Volume 39, Issue 7

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, application of these models in clinically realistic environments can result in poor generalization and decreased accuracy, mainly due to the domain shift across different hospitals, scanner vendors, imaging protocols, and patient populations etc. Common transfer learning and domain adaptation techniques are proposed to address this bottleneck. However, these solutions require data (and annotations) from the target domain to retrain the model, and is therefore restrictive in practice for widespread model deployment. Ideally, we wish to have a trained (locked) model that can work uniformly well across unseen domains without further training. In this paper, we propose a deep stacked transformation approach for domain generalization. Specifically, a series of ${n}$ stacked transformations are applied to each image during network training. The underlying assumption is that the “expected” domain shift for a specific medical imaging modality could be simulated by applying extensive data augmentation on a single source domain, and consequently, a deep model trained on the augmented “big” data (BigAug) could generalize well on unseen domains. We exploit four surprisingly effective, but previously understudied, image-based characteristics for data augmentation to overcome the domain generalization problem. We train and evaluate the BigAug model (with ${n}={9}$ transformations) on three different 3D segmentation tasks (prostate gland, left atrial, left ventricle) covering two medical imaging modalities (MRI and ultrasound) involving eight publicly available challenge datasets. The results show that when training on relatively small dataset (n = 10~32 volumes, depending on the size of the available datasets) from a single source domain: (i) BigAug models degrade an average of 11%(Dice score change) from source to unseen domain, substantially better than conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%), (ii) BigAug is better than “shallower” stacked transforms (i.e. those with fewer transforms) on unseen domains and demonstrates modest improvement to conventional augmentation on the source domain, (iii) after training with BigAug on one source domain, performance on an unseen domain is similar to training a model from scratch on that domain when using the same number of training samples. When training on large datasets (n = 465 volumes) with BigAug, (iv) application to unseen domains reaches the performance of state-of-the-art fully supervised models that are trained and tested on their source domains. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of highly robust deep segmentation models for clinical deployment.

中文摘要翻译待生成

Unsupervised domain adaptation has increasingly gained interest in medical image computing, aiming to tackle the performance degradation of deep neural networks when being deployed to unseen data with heterogeneous characteristics. In this work, we present a novel unsupervised domain adaptation framework, named as Synergistic Image and Feature Alignment (SIFA), to effectively adapt a segmentation ...

中文摘要翻译待生成

Automated skin lesion segmentation and classification are two most essential and related tasks in the computer-aided diagnosis of skin cancer. Despite their prevalence, deep learning models are usually designed for only one task, ignoring the potential benefits in jointly performing both tasks. In this paper, we propose the mutual bootstrapping deep convolutional neural networks (MB-DCNN) model fo...

中文摘要翻译待生成

Computed tomography (CT) is a widely used screening and diagnostic tool that allows clinicians to obtain a high-resolution, volumetric image of internal structures in a non-invasive manner. Increasingly, efforts have been made to improve the image quality of low-dose CT (LDCT) to reduce the cumulative radiation exposure of patients undergoing routine screening exams. The resurgence of deep learnin...

中文摘要翻译待生成

Multi-modal learning is typically performed with network architectures containing modality-specific layers and shared layers, utilizing co-registered images of different modalities. We propose a novel learning scheme for unpaired cross-modality image segmentation, with a highly compact architecture achieving superior segmentation accuracy. In our method, we heavily reuse network parameters, by sha...

中文摘要翻译待生成

Precisely labeling teeth on digitalized 3D dental surface models is the precondition for tooth position rearrangements in orthodontic treatment planning. However, it is a challenging task primarily due to the abnormal and varying appearance of patients' teeth. The emerging utilization of intraoral scanners (IOSs) in clinics further increases the difficulty in automated tooth labeling, as the raw s...

中文摘要翻译待生成

Digital histology images are amenable to the application of convolutional neural networks (CNNs) for analysis due to the sheer size of pixel data present in them. CNNs are generally used for representation learning from small image patches (e.g. $224\times 224$ ) extracted from digital histology images due to computational and memory constraints. However, this approach does not incorporate high-r...

中文摘要翻译待生成

Chronological age estimation is crucial labour in many clinical procedures, where the teeth have proven to be one of the best estimators. Although some methods to estimate the age from tooth measurements in orthopantomogram (OPG) images have been developed, they rely on time-consuming manual processes whose results are affected by the observer subjectivity. Furthermore, all those approaches have b...

中文摘要翻译待生成

Deformable image registration is a very important field of research in medical imaging. Recently multiple deep learning approaches were published in this area showing promising results. However, drawbacks of deep learning methods are the need for a large amount of training datasets and their inability to register unseen images different from the training datasets. One shot learning comes without t...

中文摘要翻译待生成

Chest X-ray radiography is one of the earliest medical imaging technologies and remains one of the most widely-used for diagnosis, screening, and treatment follow up of diseases related to lungs and heart. The literature in this field of research reports many interesting studies dealing with the challenging tasks of bone suppression and organ segmentation but performed separately, limiting any lea...

中文摘要翻译待生成

Brain network provides essential insights in diagnosing many brain disorders. Integrative analysis of multiple types of connectivity, e.g, functional connectivity (FC) and structural connectivity (SC), can take advantage of their complementary information and therefore may help to identify patients. However, traditional brain network methods usually focus on either FC or SC for describing node int...

中文摘要翻译待生成

The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale labelled training data. In medical imaging, these large labelled datasets are sparse, mainly related to the complexity in manual annotation. Deep convolutional neural networks (CNNs), with transferable knowledge, have been employed as a solution to limited annotated da...

中文摘要翻译待生成

Electromagnetic stimulation of the human brain is a key tool for neurophysiological characterization and the diagnosis of several neurological disorders. Transcranial magnetic stimulation (TMS) is a commonly used clinical procedure. However, personalized TMS requires a pipeline for individual head model generation to provide target-specific stimulation. This process includes intensive segmentation...

中文摘要翻译待生成

Accurate and automatic multi-needle detection in three-dimensional (3D) ultrasound (US) is a key step of treatment planning for US-guided brachytherapy. However, most current studies are concentrated on single-needle detection by only using a small number of images with a needle, regardless of the massive database of US images without needles. In this paper, we propose a workflow for multi-needle ...

中文摘要翻译待生成

Generative adversarial network (GAN) has been widely explored for cross-modality medical image synthesis. The existing GAN models usually adversarially learn a global sample space mapping from the source-modality to the target-modality and then indiscriminately apply this mapping to all samples in the whole space for prediction. However, due to the scarcity of training samples in contrast to the c...

中文摘要翻译待生成

Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for segmentation tasks in computer vision and medical imaging. Recently, computational blocks termed squeeze and excitation (SE) have been introduced to recalibrate F-CNN feature maps both channel- and spatial-wise, boosting segmentation performance while only minimally increasing the model complexity. So far, the de...

中文摘要翻译待生成

Point-of-care medical diagnosis demands immediate feedback on tissue pathology. Confocal endomicroscopy can provide real-time in vivo images with histology-like features. The working channel in medical endoscopes are becoming smaller in dimension. Microsystems methods can produce tiny mechanical scanners. We demonstrate a flexible fiber instrument for in vivo imaging as an endoscope accessory. The...

中文摘要翻译待生成

Recently, researchers have discovered the direct impact of the tumor mechanical environment on the growth, drug uptake and prognosis of tumors. While estimating the mechanical parameters (solid stress, fluid pressure, stiffness) can aid in the treatment planning and monitoring, most of these parameters cannot be quantified noninvasively. Shear wave elastography (SWE) has shown promise as a means o...

中文摘要翻译待生成

Recent advances in positron emission tomography (PET) have allowed to perform brain scans of freely moving animals by using rigid motion correction. One of the current challenges in these scans is that, due to the PET scanner spatially variant point spread function (SVPSF), motion corrected images have a motion dependent blurring since animals can move throughout the entire field of view (FOV). We...

中文摘要翻译待生成

Inferring brain connectivity networks from fMRI data can take place at the Region of Interest (ROI) or voxel level. With most ROI-based approaches, the signals from same-ROI voxels are simply averaged, neglecting any inhomogeneity in each ROI and assuming that the same voxels will interact with different ROIs in a similar manner. In this paper, we propose a novel method of representing ROI activit...

中文摘要翻译待生成

Linear parametric neurotransmitter PET (lp-ntPET) is a novel kinetic model that estimates the temporal characteristics of a transient neurotransmitter component in PET data. To preserve computational simplicity in estimation, the parameters of the nonlinear term that describe this transient signal are discretized, and only a limited set of values for each parameter are allowed. Thus, linear estima...

中文摘要翻译待生成

Multi-label probabilistic maps, a.k.a. probabilistic segmentations, parameterize a population of intimately co-existing anatomical shapes and are useful for various medical imaging applications, such as segmentation, anatomical atlases, shape analysis, and consensus generation. Existing methods to estimate probabilistic segmentations rely on ad hoc intermediate representations (e.g., average of Ga...

中文摘要翻译待生成

Imaging fluorescence through millimeters or centimeters of tissue has important in vivo applications, such as guiding surgery and studying the brain. Often, the important information is the location of one of more optical reporters, rather than the specifics of the local geometry, motivating the need for a localization method that provides this information. We present an optimization approach base...

中文摘要翻译待生成

Joint image reconstruction for multiphase CT can potentially improve image quality and reduce dose by leveraging the shared information among the phases. Multiphase CT scans are acquired sequentially. Inter-scan patient breathing causes small organ shifts and organ boundary misalignment among different phases. Existing multi-channel regularizers such as the joint total variation (TV) can introduce...

中文摘要翻译待生成

In the above article [1], Tables II, III, and V and Fig. 6 are incorrect. The correct images are provided below:

中文摘要翻译待生成