Robust deep learning from incomplete annotation for accurate lung nodule detection.

Deep learning plays a significant role in the detection of pulmonary nodules in low-dose computed tomography (LDCT) scans, contributing to the diagnosis and treatment of lung cancer. Nevertheless, its effectiveness often relies on the availability of extensive, meticulously annotated dataset. In this paper, we explore the utilization of an incompletely annotated dataset for pulmonary nodules detection and introduce the FULFIL (Forecasting Uncompleted Labels For Inexpensive Lung nodule detection) algorithm as an innovative approach. By instructing annotators to label only the nodules they are most confident about, without requiring complete coverage, we can substantially reduce annotation costs. Nevertheless, this approach results in an incompletely annotated dataset, which presents challenges when training deep learning models. Within the FULFIL algorithm, we employ Graph Convolution Network (GCN) to discover the relationships between annotated and unannotated nodules for self-adaptively completing the annotation. Meanwhile, a teacher-student framework is employed for self-adaptive learning using the completed annotation dataset. Furthermore, we have designed a Dual-Views loss to leverage different data perspectives, aiding the model in acquiring robust features and enhancing generalization. We carried out experiments using the LUng Nodule Analysis (LUNA) dataset, achieving a sensitivity of 0.574 at a False positives per scan (FPs/scan) of 0.125 with only 10% instance-level annotations for nodules. This performance outperformed comparative methods by 7.00%. Experimental comparisons were conducted to evaluate the performance of our model and human experts on test dataset. The results demonstrate that our model can achieve a comparable level of performance to that of human experts. The comprehensive experimental results demonstrate that FULFIL can effectively leverage an incomplete pulmonary nodule dataset to develop a robust deep learning model, making it a promising tool for assisting in lung nodule detection.

Multi modality fusion transformer with spatio-temporal feature aggregation module for psychiatric disorder diagnosis.

Bipolar disorder (BD) is characterized by recurrent episodes of depression and mild mania. In this paper, to address the common issue of insufficient accuracy in existing methods and meet the requirements of clinical diagnosis, we propose a framework called Spatio-temporal Feature Fusion Transformer (STF2Former). It improves on our previous work - MFFormer by introducing a Spatio-temporal Feature Aggregation Module (STFAM) to learn the temporal and spatial features of rs-fMRI data. It promotes intra-modality attention and information fusion across different modalities. Specifically, this method decouples the temporal and spatial dimensions and designs two feature extraction modules for extracting temporal and spatial information separately. Extensive experiments demonstrate the effectiveness of our proposed STFAM in extracting features from rs-fMRI, and prove that our STF2Former can significantly outperform MFFormer and achieve much better results among other state-of-the-art methods.

Immunogenicity Analysis of PCV3 Recombinant Capsid Protein Virus-like Particles and Their Application in Antibodies Detection.

Porcine circovirus type 3 is a newly emerging pathogen of porcine circovirus associated disease (PCVAD). Currently, there is no commercially available vaccine, resulting in huge economic losses to the pig industry. Porcine circovirus type 3 capsid protein (Cap) can self-assemble into virus-like particles (VLPs). Therefore, the expression of the recombinant Cap protein is of great significance for the prevention, diagnosis and control of porcine circovirus type 3 associated diseases. In this study, the recombinant Cap protein was successfully expressed in Escherichia coli by deleting the nuclear localization sequence (NLS). The VLPs were observed by transmission electron microscopy. To evaluate the immunogenicity of the recombinant Cap protein, mice were immunized. As a result, the recombinant Cap protein can induce higher levels of humoral and cellular immune responses. A VLP-based ELISA method was developed for the detection of antibodies. The established ELISA method has good sensitivity, specificity, repeatability and clinical applicability. These results demonstrate the successful expression of the PCV3 recombinant Cap protein and the preparation of recombinant Cap protein VLPs, which can be used for the preparation of subunit vaccines. Meanwhile, the established I-ELISA method lays a foundation for the development of the commercial PCV3 serological antibody detection kit.

Auto-DenseUNet: Searchable neural network architecture for mass segmentation in 3D automated breast ultrasound.

Accurate segmentation of breast mass in 3D automated breast ultrasound (ABUS) plays an important role in breast cancer analysis. Deep convolutional networks have become a promising approach in segmenting ABUS images. However, designing an effective network architecture is time-consuming, and highly relies on specialist's experience and prior knowledge. To address this issue, we introduce a searchable segmentation network (denoted as Auto-DenseUNet) based on the neural architecture search (NAS) to search the optimal architecture automatically for the ABUS mass segmentation task. Concretely, a novel search space is designed based on a densely connected structure to enhance the gradient and information flows throughout the network. Then, to encourage multiscale information fusion, a set of searchable multiscale aggregation nodes between the down-sampling and up-sampling parts of the network are further designed. Thus, all the operators within the dense connection structure or between any two aggregation nodes can be searched to find the optimal structure. Finally, a novel decoupled search training strategy during architecture search is also introduced to alleviate the memory limitation caused by continuous relaxation in NAS. The proposed Auto-DenseUNet method has been evaluated on our ABUS dataset with 170 volumes (from 107 patients), including 120 training volumes and 50 testing volumes split at patient level. Experimental results on testing volumes show that our searched architecture performed better than several human-designed segmentation models on the 3D ABUS mass segmentation task, indicating the effectiveness of our proposed method.

Advancements in mammalian X and Y sperm differences and sex control technology.

Mammal sex determination depends on whether the X sperm or Y sperm binds to the oocyte during fertilization. If the X sperm joins in oocyte, the offspring will be female, if the Y sperm fertilizes, the offspring will be male. Livestock sex control technology has tremendous value for livestock breeding as it can increase the proportion of female offspring and improve the efficiency of livestock production. This review discusses the detailed differences between mammalian X and Y sperm with respect to their morphology, size, and motility in the reproductive tract and in in vitro conditions, as well as 'omics analysis results. Moreover, research progress in mammalian sex control technology has been summarized.

Cross-Model Attention-Guided Tumor Segmentation for 3D Automated Breast Ultrasound (ABUS) Images.

Tumor segmentation in 3D automated breast ultrasound (ABUS) plays an important role in breast disease diagnosis and surgical planning. However, automatic segmentation of tumors in 3D ABUS images is still challenging, due to the large tumor shape and size variations, and uncertain tumor locations among patients. In this paper, we develop a novel cross-model attention-guided tumor segmentation network with a hybrid loss for 3D ABUS images. Specifically, we incorporate the tumor location into a segmentation network by combining an improved 3D Mask R-CNN head into V-Net as an end-to-end architecture. Furthermore, we introduce a cross-model attention mechanism that is able to aggregate the segmentation probability map from the improved 3D Mask R-CNN to each feature extraction level in the V-Net. Then, we design a hybrid loss to balance the contribution of each part in the proposed cross-model segmentation network. We conduct extensive experiments on 170 3D ABUS from 107 patients. Experimental results show that our method outperforms other state-of-the-art methods, by achieving the Dice similarity coefficient (DSC) of 64.57%, Jaccard coefficient (JC) of 53.39%, recall (REC) of 64.43%, precision (PRE) of 74.51%, 95th Hausdorff distance (95HD) of 11.91 mm, and average surface distance (ASD) of 4.63 mm. Our code will be available online (https://github.com/zhouyuegithub/CMVNet).

Dilated densely connected U-Net with uncertainty focus loss for 3D ABUS mass segmentation.

BACKGROUND AND OBJECTIVE: Accurate segmentation of breast mass in 3D automated breast ultrasound (ABUS) images plays an important role in qualitative and quantitative ABUS image analysis. Yet this task is challenging due to the low signal to noise ratio and serious artifacts in ABUS images, the large shape and size variation of breast masses, as well as the small training dataset compared with natural images. The purpose of this study is to address these difficulties by designing a dilated densely connected U-Net (D2U-Net) together with an uncertainty focus loss. METHODS: A lightweight yet effective densely connected segmentation network is constructed to extensively explore feature representations in the small ABUS dataset. In order to deal with the high variation in shape and size of breast masses, a set of hybrid dilated convolutions is integrated into the dense blocks of the D2U-Net. We further suggest an uncertainty focus loss to put more attention on unreliable network predictions, especially the ambiguous mass boundaries caused by low signal to noise ratio and artifacts. Our segmentation algorithm is evaluated on an ABUS dataset of 170 volumes from 107 patients. Ablation analysis and comparison with existing methods are conduct to verify the effectiveness of the proposed method. RESULTS: Experiment results demonstrate that the proposed algorithm outperforms existing methods on 3D ABUS mass segmentation tasks, with Dice similarity coefficient, Jaccard index and 95% Hausdorff distance of 69.02%, 56.61% and 4.92 mm, respectively. CONCLUSIONS: The proposed method is effective in segmenting breast masses on our small ABUS dataset, especially breast masses with large shape and size variations.

Epiphyseal enchondroma masking as osteoid osteoma: a case report.

BACKGROUND: Enchondromas originating in the epiphyses of long bones are rare and epiphyseal osteoid osteomas are also uncommon. Diagnosis can become elusive when enchondromas or osteoid osteomas occur in atypical locations and present with nonspecific clinical and imaging characteristics. CASE PRESENTATION: We report a case of epiphyseal enchondroma of the left proximal femur in a 15-year-old girl with a 2-month history of left lower extremity pain. Preoperative CT displayed thickened cortex in the anterior surface of the left proximal femur with specks of calcification and inhomogeneity of the adjacent bone marrow cavity. She was diagnosed with osteoid osteoma. Postoperative pathological examination of surgically excised specimens revealed a diagnosis of enchondromas. CONCLUSIONS: Our case highlights that enchondroma should be considered in lesions of the epiphysis.

Uncertainty Aware Temporal-Ensembling Model for Semi-Supervised ABUS Mass Segmentation.

Accurate breast mass segmentation of automated breast ultrasound (ABUS) images plays a crucial role in 3D breast reconstruction which can assist radiologists in surgery planning. Although the convolutional neural network has great potential for breast mass segmentation due to the remarkable progress of deep learning, the lack of annotated data limits the performance of deep CNNs. In this article, we present an uncertainty aware temporal ensembling (UATE) model for semi-supervised ABUS mass segmentation. Specifically, a temporal ensembling segmentation (TEs) model is designed to segment breast mass using a few labeled images and a large number of unlabeled images. Considering the network output contains correct predictions and unreliable predictions, equally treating each prediction in pseudo label update and loss calculation may degrade the network performance. To alleviate this problem, the uncertainty map is estimated for each image. Then an adaptive ensembling momentum map and an uncertainty aware unsupervised loss are designed and integrated with TEs model. The effectiveness of the proposed UATE model is mainly verified on an ABUS dataset of 107 patients with 170 volumes, including 13382 2D labeled slices. The Jaccard index (JI), Dice similarity coefficient (DSC), pixel-wise accuracy (AC) and Hausdorff distance (HD) of the proposed method on testing set are 63.65%, 74.25%, 99.21% and 3.81mm respectively. Experimental results demonstrate that our semi-supervised method outperforms the fully supervised method, and get a promising result compared with existing semi-supervised methods.

Mechanistic insights into heavy metals affinity in magnetic MnO2@Fe3O4/poly(m-phenylenediamine) core-shell adsorbent.

Adsorption represents an attractive mean to remediate polluted water. Unfortunately, the surface positive charges, low surface area and complicated separation procedures inhibit the usability of poly (m-phenylenediamine) (PmPD) as an adsorbent for heavy metal removing. To overcome these drawbacks, a magnetic MnO2@Fe3O4/PmPD core-shell adsorbent was designed to remove heavy metals from water. The MnO2 shell, came from the redox reaction between KMnO4 and PmPD, increased the surface area and changed the surface electronegativity. MnO2@Fe3O4/PmPD could be easily separated from water. It showed a significant increase in heavy metals removal efficiency, with maximum capacities of 438.6 mg/g for Pb(II) and 121.5 mg/g for Cd(II), respectively. The affinity between heavy metals and MnO2@Fe3O4/PmPD were mainly due to electrostatic attraction, ion exchanges and coordinated interaction. Density functional theory (DFT) calculations further confirmed that Pb and Cd were bonded with O atoms. The calculated adsorption energy indicated that the (111) MnO2 facet presented stronger adsorption affinity toward Pb(II) than Cd(II). Additionally, FM150 (150 mg) could regenerate 22 L Pb(II) wastewater upon single passage through the filterable column with a flux of 20 mL/min. Thus, the present work demonstrates the promising potential of using MnO2@Fe3O4/PmPD for efficiently removing heavy metals from wastewater.

Integrating the (311) facet of MnO2 and the fuctional groups of poly(m-phenylenediamine) in core-shell MnO2@poly(m-phenylenediamine) adsorbent to remove Pb ions from water.

Exposed active facets and functional groups are critical for adsorbents obtaining excellent adsorption properties. In the present study, MnO2@PmPD with exposed active facets was successfully prepared. MnO2,which came from KMnO4 by the sacrificial reductant of PmPD, deposited on the surface of PmPD. Meanwhile, we combined experimental study and theoretical calculations to elucidate the distinct adsorption nature of MnO2@PmPD towards Pb. The surface adsorption of MnO2@PmPD toward Pb was achieved by the interaction between Pb and O atoms on the surface of MnO2. The DFT calculations revealed the facet-dependent adsorption of MnO2 toward Pb. The adsorption affinity of facets toward Pb was in the order of (311) > (111) > (400) > (440), and (311) facet was predominantly adsorption site for Pb. The analysis of partial density of state revealed the strong hybridization between the Pb-p state and O-p states of MnO2. Additionally, the pores of MnO2 provide the interstitial channels for the transportation of Pb into PmPD. The Pb entered the internal of MnO2@PmPD was bonded by the amine and newly formed carboxy groups on PmPD. This study not only develops an efficient adsorbent for heavy metals removing, but also throws light on exemplifying the interaction of Pb with MnO2 based materials.

Accuracy of MRI diagnosis of early osteonecrosis of the femoral head: a meta-analysis and systematic review.

OBJECTIVE: To evaluate the overall diagnostic value related to magnetic resonance imaging (MRI) in patients with early osteonecrosis of the femoral head. METHODS: By searching multiple databases and sources, including PubMed, Cochrane, and Embase database, by the index words updated in December 2017, qualified studies were identified and relevant literature sources were also searched. The qualified studies included prospective cohort studies and cross-sectional studies. Heterogeneity of the included studies were reviewed to select proper effect model for pooled weighted sensitivity, specificity, and diagnostic odds ratio (DOR). Summary receiver operating characteristic (SROC) analyses were performed for meniscal tears. RESULTS: Forty-three studies related to diagnostic accuracy of MRI to detect early osteonecrosis of the femoral head were involved in the meta-analysis. The global sensitivity and specificity of MRI in early osteonecrosis of the femoral head were 93.0% (95% CI 92.0-94.0%) and 91.0% (95% CI 89.0%-93.0%), respectively. The global positive likelihood ratio and global negative likelihood ratio of MRI in early osteonecrosis of the femoral head were 2.74 (95% CI 1.98-3.79) and 0.18 (95% CI 0.14-0.23), respectively. The global DOR was 27.27 (95% CI 17.02-43.67), and the area under the SROC was 93.38% (95% CI 90.87%-95.89%). CONCLUSIONS: This review provides a systematic review and meta-analysis to evaluate the diagnostic accuracy of MRI in early osteonecrosis of the femoral head. Moderate to strong evidence indicated that MRI appears to be significantly associated with higher diagnostic accuracy for early osteonecrosis of the femoral head.