A Lightweight Network for Contextual and Morphological Awareness for Hepatic Vein Segmentation.

Accurate segmentation of the hepatic vein can improve the precision of liver disease diagnosis and treatment. Since the hepatic venous system is a small target and sparsely distributed, with various and diverse morphology, data labeling is difficult. Therefore, automatic hepatic vein segmentation is extremely challenging. We propose a lightweight contextual and morphological awareness network and design a novel morphology aware module based on attention mechanism and a 3D reconstruction module. The morphology aware module can obtain the slice similarity awareness mapping, which can enhance the continuous area of the hepatic veins in two adjacent slices through attention weighting. The 3D reconstruction module connects the 2D encoder and the 3D decoder to obtain the learning ability of 3D context with a very small amount of parameters. Compared with other SOTA methods, using the proposed method demonstrates an enhancement in the dice coefficient with few parameters on the two datasets. A small number of parameters can reduce hardware requirements and potentially have stronger generalization, which is an advantage in clinical deployment.

Rapid and precise detection of cancers via label-free SERS and deep learning.

Early, express, and reliable detection of cancer can provide a favorable prognosis and decrease mortality. Tumor biomarkers have been proven to be closely related to tumor occurrence and development. Conventional tumor biomarker detection based on genomic, proteomic, and metabolomic methods is time and equipment-consuming and always needs a specific target marker. Surface-enhanced Raman scattering (SERS), as a non-invasive ultrasensitive and label-free vibrational spectroscopy technique, can detect cancer-related biomedical changes in biofluids. In this paper, 110 serum samples were collected from 30 healthy controls and 80 cancer patients (including 30 bladder cancer (BC), 30 adrenal cancer (AC), and 20 acute myeloid leukemia (AML)). One microliter of blood serum was mixed with 1 µl silver colloid and then was air-dried for SERS measurements. After spectral data augmentation, one-dimensional convolutional neural network (1D-CNN) was proposed for precise and rapid identification of healthy and three different cancers with high accuracy of 98.27%. After gradient-weighted class activation mapping (Grad-CAM) based spectral interpretation, the contributions of SERS peaks corresponding to biochemical substances indicated the most potential biomarkers, i.e., L-tyrosine in bladder cancer; acetoacetate and riboflavin in adrenal cancer and phospholipids, amide-I, and α-Helix in acute myeloid leukemia, which might provide an insight into the mechanism of intelligent diagnosis of different cancers based on label-free serum SERS. The integration of label-free SERS and deep learning has great potential for the rapid, reliable, and non-invasive detection of cancers, which may significantly improve the precise diagnosis in clinical practice.

Metabolic Anomaly Appearance Aware U-Net for Automatic Lymphoma Segmentation in Whole-Body PET/CT Scans.

Positron emission tomography-computed tomography (PET/CT) is an essential imaging instrument for lymphoma diagnosis and prognosis. PET/CT image based automatic lymphoma segmentation is increasingly used in the clinical community. U-Net-like deep learning methods have been widely used for PET/CT in this task. However, their performance is limited by the lack of sufficient annotated data, due to the existence of tumor heterogeneity. To address this issue, we propose an unsupervised image generation scheme to improve the performance of another independent supervised U-Net for lymphoma segmentation by capturing metabolic anomaly appearance (MAA). Firstly, we propose an anatomical-metabolic consistency generative adversarial network (AMC-GAN) as an auxiliary branch of U-Net. Specifically, AMC-GAN learns normal anatomical and metabolic information representations using co-aligned whole-body PET/CT scans. In the generator of AMC-GAN, we propose a complementary attention block to enhance the feature representation of low-intensity areas. Then, the trained AMC-GAN is used to reconstruct the corresponding pseudo-normal PET scans to capture MAAs. Finally, combined with the original PET/CT images, MAAs are used as the prior information for improving the performance of lymphoma segmentation. Experiments are conducted on a clinical dataset containing 191 normal subjects and 53 patients with lymphomas. The results demonstrate that the anatomical-metabolic consistency representations obtained from unlabeled paired PET/CT scans can be helpful for more accurate lymphoma segmentation, which suggest the potential of our approach to support physician diagnosis in practical clinical applications.

A review of deep learning-based multiple-lesion recognition from medical images: classification, detection and segmentation.

Deep learning-based methods have become the dominant methodology in medical image processing with the advancement of deep learning in natural image classification, detection, and segmentation. Deep learning-based approaches have proven to be quite effective in single lesion recognition and segmentation. Multiple-lesion recognition is more difficult than single-lesion recognition due to the little variation between lesions or the too wide range of lesions involved. Several studies have recently explored deep learning-based algorithms to solve the multiple-lesion recognition challenge. This paper includes an in-depth overview and analysis of deep learning-based methods for multiple-lesion recognition developed in recent years, including multiple-lesion recognition in diverse body areas and recognition of whole-body multiple diseases. We discuss the challenges that still persist in the multiple-lesion recognition tasks by critically assessing these efforts. Finally, we outline existing problems and potential future research areas, with the hope that this review will help researchers in developing future approaches that will drive additional advances.

SDA-UNet: a hepatic vein segmentation network based on the spatial distribution and density awareness of blood vessels.

Objective.Hepatic vein segmentation is a fundamental task for liver diagnosis and surgical navigation planning. Unlike other organs, the liver is the only organ with two sets of venous systems. Meanwhile, the segmentation target distribution in the hepatic vein scene is extremely unbalanced. The hepatic veins occupy a small area in abdominal CT slices. The morphology of each person's hepatic vein is different, which also makes segmentation difficult. The purpose of this study is to develop an automated hepatic vein segmentation model that guides clinical diagnosis.Approach.We introduce the 3D spatial distribution and density awareness (SDA) of hepatic veins and propose an automatic segmentation network based on 3D U-Net which includes a multi-axial squeeze and excitation module (MASE) and a distribution correction module (DCM). The MASE restrict the activation area to the area with hepatic veins. The DCM improves the awareness of the sparse spatial distribution of the hepatic veins. To obtain global axial information and spatial information at the same time, we study the effect of different training strategies on hepatic vein segmentation. Our method was evaluated by a public dataset and a private dataset. The Dice coefficient achieves 71.37% and 69.58%, improving 3.60% and 3.30% compared to the other SOTA models, respectively. Furthermore, metrics based on distance and volume also show the superiority of our method.Significance.The proposed method greatly reduced false positive areas and improved the segmentation performance of the hepatic vein in CT images. It will assist doctors in making accurate diagnoses and surgical navigation planning.

PSR-Nets: Deep neural networks with prior shift regularization for PET/CT based automatic, accurate, and calibrated whole-body lymphoma segmentation.

Lymphoma is a type of lymphatic tissue originated cancer. Automatic and accurate lymphoma segmentation is critical for its diagnosis and prognosis yet challenging due to the severely class-imbalanced problem. Generally, deep neural networks trained with class-observation-frequency based re-weighting loss functions are used to address this problem. However, the majority class can be under-weighted by them, due to the existence of data overlap. Besides, they are more mis-calibrated. To resolve these, we propose a neural network with prior-shift regularization (PSR-Net), which comprises a UNet-like backbone with re-weighting loss functions, and a prior-shift regularization (PSR) module including a prior-shift layer (PSL), a regularizer generation layer (RGL), and an expected prediction confidence updating layer (EPCUL). We first propose a trainable expected prediction confidence (EPC) for each class. Periodically, PSL shifts a prior training dataset to a more informative dataset based on EPCs; RGL presents a generalized informative-voxel-aware (GIVA) loss with EPCs and calculates it on the informative dataset for model finetuning in back-propagation; and EPCUL updates EPCs to refresh PSL and RRL in next forward-propagation. PSR-Net is trained in a two- stage manner. The backbone is first trained with re-weighting loss functions, then we reload the best saved model for the backbone and continue to train it with the weighted sum of the re-weighting loss functions, the GIVA regularizer and the L2 loss function of EPCs for regularization fine-tuning. Extensive experiments are performed based on PET/CT volumes with advanced stage lymphomas. Our PSR-Net achieves 95.12% sensitivity and 87.18% Dice coefficient, demonstrating the effectiveness of PSR-Net, when compared to the baselines and the state-of-the-arts.

SCL-Net: Structured Collaborative Learning for PET/CT Based Tumor Segmentation.

Collaborative learning methods for medical image segmentation are often variants of UNet, where the constructions of classifiers depend on each other and their outputs are supervised independently. However, they cannot explicitly ensure that optimizing auxiliary classifier heads leads to improved segmentation of target classifier. To resolve this problem, we propose a structured collaborative learning (SCL) method, which consists of a context-aware structured classifier population generation (CA-SCPG) module, where the feature propagation of the target classifier path is directly enhanced by the outputs of auxiliary classifiers via a light-weighted high-level context-aware dense connection (HLCA-DC) mechanism, and a knowledge-aware structured classifier population supervision (KA-SCPS) module, where the auxiliary classifiers are properly supervised under the guidance of target classifier's segmentations. Specifically, SCL is proposed based on a recurrent-dense-siamese decoder (RDS-Decoder), which consists of multiple siamese-decoder paths. CA-SCPG enhances the feature propagation of the decoder paths by HLCA-DC, which densely reuses previous decoder paths' output prediction maps to belong to the target classes as inputs to the layers of latter decoder paths. KA-SCPS supervises the classifier heads simultaneously with KA-SCPS loss, which consists of a generalized weighted cross-entropy loss for deep class-imbalanced learning and a novel knowledge-aware Dice loss (KA-DL). KA-DL is a weighted Dice loss broadcasting knowledges learnt by the target classifier to other classifier heads, harmonizing the learning process of the classifier population. Experiments are performed based on PET/CT volumes with malignant melanoma, lymphoma, or lung cancer. Experimental results demonstrate the superiority of our SCL, when compared to the state-of-the-art methods and baselines.

A Survey of Modulation Classification Using Deep Learning: Signal Representation and Data Preprocessing.

Modulation classification is one of the key tasks for communications systems monitoring, management, and control for addressing technical issues, including spectrum awareness, adaptive transmissions, and interference avoidance. Recently, deep learning (DL)-based modulation classification has attracted significant attention due to its superiority in feature extraction and classification accuracy. In DL-based modulation classification, one major challenge is to preprocess a received signal and represent it in a proper format before feeding the signal into deep neural networks. This article provides a comprehensive survey of the state-of-the-art DL-based modulation classification algorithms, especially the techniques of signal representation and data preprocessing utilized in these algorithms. Since a received signal can be represented by either features, images, sequences, or a combination of them, existing algorithms of DL-based modulation classification can be categorized into four groups and are reviewed accordingly in this article. Furthermore, the advantages as well as disadvantages of each signal representation method are summarized and discussed.

HD-RDS-UNet: Leveraging Spatial-Temporal Correlation Between the Decoder Feature Maps for Lymphoma Segmentation.

Lymphoma is cancer originated in the lymphatic system. Clinically, automatic and accurate lymphoma segmentation is critical yet challenging. Recently, UNet-like architectures are widely used for medical image segmentation. The pure UNet-like architectures can model the spatial correlation between the feature maps very well, whereas they discard the critical temporal correlation. Some prior works combine UNet with recurrent neural networks (RNNs) to utilize the spatial and temporal correlation simultaneously. However, it is inconvenient to incorporate some advanced techniques proposed for UNet to RNNs, which hampers their further improvements. In this paper, we propose a recurrent dense siamese decoder architecture, which simulates RNNs and can densely utilize the spatial temporal correlation between the decoder feature maps following a "UNet" approach. We combine it with a modified hyper dense encoder. Therefore, the proposed model is a UNet with a hyper dense encoder and a recurrent dense siamese decoder (HD-RDS-UNet). To stabilize the training process, we propose a weighted Dice loss with stable gradient and self-adaptive parameters. We perform patient-independent five-fold cross-validation on 3D volumes collected from whole-body PET/CT scans of patients with lymphomas. The experimental results show that the volume-wise average Dice score and sensitivity are 85.58% and 94.63%, respectively. The patient-wise average Dice score and sensitivity are 85.85% and 95.01%, respectively. The different configurations of HD-RDS-UNet consistently show superiority in the performance comparison. Besides, a trained HD-RDS-UNet can be easily pruned, resulting in significantly reduced inference time and memory usage, while keeping very good segmentation performance.

IoT Platform for COVID-19 Prevention and Control: A Survey.

As a result of the worldwide transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), coronavirus disease 2019 (COVID-19) has evolved into an unprecedented pandemic. Currently, with unavailable pharmaceutical treatments and low vaccination rates, this novel coronavirus results in a great impact on public health, human society, and global economy, which is likely to last for many years. One of the lessons learned from the COVID-19 pandemic is that a long-term system with non-pharmaceutical interventions for preventing and controlling new infectious diseases is desirable to be implemented. Internet of things (IoT) platform is preferred to be utilized to achieve this goal, due to its ubiquitous sensing ability and seamless connectivity. IoT technology is changing our lives through smart healthcare, smart home, and smart city, which aims to build a more convenient and intelligent community. This paper presents how the IoT could be incorporated into the epidemic prevention and control system. Specifically, we demonstrate a potential fog-cloud combined IoT platform that can be used in the systematic and intelligent COVID-19 prevention and control, which involves five interventions including COVID-19 Symptom Diagnosis, Quarantine Monitoring, Contact Tracing & Social Distancing, COVID-19 Outbreak Forecasting, and SARS-CoV-2 Mutation Tracking. We investigate and review the state-of-the-art literatures of these five interventions to present the capabilities of IoT in countering against the current COVID-19 pandemic or future infectious disease epidemics.

EFNet: evidence fusion network for tumor segmentation from PET-CT volumes.

Precise delineation of target tumor from positron emission tomography-computed tomography (PET-CT) is a key step in clinical practice and radiation therapy. PET-CT co-segmentation actually uses the complementary information of two modalities to reduce the uncertainty of single-modal segmentation, so as to obtain more accurate segmentation results. At present, the PET-CT segmentation methods based on fully convolutional neural network (FCN) mainly adopt image fusion and feature fusion. The current fusion strategies do not consider the uncertainty of multi-modal segmentation and complex feature fusion consumes more computing resources, especially when dealing with 3D volumes. In this work, we analyze the PET-CT co-segmentation from the perspective of uncertainty, and propose evidence fusion network (EFNet). The network respectively outputs PET result and CT result containing uncertainty by proposed evidence loss, which are used as PET evidence and CT evidence. Then we use evidence fusion to reduce uncertainty of single-modal evidence. The final segmentation result is obtained based on evidence fusion of PET evidence and CT evidence. EFNet uses the basic 3D U-Net as backbone and only uses simple unidirectional feature fusion. In addition, EFNet can separately train and predict PET evidence and CT evidence, without the need for parallel training of two branch networks. We do experiments on the soft-tissue-sarcomas and lymphoma datasets. Compared with 3D U-Net, our proposed method improves the Dice by 8% and 5% respectively. Compared with the complex feature fusion method, our proposed method improves the Dice by 7% and 2% respectively. Our results show that in PET-CT segmentation methods based on FCN, by outputting uncertainty evidence and evidence fusion, the network can be simplified and the segmentation results can be improved.

AW-SDRLSE: Adaptive Weighting and Scalable Distance Regularized Level Set Evolution for Lymphoma Segmentation on PET Images.

Accurate lymphoma segmentation on Positron Emission Tomography (PET) images is of great importance for medical diagnoses, such as for distinguishing benign and malignant. To this end, this paper proposes an adaptive weighting and scalable distance regularized level set evolution (AW-SDRLSE) method for delineating lymphoma boundaries on 2D PET slices. There are three important characteristics with respect to AW-SDRLSE: 1) A scalable distance regularization term is proposed and a parameter q can control the contour's convergence rate and precision in theory. 2) A novel dynamic annular mask is proposed to calculate mean intensities of local interior and exterior regions and further define the region energy term. 3) As the level set method is sensitive to parameters, we thus propose an adaptive weighting strategy for the length and area energy terms using local region intensity and boundary direction information. AW-SDRLSE is evaluated on 90 cases of real PET data with a mean Dice coefficient of 0.8796. Comparative results demonstrate the accuracy and robustness of AW-SDRLSE as well as its performance advantages as compared with related level set methods. In addition, experimental results indicate that AW-SDRLSE can be a fine segmentation method for improving the lymphoma segmentation results obtained by deep learning (DL) methods significantly.

Modulation Classification Based on Signal Constellation Diagrams and Deep Learning.

Deep learning (DL) is a new machine learning (ML) methodology that has found successful implementations in many application domains. However, its usage in communications systems has not been well explored. This paper investigates the use of the DL in modulation classification, which is a major task in many communications systems. The DL relies on a massive amount of data and, for research and applications, this can be easily available in communications systems. Furthermore, unlike the ML, the DL has the advantage of not requiring manual feature selections, which significantly reduces the task complexity in modulation classification. In this paper, we use two convolutional neural network (CNN)-based DL models, AlexNet and GoogLeNet. Specifically, we develop several methods to represent modulated signals in data formats with gridlike topologies for the CNN. The impacts of representation on classification performance are also analyzed. In addition, comparisons with traditional cumulant and ML-based algorithms are presented. Experimental results demonstrate the significant performance advantage and application feasibility of the DL-based approach for modulation classification.

An effective computer aided diagnosis model for pancreas cancer on PET/CT images.

Background and objective: Pancreas cancer is a digestive tract tumor with high malignancy, which is difficult for diagnosis and treatment at early time. To this end, this paper proposes a computer aided diagnosis (CAD) model for pancreas cancer on Positron Emission Tomography/Computed Tomography (PET/CT) images. METHODS: There are three essential steps in the proposed CAD model, including (1) pancreas segmentation, (2) feature extraction and selection, (3) classifier design, respectively. First, pancreas segmentation is performed using simple linear iterative clustering (SLIC) on CT pseudo-color images generated by the gray interval mapping (GIP) method. Second, dual threshold principal component analysis (DT-PCA) is developed to select the most beneficial feature combination, which not only considers principal features but also integrates some non-principal features into a new polar angle representation. Finally, a hybrid feedback-support vector machine-random forest (HFB-SVM-RF) model is designed to identify normal pancreas or pancreas cancer and the key is to use 8 types of SVMs to establish the decision trees of RF. RESULTS: The proposed CAD model is tested on 80 cases of PET/CT data (from General Hospital of Shenyang Military Area Command) and achieves the average pancreas cancer identification accuracy of 96.47%, sensibility of 95.23% and specificity of 97.51%, respectively. In addition, the proposed pancreas segmentation method is also evaluated using a public dataset with 82 3D CT scans from the National Institutes of Health (NIH) Clinical Center and its performance is found to surpass other methods, with a mean Dice coefficient of 78.9% and Jaccard index of 65.4%. CONCLUSIONS: Collectively, contrast experiments in 10-fold cross validation demonstrate the efficiency and accuracy of the proposed CAD model as well as its performance advantages as compared with related methods.

Organ Location Determination and Contour Sparse Representation for Multiorgan Segmentation.

Organ segmentation on computed tomography (CT) images is of great importance in medical diagnoses and treatment. This paper proposes organ location determination and contour sparse representation methods (OLD-CSR) for multiorgan segmentation (liver, kidney, and spleen) on abdomen CT images using an extreme learning machine classifier. First, a location determination method is designed to obtain location information of each organ, which is used for coarse segmentation. Second, for coarse-to-fine segmentation, a contour gradient and rate change based feature point extraction method is proposed. A sparse optimization model is developed for refining the contour feature points. Experimentations with 153 CT images demonstrate the performance advantages of OLD-CSR as compared with related work.

An Alzheimers disease related genes identification method based on multiple classifier integration.

BACKGROUND AND OBJECTIVE: Alzheimers disease (AD) is a fatal neurodegenerative disease and the onset of AD is insidious. Full understanding of the AD-related genes (ADGs) has not been completed. The National Center for Biotechnology Information (NCBI) provides an AD dataset of 22,283 genes. Among these genes, 71 genes have been identified as ADGs. But there may still be underlying ADGs that have not yet been identified in the remaining 22,212 genes. This paper aims to identify additional ADGs using machine learning techniques. METHODS: To improve the accuracy of ADG identification, we propose a gene identification method through multiple classifier integration. First, a feature selection algorithm is applied to select the most relevant attributes. Second, a two-stage cascading classifier is developed to identify ADGs. The first stage classification task is based on the relevance vector machine and, in the second stage, the results of three classifiers, support vector machine, random forest and extreme learning machine, are combined through voting. RESULTS: According to our results, feature selection improves accuracy and reduces training time. Voting based classifier reduces the classification errors. The proposed ADG identification system provides accuracy, sensitivity and specificity at levels of 78.77%, 83.10% and 74.67%, respectively. Based on the proposed ADG identification method, potentially additional ADGs are identified and top 13 genes (predicted ADGs) are presented. CONCLUSIONS: In this paper, an ADG identification method for identifying ADGs is presented. The proposed method which combines feature selection, cascading classifier and majority voting leads to higher specificity and significantly increases the accuracy and sensitivity of ADG identification. Potentially new ADGs are identified.