IL-24 improves efficacy of CAR-T cell therapy by targeting stemness of tumor cells.

BACKGROUND: Cancer stem cells (CSCs) induce therapeutic resistance and may be an important barrier to cancer immunotherapy. Chimeric antigen receptor T (CAR-T) cell therapy has demonstrated remarkable efficacy in clinical settings. However, CAR-T cell therapy fails in a large proportion of patients, especially in those with solid tumors. It is unclear how CSCs mediate resistance to CAR-T cells, and whether CAR-T cells can more effectively eradicate CSCs. METHODS: In this study, the effect of CSCs on CAR-T cell therapy was determined using in vitro and in vivo assays. Subsequently, Interleukin-24 (IL-24) was expressed along with CAR in T cells. Further in vitro and in vivo tests were performed to determine the effects of IL-24 on CSCs and CAR-T cell therapy. RESULTS: IL-24 induced apoptosis in CSCs and contributed to T cell activation, differentiation, and proliferation. CAR.IL-24-T cells inhibited CSC enrichment and exhibited stronger antitumor activity in vitro and in vivo. CONCLUSIONS: IL-24 helps eliminate CSCs and endows CAR-T cells with improved antitumor reactivity.

The Diagnostic and Prognostic Value of EBUS-TBNA for Intrathoracic Metastasis in Previously Treated Patients With Head and Neck Cancer.

OBJECTIVE: The present study assessed the diagnostic and prognostic significance of endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) for suspected intrathoracic metastasis after HNC treatment. METHODS: A retrospective analysis was conducted on 75 patients with a prior history of head and neck cancer treatment who underwent EBUS-TBNA for suspected intrathoracic metastases between March 2012 and December 2021. RESULTS: A total of 126 targeted lesions, including 107 mediastinal/hilar lymph nodes and 19 intrapulmonary/mediastinal masses, were sampled. The metastatic head and neck cancer (HNC) cases detected by EBUS-TBNA consisted of nasopharyngeal carcinoma (n = 24), oropharyngeal carcinoma (n = 3), hypopharynx carcinoma (n = 6), laryngeal carcinoma (n = 6), and oral cavity carcinoma (n = 6). Cases with negative EBUS-TBNA results consisted of tuberculosis (n = 9), sarcoidosis (n = 3), anthracosis (n = 9), and reactive lymphadenitis (n = 9). Six false-negative cases were found among the 75 patients with suspected intrathoracic metastases. The diagnostic sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of the EBUS-TBNA procedure for metastatic HNC were 88.2, 100.0, 100.0, 80, and 92.0%, respectively. The diagnosis of HNC intrathoracic metastasis by EBUS-TBNA correlated with an adverse prognosis in terms of overall survival (OS) (P = .008). The log-rank univariate analysis and Cox regression multivariate analysis results indicated that the detection of metastatic HNC through EBUS-TBNA was a significant independent prognostic factor for patients with HNC who had received prior treatment. CONCLUSIONS: Endobronchial ultrasound-guided transbronchial needle aspiration is a safe, effective, and minimally invasive procedure for assessing suspected intrathoracic metastasis in HNC patients after treatment. The intrathoracic metastasis detected by EBUS-TBNA has crucial prognostic significance in previously treated HNC patients.

Toripalimab Plus Paclitaxel and Carboplatin as Neoadjuvant Therapy in Locally Advanced Resectable Esophageal Squamous Cell Carcinoma.

INTRODUCTION: Immune checkpoint inhibitors (ICIs) are effective in the treatment of advanced esophageal squamous cell carcinoma (ESCC); however, their efficacy in locally advanced resectable ESCC and the potential predictive biomarkers have limited data. METHODS: In this study, locally advanced resectable ESCC patients were enrolled and received neoadjuvant toripalimab (240 mg, day 1) plus paclitaxel (135 mg/m2, day 1) and carboplatin (area under the curve 5 mg/mL per min, day 1) in each 3-week cycle for 2 cycles, followed by esophagectomy planned 4-6 weeks after preoperative therapy. The primary endpoints were safety, feasibility, and the major pathological response (MPR) rate; the secondary endpoints were the pathological complete response (pCR) rate, disease-free survival (DFS), and overall survival (OS). Association between molecular signatures/tumor immune microenvironment and treatment response was also explored. RESULTS: Twenty resectable ESCC patients were enrolled. Treatment-related adverse events (AEs) occurred in all patients (100%), and 4 patients (22.2%) experienced grade 3 or higher treatment-related AEs. Sixteen patients underwent surgery without treatment-related surgical delay, and the R0 resection rate was 87.5% (14/16). Among the 16 patients, the MPR rate was 43.8% (7/16) and the pCR rate was 18.8% (3/16). The abundance of CD8+ T cells in surgical specimens increased (P = .0093), accompanied by a decreased proportion of M2-type tumor-associated macrophages (P = .036) in responders upon neoadjuvant therapy. Responders were associated with higher baseline gene expression levels of CXCL5 (P = .03) and lower baseline levels of CCL19 (P = .017) and UMODL1 (P = .03). CONCLUSIONS: The combination of toripalimab plus paclitaxel and carboplatin is safe, feasible, and effective in locally advanced resectable ESCC, indicating its potential as a neoadjuvant treatment for ESCC. CLINICAL TRIAL REGISTRATION: NCT04177797.

Sulforaphane enhances the antitumor response of chimeric antigen receptor T cells by regulating PD-1/PD-L1 pathway.

BACKGROUND: Chimeric antigen receptor T (CAR-T) cell therapy has limited effects in the treatment of solid tumors. Sulforaphane (SFN) is known to play an important role in inhibiting tumor growth, but its effect on CAR-T cells remains unclear. The goal of the current study was to determine whether combined CAR-T cells and SFN could provide antitumor efficacy against solid tumors. METHODS: The effect of combined SFN and CAR-T cells was determined in vitro using a co-culture system and in vivo using a xenograft mouse model. We further validated the effects of combination therapy in patients with cancer. RESULTS: In vitro, the combination of SFN and CAR-T cells resulted in enhanced cytotoxicity and increased lysis of tumor cells. We found that SFN suppressed programmed cell death 1 (PD-1) expression in CAR-T cells and potentiated antitumor functions in vitro and in vivo. As a ligand of PD-1, programmed cell death ligand 1 (PD-L1) expression was also decreased in tumor cells after SFN treatment. In addition, ß-TrCP was increased by SFN, resulting in higher activation of ubiquitination-mediated proteolysis of PD-L1, which induced PD-L1 degradation. The combination of SFN and CAR-T cell therapy acted synergistically to promote better immune responses in vivo compared with monotherapy. In clinical treatments, PD-1 expression was lower, and proinflammatory cytokine levels were higher in patients with various cancers who received CAR-T cells and took SFN orally than that in the control group. CONCLUSION: SFN improves the cytotoxicity of CAR-T cells by modulating the PD-1/PD-L1 pathway, which may provide a promising strategy for the combination of SFN with CAR-T cells for cancer immunotherapy.

Autophagy is required for the promoting effect of angiogenic factor with G patch domain and forkhead-associated domain 1 (AGGF1) in retinal angiogenesis.

OBJECTIVE: To investigate the effect of angiogenic factor with G patch domain and forkhead-associated domain 1 (AGGF1) on retinal angiogenesis in ischemic retinopathy and its association with autophagy. METHODS: RF/6A cells were divided into the control group, hypoxia group and high-glucose group, and the expression of AGGF1 in cells was detected. C57BL/6 J mice were divided into the control group, oxygen-induced retinopathy (OIR) group and diabetic retinopathy (DR) group, and AGGF1 expression in the retina was observed. RF/6A cells were then divided into the control group and different AGGF1 concentration groups, and the expression of autophagy marker, LC3 was detected. Then, RF/6A cells were divided into the control group, AGGF1 group, 3-methyladenine (3-MA, an early autophagy inhibitor) + AGGF1 group and chloroquine (CQ, a late autophagy inhibitor) + AGGF1 group, and the expression of autophagy markers, LC3 and p62, autophagic flux, as well as was key signaling pathway proteins in autophagy, PI3K, AKT, and mTOR was detected. Finally, the cell proliferation, migration and tube formation were detected in the four groups. RESULTS: AGGF1 expression in RF/6A cells and in the retinas of OIR and DR mouse model was found to be increased in the state of hypoxic and high glucose condition. AGGF1 treatment led to increased expressions of LC3 and decreased p62; therby induced autophagic flux, and the phosphorylation of PI3K, AKT and mTOR was down-regulated in RF/6A cells. When autophagy was inhibited by 3-MA or CQ, confirmed by corresponding changes of these indicators of autophagy, cellular proliferation, migration and tube formation of RF/6A cells were weakened by AGGF1 treatment when compared with that of AGGF1 treatment alone. CONCLUSION: This study experimentally revealed that AGGF1 activates autophagy to promote angiogenesis for ischemic retinopathy and inhibition of PI3K/AKT/mTOR pathway may be involved in the activation of autophagy by AGGF1.

Combining spatial and chemical information for clustering pharmacophores.

BACKGROUND: A pharmacophore model consists of a group of chemical features arranged in three-dimensional space that can be used to represent the biological activities of the described molecules. Clustering of molecular interactions of ligands on the basis of their pharmacophore similarity provides an approach for investigating how diverse ligands can bind to a specific receptor site or different receptor sites with similar or dissimilar binding affinities. However, efficient clustering of pharmacophore models in three-dimensional space is currently a challenge. RESULTS: We have developed a pharmacophore-assisted Iterative Closest Point (ICP) method that is able to group pharmacophores in a manner relevant to their biochemical properties, such as binding specificity etc. The implementation of the method takes pharmacophore files as input and produces distance matrices. The method integrates both alignment-dependent and alignment-independent concepts. CONCLUSIONS: We apply our three-dimensional pharmacophore clustering method to two sets of experimental data, including 31 globulin-binding steroids and 4 groups of selected antibody-antigen complexes. Results are translated from distance matrices to Newick format and visualised using dendrograms. For the steroid dataset, the resulting classification of ligands shows good correspondence with existing classifications. For the antigen-antibody datasets, the classification of antigens reflects both antigen type and binding antibody. Overall the method runs quickly and accurately for classifying the data based on their binding affinities or antigens.

TDASD: Generating medically significant fine-grained lung adenocarcinoma nodule CT images based on stable diffusion models with limited sample size.

BACKGROUND AND OBJECTIVES: Spread through air spaces (STAS) is an emerging lung cancer infiltration pattern. Predicting its spread through CT scans is crucial. However, limited STAS data makes this prediction task highly challenging. Stable diffusion is capable of generating more diverse and higher-quality images compared to traditional GAN models, surpassing the dominating GAN family models in image synthesis over the past few years. To alleviate the issue of limited STAS data, we propose a method TDASD based on stable diffusion, which is able to generate high-resolution CT images of pulmonary nodules corresponding to specific nodular signs according to the medical professionals. METHODS: First, we apply the stable diffusion method for fine-tuning training on publicly available lung datasets. Subsequently, we extract nodules from our hospital's lung adenocarcinoma data and apply slight rotations to the original nodule CT slices within a reasonable range before undergoing another round of fine-tuning through stable diffusion. Finally, employing DDIM and Ksample sampling methods, we generate lung adenocarcinoma nodule CT images with signs based on prompts provided by doctors. The method we propose not only safeguards patient privacy but also enhances the diversity of medical images under limited data conditions. Furthermore, our approach to generating medical images incorporates medical knowledge, resulting in images that exhibit pertinent medical features, thus holding significant value in tumor discrimination diagnostics. RESULTS: Our TDASD method has the capability to generate medically meaningful images by optimizing input prompts based on medical descriptions provided by experts. The images generated by our method can improve the model's classification accuracy. Furthermore, Utilizing solely the data generated by our method for model training, the test results on the original real dataset reveal an accuracy rate that closely aligns with the testing accuracy achieved through training on real data. CONCLUSIONS: The method we propose not only safeguards patient privacy but also enhances the diversity of medical images under limited data conditions. Furthermore, our approach to generating medical images incorporates medical knowledge, resulting in images that exhibit pertinent medical features, thus holding significant value in tumor discrimination diagnostics.

Ghrelin inhibits autophagy mediated by AKT/mTOR pathway to ameliorate retinal angiogenesis induced by high glucose stress.

AIM: To observe the effect of ghrelin, a growth hormone-releasing peptide, on retinal angiogenesis in vitro under high glucose (HG) stress and to explore the possible mechanism of autophagy. METHODS: Human retinal microvascular endothelial cells (HRMECs) were treated with high concentration of glucose alone or in combination with ghrelin. The cell migration, tube formation and the expression of the autophagy-related proteins LC3-II/I, Beclin-1, p62, phosphorylated AKT (p-AKT)/AKT and phosphorylated mammalian target of rapamycin (p-mTOR)/mTOR were detected. Then, to clarify the correlation between ghrelin effect and autophagy, AKT inhibitor VIII was adopted to treat HRMECs, and cell migration, tube formation as well as the protein expressions of LC3-II/I, Beclin-1 and p62 were observed. RESULTS: Under HG stress, ghrelin inhibited migration and tube formation of HRMECs. Ghrelin inhibited the increases in the protein levels of LC3-II/I, Beclin-1 and the decreases in the protein levels of p62, p-AKT/AKT and p-mTOR/mTOR induced by HG stress. Moreover, under the action of AKT/mTOR pathway inhibitors, the effects of ghrelin on migration and tube formation were both reduced. In addition, the expression of LC3-II/I and Beclin-1 were significantly up-regulated and the expression of p62 was down-regulated. CONCLUSION: Retinal angiogenesis under in vitro HG stress can be inhibited by ghrelin through activating AKT/mTOR pathway to inhibit autophagy.

A graph neural network model for the diagnosis of lung adenocarcinoma based on multimodal features and an edge-generation network.

Background: Lung cancer is a global disease with high lethality, with early screening being considerably helpful for improving the 5-year survival rate. Multimodality features in early screening imaging are an important part of the prediction for lung adenocarcinoma, and establishing a model for adenocarcinoma diagnosis based on multimodal features is an obvious clinical need. Through our practice and investigation, we found that graph neural networks (GNNs) are excellent platforms for multimodal feature fusion, and the data can be completed using the edge-generation network. Therefore, we propose a new lung adenocarcinoma multiclassification model based on multimodal features and an edge-generation network. Methods: According to a ratio of 80% to 20%, respectively, the dataset of 338 cases was divided into the training set and the test set through 5-fold cross-validation, and the distribution of the 2 sets was the same. First, the regions of interest (ROIs) cropped from computed tomography (CT) images were separately fed into convolutional neural networks (CNNs) and radiomics processing platforms. The results of the 2 parts were then input into a graph embedding representation network to obtain the fused feature vectors. Subsequently, a graph database based on the clinical and semantic features was established, and the data were supplemented by an edge-generation network, with the fused feature vectors being used as the input of the nodes. This enabled us to clearly understand where the information transmission of the GNN takes place and improves the interpretability of the model. Finally, the nodes were classified using GNNs. Results: On our dataset, the proposed method presented in this paper achieved superior results compared to traditional methods and showed some comparability with state-of-the-art methods for lung nodule classification. The results of our method are as follows: accuracy (ACC) =66.26% (±4.46%), area under the curve (AUC) =75.86% (±1.79%), F1-score =64.00% (±3.65%), and Matthews correlation coefficient (MCC) =48.40% (±5.07%). The model with the edge-generating network consistently outperformed the model without it in all aspects. Conclusions: The experiments demonstrate that with appropriate data=construction methods GNNs can outperform traditional image processing methods in the field of CT-based medical image classification. Additionally, our model has higher interpretability, as it employs subjective clinical and semantic features as the data construction approach. This will help doctors better leverage human-computer interactions.

Pulmonary Nodule Detection and Classification Using All-Optical Deep Diffractive Neural Network.

A deep diffractive neural network (D2NN) is a fast optical computing structure that has been widely used in image classification, logical operations, and other fields. Computed tomography (CT) imaging is a reliable method for detecting and analyzing pulmonary nodules. In this paper, we propose using an all-optical D2NN for pulmonary nodule detection and classification based on CT imaging for lung cancer. The network was trained based on the LIDC-IDRI dataset, and the performance was evaluated on a test set. For pulmonary nodule detection, the existence of nodules scanned from CT images were estimated with two-class classification based on the network, achieving a recall rate of 91.08% from the test set. For pulmonary nodule classification, benign and malignant nodules were also classified with two-class classification with an accuracy of 76.77% and an area under the curve (AUC) value of 0.8292. Our numerical simulations show the possibility of using optical neural networks for fast medical image processing and aided diagnosis.

Anlotinib plus camrelizumab achieved long-term survival in a patient with metastatic esophageal neuroendocrine carcinoma.

BACKGROUND: Esophageal neuroendocrine carcinoma (NEC) is a rare cancer with an extremely poor prognosis. The average overall survival of patients with metastatic disease is only 1 year. The efficacy of anti-angiogenic agents combined with immune checkpoint inhibitors remains unknown. CASE PRESENTATION: A 64-year-old man, initially diagnosed with esophageal NEC, underwent neoadjuvant chemotherapy and esophagectomy. Although the patient remained disease-free for 11 months, eventually the tumor progressed and did not respond to three lines of combined therapy (etoposide plus carboplatin with local radiotherapy, albumin-bound paclitaxel plus durvalumab, and irinotecan plus nedaplatin). The patient then received anlotinib plus camrelizumab, and a dramatic regression was observed (confirmed by positron emission tomography-computed tomography). The patient has been disease-free for over 29 months and has survived for over 4 years since diagnosis. CONCLUSION: Combined therapy with anti-angiogenic agents and immune checkpoint inhibitors may be a promising strategy for esophageal NEC, although more evidence is warranted to validate its efficacy.

An uncertainty-aware self-training framework with consistency regularization for the multilabel classification of common computed tomography signs in lung nodules.

Background: Computed tomography (CT) signs of lung nodules play an important role in indicating lung nodules' malignancy, and accurate automatic classification of these signs can help doctors improve their diagnostic efficiency. However, few relevant studies targeting multilabel classification (MLC) of nodule signs have been conducted. Moreover, difficulty in obtaining labeled data also restricts this avenue of research to a large extent. To address these problems, a multilabel automatic classification system for nodule signs is proposed, which consists of a 3-dimensional (3D) convolutional neural network (CNN) and an efficient new semi-supervised learning (SSL) framework. Methods: Two datasets were used in our experiments: Lung Nodule Analysis 16 (LUNA16), a public dataset for lung nodule classification, and a private dataset of nodule signs. The private dataset contains 641 nodules, 454 of which were annotated with 6 important signs by radiologists. Our classification system consists of 2 main parts: a 3D CNN model and an SSL method called uncertainty-aware self-training framework with consistency regularization (USC). In the system, supervised training is performed with labeled data, and simultaneously, an uncertainty-and-confidence-based strategy is used to select pseudo-labeled samples for unsupervised training, thus jointly realizing the optimization of the model. Results: For the MLC of nodule signs, our proposed 3D CNN achieved satisfactory results with a mean average precision (mAP) of 0.870 and a mean area under the curve (AUC) of 0.782. In semi-supervised experiments, compared with supervised learning, our proposed SSL method could increase the mAP by 7.6% (from 0.730 to 0.806) and the mean AUC by 8.1% (from 0.631 to 0.712); it thus efficiently utilized the unlabeled data and achieved superior performance improvement compared to the recently advanced methods. Conclusions: We realized the optimal MLC of lung nodule signs with our proposed 3D CNN. Our proposed SSL method can also offer an efficient solution for the insufficiency of labeled data that may exist in the MLC tasks of 3D medical images.

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.

The ghrelin-GHSR-1a pathway inhibits high glucose-induced retinal angiogenesis in vitro by alleviating endoplasmic reticulum stress.

BACKGROUND: To investigate the effect of ghrelin, a brain-gut peptide hormone, on high glucose-induced retinal angiogenesis in vitro and explore its association with endoplasmic reticulum (ER) stress. METHODS: Human retinal microvascular endothelial cells (HRMECs) were first divided into control and high-glucose groups, and the mRNA and protein expression levels of the receptor for ghrelin [growth hormone secretin receptor 1a, (GHSR-1a)] in cells were determined. HRMECs were then treated with high glucose alone or in combination with ghrelin or siGHSR-1a, and cell viability, migration, tube formation and the expression of the ER stress-related proteins PERK, ATF4 and CHOP were detected. Finally, to clarify whether the effects of ghrelin are related to ER stress, tunicamycin, an inducer of ER stress, was used to treat HRMECs, and cell viability, cell migration, and tube formation were evaluated. RESULTS: GHSR-1a expression in HRMECs at both the mRNA and protein levels was inhibited by high-glucose treatment. Under high-glucose conditions, ghrelin promoted cell viability and inhibited migration and tube formation, which were blocked by siGHSR-1a treatment. Ghrelin inhibited the increases in the protein levels of p-PERK, ATF4 and CHOP induced by high-glucose treatment, and combination treatment with siGHSR-1a reversed this effect of ghrelin. When tunicamycin was added, the effects of ghrelin on cell viability, migration and tube formation were all weakened. CONCLUSIONS: This study experimentally revealed that ghrelin can inhibit high glucose-induced retinal angiogenesis in vitro through GHSR-1a, and alleviation of ER stress may be one of the mechanisms underlying this effect.

Modeling long-range dependencies for weakly supervised disease classification and localization on chest X-ray.

Background: Computer-aided diagnosis based on chest X-ray (CXR) is an exponentially growing field of research owing to the development of deep learning, especially convolutional neural networks (CNNs). However, due to the intrinsic locality of convolution operations, CNNs cannot model long-range dependencies. Although vision transformers (ViTs) have recently been proposed to alleviate this limitation, those trained on patches cannot learn any dependencies for inter-patch pixels and thus, are insufficient for medical image detection. To address this problem, in this paper, we propose a CXR detection method which integrates CNN with a ViT for modeling patch-wise and inter-patch dependencies. Methods: We experimented on the ChestX-ray14 dataset and followed the official training-test set split. Because the training data only had global annotations, the detection network was weakly supervised. A DenseNet with a feature pyramid structure was designed and integrated with an adaptive ViT to model inter-patch and patch-wise long-range dependencies and obtain fine-grained feature maps. We compared the performance using our method with that of other disease detection methods. Results: For disease classification, our method achieved the best result among all the disease detection methods, with a mean area under the curve (AUC) of 0.829. For lesion localization, our method achieved significantly higher intersection of the union (IoU) scores on the test images with bounding box annotations than did the other detection methods. The visualized results showed that our predictions were more accurate and detailed. Furthermore, evaluation of our method in an external validation dataset demonstrated its generalization ability. Conclusions: Our proposed method achieves the new state of the art for thoracic disease classification and weakly supervised localization. It has potential to assist in clinical decision-making.

Study on Microstructural Evolution of DP Steel Considering the Interface Layer Based on Multi Mechanism Strain Gradient Theory.

A multi-mechanism constitutive model is proposed in this paper to better describe the effect of the local hardening behavior of the interface layer on the mechanical heterogeneity of dual-phase (DP) steel. The constitutive equations considering the geometrically necessary dislocations (GNDs) and back stress at grain level and sample level were established. Based on the finite element simulation results, the influences of local hardening and microstructure characteristics on the strain-stress evolution, statistical storage dislocations, GNDs, and back stress of DP steel were studied and discussed. Due to the local hardening effect, the ferrite phase was treated as an inhomogeneous matrix reinforced by some small islands of martensite in the simulation. The simulation results show that the thickness of the interface layer has a significant effect on the macroscopic hardening property of DP steel, while the number of interface layers has little effect. Meanwhile, the GNDs and back stress at the grain level also have little effect on the strengthening of DP steel. The contribution of GNDs at the sample level to the flow stress is about 47%.

Repeatability and Reproducibility of Computed Tomography Radiomics for Pulmonary Nodules: A Multicenter Phantom Study.

BACKGROUND: Radiomics can yield minable information from medical images, which can facilitate computer-aided diagnosis. However, the lack of repeatability and reproducibility of radiomic features (RFs) may hinder their generalizability in clinical applications. OBJECTIVES: The aims of this study were to explore 3 main sources of variability in RFs, investigate their influencing magnitudes and patterns, and identify a subset of robust RFs for further studies. MATERIALS AND METHODS: A chest phantom with nodules was scanned with different computed tomography (CT) scanners repeatedly with varying acquisition and reconstruction parameters (April-May 2019) to evaluate 3 sources of variability: test-retest, inter-CT, and intra-CT protocol variability. The robustness of the RFs was measured using the concordance correlation coefficient, dynamic range, and intraclass correlation coefficient (ICC). The influencing magnitudes and patterns were analyzed using the Friedman test and Spearman rank correlation coefficient. Stable and informative RFs were selected, and their redundancy was eliminated using hierarchical clustering. Clinical validation was also performed to verify the clinical effectiveness and potential enhancement of the generalizability of radiomics research. RESULTS: A total of 1295 RFs that showed all 3 sources of variability were included. The reconstruction kernel and the iteration level showed the greatest (ICC, 0.35 ± 0.31) and the least (ICC, 0.63 ± 0.27) influence on magnitudes. The different sources of variability showed relatively consistent patterns of influence (false discovery rate <0.001). Finally, we obtained a subset of 19 stable, informative, and nonredundant RFs under all 3 sources of variability. These RFs exhibited clinical effectiveness and showed better prediction performance than unstable RFs in the validation dataset (P = 0.017, Delong test). CONCLUSIONS: The stability of RFs was affected to different degrees by test-retest and differences in CT manufacturers and models and CT acquisition and reconstruction parameters, but the influences of these factors showed relatively consistent patterns. We also obtained a subset of 19 stable, informative, and nonredundant RFs that should be preferably used to enhance the generalizability of further radiomics research.

How does the artificial intelligence-based image-assisted technique help physicians in diagnosis of pulmonary adenocarcinoma? A randomized controlled experiment of multicenter physicians in China.

OBJECTIVE: Although artificial intelligence (AI) has achieved high levels of accuracy in the diagnosis of various diseases, its impact on physicians' decision-making performance in clinical practice is uncertain. This study aims to assess the impact of AI on the diagnostic performance of physicians with differing levels of self-efficacy under working conditions involving different time pressures. MATERIALS AND METHODS: A 2 (independent diagnosis vs AI-assisted diagnosis) × 2 (no time pressure vs 2-minute time limit) randomized controlled experiment of multicenter physicians was conducted. Participants diagnosed 10 pulmonary adenocarcinoma cases and their diagnostic accuracy, sensitivity, and specificity were evaluated. Data analysis was performed using multilevel logistic regression. RESULTS: One hundred and four radiologists from 102 hospitals completed the experiment. The results reveal (1) AI greatly increases physicians' diagnostic accuracy, either with or without time pressure; (2) when no time pressure, AI significantly improves physicians' diagnostic sensitivity but no significant change in specificity, while under time pressure, physicians' diagnostic sensitivity and specificity are both improved with the aid of AI; (3) when no time pressure, physicians with low self-efficacy benefit from AI assistance thus improving diagnostic accuracy but those with high self-efficacy do not, whereas physicians with low and high levels of self-efficacy both benefit from AI under time pressure. DISCUSSION: This study is one of the first to provide real-world evidence regarding the impact of AI on physicians' decision-making performance, taking into account 2 boundary factors: clinical time pressure and physicians' self-efficacy. CONCLUSION: AI-assisted diagnosis should be prioritized for physicians working under time pressure or with low self-efficacy.

Label-free identification of human glioma xenograft of mouse brain with quantitative ultraviolet photoacoustic histology imaging.

The ability to unveil molecular specificities of endogenous nonfluorescent chromophores of ultraviolet photoacoustic imaging technology enables label-free histology imaging of tissue specimens. In this work, we exploit ultraviolet photoacoustic microscopy for identifying human glioma xenograft of mouse brain ex vivo. Intrinsically excellent imaging contrast of cell nucleus at ultraviolet photoacoustic illumination along with good spatial resolution allows for discerning the brain glioma of freshly-harvested thick brain slices, which circumvents laborious time-consuming preparations of the tissue specimens including micrometer-thick slicing and H&E staining that are prerequisites in standard histology analysis. The identification of tumor margins and quantitative analysis of tumor areas is implemented, representing good agreement with the standard H&E-stained observations. Quantitative ultraviolet photoacoustic microscopy can access fast pathological assessment to the brain tissues, and thus potentially facilitates intraoperative brain tumor resection to precisely remove all cancerous cells and preserve healthy tissue for maintaining its essential function.

A multi-scale convolutional neural network with context for joint segmentation of optic disc and cup.

Glaucoma is the leading cause of irreversible blindness. For glaucoma screening, the cup to disc ratio (CDR) is a significant indicator, whose calculation relies on the segmentation of optic disc(OD) and optic cup(OC) in color fundus images. This study proposes a residual multi-scale convolutional neural network with a context semantic extraction module to jointly segment the OD and OC. The proposed method uses a W-shaped backbone network, including image pyramid multi-scale input with the side output layer as an early classifier to generate local prediction output. The proposed method includes a context extraction module that extracts contextual semantic information from multiple level receptive field sizes and adaptively recalibrates channel-wise feature responses. It can effectively extract global information and reduce the semantic gaps in the fusion of deep and shallow semantic information. We validated the proposed method on four datasets, including DRISHTI-GS1, REFUGE, RIM-ONE r3, and a private dataset. The overlap errors are 0.0540, 0.0684, 0.0492, 0.0511 in OC segmentation and 0.2332, 0.1777, 0.2372, 0.2547 in OD segmentation, respectively. Experimental results indicate that the proposed method can estimate the CDR for a large-scale glaucoma screening.