Sonodynamic and sonomechanical effect on cellular stemness and extracellular physicochemical environment to potentiate chemotherapy.

BACKGROUND: Hypoxia-activated prodrug (HAP) is a promising candidate for highly tumor-specific chemotherapy. However, the oxygenation heterogeneity and dense extracellular matrix (ECM) of tumor, as well as the potential resistance to chemotherapy, have severely impeded the resulting overall efficacy of HAP. RESULTS: A HAP potentiating strategy is proposed based on ultrasound responsive nanodroplets (PTP@PLGA), which is composed of protoporphyrin (PpIX), perfluoropropane (PFP) and a typical HAP, tirapazamine (TPZ). The intense vaporization of PFP upon ultrasound irradiation can magnify the sonomechanical effect, which loosens the ECM to promote the penetration of TPZ into the deep hypoxic region. Meanwhile, the PpIX enabled sonodynamic effect can further reduce the oxygen level, thus activating the TPZ in the relatively normoxic region as well. Surprisingly, abovementioned ultrasound effect also results in the downregulation of the stemness of cancer cells, which is highly associated with drug-refractoriness. CONCLUSIONS: This work manifests an ideal example of ultrasound-based nanotechnology for potentiating HAP and also reveals the potential acoustic effect of intervening cancer stem-like cells.

Axillary lymph node metastasis in pure mucinous carcinoma of breast: clinicopathologic and ultrasonographic features.

BACKGROUND: The purpose of this research is to study the sonographic and clinicopathologic characteristics that associate with axillary lymph node metastasis (ALNM) for pure mucinous carcinoma of breast (PMBC). METHODS: A total of 176 patients diagnosed as PMBC after surgery were included. According to the status of axillary lymph nodes, all patients were classified into ALNM group (n = 15) and non-ALNM group (n = 161). The clinical factors (patient age, tumor size, location), molecular biomarkers (ER, PR, HER2 and Ki-67) and sonographic features (shape, orientation, margin, echo pattern, posterior acoustic pattern and vascularity) between two groups were analyzed to unclose the clinicopathologic and ultrasonographic characteristics in PMBC with ALNM. RESULTS: The incidence of axillary lymph node metastasis was 8.5% in this study. Tumors located in the outer side of the breast (upper outer quadrant and lower outer quadrant) were more likely to have lymphatic metastasis, and the difference between the two group was significantly (86.7% vs. 60.3%, P = 0.043). ALNM not associated with age (P = 0.437). Although tumor size not associated with ALNM(P = 0.418), the tumor size in ALNM group (32.3 ± 32.7 mm) was bigger than non-ALNM group (25.2 ± 12.8 mm). All the tumors expressed progesterone receptor (PR) positively, and 90% of all expressed estrogen receptor (ER) positively, human epidermal growth factor receptor 2 (HER2) were positive in two cases of non-ALNM group. Ki-67 high expression was observed in 36 tumors in our study (20.5%), and it was higher in ALNM group than non-ALNM group (33.3% vs. 19.3%), but the difference wasn't significantly (P = 0.338). CONCLUSIONS: Tumor location is a significant factor for ALNM in PMBC. Outer side location is more easily for ALNM. With the bigger size and/or Ki-67 higher expression status, the lymphatic metastasis seems more likely to present.

Standardization of ultrasound images across various centers: M2O-DiffGAN bridging the gaps among unpaired multi-domain ultrasound images.

Domain shift problem is commonplace for ultrasound image analysis due to difference imaging setting and diverse medical centers, which lead to poor generalizability of deep learning-based methods. Multi-Source Domain Transformation (MSDT) provides a promising way to tackle the performance degeneration caused by the domain shift, which is more practical and challenging compared to conventional single-source transformation tasks. An effective unsupervised domain combination strategy is highly required to handle multiple domains without annotations. Fidelity and quality of generated images are also important to ensure the accuracy of computer-aided diagnosis. However, existing MSDT approaches underperform in above two areas. In this paper, an efficient domain transformation model named M2O-DiffGAN is introduced to achieve a unified mapping from multiple unlabeled source domains to the target domain. A cycle-consistent "many-to-one" adversarial learning architecture is introduced to model various unlabeled domains jointly. A condition adversarial diffusion process is employed to generate images with high-fidelity, combining an adversarial projector to capture reverse transition probabilities over large step sizes for accelerating sampling. Considering the limited perceptual information of ultrasound images, an ultrasound-specific content loss helps to capture more perceptual features for synthesizing high-quality ultrasound images. Massive comparisons on six clinical datasets covering thyroid, carotid and breast demonstrate the superiority of the M2O-DiffGAN in the performance of bridging the domain gaps and enlarging the generalization of downstream analysis methods compared to state-of-the-art algorithms. It improves the mean MI, Bhattacharyya Coefficient, dice and IoU assessments by 0.390, 0.120, 0.245 and 0.250, presenting promising clinical applications.

Revealing nitrogenous VX metabolites and the whole-molecule VX metabolism in the urine of guinea pigs.

VX, a well-known organophosphorus nerve agent (OPNA), poses a significant threat to public safety if employed by terrorists. Obtaining complete metabolites is critical to unequivocally confirm its alleged use/exposure and elucidate its whole-molecular metabolism. However, the nitrogenous VX metabolites containing 2-diisopropylaminoethyl moiety from urinary excretion remain unknown. Therefore, this study applied a newly developed untargeted workflow platform to discover and identify them using VX-exposed guinea pigs as animal models. 2-(N,N-diisopropylamino)ethanesulfonic acid (DiPSA) was revealed as a novel nitrogenous VX metabolite in urine, and 2-(Diisopropylaminoethyl) methyl sulfide (DAEMS) was confirmed as another in plasma, indicating that VX metabolism differed between urine and plasma. It is the first report of a nitrogenous VX metabolite in urine and a complete elucidation of the VX metabolic pathway. DiPSA was evaluated as an excellent VX exposure biomarker. The whole-molecule VX metabolism in urine was characterized entirely for the first time via the simultaneous quantification of DiPSA and two known P-based biomarkers. About 52.1% and 32.4% of VX were excreted in urine as P-based and nitrogenous biomarkers within 24 h. These findings provide valuable insights into the unambiguous detection of OPNA exposure/intoxication and human and environmental exposure risk assessment.

Deep learning based ultrasound analysis facilitates precise distinction between parotid pleomorphic adenoma and Warthin tumor.

Background: Pleomorphic adenoma (PA), often with the benign-like imaging appearances similar to Warthin tumor (WT), however, is a potentially malignant tumor with a high recurrence rate. It is worse that pathological fine-needle aspiration cytology (FNAC) is difficult to distinguish PA and WT for inexperienced pathologists. This study employed deep learning (DL) technology, which effectively utilized ultrasound images, to provide a reliable approach for discriminating PA from WT. Methods: 488 surgically confirmed patients, including 266 with PA and 222 with WT, were enrolled in this study. Two experienced ultrasound physicians independently evaluated all images to differentiate between PA and WT. The diagnostic performance of preoperative FNAC was also evaluated. During the DL study, all ultrasound images were randomly divided into training (70%), validation (20%), and test (10%) sets. Furthermore, ultrasound images that could not be diagnosed by FNAC were also randomly allocated to training (60%), validation (20%), and test (20%) sets. Five DL models were developed to classify ultrasound images as PA or WT. The robustness of these models was assessed using five-fold cross-validation. The Gradient-weighted Class Activation Mapping (Grad-CAM) technique was employed to visualize the region of interest in the DL models. Results: In Grad-CAM analysis, the DL models accurately identified the mass as the region of interest. The area under the receiver operating characteristic curve (AUROC) of the two ultrasound physicians were 0.351 and 0.598, and FNAC achieved an AUROC of only 0.721. Meanwhile, for DL models, the AUROC value for discriminating between PA and WT in the test set was from 0.828 to 0.908. ResNet50 demonstrated the optimal performance with an AUROC of 0.908, an accuracy of 0.833, a sensitivity of 0.736, and a specificity of 0.904. In the test set of cases that FNAC failed to provide a diagnosis, DenseNet121 demonstrated the optimal performance with an AUROC of 0.897, an accuracy of 0.806, a sensitivity of 0.789, and a specificity of 0.824. Conclusion: For the discrimination of PA and WT, DL models are superior to ultrasound and FNAC, thereby facilitating surgeons in making informed decisions regarding the most appropriate surgical approach.

Quantitative Analysis of Shear Wave Elastography and US-Guided Diffuse Optical Tomography for Evaluating Biological Characteristics of Breast Cancer.

RATIONALE AND OBJECTIVES: Shear Wave Elastography (SWE) and Ultrasound-guided Diffuse Optical Tomography (US-guided DOT) demonstrate promise in distinguishing between benign and malignant breast lesions. This study aims to assess the feasibility and correlation of SWE and US-guided DOT in evaluating the biological characteristics of breast cancer. MATERIALS AND METHODS: A cohort of 235 breast cancer patients with 238 lesions, scheduled for surgery within one to three days, underwent B-mode ultrasound (US), US-guided DOT, and SWE. Parameters such as Total Hemoglobin Concentration (THC), Maximal Elasticity (Emax), Mean Elasticity (Emean), Standard Deviation of Elasticity (Esd), and Area Ratio were measured. Correlation with post-surgical pathology reports was examined to explore associations between THC, SWE Parameters, and pathology characteristics. RESULTS: Lesions in patient groups with ER-, PR-, HER2 + , high Ki67, LVI+ , and ALN+ exhibited higher THC, Emax, and Esd compared to groups with ER+ , PR+ , HER2-, low Ki67, LVI-, and ALN-. The increase was seen in all grades of IDC-I to -III. THC significantly correlated with Smax (r = 0.340, P < 0.001), Emax (r = 0.339, P < 0.001), Emean (r = 0.201, P = 0.003), and Esd (r = 0.313, P < 0.001). CONCLUSION: US-guided DOT and SWE prove valuable for the quantitative assessment of breast cancer's biological characteristics, with THC positively correlated with Emax, Emean, and Esd.

Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers With Partially Annotated Ultrasound Images.

Deep learning (DL) has proven highly effective for ultrasound-based computer-aided diagnosis (CAD) of breast cancers. In an automatic CAD system, lesion detection is critical for the following diagnosis. However, existing DL-based methods generally require voluminous manually-annotated region of interest (ROI) labels and class labels to train both the lesion detection and diagnosis models. In clinical practice, the ROI labels, i.e. ground truths, may not always be optimal for the classification task due to individual experience of sonologists, resulting in the issue of coarse annotation to limit the diagnosis performance of a CAD model. To address this issue, a novel Two-Stage Detection and Diagnosis Network (TSDDNet) is proposed based on weakly supervised learning to improve diagnostic accuracy of the ultrasound-based CAD for breast cancers. In particular, all the initial ROI-level labels are considered as coarse annotations before model training. In the first training stage, a candidate selection mechanism is then designed to refine manual ROIs in the fully annotated images and generate accurate pseudo-ROIs for the partially annotated images under the guidance of class labels. The training set is updated with more accurate ROI labels for the second training stage. A fusion network is developed to integrate detection network and classification network into a unified end-to-end framework as the final CAD model in the second training stage. A self-distillation strategy is designed on this model for joint optimization to further improves its diagnosis performance. The proposed TSDDNet is evaluated on three B-mode ultrasound datasets, and the experimental results indicate that it achieves the best performance on both lesion detection and diagnosis tasks, suggesting promising application potential.

Ultrasound-Based Nomogram for Predicting the Aggressiveness of Papillary Thyroid Carcinoma in Adolescents and Young Adults.

RATIONALE AND OBJECTIVES: Assessing the aggressiveness of papillary thyroid carcinoma (PTC) preoperatively might play an important role in guiding therapeutic strategy. This study aimed to develop and validate a nomogram that integrated ultrasound (US) features with clinical characteristics to preoperatively predict aggressiveness in adolescents and young adults with PTC. MATERIALS AND METHODS: In this retrospective study, a total of 2373 patients were enrolled and randomly divided into two groups with 1000 bootstrap sampling. The multivariable logistic regression (LR) analysis or least absolute shrinkage and selection operator LASSO regression was applied to select predictive US and clinical characteristics in the training cohort. By incorporating most powerful predictors, two predictive models presented as nomograms were developed, and their performance was assessed with respect to discrimination, calibration, and clinical usefulness. RESULTS: The LR_model that incorporated gender, tumor size, multifocality, US-reported cervical lymph nodes (CLN) status, and calcification demonstrated good discrimination and calibration with an area under curve (AUC), sensitivity and specificity of 0.802 (0.781-0.821), 65.58% (62.61%-68.55%), and 82.31% (79.33%-85.46%), respectively, in the training cohort; and 0.768 (0.736-0.797), 60.04% (55.62%-64.46%), and 83.62% (78.84%-87.71%), respectively, in the validation cohort. Gender, tumor size, orientation, calcification, and US-reported CLN status were combined to build LASSO_model. Compared with LR_model, the LASSO_model yielded a comparable diagnostic performance in both cohorts, the AUC, sensitivity, and specificity were 0.800 (0.780-0.820), 65.29% (62.26%-68.21%), and 81.93% (78.77%-84.91%), respectively, in the training cohort; and 0.763 (0.731-0.792), 59.43% (55.12%-63.93%), and 84.98% (80.89%-89.08%), respectively, in the validation cohort. The decision curve analysis indicated that using the two nomograms to predict the aggressiveness of PTC provided a greater benefit than either the treat-all or treat-none strategy. CONCLUSION: Through these two easy-to-use nomograms, the possibility of the aggressiveness of PTC in adolescents and young adults can be objectively quantified preoperatively. The two nomograms may serve as a useful clinical tool to provide valuable information for clinical decision-making.

IMAGGS: a radiogenomic framework for identifying multi-way associations in breast cancer subtypes.

Investigating correlations between radiomic and genomic profiling in breast cancer (BC) molecular subtypes is crucial for understanding disease mechanisms and providing personalized treatment. We present a well-designed radiogenomic framework image-gene-gene set (IMAGGS), which detects multi-way associations in BC subtypes by integrating radiomic and genomic features. Our dataset consists of 721 patients, each of whom has 12 ultrasound (US) images captured from different angles and gene mutation data. To better characterize tumor traits, 12 multi-angle US images are fused using two distinct strategies. Then, we analyze complex many-to-many associations between phenotypic and genotypic features using a machine learning algorithm, deviating from the prevalent one-to-one relationship pattern observed in previous studies. Key radiomic and genomic features are screened using these associations. In addition, gene set enrichment analysis is performed to investigate the joint effects of gene sets and delve deeper into the biological functions of BC subtypes. We further validate the feasibility of IMAGGS in a glioblastoma multiforme dataset to demonstrate the scalability of IMAGGS across different modalities and diseases. Taken together, IMAGGS provides a comprehensive characterization for diseases by associating imaging, genes, and gene sets, paving the way for biological interpretation of radiomics and development of targeted therapy.

Discriminative detection of soman or VX exposure using europium chelated microparticle-based immunofluorescence microfluidic chip.

The retrospective detection of organophosphorus nerve agents (OPNAs) exposure has been achieved by the off-site analysis of OPNA-human serum albumin (HSA) adducts using mass spectrometry-based detection approaches. However, few specific methods are accessible for on-site detection. To address this, a novel immunofluorescence microfluidic chip (IFMC) testing system combining europium chelated microparticle (EuCM) with self-driven microfluidic chip assay has been established to unambiguously determine soman (GD) and VX exposure within 20 min, respectively. The detection system was based on the principle of indirect competitive enzyme-linked immunosorbent assay. The specific monoclonal antibodies that respectively recognized the phosphonylated tyrosine 411 of GD-HSA and VX-HSA adducts were labeled by EuCM to capture corresponding adducts in the exposed samples. The phosphonylated peptides in the test line and goat-anti-rabbit antibody in the control line were utilized to bind the EuCM-labeled antibodies for signal exhibition. The developed IFMC chip could discriminatively detect exposed HSA adducts with high specificity, demonstrating a low limit of detection at exposure concentrations of 0.5 × 10-6 mol/L VX and 1.0 × 10-6 mol/L GD. The exposed serum samples can be qualitatively detected following an additional pretreatment procedure. This is a novel rapid detection system capable of discriminating GD and VX exposure, providing an alternative method for rapidly identifying OPNA exposure.

Application of ultrasound-based radiomics models of breast masses to predict invasive components of encapsulated papillary carcinoma.

Background: Axillary lymph node (ALN) metastasis is seen in encapsulated papillary carcinoma (EPC), mostly with an invasive component (INV). Radiomics can offer more information beyond subjective grayscale and color Doppler ultrasound (US) image interpretation. This study aimed to develop radiomics models for predicting an INV of EPC in the breast based on US images. Methods: This study retrospectively enrolled 105 patients (107 masses) with a pathological diagnosis of EPC from January 2016 to April 2021, and all masses had preoperative US images. Of the 107 masses, 64 were randomized to a training set and 43 to a test set. US and clinical features were analyzed to identify features associated with INVs. Then, based on the manually segmented US images to obtain radiomics features, the models to predict INVs were built with 5 ensemble machine learning classifiers. We estimated the performance of the predictive models using accuracy, the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity. Results: The mean age was 63.71 years (range, 31 to 85 years); the mean size of tumors was 23.40 mm (range, 9 to 120 mm). Among all clinical and US features, only shape was statistically different between EPC with INVs and those without (P<0.05). In this study, the models based on Random Under Sampling (RUS) Boost, Random Forest, XGBoost, AdaBoost, and Easy Ensemble methods had good performance, among which RUS Boost had the best performance with an AUC of 0.875 [95% confidence interval (CI): 0.750-0.974] in the test set. Conclusions: Radiomics prediction models were effective in predicting the INV of EPC, whereas clinical and US features demonstrated relatively decreased predictive utility.

A protein standard absolute quantification strategy for enhanced absolute quantification of ricin in complex matrices using in vitro synthesized mutant holoprotein as internal standard by ultra-high-performance liquid chromatography-tandem mass spectrometry.

Ricin is a highly toxic protein toxin that poses a potential bioterrorism threat due to its potency and widespread availability. However, the accurate quantification of ricin through absolute mass spectrometry (MS) using a protein standard absolute quantification (PSAQ) strategy is not widely practiced. This limitation primarily arises from the presence of interchain disulfide bonds, which hinder the production of full-length isotope-labeled ricin as an internal standard (IS) in vitro. In this study, we have developed a novel approach for the absolute quantification of ricin in complex matrices using recombinant single-chain and full-length mutant ricin as the protein IS, instead of isotope-labeled ricin, in conjunction with ultra-high-performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS). The amino acid sequence of the ricin mutant internal standard (RMIS) was designed by introducing site mutations in specific amino acids of trypsin/Glu-C enzymatic digestion marker peptides of ricin. To simplify protein expression, the A-chain and B-chain of RMIS were directly linked to replace the original interchain disulfide bonds. The RMISs were synthesized using an Escherichia coli expression system. An appropriate RMIS was selected as the protein IS based on consistent digestion efficiency, UHPLC-MS/MS behavior, antibody recognition function, lectin activity, and proper depurination activity with intact ricin. The RMIS was utilized to simultaneously quantify A- and B-chain marker peptides of ricin through UHPLC-MS/MS. This method was thoroughly validated using a milk matrix. By employing internal protein standards, this quantitative strategy overcomes the challenges posed by variations in extraction recoveries, matrix effects, and digestion efficiency encountered when working with different matrices. Consequently, calibration curves generated from milk matrix-spiked samples were utilized to accurately and precisely quantify ricin in river water and plasma samples. Moreover, the established method successfully detected intact ricin in samples obtained from the sixth Organization for the Prohibition of Chemical Weapons (OPCW) exercise on biotoxin analysis. This study presents a novel PSAQ strategy that enables the accurate quantification of ricin in complex matrices.

Artificial intelligence in breast imaging: potentials and challenges.

Breast cancer, which is the most common type of malignant tumor among humans, is a leading cause of death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative chemotherapy, targeted therapy, endocrine therapy, and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced the threat of breast cancer in females. Furthermore, early imaging screening plays an important role in reducing the treatment cycle and improving breast cancer prognosis. The recent innovative revolution in artificial intelligence (AI) has aided radiologists in the early and accurate diagnosis of breast cancer. In this review, we introduce the necessity of incorporating AI into breast imaging and the applications of AI in mammography, ultrasonography, magnetic resonance imaging, and positron emission tomography/computed tomography based on published articles since 1994. Moreover, the challenges of AI in breast imaging are discussed.

Unraveling the Pivotal Network of Ultrasound and Somatic Mutations in Triple-Negative and Non-Triple-Negative Breast Cancer.

Purpose: The emergence of genomic targeted therapy has improved the prospects of treatment for breast cancer (BC). However, genetic testing relies on invasive and sophisticated procedures. Patients and Methods: Here, we performed ultrasound (US) and target sequencing to unravel the possible association between US radiomics features and somatic mutations in TNBC (n=83) and non-TNBC (n=83) patients. Least absolute shrinkage and selection operator (Lasso) were utilized to perform radiomic feature selection. The Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis was utilized to identify the signaling pathways associated with radiomic features. Results: Thirteen differently represented radiomic features were identified in TNBC and non-TNBC, including tumor shape, textual, and intensity features. The US radiomic-gene pairs were differently exhibited between TNBC and non-TNBC. Further investigation with KEGG verified radiomic-pathway (ie, JAK-STAT, MAPK, Ras, Wnt, microRNAs in cancer, PI3K-Akt) associations in TNBC and non-TNBC. Conclusion: The pivotal network provided the connections of US radiogenomic signature and target sequencing for non-invasive genetic assessment of precise BC treatment.

Differentiation between Phyllodes Tumors and Fibroadenomas through Breast Ultrasound: Deep-Learning Model Outperforms Ultrasound Physicians.

The preoperative differentiation of breast phyllodes tumors (PTs) from fibroadenomas (FAs) plays a critical role in identifying an appropriate surgical treatment. Although several imaging modalities are available, reliable differentiation between PT and FA remains a great challenge for radiologists in clinical work. Artificial intelligence (AI)-assisted diagnosis has shown promise in distinguishing PT from FA. However, a very small sample size was adopted in previous studies. In this work, we retrospectively enrolled 656 breast tumors (372 FAs and 284 PTs) with 1945 ultrasound images in total. Two experienced ultrasound physicians independently evaluated the ultrasound images. Meanwhile, three deep-learning models (i.e., ResNet, VGG, and GoogLeNet) were applied to classify FAs and PTs. The robustness of the models was evaluated by fivefold cross validation. The performance of each model was assessed by using the receiver operating characteristic (ROC) curve. The area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were also calculated. Among the three models, the ResNet model yielded the highest AUC value, of 0.91, with an accuracy value of 95.3%, a sensitivity value of 96.2%, and a specificity value of 94.7% in the testing data set. In contrast, the two physicians yielded an average AUC value of 0.69, an accuracy value of 70.7%, a sensitivity value of 54.4%, and a specificity value of 53.2%. Our findings indicate that the diagnostic performance of deep learning is better than that of physicians in the distinction of PTs from FAs. This further suggests that AI is a valuable tool for aiding clinical diagnosis, thereby advancing precision therapy.

HAL-IA: A Hybrid Active Learning framework using Interactive Annotation for medical image segmentation.

High performance of deep learning models on medical image segmentation greatly relies on large amount of pixel-wise annotated data, yet annotations are costly to collect. How to obtain high accuracy segmentation labels of medical images with limited cost (e.g. time) becomes an urgent problem. Active learning can reduce the annotation cost of image segmentation, but it faces three challenges: the cold start problem, an effective sample selection strategy for segmentation task and the burden of manual annotation. In this work, we propose a Hybrid Active Learning framework using Interactive Annotation (HAL-IA) for medical image segmentation, which reduces the annotation cost both in decreasing the amount of the annotated images and simplifying the annotation process. Specifically, we propose a novel hybrid sample selection strategy to select the most valuable samples for segmentation model performance improvement. This strategy combines pixel entropy, regional consistency and image diversity to ensure that the selected samples have high uncertainty and diversity. In addition, we propose a warm-start initialization strategy to build the initial annotated dataset to avoid the cold-start problem. To simplify the manual annotation process, we propose an interactive annotation module with suggested superpixels to obtain pixel-wise label with several clicks. We validate our proposed framework with extensive segmentation experiments on four medical image datasets. Experimental results showed that the proposed framework achieves high accuracy pixel-wise annotations and models with less labeled data and fewer interactions, outperforming other state-of-the-art methods. Our method can help physicians efficiently obtain accurate medical image segmentation results for clinical analysis and diagnosis.

Deep learning radiomics model based on breast ultrasound video to predict HER2 expression status.

Purpose: The detection of human epidermal growth factor receptor 2 (HER2) expression status is essential to determining the chemotherapy regimen for breast cancer patients and to improving their prognosis. We developed a deep learning radiomics (DLR) model combining time-frequency domain features of ultrasound (US) video of breast lesions with clinical parameters for predicting HER2 expression status. Patients and Methods: Data for this research was obtained from 807 breast cancer patients who visited from February 2019 to July 2020. Ultimately, 445 patients were included in the study. Pre-operative breast ultrasound examination videos were collected and split into a training set and a test set. Building a training set of DLR models combining time-frequency domain features and clinical features of ultrasound video of breast lesions based on the training set data to predict HER2 expression status. Test the performance of the model using test set data. The final models integrated with different classifiers are compared, and the best performing model is finally selected. Results: The best diagnostic performance in predicting HER2 expression status is provided by an Extreme Gradient Boosting (XGBoost)-based time-frequency domain feature classifier combined with a logistic regression (LR)-based clinical parameter classifier of clinical parameters combined DLR, particularly with a high specificity of 0.917. The area under the receiver operating characteristic curve (AUC) for the test cohort was 0.810. Conclusion: Our study provides a non-invasive imaging biomarker to predict HER2 expression status in breast cancer patients.

Generic detection of organophosphorus nerve agent adducts to butyrylcholinesterase in plasma using liquid chromatography-tandem mass spectrometry combined with an improved procainamide-gel separation and pepsin digestion method.

Organophosphorus nerve agent (OPNA) adducts to butyrylcholinesterase (BChE) can be applied to confirm exposure in humans. A sensitive method for generic detection of G- and V-series OPNA adducts to BChE in plasma was developed by combining an improved procainamide-gel separation (PGS) and pepsin digestion protocol with ultra-high-pressure liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS). Residual matrix interferences from prior PGS purification of OPNA-BChE adducts from plasma were found to be a critical cause of significantly reduced UHPLC-MS/MS detection sensitivity. In our developed on-column PGS approach, the matrix interference was successfully removed by adding an appropriate concentration of NaCl to the washing buffer, and it could capture ≥92.5% of the BChE in plasma. The lower pH value and the longer digestion time in all previous pepsin digestion methods were found to be a key accelerated aging factor of several adducts such as tabun (GA)-, cyclohexylsarin (GF)-, and soman (GD)-BChE nonapeptide adducts, making them difficult to detect. The aging event of several OPNA-BChE nonapeptide adducts was so successfully addressed that the formic acid level in enzymatic buffer and digestion time were lowered to 0.05% (pH 2.67) and 0.5 h, respectively, and the post-digestion reaction was immediately terminated. The improved condition parameters were optimal for pepsin digestion of all types of OPNA-BChE adducts into their individual unaged nonapeptide adducts with the highest yields, expanding the applicability of the method. The method had a nearly one-fold decrease in sample preparation time through the reduction of digestion time and removal of ultrafiltration procedure after digestion. The limit of identification (LOI) were determined respectively as 0.13 ng mL-1, 0.28 ng mL-1, 0.50 ng mL-1, 0.41 ng mL-1 and 0.91 ng mL-1 for VX-, sarin (GB)-, GA-, GF-, and GD-exposed human plasma, being low exposure value compared to previously documented approaches. The approach was utilized to fully characterize the adducted (aged and unaged) BChE levels of five OPNAs in a series of their individual exposed concentration (1.00-400 nM) of plasma sample, and successfully detect OPNA exposure from all unknown plasma samples from OPCW's second and third biomedical proficiency tests. The OPNA-BChE adducts, their aged adducts, and unadducted BChE from OPNA-exposed plasma can simultaneously be measured using the method. The study provides a recommended diagnostic tool for generic verification of any OPNA exposure with high confidence by detecting its corresponding BChE adduct.

Virtual elastography ultrasound via generative adversarial network for breast cancer diagnosis.

Elastography ultrasound (EUS) imaging is a vital ultrasound imaging modality. The current use of EUS faces many challenges, such as vulnerability to subjective manipulation, echo signal attenuation, and unknown risks of elastic pressure in certain delicate tissues. The hardware requirement of EUS also hinders the trend of miniaturization of ultrasound equipment. Here we show a cost-efficient solution by designing a deep neural network to synthesize virtual EUS (V-EUS) from conventional B-mode images. A total of 4580 breast tumor cases were collected from 15 medical centers, including a main cohort with 2501 cases for model establishment, an external dataset with 1730 cases and a portable dataset with 349 cases for testing. In the task of differentiating benign and malignant breast tumors, there is no significant difference between V-EUS and real EUS on high-end ultrasound, while the diagnostic performance of pocket-sized ultrasound can be improved by about 5% after V-EUS is equipped.

An omics-to-omics joint knowledge association subtensor model for radiogenomics cross-modal modules from genomics and ultrasonic images of breast cancers.

The radiogenomics analysis can provide the connections between genomics and radiomics, which can infer the genomic features of tumors from their radiogenomic associations through the low-cost and non-invasiveness screening ultrasonic images. Although there are a number of pioneer approaches exploring the connections between genomic aberrations and ultrasonic features, these studies mainly focus on the relationship between ultrasonic features and only the most popular cancer genes, confronting two difficulties: missing many-to-many relationships as omics-to-omics view, and confounding group-specific associations with whole sample associations. To overcome the difficulty of omics-to-omics view and the issue of tumor heterogeneity, we propose an omics-to-omics joint knowledge association subtensor model. Specifically, the subtensor factorization framework can successfully discover the joint cross-modal module via an omics-to-omics view, while the sparse weight sample indication strategy can mine sample subgroups from the multi-omic data with tumor heterogeneity. The experimental evaluation result shows the jointness of the discovered modules across omics, their association with tumorigenesis contribution, and their relation for cancer related functions. In summary, our proposed omics-to-omics joint knowledge association subtensor model can serve as an efficient tool for radiogenomic knowledge associations, promoting the cross-modal knowledge graph construction of in explainable artificial intelligence cancer diagnosis.