Cross-modality cerebrovascular segmentation based on pseudo-label generation via paired data.

Accurate segmentation of cerebrovascular structures from Computed Tomography Angiography (CTA), Magnetic Resonance Angiography (MRA), and Digital Subtraction Angiography (DSA) is crucial for clinical diagnosis of cranial vascular diseases. Recent advancements in deep Convolution Neural Network (CNN) have significantly improved the segmentation process. However, training segmentation networks for all modalities requires extensive data labeling for each modality, which is often expensive and time-consuming. To circumvent this limitation, we introduce an approach to train cross-modality cerebrovascular segmentation network based on paired data from source and target domains. Our approach involves training a universal vessel segmentation network with manually labeled source domain data, which automatically produces initial labels for target domain training images. We improve the initial labels of target domain training images by fusing paired images, which are then used to refine the target domain segmentation network. A series of experimental arrangements is presented to assess the efficacy of our method in various practical application scenarios. The experiments conducted on an MRA-CTA dataset and a DSA-CTA dataset demonstrate that the proposed method is effective for cross-modality cerebrovascular segmentation and achieves state-of-the-art performance.

Multi-task global optimization-based method for vascular landmark detection.

Vascular landmark detection plays an important role in medical analysis and clinical treatment. However, due to the complex topology and similar local appearance around landmarks, the popular heatmap regression based methods always suffer from the landmark confusion problem. Vascular landmarks are connected by vascular segments and have special spatial correlations, which can be utilized for performance improvement. In this paper, we propose a multi-task global optimization-based framework for accurate and automatic vascular landmark detection. A multi-task deep learning network is exploited to accomplish landmark heatmap regression, vascular semantic segmentation, and orientation field regression simultaneously. The two auxiliary objectives are highly correlated with the heatmap regression task and help the network incorporate the structural prior knowledge. During inference, instead of performing a max-voting strategy, we propose a global optimization-based post-processing method for final landmark decision. The spatial relationships between neighboring landmarks are utilized explicitly to tackle the landmark confusion problem. We evaluated our method on a cerebral MRA dataset with 564 volumes, a cerebral CTA dataset with 510 volumes, and an aorta CTA dataset with 50 volumes. The experiments demonstrate that the proposed method is effective for vascular landmark localization and achieves state-of-the-art performance.

3D Vascular Segmentation Supervised by 2D Annotation of Maximum Intensity Projection.

Vascular structure segmentation plays a crucial role in medical analysis and clinical applications. The practical adoption of fully supervised segmentation models is impeded by the intricacy and time-consuming nature of annotating vessels in the 3D space. This has spurred the exploration of weakly-supervised approaches that reduce reliance on expensive segmentation annotations. Despite this, existing weakly supervised methods employed in organ segmentation, which encompass points, bounding boxes, or graffiti, have exhibited suboptimal performance when handling sparse vascular structure. To alleviate this issue, we employ maximum intensity projection (MIP) to decrease the dimensionality of 3D volume to 2D image for efficient annotation, and the 2D labels are utilized to provide guidance and oversight for training 3D vessel segmentation model. Initially, we generate pseudo-labels for 3D blood vessels using the annotations of 2D projections. Subsequently, taking into account the acquisition method of the 2D labels, we introduce a weakly-supervised network that fuses 2D-3D deep features via MIP to further improve segmentation performance. Furthermore, we integrate confidence learning and uncertainty estimation to refine the generated pseudo-labels, followed by fine-tuning the segmentation network. Our method is validated on five datasets (including cerebral vessel, aorta and coronary artery), demonstrating highly competitive performance in segmenting vessels and the potential to significantly reduce the time and effort required for vessel annotation. Our code is available at: https://github.com/gzq17/Weakly-Supervised-by-MIP.

ZJUT-EIFD: A Synchronously Collected External and Internal Fingerprint Database.

External fingerprints (EFs) based only on epidermal information are vulnerable to spoofing attacks and non-ideal skin conditions. To solve such shortcomings, internal fingerprints (IFs) collected using optical coherence tomography (OCT) have been proposed and widely researched. However, the development of IF is limited by the lack of in-depth researches on the IF and the EF-IF interoperability, which is partially caused by the lack of public OCT database. The obvious gap in the applications of EF and IF recognition motivated us to design and publish a comprehensive fingerprint database containing both traditional EFs and OCT IFs, denoted as ZJUT-EIFD. To the best of our knowledge, ZJUT-EIFD is the first public database that combines OCT and total internal reflection (TIR) via synchronous acquisition, with 399 different fingers from 60 subjects. In this article, the composition of the database, the quality of EFs and IFs, and the verification performance of different types of fingerprints were detailed. In addition, potential application directions of ZJUT-EIFD were demonstrated. ZJUT-EIFD can serve benchmarks and interoperability tests for EF-IF research, which will promote the research and development of EF and IF.

Automated diagnosis of pancreatic mucinous and serous cystic neoplasms with modality-fusion deep neural network using multi-modality MRIs.

Background: Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their sub-types, serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN), are often misclassified from each other. Because SCN is primarily benign and MCN has a high rate of malignant transformation. Distinguishing SCN and MCN is challenging and essential. Purpose: MRIs have many different modalities, complete with SCN and MCN diagnosis information. With the help of an artificial intelligence-based algorithm, we aimed to propose a multi-modal hybrid deep learning network that can efficiently diagnose SCN and MCN using multi-modality MRIs. Methods: A cross-modal feature fusion structure was innovatively designed, combining features of seven modalities to realize the classification of SCN and MCN. 69 Patients with multi-modalities of MRIs were included, and experiments showed performances of every modality. Results: The proposed method with the optimized settings outperformed all other techniques and human radiologists with high accuracy of 75.07% and an AUC of 82.77%. Besides, the proposed disentanglement method outperformed other fusion methods, and delayed contrast-enhanced T1-weighted MRIs proved most valuable in diagnosing SCN and MCN. Conclusions: Through the use of a contemporary artificial intelligence algorithm, physicians can attain high performance in the complex challenge of diagnosing SCN and MCN, surpassing human radiologists to a significant degree.

Molecular characterization of a novel 83.9-kb deletion of the α-globin upstream regulatory elements by long-read sequencing.

Inherited deletions of upstream regulatory elements of α-globin genes give rise to α-thalassemia, which is an autosomal recessive monogenic disease. However, conventional thalassemia target diagnosis often fails to identify these rare deletions. Here we reported a family with two previous pregnancies of Hb Bart's hydrops fetalis and was seeking for prenatal diagnosis during the third pregnancy. Both parents had low level of Hemoglobin A2 indicating α-thalassemia. Conventional Gap-PCR and PCR-reverse dot blot showed the father carried -SEA deletion but did not identify any variants in the mother. Multiplex ligation-dependent probe amplification identified a deletion containing two HS-40 probes but could not determine the exact region. Finally, a long-read sequencing (LRS)-based approach directly identified that the exact deletion region was chr16: 48,642-132,584, which was located in the α-globin upstream regulatory elements and named (αα)JM after the Jiangmen city. Gap-PCR and Sanger sequencing confirmed the breakpoint. Both the mother and fetus from the third pregnancy carried heterozygous (αα)JM, and the fetus was normally delivered at gestational age of 39 weeks. This study demonstrated that LRS technology had great advantages over conventional target diagnosis methods for identifying rare thalassemia variants and assisted better carrier screening and prenatal diagnosis of thalassemia.

Monocular 3D Fingerprint Reconstruction and Unwarping.

Compared with contact-based fingerprint acquisition techniques, contactless acquisition has the advantages of less skin distortion, more complete fingerprint area, and hygienic acquisition. However, perspective distortion is a challenge in contactless fingerprint recognition, which changes the ridge frequency and relative minutiae location, and thus degrades the recognition accuracy. We propose a learning-based shape-from-texture algorithm to reconstruct a 3-D finger shape from a single image and unwarp the raw image to suppress the perspective distortion. Our experimental results for 3-D reconstruction on contactless fingerprint databases show that the proposed method has high 3-D reconstruction accuracy. Experimental results for contactless-to-contactless and contactless-to-contact-based fingerprint matching indicate that the proposed method can improve the matching accuracy.

The comprehensive analysis of thalassemia alleles (CATSA) based on single-molecule real-time technology (SMRT) is a more powerful strategy in the diagnosis of thalassemia caused by rare variants.

Thalassemia is one of the most widely distributed monogenic disorders in the world and affects the largest number of people. It can manifest a wide spectrum of phenotypes from asymptomatic to fatal, which is associated with the degree of imbalance between α- and ß-globin chains. Therefore, individuals with different genotypes could present with a similar phenotype. Genetic analysis is always needed to make a correct diagnosis. However, routine genetic analysis of thalassemia used in the Chinese population identifies only 23 common variants, resulting in many cases undiagnosed or being misdiagnosed. In this study, we applied a long-read sequencing-based approach termed comprehensive analysis of thalassemia alleles (CATSA) to 30 subjects whose hematologic screening results could not be explained by the routine genetic test results. The identification of additional variants and the correction of genotypes allowed the interpretation of the clinical phenotype in 24 subjects, which have been confirmed to be correct by independent experiments. Moreover, we identified a novel 8.4-kb deletion containing the entire HBB and HBD genes as well as part of the HBBP1 gene, expanding the genotype spectrum of ß-thalassemia. CATSA showed a great advantage over other genetic tests in the diagnosis of thalassemia caused by rare variants.

MetaAge: Meta-Learning Personalized Age Estimators.

Different people age in different ways. Learning a personalized age estimator for each person is a promising direction for age estimation given that it better models the personalization of aging processes. However, most existing personalized methods suffer from the lack of large-scale datasets due to the high-level requirements: identity labels and enough samples for each person to form a long-term aging pattern. In this paper, we aim to learn personalized age estimators without the above requirements and propose a meta-learning method named MetaAge for age estimation. Unlike most existing personalized methods that learn the parameters of a personalized estimator for each person in the training set, our method learns the mapping from identity information to age estimator parameters. Specifically, we introduce a personalized estimator meta-learner, which takes identity features as the input and outputs the parameters of customized estimators. In this way, our method learns the meta knowledge without the above requirements and seamlessly transfers the learned meta knowledge to the test set, which enables us to leverage the existing large-scale age datasets without any additional annotations. Extensive experimental results on three benchmark datasets including MORPH II, ChaLearn LAP 2015 and ChaLearn LAP 2016 databases demonstrate that our MetaAge significantly boosts the performance of existing personalized methods and outperforms the state-of-the-art approaches.

The Medical Segmentation Decathlon.

International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)-a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.

Deep diagnostic agent forest (DDAF): A deep learning pathogen recognition system for pneumonia based on CT.

BACKGROUND: Even though antibiotics agents are widely used, pneumonia is still one of the most common causes of death around the world. Some severe, fast-spreading pneumonia can even cause huge influence on global economy and life security. In order to give optimal medication regimens and prevent infectious pneumonia's spreading, recognition of pathogens is important. METHOD: In this single-institution retrospective study, 2,353 patients with their CT volumes are included, each of whom was infected by one of 12 known kinds of pathogens. We propose Deep Diagnostic Agent Forest (DDAF) to recognize the pathogen of a patient based on ones' CT volume, which is a challenging multiclass classification problem, with large intraclass variations and small interclass variations and very imbalanced data. RESULTS: The model achieves 0.899 ± 0.004 multi-way area under curves of receiver (AUC) for level-I pathogen recognition, which are five rough groups of pathogens, and 0.851 ± 0.003 AUC for level-II recognition, which are 12 fine-level pathogens. The model also outperforms the average result of seven human readers in level-I recognition and outperforms all readers in level-II recognition, who can only reach an average result of 7.71 ± 4.10% accuracy. CONCLUSION: Deep learning model can help in recognition pathogens using CTs only, which might help accelerate the process of etiological diagnosis.

Reasoning Graph Networks for Kinship Verification: From Star-Shaped to Hierarchical.

In this paper, we investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. Conventional methods usually focus on learning discriminative features for each facial image of a paired sample and neglect how to fuse the obtained two facial image features and reason about the relations between them. To address this, we propose a Star-shaped Reasoning Graph Network (S-RGN). Our S-RGN first constructs a star-shaped graph where each surrounding node encodes the information of comparisons in a feature dimension and the central node is employed as the bridge for the interaction of surrounding nodes. Then we perform relational reasoning on this star graph with iterative message passing. The proposed S-RGN uses only one central node to analyze and process information from all surrounding nodes, which limits its reasoning capacity. We further develop a Hierarchical Reasoning Graph Network (H-RGN) to exploit more powerful and flexible capacity. More specifically, our H-RGN introduces a set of latent reasoning nodes and constructs a hierarchical graph with them. Then bottom-up comparative information abstraction and top-down comprehensive signal propagation are iteratively performed on the hierarchical graph to update the node features. Extensive experimental results on four widely used kinship databases show that the proposed methods achieve very competitive results.

A rapid screening classifier for diagnosing COVID-19.

Rationale: Coronavirus disease 2019 (COVID-19) has caused a global pandemic. A classifier combining chest X-ray (CXR) with clinical features may serve as a rapid screening approach. Methods: The study included 512 patients with COVID-19 and 106 with influenza A/B pneumonia. A deep neural network (DNN) was applied, and deep features derived from CXR and clinical findings formed fused features for diagnosis prediction. Results: The clinical features of COVID-19 and influenza showed different patterns. Patients with COVID-19 experienced less fever, more diarrhea, and more salient hypercoagulability. Classifiers constructed using the clinical features or CXR had an area under the receiver operating curve (AUC) of 0.909 and 0.919, respectively. The diagnostic efficacy of the classifier combining the clinical features and CXR was dramatically improved and the AUC was 0.952 with 91.5% sensitivity and 81.2% specificity. Moreover, combined classifier was functional in both severe and non-serve COVID-19, with an AUC of 0.971 with 96.9% sensitivity in non-severe cases, which was on par with the computed tomography (CT)-based classifier, but had relatively inferior efficacy in severe cases compared to CT. In extension, we performed a reader study involving three experienced pulmonary physicians, artificial intelligence (AI) system demonstrated superiority in turn-around time and diagnostic accuracy compared with experienced pulmonary physicians. Conclusions: The classifier constructed using clinical and CXR features is efficient, economical, and radiation safe for distinguishing COVID-19 from influenza A/B pneumonia, serving as an ideal rapid screening tool during the COVID-19 pandemic.

Development and evaluation of an artificial intelligence system for COVID-19 diagnosis.

Early detection of COVID-19 based on chest CT enables timely treatment of patients and helps control the spread of the disease. We proposed an artificial intelligence (AI) system for rapid COVID-19 detection and performed extensive statistical analysis of CTs of COVID-19 based on the AI system. We developed and evaluated our system on a large dataset with more than 10 thousand CT volumes from COVID-19, influenza-A/B, non-viral community acquired pneumonia (CAP) and non-pneumonia subjects. In such a difficult multi-class diagnosis task, our deep convolutional neural network-based system is able to achieve an area under the receiver operating characteristic curve (AUC) of 97.81% for multi-way classification on test cohort of 3,199 scans, AUC of 92.99% and 93.25% on two publicly available datasets, CC-CCII and MosMedData respectively. In a reader study involving five radiologists, the AI system outperforms all of radiologists in more challenging tasks at a speed of two orders of magnitude above them. Diagnosis performance of chest x-ray (CXR) is compared to that of CT. Detailed interpretation of deep network is also performed to relate system outputs with CT presentations. The code is available at https://github.com/ChenWWWeixiang/diagnosis_covid19 .

Uniform and Variational Deep Learning for RGB-D Object Recognition and Person Re-Identification.

In this paper, we propose a uniform and variational deep learning (UVDL) method for RGB-D object recognition and person re-identification. Unlike most existing object recognition and person re-identification methods, which usually use only the visual appearance information from RGB images, our method recognizes visual objects and persons with RGB-D images to exploit more reliable information such as geometric and anthropometric information that are robust to different viewpoints. Specifically, we extract the depth feature and the appearance feature from the depth and RGB images with two deep convolutional neural networks, respectively. In order to combine the depth feature and the appearance feature to exploit their relationship, we design a uniform and variational multi-modal auto-encoder at the top layer of our deep network to seek a uniform latent variable by projecting them into a common space, which contains the whole information of RGB-D images and has small intra-class variation and large inter-class variation, simultaneously. Finally, we optimize the auto-encoder layer and two deep convolutional neural networks jointly to minimize the discriminative loss and the reconstruction error. The experimental results on both RGB-D object recognition and RGB-D person re-identification are presented to show the efficiency of our proposed approach.

Learning Deep Binary Descriptor with Multi-Quantization.

In this paper, we propose an unsupervised feature learning method called deep binary descriptor with multi-quantization (DBD-MQ) for visual analysis. Existing learning-based binary descriptors such as compact binary face descriptor (CBFD) and DeepBit utilize the rigid sign function for binarization despite of data distributions, which usually suffer from severe quantization loss. In order to address the limitation, we propose a deep multi-quantization network to learn a data-dependent binarization in an unsupervised manner. More specifically, we design a K-Autoencoders (KAEs) network to jointly learn the parameters of feature extractor and the binarization functions under a deep learning framework, so that discriminative binary descriptors can be obtained with a fine-grained multi-quantization. As DBD-MQ simply allocates the same number of quantizers to each real-valued feature dimension ignoring the elementwise diversity of informativeness, we further propose a deep competitive binary descriptor with multi-quantization (DCBD-MQ) method to learn optimal allocation of bits with the fixed binary length in a competitive manner, where informative dimensions gain more bits for complete representation. Moreover, we present a similarity-aware binary encoding strategy based on the earth mover's distance of Autoencoders, so that elements that are quantized into similar Autoencoders will have smaller Hamming distances. Extensive experimental results on six widely-used datasets show that our DBD-MQ and DCBD-MQ outperform most state-of-the-art unsupervised binary descriptors.

Left Atrial Appendage Segmentation Using Fully Convolutional Neural Networks and Modified Three-Dimensional Conditional Random Fields.

Thrombosis has become a global disease threatening human health. The left atrial appendage (LAA) is a major source of thrombosis in patients with atrial fibrillation (AF). Positive correlation exists between LAA volume and AF risk. LAA morphology has been suggested to influence thromboembolic risk in AF patients and to help predict thromboembolic events in low-risk patient groups. Automatic segmentation of LAA can greatly help physicians diagnose AF. In consideration of the large anatomical variations of the LAA, we proposed a robust method for automatic LAA segmentation on computed tomographic angiography (CTA) data using fully convolutional neural networks with three-dimensional (3-D) conditional random fields (CRFs). After manual localization of ROI of LAA, we adopted the FCN in natural image segmentation and transferred their learned models by fine-tuning the networks to segment each 2-D LAA slice. Subsequently, we used a modified dense 3-D CRF that accounts for the 3-D spatial information and larger contextual information to refine the segmentations of all slices. Our method was evaluated on 150 sets of CTA data using five-fold cross validation. Compared with manual annotation, we obtained a mean dice overlap of and a mean volume overlap of with a computation time of less than 40 s per volume. Experimental results demonstrated the robustness of our method in dealing with large anatomical variations and computational efficiency for adoption in a daily clinical routine.).

Context-Aware Local Binary Feature Learning for Face Recognition.

In this paper, we propose a context-aware local binary feature learning (CA-LBFL) method for face recognition. Unlike existing learning-based local face descriptors such as discriminant face descriptor (DFD) and compact binary face descriptor (CBFD) which learn each feature code individually, our CA-LBFL exploits the contextual information of adjacent bits by constraining the number of shifts from different binary bits, so that more robust information can be exploited for face representation. Given a face image, we first extract pixel difference vectors (PDV) in local patches, and learn a discriminative mapping in an unsupervised manner to project each pixel difference vector into a context-aware binary vector. Then, we perform clustering on the learned binary codes to construct a codebook, and extract a histogram feature for each face image with the learned codebook as the final representation. In order to exploit local information from different scales, we propose a context-aware local binary multi-scale feature learning (CA-LBMFL) method to jointly learn multiple projection matrices for face representation. To make the proposed methods applicable for heterogeneous face recognition, we present a coupled CA-LBFL (C-CA-LBFL) method and a coupled CA-LBMFL (C-CA-LBMFL) method to reduce the modality gap of corresponding heterogeneous faces in the feature level, respectively. Extensive experimental results on four widely used face datasets clearly show that our methods outperform most state-of-the-art face descriptors.

Left atrial appendage segmentation and quantitative assisted diagnosis of atrial fibrillation based on fusion of temporal-spatial information.

In this paper, we present an approach for left atrial appendage (LAA) multi-phase fast segmentation and quantitative assisted diagnosis of atrial fibrillation (AF) based on 4D-CT data. We take full advantage of the temporal dimension information to segment the living, flailed LAA based on a parametric max-flow method and graph-cut approach to build 3-D model of each phase. To assist the diagnosis of AF, we calculate the volumes of 3-D models, and then generate a "volume-phase" curve to calculate the important dynamic metrics: ejection fraction, filling flux, and emptying flux of the LAA's blood by volume. This approach demonstrates more precise results than the conventional approaches that calculate metrics by area, and allows for the quick analysis of LAA-volume pattern changes of in a cardiac cycle. It may also provide insight into the individual differences in the lesions of the LAA. Furthermore, we apply support vector machines (SVMs) to achieve a quantitative auto-diagnosis of the AF by exploiting seven features from volume change ratios of the LAA, and perform multivariate logistic regression analysis for the risk of LAA thrombosis. The 100 cases utilized in this research were taken from the Philips 256-iCT. The experimental results demonstrate that our approach can construct the 3-D LAA geometries robustly compared to manual annotations, and reasonably infer that the LAA undergoes filling, emptying and re-filling, re-emptying in a cardiac cycle. This research provides a potential for exploring various physiological functions of the LAA and quantitatively estimating the risk of stroke in patients with AF.