMIR-NIH Investigators in Acupuncture in Medicine

Deep learning-based methods have recently demonstrated promising results in deformable image registration for a wide range of medical image analysis tasks. However, existing deep learning-based methods are usually limited to small deformation settings, and desirable properties of the transformation including bijective mapping and topology preservation are often being ignored by these approaches. In this paper, we propose a deep Laplacian Pyramid Image Registration Network, which can solve the image registration optimization problem in a coarse-to-fine fashion within the space of diffeomorphic maps. Extensive quantitative and qualitative evaluations on two MR brain scan datasets show that our method outperforms the existing methods by a significant margin while maintaining desirable diffeomorphic properties and promising registration speed., Comment: Paper accepted by MICCAI 2020

The impact of smoking on the effectiveness of immune checkpoint inhibitors — a systematic review and meta-analysis

Figure S1. (A) PM2.5 and NNK induced lung Bet1A1 and NCI-H23 cell proliferation. (B) Sphere formation of lung cancer stem cells induced by PM2.5 or NNK. (C) CSC tumor sphere assay on PM2.5- or NNK-treated Bet1A and NCI-H23 cells. (D) PM2.5 induced Bet1A and NCI-H23 cell invasion. (E) PM2.5and NNK treatment with 28 days promoted the expression of lung cell carcinogenesis-related biomarkers. Figure S2. (A) 15-LOX1 and 15-LOX2 expression in human lung tumor tissues and non-tumor tissues. (B) The levels of vimentin in 109 paired NSCLC tissues and adjacent normal non-tumor tissues. (C) Vimentin expression in human lung tumor tissues and non-tumor tissues. (D) Restoration of 15-LOX1 and 15-LOX2 activities inhibited the effects of PM2.5 or NNK on the expression of lung carcinogenetic proteins. (E) Restoration of 15-LOX1 and 15-LOX2 activities inhibited the effects of PM2.5 or NNK on cell migration. Figure S3. MassArray design for 15-LOX1 methylation detection. (A) Sequence information of 15-LOX1 methylation design. (B) Prediction of potential CpG islands using http://www.ebi.ac.uk/Tools/seqstats/emboss_cpgplot/ website. (C) Primers design using sequenomÂŽEpiDesigner program. Figure S4. Cloning of 15-LOX1 3'-UTR and 15-LOX2 3'-UTR. Table S1. Baseline demographic characteristics of 109 human NSCLC patients underwent Vimentin analysis. Table S2. Human 15-LOX1 gene methylation level in NCI-H23 and Bet1A cells treated by PM2.5 and NNK. (DOCX 8597 kb)

There is a common belief that the successful training of deep neural networks requires many annotated training samples, which are often expensive and difficult to obtain especially in the biomedical imaging field. While it is often easy for researchers to use data augmentation to expand the size of training sets, constructing and generating generic augmented data that is able to teach the network the desired invariance and robustness properties using traditional data augmentation techniques is challenging in practice. In this paper, we propose a novel automatic data augmentation method that uses generative adversarial networks to learn augmentations that enable machine learning based method to learn the available annotated samples more efficiently. The architecture consists of a coarse-to-fine generator to capture the manifold of the training sets and generate generic augmented data. In our experiments, we show the efficacy of our approach on a Magnetic Resonance Imaging (MRI) image, achieving improvements of 3.5% Dice coefficient on the BRATS15 Challenge dataset as compared to traditional augmentation approaches. Also, our proposed method successfully boosts a common segmentation network to reach the state-of-the-art performance on the BRATS15 Challenge.

BACKGROUND: The efficacy of the ALK inhibitor crizotinib as compared with standard chemotherapy as first-line treatment for advanced ALK-positive non-small-cell lung cancer (NSCLC) is unknown. METHODS: We conducted an open-label, phase 3 trial comparing crizotinib with chemotherapy in 343 patients with advanced ALK-positive nonsquamous NSCLC who had received no previous systemic treatment for advanced disease. Patients were randomly assigned to receive oral crizotinib at a dose of 250 mg twice daily or to receive intravenous chemotherapy (pemetrexed, 500 mg per square meter of body-surface area, plus either cisplatin, 75 mg per square meter, or carboplatin, target area under the curve of 5 to 6 mg per milliliter per minute) every 3 weeks for up to six cycles. Crossover to crizotinib treatment after disease progression was permitted for patients receiving chemotherapy. The primary end point was progression-free survival as assessed by independent radiologic review. RESULTS: Progression-free survival was significantly longer with crizotinib than with chemotherapy (median, 10.9 months vs. 7.0 months; hazard ratio for progression or death with crizotinib, 0.45; 95% confidence interval [CI], 0.35 to 0.60; P

Supplementary Methods and Figures. (DOCX 3930Â kb)

Clinical characteristics of NSCLC patients. Table S2. DNA sequences of real-time PCR primers used for the detection of mRNA expression. Table S3. Clinical characteristics and distribution of patients according to their FOXP3 expression levels. Table S4. Cox proportional Hazard regression analysis of patients’ overall survival. Table S5. Cox proportional Hazard regression analysis of patients’ recurrence-free survival. (PDF 392 kb)