Abstract Non-invasive assessment of the risk lymph node metastasis (LNM) in patients with papillary thyroid carcinoma (PTC) is great value for treatment option selection. The purpose this paper to develop a transfer learning radiomics (TLR) model preoperative prediction LNM PTC multicenter, cross-machine, multi-operator scenario. Here we report TLR produces stable prediction. In experiments cross-validation and independent testing main cohort according diagnostic time, machine, operator,...

Due to the low contrast, blurry boundaries, and large amount of shadows in breast ultrasound (BUS) images, automatic tumor segmentation remains a challenging task. Deep learning provides solution this problem, since it can effectively extract representative features from lesions background BUS images.A novel method is proposed by combining dilated fully convolutional network (DFCN) with phase-based active contour (PBAC) model. The DFCN an improved neural convolution deeper layers, fewer...

Multicomponent deoxyribozymes (MNAzymes) have great potential in gene therapy, but their ability to recognize disease tissue and further achieve synergistic regulation has rarely been studied. Herein, Arginylglycylaspartic acid (RGD)-modified Distearyl acylphosphatidyl ethanolamine (DSPE)-polyethylene glycol (PEG) (DSPE-PEG-RGD) micelle is prepared with a DSPE hydrophobic core load the photothermal therapy (PTT) dye IR780 calcium efflux pump inhibitor curcumin. Then, MNAzyme distributed into...

Background: Papillary thyroid carcinoma is a type of indolent tumor with dramatically increasing incidence rate and stably high survival rate. Reducing the overdiagnosis overtreatment papillary clinically emergent important. A radiomics model proposed in this article to predict lymph node metastasis, most important risk factor carcinoma, based on noninvasive routine preoperative ultrasound images. Methods: Four hundred fifty manually segmented images patients status obtained from pathology...

Accurate preoperative identification of lateral cervical lymph node metastasis (LNM) is important for decision-making and clinical management patients with papillary thyroid carcinoma (PTC). The aim this study was to develop an ultrasound (US)-based radiomic nomogram preoperatively predict the LNM in PTC patients.In retrospective study, a total 886 were enrolled randomly divided into 2 groups. Radiomic features extracted from US images. A signature constructed using least absolute shrinkage...

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 the following diagnosis. However, existing DL-based methods generally require voluminous manually-annotated region interest (ROI) labels and class to train both models. clinical practice, ROI labels, i.e. ground truths, may not always be optimal classification task due individual experience sonologists, resulting in...

Purpose: This study aimed to establish and validate an ultrasound radiomics nomogram for the preoperative prediction of central lymph node (LN) metastasis in patients with papillary thyroid carcinoma (PTC). Patients Methods: The model was developed 609 clinicopathologically confirmed unifocal PTC who received ultrasonography between Jan 2018 June 2018. Radiomic features were extracted after PTC. Lasso regression used data dimensionality reduction, feature selection, signature building....

Segmentation of the breast ultrasound (BUS) image is an important step for subsequent assessment and diagnosis lesions. Recently, Deep-learning-based methods have achieved satisfactory performance in many computer vision tasks, especially medical segmentation. Nevertheless, those always require a large number pixel-wise labeled data that expensive practices. In this study, we propose new segmentation method by dense prediction local fusion superpixels anatomy with scarce data. First,...

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and ultrasound (US), which are two common modalities for clinical breast tumor diagnosis besides Mammograms, can provide different complementary information the same regions. Although many machine learning methods have been proposed classification based on either single modality, it remains unclear how to further boost performance by utilizing paired multi-modality with dimensions. In this paper, we propose MRI-US network...

In clinical practice, we noticed that triple negative breast cancer (TNBC) patients had higher shear-wave elasticity (SWE) stiffness than non-TNBC and a α-SMA expression was found in TNBC tissues the tissues. Moreover, SWE also shows clear correlation to neoadjuvant response efficiency. To elaborate this phenomenon, cell membrane-modified polylactide acid-glycolic acid (PLGA) nanoparticle fabricated specifically deliver artesunate regulate through inhibiting CAFs functional status. As tested...

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 improving their prognosis. We developed a deep learning radiomics (DLR) model combining time-frequency domain features ultrasound (US) video lesions with clinical parameters predicting HER2 status. Patients Methods Data this research was obtained from 807 who visited February 2019 July 2020. Ultimately, 445 were...

An accurate preoperative assessment of cervical lymph node metastasis (LNM) is important for choosing an optimal therapeutic strategy papillary thyroid carcinoma (PTC) patients. This study aimed to develop and validate two ultrasound (US) nomograms the individual prediction central lateral compartment LNM in patients with PTC.A total 720 PTC from 3 institutions were enrolled this study. They categorized into a primary cohort, internal validation, external validation cohorts. Radiomics...

Unsupervised anomaly detection (UAD) from images strives to model normal data distributions, creating discriminative representations distinguish and precisely localize anomalies. Despite recent advancements in the efficient unified one-for-all scheme, challenges persist accurately segmenting anomalies for further monitoring. Moreover, this problem is obscured by widely-used AUROC metric under imbalanced UAD settings. This motivates us emphasize significance of precise segmentation pixels...

Triple-negative breast cancer (TNBC) is highly malignant, with rapid tumor growth and metastasis. Due to ER-, PR- HER2-of TNBC, FGFR pathway play a pivotal role in the progression of TNBC. Its ligand FGFs mostly released from extracellular matrix by fibroblast factor binding protein 1 (FGFBP1). However, little known about FGFBP1 In this study, we found that overexpression significantly promoted proliferation, migration invasion TNBC cells vitro vivo vice versa. Mechanistically, upregulated...

In the clinical setting, efficacy of single-agent immune checkpoint inhibitors (ICIs) in triple-negative breast cancer (TNBC) remains suboptimal. Therefore, there is a pressing need to develop predictive biomarkers identify non-responders. Considering that cancer-associated fibroblasts (CAFs) represent an integral component tumor microenvironment affects stiffness solid tumors on shear-wave elastography (SWE) imaging, wound healing CAFs (WH CAFs) were identified highly heterogeneous TNBC....

Convolutional neural networks (CNNs) have been successfully applied in the computer-aided ultrasound diagnosis for breast cancer. Up to now, several CNN-based methods proposed. However, most of them consider tumor localization and classification as two separate steps, rather than performing simultaneously. Besides, they suffer from limited information B-mode (BUS) images. In this study, we develop a novel network ResNet-GAP that incorporates both into unified procedure. To enhance...