Few-Shot Learning by a Cascaded Framework With Shape-Constrained Pseudo Label Assessment for Whole Heart Segmentation

One-shot learning for generalization in medical image classification across modalities

Generalizability is one of the biggest challenges hindering the advancement of medical sensing technologies across multiple imaging modalities. This issue is further impaired when the imaging data is limited in scope or of poor quality. To tackle this, we propose a generalized and robust, lightweight one-shot learning method for medical image classification across various imaging modalities, including X-ray, microscopic, and CT scans. Our model introduces a collaborative one-shot training (COST) approach, incorporating both meta-learning and metric-learning. This approach allows for effective training on only one image per class. To ensure generalization with fewer epochs, we employ gradient generalization at dense and fully connected layers, utilizing a lightweight Siamese network with triplet loss and shared parameters. The proposed model was evaluated on 12 medical image datasets from MedMNIST2D, achieving an average accuracy of 91.5 % and area under the curve (AUC) of 0.89, outperforming state-of-the-art models such as ResNet-50 and AutoML by over 10 % on certain datasets. Further, in the OCTMNIST dataset, our model achieved an AUC of 0.91 compared to ResNet-50's 0.77. Ablation studies further validate the superiority of our approach, with the COST method showing significant improvement in convergence speed and accuracy when compared to traditional one-shot learning setups. Additionally, our model's lightweight architecture requires only 0.15 million parameters, making it well-suited for deployment on resource-constrained devices.

Multi-scale multi-object semi-supervised consistency learning for ultrasound image segmentation

Manual annotation of ultrasound images relies on expert knowledge and requires significant time and financial resources. Semi-supervised learning (SSL) exploits large amounts of unlabeled data to improve model performance under limited labeled data. However, it faces two challenges: fusion of contextual information at multiple scales and bias of spatial information between multiple objects. We propose a consistency learning-based multi-scale multi-object (MSMO) semi-supervised framework for ultrasound image segmentation. MSMO addresses these challenges by employing a contextual-aware encoder coupled with a multi-object semantic calibration and fusion decoder. First, the encoder extracts multi-scale multi-objects context-aware features, and introduces attention module to refine the feature map and enhance channel information interaction. Then, the decoder uses HConvLSTM to calibrate the output features of the current object by using the hidden state of the previous object, and recursively fuses multi-object semantics at different scales. Finally, MSMO further reduces variations among multiple decoders in different perturbations through consistency constraints, thereby producing consistent predictions for highly uncertain areas. Extensive experiments show that proposed MSMO outperforms the SSL baseline on four benchmark datasets, whether for single-object or multi-object ultrasound image segmentation. MSMO significantly reduces the burden of manual analysis of ultrasound images and holds great potential as a clinical tool. The source code is accessible to the public at: https://github.com/lol88/MSMO.

A semi-supervised domain adaptive medical image segmentation method based on dual-level multi-scale alignment

In the actual image segmentation tasks in the medical field, the phenomenon of limited labeled data accompanied by domain shifts often occurs and such domain shifts may exist in homologous or even heterologous data. In the study, a novel method was proposed to deal with this challenging phenomenon. Firstly, a model was trained with labeled data in source and target domains so as to adapt to unlabeled data. Then, the alignment at two main levels was realized. At the style level, based on multi-scale stylistic features, the alignment of unlabeled target images was maximized and unlabeled target image features were enhanced. At the inter-domain level, the similarity of the category centroids between target domain data and mixed image data was also maximized. Additionally, a fused supervised loss and alignment loss computation method was proposed. In validation experiments, two cross-domain medical image datasets were constructed: homologous and heterologous datasets. Experimental results showed that the proposed method had the more advantageous comprehensive performance than common semi-supervised and domain adaptation methods.

Enhanced Domain Adaptation for Foot Ulcer Segmentation Through Mixing Self-Trained Weak Labels

Wound management requires the measurement of the wound parameters such as its shape and area. However, computerized analysis of the wound suffers the challenge of inexact segmentation of the wound images due to limited or inaccurate labels. It is a common scenario that the source domain provides an abundance of labeled data, while the target domain provides only limited labels. To overcome this, we propose a novel approach that combines self-training learning and mixup augmentation. The neural network is trained on the source domain to generate weak labels on the target domain via the self-training process. In the second stage, generated labels are mixed up with labels from the source domain to retrain the neural network and enhance generalization across diverse datasets. The efficacy of our approach was evaluated using the DFUC 2022, FUSeg, and RMIT datasets, demonstrating substantial improvements in segmentation accuracy and robustness across different data distributions. Specifically, in single-domain experiments, segmentation on the DFUC 2022 dataset scored a dice score of 0.711, while the score on the FUSeg dataset achieved 0.859. For domain adaptation, when these datasets were used as target datasets, the dice scores were 0.714 for DFUC 2022 and 0.561 for FUSeg.

Adaptive dynamic inference for few-shot left atrium segmentation

Accurate segmentation of the left atrium (LA) from late gadolinium-enhanced cardiac magnetic resonance (LGE CMR) images is crucial for aiding the treatment of patients with atrial fibrillation. Few-shot learning holds significant potential for achieving accurate LA segmentation with low demand on high-cost labeled LGE CMR data and fast generalization across different centers. However, accurate LA segmentation with few-shot learning is a challenging task due to the low-intensity contrast between the LA and other neighboring organs in LGE CMR images. To address this issue, we propose an Adaptive Dynamic Inference Network (ADINet) that explicitly models the differences between the foreground and background. Specifically, ADINet leverages dynamic collaborative inference (DCI) and dynamic reverse inference (DRI) to adaptively allocate semantic-aware and spatial-specific convolution weights and indication information. These allocations are conditioned on the support foreground and background knowledge, utilizing pixel-wise correlations, for different spatial positions of query images. The convolution weights adapt to different visual patterns based on spatial positions, enabling effective encoding of differences between foreground and background regions. Meanwhile, the indication information adapts to the background visual pattern to reversely decode foreground LA regions, leveraging their spatial complementarity. To promote the learning of ADINet, we propose hierarchical supervision, which enforces spatial consistency and differences between the background and foreground regions through pixel-wise semantic supervision and pixel-pixel correlation supervision. We demonstrated the performance of ADINet on three LGE CMR datasets from different centers. Compared to state-of-the-art methods with ten available samples, ADINet yielded better segmentation performance in terms of four metrics.

SenseCare: a research platform for medical image informatics and interactive 3D visualization

Introduction

Clinical research on smart health has an increasing demand for intelligent and clinic-oriented medical image computing algorithms and platforms that support various applications. However, existing research platforms for medical image informatics have limited support for Artificial Intelligence (AI) algorithms and clinical applications.

Methods

To this end, we have developed SenseCare research platform, which is designed to facilitate translational research on intelligent diagnosis and treatment planning in various clinical scenarios. It has several appealing functions and features such as advanced 3D visualization, concurrent and efficient web-based access, fast data synchronization and high data security, multi-center deployment, support for collaborative research, etc.

Results and discussion

SenseCare provides a range of AI toolkits for different tasks, including image segmentation, registration, lesion and landmark detection from various image modalities ranging from radiology to pathology. It also facilitates the data annotation and model training processes, which makes it easier for clinical researchers to develop and deploy customized AI models. In addition, it is clinic-oriented and supports various clinical applications such as diagnosis and surgical planning for lung cancer, liver tumor, coronary artery disease, etc. By simplifying AI-based medical image analysis, SenseCare has a potential to promote clinical research in a wide range of disease diagnosis and treatment applications.

Boundary-Aware Prototype in Semi-Supervised Medical Image Segmentation

The true label plays an important role in semi-supervised medical image segmentation (SSMIS) because it can provide the most accurate supervision information when the label is limited. The popular SSMIS method trains labeled and unlabeled data separately, and the unlabeled data cannot be directly supervised by the true label. This limits the contribution of labels to model training. Is there an interactive mechanism that can break the separation between two types of data training to maximize the utilization of true labels? Inspired by this, we propose a novel consistency learning framework based on the non-parametric distance metric of boundary-aware prototypes to alleviate this problem. This method combines CNN-based linear classification and nearest neighbor-based non-parametric classification into one framework, encouraging the two segmentation paradigms to have similar predictions for the same input. More importantly, the prototype can be clustered from both labeled and unlabeled data features so that it can be seen as a bridge for interactive training between labeled and unlabeled data. When the prototype-based prediction is supervised by the true label, the supervisory signal can simultaneously affect the feature extraction process of both data. In addition, boundary-aware prototypes can explicitly model the differences in boundaries and centers of adjacent categories, so pixel-prototype contrastive learning is introduced to further improve the discriminability of features and make them more suitable for non-parametric distance measurement. Experiments show that although our method uses a modified lightweight UNet as the backbone, it outperforms the comparison method using a 3D VNet with more parameters.

A systematic review of few-shot learning in medical imaging

The lack of annotated medical images limits the performance of deep learning models, which usually need large-scale labelled datasets. Few-shot learning techniques can reduce data scarcity issues and enhance medical image analysis speed and robustness. This systematic review gives a comprehensive overview of few-shot learning methods for medical image analysis, aiming to establish a standard methodological pipeline for future research reference. With a particular emphasis on the role of meta-learning, we analysed 80 relevant articles published from 2018 to 2023, conducting a risk of bias assessment and extracting relevant information, especially regarding the employed learning techniques. From this, we delineated a comprehensive methodological pipeline shared among all studies. In addition, we performed a statistical analysis of the studies' results concerning the clinical task and the meta-learning method employed while also presenting supplemental information such as imaging modalities and model robustness evaluation techniques. We discussed the findings of our analysis, providing a deep insight into the limitations of the state-of-the-art methods and the most promising approaches. Drawing on our investigation, we yielded recommendations on potential future research directions aiming to bridge the gap between research and clinical practice.

Self-adaptive deep learning-based segmentation for universal and functional clinical and preclinical CT image analysis

BACKGROUND

Methods to monitor cardiac functioning non-invasively can accelerate preclinical and clinical research into novel treatment options for heart failure. However, manual image analysis of cardiac substructures is resource-intensive and error-prone. While automated methods exist for clinical CT images, translating these to preclinical μCT data is challenging. We employed deep learning to automate the extraction of quantitative data from both CT and μCT images.

METHODS

We collected a public dataset of cardiac CT images of human patients, as well as acquired μCT images of wild-type and accelerated aging mice. The left ventricle, myocardium, and right ventricle were manually segmented in the μCT training set. After template-based heart detection, two separate segmentation neural networks were trained using the nnU-Net framework.

RESULTS

The mean Dice score of the CT segmentation results (0.925 ± 0.019, n = 40) was superior to those achieved by state-of-the-art algorithms. Automated and manual segmentations of the μCT training set were nearly identical. The estimated median Dice score (0.940) of the test set results was comparable to existing methods. The automated volume metrics were similar to manual expert observations. In aging mice, ejection fractions had significantly decreased, and myocardial volume increased by age 24 weeks.

CONCLUSIONS

With further optimization, automated data extraction expands the application of (μ)CT imaging, while reducing subjectivity and workload. The proposed method efficiently measures the left and right ventricular ejection fraction and myocardial mass. With uniform translation between image types, cardiac functioning in diastolic and systolic phases can be monitored in both animals and humans.

AVDNet: Joint coronary artery and vein segmentation with topological consistency

Coronary CT angiography (CCTA) is an effective and non-invasive method for coronary artery disease diagnosis. Extracting an accurate coronary artery tree from CCTA image is essential for centerline extraction, plaque detection, and stenosis quantification. In practice, data quality varies. Sometimes, the arteries and veins have similar intensities and locate closely, which may confuse segmentation algorithms, even deep learning based ones, to obtain accurate arteries. However, it is not always feasible to re-scan the patient for better image quality. In this paper, we propose an artery and vein disentanglement network (AVDNet) for robust and accurate segmentation by incorporating the coronary vein into the segmentation task. This is the first work to segment coronary artery and vein at the same time. The AVDNet consists of an image based vessel recognition network (IVRN) and a topology based vessel refinement network (TVRN). IVRN learns to segment the arteries and veins, while TVRN learns to correct the segmentation errors based on topology consistency. We also design a novel inverse distance weighted dice (IDD) loss function to recover more thin vessel branches and preserve the vascular boundaries. Extensive experiments are conducted on a multi-center dataset of 700 patients. Quantitative and qualitative results demonstrate the effectiveness of the proposed method by comparing it with state-of-the-art methods and different variants. Prediction results of the AVDNet on the Automated Segmentation of Coronary Artery Challenge dataset are avaliabel at https://github.com/WennyJJ/Coronary-Artery-Vein-Segmentation for follow-up research.

Sparse annotation learning for dense volumetric MR image segmentation with uncertainty estimation

Objective.Training neural networks for pixel-wise or voxel-wise image segmentation is a challenging task that requires a considerable amount of training samples with highly accurate and densely delineated ground truth maps. This challenge becomes especially prominent in the medical imaging domain, where obtaining reliable annotations for training samples is a difficult, time-consuming, and expert-dependent process. Therefore, developing models that can perform well under the conditions of limited annotated training data is desirable.Approach.In this study, we propose an innovative framework called the extremely sparse annotation neural network (ESA-Net) that learns with only the single central slice label for 3D volumetric segmentation which explores both intra-slice pixel dependencies and inter-slice image correlations with uncertainty estimation. Specifically, ESA-Net consists of four specially designed distinct components: (1) an intra-slice pixel dependency-guided pseudo-label generation module that exploits uncertainty in network predictions while generating pseudo-labels for unlabeled slices with temporal ensembling; (2) an inter-slice image correlation-constrained pseudo-label propagation module which propagates labels from the labeled central slice to unlabeled slices by self-supervised registration with rotation ensembling; (3) a pseudo-label fusion module that fuses the two sets of generated pseudo-labels with voxel-wise uncertainty guidance; and (4) a final segmentation network optimization module to make final predictions with scoring-based label quantification.Main results.Extensive experimental validations have been performed on two popular yet challenging magnetic resonance image segmentation tasks and compared to five state-of-the-art methods.Significance.Results demonstrate that our proposed ESA-Net can consistently achieve better segmentation performances even under the extremely sparse annotation setting, highlighting its effectiveness in exploiting information from unlabeled data.

Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration

The prowess that makes few-shot learning desirable in medical image analysis is the efficient use of the support image data, which are labelled to classify or segment new classes, a task that otherwise requires substantially more training images and expert annotations. This work describes a fully 3D prototypical few-shot segmentation algorithm, such that the trained networks can be effectively adapted to clinically interesting structures that are absent in training, using only a few labelled images from a different institute. First, to compensate for the widely recognised spatial variability between institutions in episodic adaptation of novel classes, a novel spatial registration mechanism is integrated into prototypical learning, consisting of a segmentation head and an spatial alignment module. Second, to assist the training with observed imperfect alignment, support mask conditioning module is proposed to further utilise the annotation available from the support images. Extensive experiments are presented in an application of segmenting eight anatomical structures important for interventional planning, using a data set of 589 pelvic T2-weighted MR images, acquired at seven institutes. The results demonstrate the efficacy in each of the 3D formulation, the spatial registration, and the support mask conditioning, all of which made positive contributions independently or collectively. Compared with the previously proposed 2D alternatives, the few-shot segmentation performance was improved with statistical significance, regardless whether the support data come from the same or different institutes.

MUE-CoT: multi-scale uncertainty entropy-aware co-training framework for left atrial segmentation

Objective.Accurate left atrial segmentation is the basis of the recognition and clinical analysis of atrial fibrillation. Supervised learning has achieved some competitive segmentation results, but the high annotation cost often limits its performance. Semi-supervised learning is implemented from limited labeled data and a large amount of unlabeled data and shows good potential in solving practical medical problems.Approach. In this study, we proposed a collaborative training framework for multi-scale uncertain entropy perception (MUE-CoT) and achieved efficient left atrial segmentation from a small amount of labeled data. Based on the pyramid feature network, learning is implemented from unlabeled data by minimizing the pyramid prediction difference. In addition, novel loss constraints are proposed for co-training in the study. The diversity loss is defined as a soft constraint so as to accelerate the convergence and a novel multi-scale uncertainty entropy calculation method and a consistency regularization term are proposed to measure the consistency between prediction results. The quality of pseudo-labels cannot be guaranteed in the pre-training period, so a confidence-dependent empirical Gaussian function is proposed to weight the pseudo-supervised loss.Main results.The experimental results of a publicly available dataset and an in-house clinical dataset proved that our method outperformed existing semi-supervised methods. For the two datasets with a labeled ratio of 5%, the Dice similarity coefficient scores were 84.94% ± 4.31 and 81.24% ± 2.4, the HD95values were 4.63 mm ± 2.13 and 3.94 mm ± 2.72, and the Jaccard similarity coefficient scores were 74.00% ± 6.20 and 68.49% ± 3.39, respectively.Significance.The proposed model effectively addresses the challenges of limited data samples and high costs associated with manual annotation in the medical field, leading to enhanced segmentation accuracy.

Curriculum label distribution learning for imbalanced medical image segmentation

Label distribution learning (LDL) has the potential to resolve boundary ambiguity in semantic segmentation tasks. However, existing LDL-based segmentation methods suffer from severe label distribution imbalance: the ambiguous label distributions contain a small fraction of the data, while the unambiguous label distributions occupy the majority of the data. The imbalanced label distributions induce model-biased distribution learning and make it challenging to accurately predict ambiguous pixels. In this paper, we propose a curriculum label distribution learning (CLDL) framework to address the above data imbalance problem by performing a novel task-oriented curriculum learning strategy. Firstly, the region label distribution learning (R-LDL) is proposed to construct more balanced label distributions and improves the imbalanced model learning. Secondly, a novel learning curriculum (TCL) is proposed to enable easy-to-hard learning in LDL-based segmentation by decomposing the segmentation task into multiple label distribution estimation tasks. Thirdly, the prior perceiving module (PPM) is proposed to effectively connect easy and hard learning stages based on the priors generated from easier stages. Benefiting from the balanced label distribution construction and prior perception, the proposed CLDL effectively conducts a curriculum learning-based LDL and significantly improves the imbalanced learning. We evaluated the proposed CLDL using the publicly available BRATS2018 and MM-WHS2017 datasets. The experimental results demonstrate that our method significantly improves different segmentation metrics compared to many state-of-the-art methods. The code will be available.1.

Mining multi-center heterogeneous medical data with distributed synthetic learning

Overcoming barriers on the use of multi-center data for medical analytics is challenging due to privacy protection and data heterogeneity in the healthcare system. In this study, we propose the Distributed Synthetic Learning (DSL) architecture to learn across multiple medical centers and ensure the protection of sensitive personal information. DSL enables the building of a homogeneous dataset with entirely synthetic medical images via a form of GAN-based synthetic learning. The proposed DSL architecture has the following key functionalities: multi-modality learning, missing modality completion learning, and continual learning. We systematically evaluate the performance of DSL on different medical applications using cardiac computed tomography angiography (CTA), brain tumor MRI, and histopathology nuclei datasets. Extensive experiments demonstrate the superior performance of DSL as a high-quality synthetic medical image provider by the use of an ideal synthetic quality metric called Dist-FID. We show that DSL can be adapted to heterogeneous data and remarkably outperforms the real misaligned modalities segmentation model by 55% and the temporal datasets segmentation model by 8%.

Robust Prototypical Few-Shot Organ Segmentation With Regularized Neural-ODEs

Despite the tremendous progress made by deep learning models in image semantic segmentation, they typically require large annotated examples, and increasing attention is being diverted to problem settings like Few-Shot Learning (FSL) where only a small amount of annotation is needed for generalisation to novel classes. This is especially seen in medical domains where dense pixel-level annotations are expensive to obtain. In this paper, we propose Regularized Prototypical Neural Ordinary Differential Equation (R-PNODE), a method that leverages intrinsic properties of Neural-ODEs, assisted and enhanced by additional cluster and consistency losses to perform Few-Shot Segmentation (FSS) of organs. R-PNODE constrains support and query features from the same classes to lie closer in the representation space thereby improving the performance over the existing Convolutional Neural Network (CNN) based FSS methods. We further demonstrate that while many existing Deep CNN-based methods tend to be extremely vulnerable to adversarial attacks, R-PNODE exhibits increased adversarial robustness for a wide array of these attacks. We experiment with three publicly available multi-organ segmentation datasets in both in-domain and cross-domain FSS settings to demonstrate the efficacy of our method. In addition, we perform experiments with seven commonly used adversarial attacks in various settings to demonstrate R-PNODE's robustness. R-PNODE outperforms the baselines for FSS by significant margins and also shows superior performance for a wide array of attacks varying in intensity and design.

Latest Developments in Adapting Deep Learning for Assessing TAVR Procedures and Outcomes

Aortic valve defects are among the most prevalent clinical conditions. A severely damaged or non-functioning aortic valve is commonly replaced with a bioprosthetic heart valve (BHV) via the transcatheter aortic valve replacement (TAVR) procedure. Accurate pre-operative planning is crucial for a successful TAVR outcome. Assessment of computational fluid dynamics (CFD), finite element analysis (FEA), and fluid-solid interaction (FSI) analysis offer a solution that has been increasingly utilized to evaluate BHV mechanics and dynamics. However, the high computational costs and the complex operation of computational modeling hinder its application. Recent advancements in the deep learning (DL) domain can offer a real-time surrogate that can render hemodynamic parameters in a few seconds, thus guiding clinicians to select the optimal treatment option. Herein, we provide a comprehensive review of classical computational modeling approaches, medical imaging, and DL approaches for planning and outcome assessment of TAVR. Particularly, we focus on DL approaches in previous studies, highlighting the utilized datasets, deployed DL models, and achieved results. We emphasize the critical challenges and recommend several future directions for innovative researchers to tackle. Finally, an end-to-end smart DL framework is outlined for real-time assessment and recommendation of the best BHV design for TAVR. Ultimately, deploying such a framework in future studies will support clinicians in minimizing risks during TAVR therapy planning and will help in improving patient care.

Root canal treatment planning by automatic tooth and root canal segmentation in dental CBCT with deep multi-task feature learning

Accurate and automatic segmentation of individual tooth and root canal from cone-beam computed tomography (CBCT) images is an essential but challenging step for dental surgical planning. In this paper, we propose a novel framework, which consists of two neural networks, DentalNet and PulpNet, for efficient, precise, and fully automatic tooth instance segmentation and root canal segmentation from CBCT images. We first use the proposed DentalNet to achieve tooth instance segmentation and identification. Then, the region of interest (ROI) of the affected tooth is extracted and fed into the PulpNet to obtain precise segmentation of the pulp chamber and the root canal space. These two networks are trained by multi-task feature learning and evaluated on two clinical datasets respectively and achieve superior performances to several comparing methods. In addition, we incorporate our method into an efficient clinical workflow to improve the surgical planning process. In two clinical case studies, our workflow took only 2 min instead of 6 h to obtain the 3D model of tooth and root canal effectively for the surgical planning, resulting in satisfying outcomes in difficult root canal treatments.

A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR

Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. The most popular CNN-based methods are optimised using pixel wise loss functions, ignorant of the spatially extended features that characterise anatomy. Therefore, whilst sharing a high spatial overlap with the ground truth, inferred CNN-based segmentations can lack coherence, including spurious connected components, holes and voids. Such results are implausible, violating anticipated anatomical topology. In response, (single-class) persistent homology-based loss functions have been proposed to capture global anatomical features. Our work extends these approaches to the task of multi-class segmentation. Building an enriched topological description of all class labels and class label pairs, our loss functions make predictable and statistically significant improvements in segmentation topology using a CNN-based post-processing framework. We also present (and make available) a highly efficient implementation based on cubical complexes and parallel execution, enabling practical application within high resolution 3D data for the first time. We demonstrate our approach on 2D short axis and 3D whole heart CMR segmentation, advancing a detailed and faithful analysis of performance on two publicly available datasets.

DeepHeartCT: A fully automatic artificial intelligence hybrid framework based on convolutional neural network and multi-atlas segmentation for multi-structure cardiac computed tomography angiography image segmentation

Cardiac computed tomography angiography (CTA) is an emerging imaging modality for assessing coronary artery as well as various cardiovascular structures. Recently, deep learning (DL) methods have been successfully applied to many applications of medical image analysis including cardiac CTA structure segmentation. However, DL requires a large amounts of data and high-quality labels for training which can be burdensome to obtain due to its labor-intensive nature. In this study, we aim to develop a fully automatic artificial intelligence (AI) system, named DeepHeartCT, for accurate and rapid cardiac CTA segmentation based on DL. The proposed system was trained using a large clinical dataset with computer-generated labels to segment various cardiovascular structures including left and right ventricles (LV, RV), left and right atria (LA, RA), and LV myocardium (LVM). This new system was trained directly using high-quality computer labels generated from our previously developed multi-atlas based AI system. In addition, a reverse ranking strategy was proposed to assess the segmentation quality in the absence of manual reference labels. This strategy allowed the new framework to assemble optimal computer-generated labels from a large dataset for effective training of a deep convolutional neural network (CNN). A large clinical cardiac CTA studies (n = 1,064) were used to train and validate our framework. The trained model was then tested on another independent dataset with manual labels (n = 60). The Dice score, Hausdorff distance and mean surface distance were used to quantify the segmentation accuracy. The proposed DeepHeartCT framework yields a high median Dice score of 0.90 [interquartile range (IQR), 0.90-0.91], a low median Hausdorff distance of 7 mm (IQR, 4-15 mm) and a low mean surface distance of 0.80 mm (IQR, 0.57-1.29 mm) across all segmented structures. An additional experiment was conducted to evaluate the proposed DL-based AI framework trained with a small vs. large dataset. The results show our framework also performed well when trained on a small optimal training dataset (n = 110) with a significantly reduced training time. These results demonstrated that the proposed DeepHeartCT framework provides accurate and rapid cardiac CTA segmentation that can be readily generalized for handling large-scale medical imaging applications.

Machine Learning and Deep Learning in Cardiothoracic Imaging: A Scoping Review

Machine-learning (ML) and deep-learning (DL) algorithms are part of a group of modeling algorithms that grasp the hidden patterns in data based on a training process, enabling them to extract complex information from the input data. In the past decade, these algorithms have been increasingly used for image processing, specifically in the medical domain. Cardiothoracic imaging is one of the early adopters of ML/DL research, and the COVID-19 pandemic resulted in more research focus on the feasibility and applications of ML/DL in cardiothoracic imaging. In this scoping review, we systematically searched available peer-reviewed medical literature on cardiothoracic imaging and quantitatively extracted key data elements in order to get a big picture of how ML/DL have been used in the rapidly evolving cardiothoracic imaging field. During this report, we provide insights on different applications of ML/DL and some nuances pertaining to this specific field of research. Finally, we provide general suggestions on how researchers can make their research more than just a proof-of-concept and move toward clinical adoption.

Advancing Brain Metastases Detection in T1-Weighted Contrast-Enhanced 3D MRI Using Noisy Student-Based Training

The detection of brain metastases (BM) in their early stages could have a positive impact on the outcome of cancer patients. The authors previously developed a framework for detecting small BM (with diameters of <15 mm) in T1-weighted contrast-enhanced 3D magnetic resonance images (T1c). This study aimed to advance the framework with a noisy-student-based self-training strategy to use a large corpus of unlabeled T1c data. Accordingly, a sensitivity-based noisy-student learning approach was formulated to provide high BM detection sensitivity with a reduced count of false positives. This paper (1) proposes student/teacher convolutional neural network architectures, (2) presents data and model noising mechanisms, and (3) introduces a novel pseudo-labeling strategy factoring in the sensitivity constraint. The evaluation was performed using 217 labeled and 1247 unlabeled exams via two-fold cross-validation. The framework utilizing only the labeled exams produced 9.23 false positives for 90% BM detection sensitivity, whereas the one using the introduced learning strategy led to ~9% reduction in false detections (i.e., 8.44). Significant reductions in false positives (>10%) were also observed in reduced labeled data scenarios (using 50% and 75% of labeled data). The results suggest that the introduced strategy could be utilized in existing medical detection applications with access to unlabeled datasets to elevate their performances.

Using Sparse Patch Annotation for Tumor Segmentation in Histopathological Images

Tumor segmentation is a fundamental task in histopathological image analysis. Creating accurate pixel-wise annotations for such segmentation tasks in a fully-supervised training framework requires significant effort. To reduce the burden of manual annotation, we propose a novel weakly supervised segmentation framework based on sparse patch annotation, i.e., only small portions of patches in an image are labeled as 'tumor' or 'normal'. The framework consists of a patch-wise segmentation model called PSeger, and an innovative semi-supervised algorithm. PSeger has two branches for patch classification and image classification, respectively. This two-branch structure enables the model to learn more general features and thus reduce the risk of overfitting when learning sparsely annotated data. We incorporate the idea of consistency learning and self-training into the semi-supervised training strategy to take advantage of the unlabeled images. Trained on the BCSS dataset with only 25% of the images labeled (five patches for each labeled image), our proposed method achieved competitive performance compared to the fully supervised pixel-wise segmentation models. Experiments demonstrate that the proposed solution has the potential to reduce the burden of labeling histopathological images.

Clinical validation of an AI-based motion correction reconstruction algorithm in cerebral CT

OBJECTIVES

To evaluate the clinical performance of an artificial intelligence (AI)-based motion correction (MC) reconstruction algorithm for cerebral CT.

METHODS

A total of 53 cases, where motion artifacts were found in the first scan so that an immediate rescan was taken, were retrospectively enrolled. While the rescanned images were reconstructed with a hybrid iterative reconstruction (IR) algorithm (reference group), images of the first scan were reconstructed with both the hybrid IR (motion group) and the MC algorithm (MC group). Image quality was compared in terms of standard deviation (SD), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), the mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mutual information (MI), as well as subjective scores. The diagnostic performance for each case was evaluated accordingly by lesion detectability or the Alberta Stroke Program Early CT Score (ASPECTS) assessment.

RESULTS

Compared with the motion group, the SNR and CNR of the MC group were significantly increased. The MSE, PSNR, SSIM, and MI with respect to the reference group were improved by 44.1%, 15.8%, 7.4%, and 18.3%, respectively (all p < 0.001). Subjective image quality indicators were scored higher for the MC than the motion group (p < 0.05). Improved lesion detectability and higher AUC (0.817 vs 0.614) in the ASPECTS assessment were found for the MC to the motion group.

CONCLUSIONS

The AI-based MC reconstruction algorithm has been clinically validated for reducing motion artifacts and improving diagnostic performance of cerebral CT.

KEY POINTS

• An artificial intelligence-based motion correction (MC) reconstruction algorithm has been clinically validated in both qualitative and quantitative manner. • The MC algorithm reduces motion artifacts in cerebral CT and increases the diagnostic confidence for brain lesions. • The MC algorithm can help avoiding rescans caused by motion and improving the efficiency of cerebral CT in the emergency department.