Dynamic ultrasound molecular-targeted imaging of senescence in evaluation of lapatinib resistance in HER2-positive breast cancer.

BACKGROUND: Prolonged treatment of HER2+ breast cancer with lapatinib (LAP) causes cellular senescence and acquired drug resistance, which often associating with poor prognosis for patients. We aim to explore the correlation between cellular senescence and LAP resistance in HER2+ breast cancer, screen for molecular marker of reversible senescence, and construct targeted nanobubbles for ultrasound molecular imaging to dynamically evaluate LAP resistance. METHODS AND RESULTS: In this study, we established a new cellular model of reversible cellular senescence using LAP and HER2+ breast cancer cells and found that reversible senescence contributed to LAP resistance in HER2+ breast cancer. Then, we identified ecto-5'-nucleotidase (NT5E) as a marker of reversible senescence in HER2+ breast cancer. Based on this, we constructed NT5E-targeted nanobubbles (NT5E-FITC-NBs) as a new molecular imaging modality which could both target reversible senescent cells and be used for ultrasound imaging. NT5E-FITC-NBs showed excellent physical and imaging characteristics. As an ultrasound contrast agent, NT5E-FITC-NBs could accurately identify reversible senescent cells both in vitro and in vivo. CONCLUSIONS: Our data demonstrate that cellular senescence-based ultrasound-targeted imaging can identify reversible senescence and evaluate LAP resistance effectively in HER2+ breast cancer cells, which has the potential to improve cancer treatment outcomes by altering therapeutic strategies ahead of aggressive recurrences.

Aided diagnosis of thyroid nodules based on an all-optical diffraction neural network.

Background: Thyroid cancer is the most common malignancy in the endocrine system, with its early manifestation being the presence of thyroid nodules. With the advantages of convenience, noninvasiveness, and a lack of radiation, ultrasound is currently the first-line screening tool for the clinical diagnosis of thyroid nodules. The use of artificial intelligence to assist diagnosis is an emerging technology. This paper proposes the use optical neural networks for potential application in the auxiliary diagnosis of thyroid nodules. Methods: Ultrasound images obtained from January 2013 to December 2018 at the Institute and Hospital of Oncology, Tianjin Medical University, were included in a dataset. Patients who consecutively underwent thyroid ultrasound diagnosis and follow-up procedures were included. We developed an all-optical diffraction neural network to assist in the diagnosis of thyroid nodules. The network is composed of 5 diffraction layers and 1 detection plane. The input image is placed 10 mm away from the first diffraction layer. The input of the diffractive neural network is light at a wavelength of 632.8 nm, and the output of this network is determined by the amplitude and light intensity obtained from the detection region. Results: The all-optical neural network was used to assist in the diagnosis of thyroid nodules. In the classification task of benign and malignant thyroid nodules, the accuracy of classification on the test set was 97.79%, with an area under the curve value of 99.8%. In the task of detecting thyroid nodules, we first trained the model to determine whether any nodules were present and achieved an accuracy of 84.92% on the test set. Conclusions: Our study demonstrates the potential of all-optical neural networks in the field of medical image processing. The performance of the models based on optical neural networks is comparable to other widely used network models in the field of image classification.

Nomogram for preoperative estimation risk of lateral cervical lymph node metastasis in papillary thyroid carcinoma: a multicenter study.

BACKGROUND: Lateral lymph node metastasis (LLNM) is frequent in papillary thyroid carcinoma (PTC) and is associated with a poor prognosis. This study aimed to developed a clinical-ultrasound (Clin-US) nomogram to predict LLNM in patients with PTC. METHODS: In total, 2612 PTC patients from two hospitals (H1: 1732 patients in the training cohort and 578 patients in the internal testing cohort; H2: 302 patients in the external testing cohort) were retrospectively enrolled. The associations between LLNM and preoperative clinical and sonographic characteristics were evaluated by the univariable and multivariable logistic regression analysis. The Clin-US nomogram was built basing on multivariate logistic regression analysis. The predicting performance of Clin-US nomogram was evaluated by calibration, discrimination and clinical usefulness. RESULTS: The age, gender, maximum diameter of tumor (tumor size), tumor position, internal echo, microcalcification, vascularization, mulifocality, and ratio of abutment/perimeter (A/P) > 0.25 were independently associated with LLNM metastatic status. In the multivariate analysis, gender, tumor size, mulifocality, position, microcacification, and A/P > 0.25 were independent correlative factors. Comparing the Clin-US nomogram and US features, Clin-US nomogram had the highest AUC both in the training cohort and testing cohorts. The Clin­US model revealed good discrimination between PTC with LLNM and without LLNM in the training cohort (AUC = 0.813), internal testing cohort (AUC = 0.815) and external testing cohort (AUC = 0.870). CONCLUSION: Our findings suggest that the ClinUS nomogram we newly developed can effectively predict LLNM in PTC patients and could help clinicians choose appropriate surgical procedures.

An integrated nomogram combining deep learning, clinical characteristics and ultrasound features for predicting central lymph node metastasis in papillary thyroid cancer: A multicenter study.

Objective: Central lymph node metastasis (CLNM) is a predictor of poor prognosis for papillary thyroid carcinoma (PTC) patients. The options for surgeon operation or follow-up depend on the state of CLNM while accurate prediction is a challenge for radiologists. The present study aimed to develop and validate an effective preoperative nomogram combining deep learning, clinical characteristics and ultrasound features for predicting CLNM. Materials and methods: In this study, 3359 PTC patients who had undergone total thyroidectomy or thyroid lobectomy from two medical centers were enrolled. The patients were divided into three datasets for training, internal validation and external validation. We constructed an integrated nomogram combining deep learning, clinical characteristics and ultrasound features using multivariable logistic regression to predict CLNM in PTC patients. Results: Multivariate analysis indicated that the AI model-predicted value, multiple, position, microcalcification, abutment/perimeter ratio and US-reported LN status were independent risk factors predicting CLNM. The area under the curve (AUC) for the nomogram to predict CLNM was 0.812 (95% CI, 0.794-0.830) in the training cohort, 0.809 (95% CI, 0.780-0.837) in the internal validation cohort and 0.829(95%CI, 0.785-0.872) in the external validation cohort. Based on the analysis of the decision curve, our integrated nomogram was superior to other models in terms of clinical predictive ability. Conclusion: Our proposed thyroid cancer lymph node metastasis nomogram shows favorable predictive value to assist surgeons in making appropriate surgical decisions in PTC treatment.

Automatic classification of thyroid nodules in ultrasound images using a multi-task attention network guided by clinical knowledge.

Thyroid cancer has been the most prevalent cancer in the recent three decades. Ultrasonography is one of the mainly used methods for diagnosing thyroid nodules. Several computer-aided diagnostic methods were proposed to aid radiologists in analyzing ultrasound images of the thyroid gland. Most methods, however, only determine the benignity or malignancy of the thyroid nodule and do not explain the decision-making process of them, which cannot gain the trustworthiness of clinicians because they are not consistent with the physician's diagnostic process. In our work, we design a multi-task branching attention network in which each of the descriptors of the ACR TI-RADS lexicon is first classified. All respective scores are calculated to get the risk stratification of the nodule. Ultimately, based on the risk stratification, the benignity or malignancy of the nodule is determined. This work provides an automated method that incorporates the ACR TI-RADS characterization of thyroid nodules for detecting the level of risk and the benignity or malignancy of thyroid nodules. Thus the work establishes the trustworthiness of clinicians in deep learning models and improves physician efficiency and diagnostic rates to some extent compared to previous studies. For the diagnosis of thyroid nodules, evaluation indices including accuracy, sensitivity, and specificity were 93.55%, 93.86%, and 93.14%, respectively. The experiments show that our approach obtains comparable performance to most advanced methods in diagnosing ultrasound images of the thyroid nodules and is supported by explanations in clinical terms using the ACR TI-RADS lexicon.

Multitask network for thyroid nodule diagnosis based on TI-RADS.

PURPOSE: Assessment of thyroid nodules is usually relied on the experience of the radiologist and is time-consuming. Classification model of thyroid nodules cannot only reduce the burden on physicians but also provide objective recommendations. However, most classification models based on deep learning simply give a prediction result of the benignity or malignancy of nodules; thus, physicians have no way of knowing how the deep learning gets the prediction result due to the black-box nature of neural networks. In this work, we integrate the explainability directly into the outputs generated by the model through combining thyroid imaging reporting and data system (TI-RADS). The inference process of the proposed method is consistent with doctor's clinical diagnosis process; therefore, doctors can better explain the diagnosis results of the model to the patient. METHODS: A multitask network based on TI-RADS (MTN-TI-RADS) for the classification of thyroid nodules is proposed. In this network, a set of TI-RADS classifications of nodules is first obtained by multitask learning, then the TI-RADS points and the corresponding risk levels are calculated, and finally, nodules are classified as benign and malignant. The classification process through the network is consistent with the diagnostic process of physician; thus, the results of classification can be easily understood by physicians. In addition, the attention modules are introduced to the spatial and channel domains to let the network focus more on critical features. RESULTS: To verify the classification performance of our method, we compared the results obtained through our method with the results of the radiologist's evaluation. For the 781 test nodules in the internal dataset and the 886 test nodules in the external dataset, the sensitivity and specificity of MTN-TI-RADS were 0.988, 0.912 in internal dataset, 0.949, 0.930 in external dataset, versus the senior radiologist of 0.925 ( p < 0.001 $p<0.001$ ), 0.816 ( p = 0.005 $p=0.005$ ), and 0.910 ( p = 0.009 $p=0.009$ ), 0.836 ( p < 0.001 $p<0.001$ ), respectively. And the area under the receiver operating characteristic curve of MTN-TI-RADS was 0.981 in internal dataset, 0.973 in external dataset, versus the senior radiologist of 0.905, 0.923. For the internal dataset, we also computed the accuracy of the risk level (TR1 to TR5) and the mean absolute error (MAE). The accuracy of the risk level of the proposed method is 78%, and the MAE is 1.30. The MAE of the total points (0-14 points) is 1.30. CONCLUSIONS: An effective and result-interpretable end-to-end thyroid nodule classification network (MTN-TI-RADS) is proposed. MTN-TI-RADS has superior ability to classify malignant and benign thyroid nodules compared to senior radiologists. Based on MTN-TI-RADS, a classification model with strong interpretation and a high degree of physician trust is constructed. The proposed classification network is consistent with the diagnosis process of physicians, thus is more reliable and interpretable, and has great potential for clinical application.

Pharmacological inhibition of Ref-1 enhances the therapeutic sensitivity of papillary thyroid carcinoma to vemurafenib.

The use of the BRAF inhibitor vemurafenib exhibits drug resistance in the treatment of thyroid cancer (TC), and finding more effective multitarget combination therapies may be an important solution. In the present study, we found strong correlations between Ref-1 high expression and BRAF mutation, lymph node metastasis, and TNM stage. The oxidative stress environment induced by structural activation of BRAF upregulates the expression of Ref-1, which caused intrinsic resistance of PTC to vemurafenib. Combination inhibition of the Ref-1 redox function and BRAF could enhance the antitumor effects of vemurafenib, which was achieved by blocking the action of Ref-1 on BRAF proteins. Furthermore, combination treatment could cause an overload of autophagic flux via excessive AMPK protein activation, causing cell senescence and cell death in vitro. And combined administration of Ref-1 and vemurafenib in vivo suppressed PTC cell growth and metastasis in a cell-based lung metastatic tumor model and xenogeneic subcutaneous tumor model. Collectively, our study provides evidence that Ref-1 upregulation via constitutive activation of BRAF in PTC contributes to intrinsic resistance to vemurafenib. Combined treatment with a Ref-1 redox inhibitor and a BRAF inhibitor could make PTC more sensitive to vemurafenib and enhance the antitumor effects of vemurafenib by further inhibiting the MAPK pathway and activating the excessive autophagy and related senescence process.

Targeting delivery of synergistic dual drugs with elastic PEG-modified multi-functional nanoparticles for hepatocellular carcinoma therapy.

Integration of multiple advantages in one system has been leveraged to overcome multiple biological barriers in anti-tumor therapeutic strategies. In this study, multi-functional nanoparticles (MFNPs) are constructed by layer-by-layer method. MFNPs are modified with pH-responsive elastic PEG-GPC3MAb (glypican-3 monoclonal antibody), which draws back into PEG layer in blood and normal tissues; and stretches out of MFNPs surface in the acidic tumor microenvironment. It is proved that blank MFNPs have good biocompatibility by MTT and acute toxicity assays. Elastic PEG chains are able to respond sensitively in different pH environments (6.8 and 7.4), which is demonstrated by transmission electron microscope (TEM) and 1H nuclear magnetic resonance (1H NMR). In vitro experiments show that MFNPs have better specificity to Hepa 1-6 cells, can escape from lysosomes, and are able to increase the nuclear delivery of dual drugs for synergistic therapy, which are proved by flow cytometry, MTT, confocal laser scanning microscopy, and western blot studies. In vivo experiments indicate that MFNPs show extending circulation half-life in blood, promoting localization into tumor tissues, improving the therapeutic efficacy of BAL b/c nude mice with subcutaneous tumors. Overall, the results indicate that FMNPs are a potential candidate for hepatocellular carcinoma therapy.

Hepatitis B Virus X Protein Modulates Chemokine CCL15 Upregulation in Hepatocellular Carcinoma.

BACKGROUND: Hepatitis B virus X protein (HBx) is an indispensable progression factor in Hepatocellular Carcinoma (HCC). CCL15 could be a peculiar proteomic biomarker of HCC with tumorigenesis and tumor invasion. OBJECTIVE: The aim of the study was to explore the relationship between HBx and CCL15 expression in HCC. METHODS: HBV-positive HCC pathological tissue samples and corresponding adjacent non-tumor liver tissues were collected. The expression of HBx and CCL15 was analyzed by immunohistochemistry, real-time Polymerase Chain Reaction (PCR), and western blot analysis in tissues or in vitro. RESULTS: The levels of CCL15 mRNA and protein expression in HCC samples were observably higher than those of adjacent non-tumor liver tissues. The CCL15 was significantly associated with the expression of HBx in HBV-positive HCC samples. The up-regulation of HBx induced CCL15 expression in vitro. The high expression score of CCL15 was significant associated with the poor prognosis of HCC patients. CONCLUSION: The CCL15 expression was observably associated with HBx in HCC patients. The CCL15 may be considered as an indicator in the clinical management of HBV-associated HCC.

Thyroid nodules risk stratification through deep learning based on ultrasound images.

PURPOSE: Clinically, the risk stratification of thyroid nodules is usually used to formulate the next treatment plan. The American College of Radiology (ACR) thyroid imaging reporting and data system (TI-RADS) is a type of medical standard widely used in classification diagnosis. It divides the nodule's ACR TI-RADS level into five levels by quantitative scoring, from benign to high suspicion of malignancy. However, such assessment often relies on the radiologists' experience and is time consuming. So computer-aided diagnosis is necessary. But many deep learning (DL) models are difficult for doctors to understand, limiting their applicability in clinical practice. In this work, we mainly focus on how to achieve automatic thyroid nodules risk stratification based on deep integration of deep learning and clinical experience. METHODS: An automatic hierarchical method of thyroid nodules risk based on deep learning is proposed, called risk stratification network (RS-Net). It incorporates medical experience based on ACR TI-RADS. The convolutional neural network (CNN) is used to classify the five categories in ACR TI-RADS and assign their points respectively. According to the point totals, the level of risk can be obtained. In addition, a dataset involving 13 984 thyroid ultrasound images is established to develop and evaluate the proposed method. RESULTS: We have extensively compared the results of this paper with the evaluation results of sonographers. The accuracy of the risk stratification (TR1 to TR5) of the proposed method is 65%, and the mean absolute error (MAE) is 0.54. The MAE of the point totals (0 to 13 points) is 1.67. The Pearson's correlation between our method evaluation and doctor evaluation reached 0.84. For the benign and malignant classification, the performance indices accuracy, sensitivity, specificity, PPV, and NPV were 88.0%, 98.1%, 79.1%, 80.5%, and 97.9%, respectively. Our method's level of thyroid nodules risk stratification is comparable to that of a senior doctor. CONCLUSIONS: This work provides a way to automate the risk stratification of thyroid nodules. Our method can effectively avoid missed diagnosis and misdiagnosis caused by the difference of observers so as to assist doctors to improve efficiency and diagnosis rate. Compared with the previous benign and malignant classification, the proposed method incorporates clinical experience. So it can greatly increase the clinicians' trust in the DL model, thereby improving the applicability of the model in clinical practice.

Systematic profiling of alternative splicing signature reveals prognostic predictor for prostate cancer.

Alternative splicing (AS) provides the primary mechanism for producing protein diversity. There is growing evidence that AS is involved in the development and progression of cancers. The rapid accumulation of high-throughput sequencing technologies and clinical data sets offers an opportunity to systematically profile the relationship between mRNA variants and clinical outcomes. However, there is a lack of systematic analysis of AS in prostate cancer: Download RNA-seq data and clinical information from The Cancer Genome Atlas (TCGA) data portal. Evaluate RNA splicing patterns by SpliceSeq and calculate splicing percentage (PSI) values. Different expressions were identified as differently expressed AS events (DEAs) based on PSI values. Bioinformatics methods were used for further analysis of DEAs and their splicing networks. Kaplan-Meier, Cox proportional regression, and unsupervised cluster analysis were used to assess the correlation between DEAs and clinical characteristics. In total, 43 834 AS events were identified, of which 1628 AS events were differentially expressed. The parental genes of these DEAs played a significant role in the regulation of prostate cancer-related processes. In total, 226 DEAs events were found to be associated with disease-free survival. Four clusters of molecules with different survival modes were revealed by unsupervised cluster analysis of DEAs. AS events may be important determinants of prognosis and bio-modulation in prostate cancer. In this study, we established strong prognostic predictors, discovered a splicing network that may be a potential mechanism, and provided further validated therapeutic targets.