Radiomic signatures reveal multiscale intratumor heterogeneity associated with tissue tolerance and survival in re-irradiated nasopharyngeal carcinoma: a multicenter study.

BACKGROUND: Post-radiation nasopharyngeal necrosis (PRNN) is a severe adverse event following re-radiotherapy for patients with locally recurrent nasopharyngeal carcinoma (LRNPC) and associated with decreased survival. Biological heterogeneity in recurrent tumors contributes to the different risks of PRNN. Radiomics can be used to mine high-throughput non-invasive image features to predict clinical outcomes and capture underlying biological functions. We aimed to develop a radiogenomic signature for the pre-treatment prediction of PRNN to guide re-radiotherapy in patients with LRNPC. METHODS: This multicenter study included 761 re-irradiated patients with LRNPC at four centers in NPC endemic area and divided them into training, internal validation, and external validation cohorts. We built a machine learning (random forest) radiomic signature based on the pre-treatment multiparametric magnetic resonance images for predicting PRNN following re-radiotherapy. We comprehensively assessed the performance of the radiomic signature. Transcriptomic sequencing and gene set enrichment analyses were conducted to identify the associated biological processes. RESULTS: The radiomic signature showed discrimination of 1-year PRNN in the training, internal validation, and external validation cohorts (area under the curve (AUC) 0.713-0.756). Stratified by a cutoff score of 0.735, patients with high-risk signature had higher incidences of PRNN than patients with low-risk signature (1-year PRNN rates 42.2-62.5% vs. 16.3-18.8%, P < 0.001). The signature significantly outperformed the clinical model (P < 0.05) and was generalizable across different centers, imaging parameters, and patient subgroups. The radiomic signature had prognostic value concerning its correlation with PRNN-related deaths (hazard ratio (HR) 3.07-6.75, P < 0.001) and all causes of deaths (HR 1.53-2.30, P < 0.01). Radiogenomics analyses revealed associations between the radiomic signature and signaling pathways involved in tissue fibrosis and vascularity. CONCLUSIONS: We present a radiomic signature for the individualized risk assessment of PRNN following re-radiotherapy, which may serve as a noninvasive radio-biomarker of radiation injury-associated processes and a useful clinical tool to personalize treatment recommendations for patients with LANPC.

CT-based identification of pediatric non-Wilms tumors using convolutional neural networks at a single center.

BACKGROUND: Deep learning (DL) is more and more widely used in children's medical treatment. In this study, we have developed a computed tomography (CT)-based DL model for identifying undiagnosed non-Wilms tumors (nWTs) from pediatric renal tumors. METHODS: This study collected and analyzed the preoperative clinical data and CT images of pediatric renal tumor patients diagnosed by our center from 2008 to 2020, and established a DL model to identify nWTs noninvasively. RESULTS: A total of 364 children who had been confirmed by histopathology with renal tumors from our center were enrolled, including 269 Wilms tumors (WTs) and 95 nWTs. For DL model development, all cases were randomly allocated to training set (218 cases), validation set (73 cases), and test set (73 cases). In the test set, the DL model achieved area under the curve of 0.831 (95% CI: 0.712-0.951) in discriminating WTs from nWTs, with the accuracy, sensitivity, and specificity of 0.781, 0.563, and 0.842, respectively. The sensitivity of our model was higher than a radiologist with 15 years of experience. CONCLUSIONS: We presented a DL model for identifying undiagnosed nWTs from pediatric renal tumors, with the potential to improve the image-based diagnosis. IMPACT: Deep learning model was used for the first time to identify pediatric renal tumors in this study. Deep learning model can identify non-Wilms tumors from pediatric renal tumors. Deep learning model based on computed tomography images can improve tumor diagnosis rate.

Genome-wide identification, expression analysis, and transcriptome analysis of the IAA gene family in Zoysia japonica.

BACKGROUND: AUX/IAA is an essential signaling molecule and has great physiological importance in various plants, but its function in Zoysia japonica remains unknown. METHODS AND RESULTS: Genome-wide identification and analysis of AUX/IAA genes used bioinformatics methods to investigate the ZjIAA genes' expression of exogenous IAA hydroponics treatment for 2 h by qRT-PCR, control and exogenous IAA treated zoysia were subjected to transcriptome sequencing. ZjIAAs were distributed across the 13 subfamilies by phylogenetic analysis with Oryza sativa and Arabidopsis thaliana. Multiple sequence alignment revealed that the majority of genes were non-canonical ZjIAAs with incomplete domain. The optimal growth concentration of the IAA hormone was 0.05 mM, and the qRT-PCR analysis revealed that eight ZjIAAs were differentially expressed, with seven genes considerably upregulating and one gene significantly downregulating. The result of transcriptome sequencing revealed that 515 differentially expressed genes (DEGs) were identified, with 344 upregulated genes and 171 downregulated genes. A total of 18 genes were annotated as involved in the plant hormone signal transduction pathway. And 8 ZjIAAs exhibited distinct expressions, 7 upregulated, and only one downregulated, according to the qRT-PCR study. CONCLUSIONS: Genome-wide identification and analysis increased the understanding of the evolution and function of the IAA family in zoysia. DEGs of control and treatment with 0.05 mM exogenous IAA hormone were investigated by transcriptome sequencing. ZjIAAs had substantial variations in the expression of associated genes, with the majority of genes upregulated and 18 genes implicated in plant hormone signal transduction.

Estimating the effect of non-pharmaceutical interventions to mitigate COVID-19 spread in Saudi Arabia.

BACKGROUND: The Kingdom of Saudi Arabia (KSA) quickly controlled the spread of SARS-CoV-2 by implementing several non-pharmaceutical interventions (NPIs), including suspension of international and national travel, local curfews, closing public spaces (i.e., schools and universities, malls and shops), and limiting religious gatherings. The KSA also mandated all citizens to respect physical distancing and to wear face masks. However, after relaxing some restrictions during June 2020, the KSA is now planning a strategy that could allow resuming in-person education and international travel. The aim of our study was to evaluate the effect of NPIs on the spread of the COVID-19 and test strategies to open schools and resume international travel. METHODS: We built a spatial-explicit individual-based model to represent the whole KSA population (IBM-KSA). The IBM-KSA was parameterized using country demographic, remote sensing, and epidemiological data. A social network was created to represent contact heterogeneity and interaction among age groups of the population. The IBM-KSA also simulated the movement of people across the country based on a gravity model. We used the IBM-KSA to evaluate the effect of different NPIs adopted by the KSA (physical distancing, mask-wearing, and contact tracing) and to forecast the impact of strategies to open schools and resume international travels. RESULTS: The IBM-KSA results scenarios showed the high effectiveness of mask-wearing, physical distancing, and contact tracing in controlling the spread of the disease. Without NPIs, the KSA could have reported 4,824,065 (95% CI: 3,673,775-6,335,423) cases by June 2021. The IBM-KSA showed that mandatory mask-wearing and physical distancing saved 39,452 lives (95% CI: 26,641-44,494). In-person education without personal protection during teaching would have resulted in a high surge of COVID-19 cases. Compared to scenarios with no personal protection, enforcing mask-wearing and physical distancing in schools reduced cases, hospitalizations, and deaths by 25% and 50%, when adherence to these NPIs was set to 50% and 70%, respectively. The IBM-KSA also showed that a quarantine imposed on international travelers reduced the probability of outbreaks in the country. CONCLUSIONS: This study showed that the interventions adopted by the KSA were able to control the spread of SARS-CoV-2 in the absence of a vaccine. In-person education should be resumed only if NPIs could be applied in schools and universities. International travel can be resumed but with strict quarantine rules. The KSA needs to keep strict NPIs in place until a high fraction of the population is vaccinated in order to reduce hospitalizations and deaths.

Deep learning signatures reveal multiscale intratumor heterogeneity associated with biological functions and survival in recurrent nasopharyngeal carcinoma.

PURPOSE: How to discriminate different risks of recurrent nasopharyngeal carcinoma (rNPC) patients and guide individual treatment has become of great importance. This study aimed to explore the associations between deep learning signatures and biological functions as well as survival in (rNPC) patients. METHODS: A total of 420 rNPC patients with PET/CT imaging and follow-up of overall survival (OS) were retrospectively enrolled. All patients were randomly divided into a training set (n = 269) and test set (n = 151) with a 6:4 ratio. We constructed multi-modality deep learning signatures from PET and CT images with a light-weighted deep convolutional neural network EfficienetNet-lite0 and survival loss DeepSurvLoss. An integrated nomogram was constructed incorporating clinical factors and deep learning signatures from PET/CT. Clinical nomogram and single-modality deep learning nomograms were also built for comparison. Furthermore, the association between biological functions and survival risks generated from an integrated nomogram was analyzed by RNA sequencing (RNA-seq). RESULTS: The C-index of the integrated nomogram incorporating age, rT-stage, and deep learning PET/CT signature was 0.741 (95% CI: 0.688-0.794) in the training set and 0.732 (95% CI: 0.679-0.785) in the test set. The nomogram stratified patients into two groups with high risk and low risk in both the training set and test set with hazard ratios (HR) of 4.56 (95% CI: 2.80-7.42, p < 0.001) and 4.05 (95% CI: 2.21-7.43, p < 0.001), respectively. The C-index of the integrated nomogram was significantly higher than the clinical nomogram and single-modality nomograms. When stratified by sex, N-stage, or EBV DNA, risk prediction of our integrated nomogram was valid in all patient subgroups. Further subgroup analysis showed that patients with a low-risk could benefit from surgery and re-irradiation, while there was no difference in survival rates between patients treated by chemotherapy in the high-risk and low-risk groups. RNA sequencing (RNA-seq) of data further explored the mechanism of high- and low-risk patients from the genetic and molecular level. CONCLUSION: Our study demonstrated that PET/CT-based deep learning signatures showed satisfactory prognostic predictive performance in rNPC patients. The nomogram incorporating deep learning signatures successfully divided patients into different risks and had great potential to guide individual treatment: patients with a low-risk were supposed to be treated with surgery and re-irradiation, while for high-risk patients, the application of palliative chemotherapy may be sufficient.

The role of Tim-3/Galectin-9 pathway in T-cell function and prognosis of patients with human papilloma virus-associated cervical carcinoma.

The interaction between Tim-3 on T cell and its ligand, Galectin-9, negatively regulates cellular immune responses. However, the role of Tim-3/Galectin-9 pathway in the immune evasion of cervical cancer remains unknown. This study is to investigate the expression, function, and regulation of Tim-3/Galectin-9 signaling pathway in human papilloma virus (HPV) positive cervical cancer. Flow cytometry showed that Tim-3 expression on T cell and Galectin-9 expression on monocytes in HPV positive cervical cancer patients were significantly higher compared to cervical intraepithelial neoplasia and benign uterine fibroids Tim-3 + CD4+ Th1 cells and Tim-3 + CD8+ T cells in HPV positive cervical cancer patients were significantly reduced after surgery. Serum TGF-ß and IL-10 levels were positively correlated with Tim-3 + Treg cells, while IFN-γ and IL-2 were negatively correlated with Tim-3 + Th1 cells. Additionally, Tim-3 + CD4+ T cells were positively correlated with Galectin-9 + monocytes. Survival curve analysis showed that Tim-3 + CD4+ T cells were negatively correlated with patient survival, and closely related to FIGO stage, degree of differentiation, and lymph node metastasis of HPV positive cervical cancer. In vitro experiments showed that by blocking the Tim-3/Galectin-9 pathway, the proliferation of T cells and their ability to express IFN-γ, IL-2, perforin, and granzyme B was significantly restored. In conclusion, high levels of Tim-3 and Galectin-9 in HPV positive cervical cancer patients play roles in the progression of disease by promoting Treg cells to inhibit the cytotoxic function of Th1 and CD8+ T cells. Tim-3/Galectin-9 may serve as a new immunotherapy target for patients with HPV positive cervical cancer.

Automatic captioning of early gastric cancer using magnification endoscopy with narrow-band imaging.

BACKGROUND AND AIMS: The detection rate for early gastric cancer (EGC) is unsatisfactory, and mastering the diagnostic skills of magnifying endoscopy with narrow-band imaging (ME-NBI) requires rich expertise and experience. We aimed to develop an EGC captioning model (EGCCap) to automatically describe the visual characteristics of ME-NBI images for endoscopists. METHODS: ME-NBI images (n = 1886) from 294 cases were enrolled from multiple centers, and corresponding 5658 text data were designed following the simple EGC diagnostic algorithm. An EGCCap was developed using the multiscale meshed-memory transformer. We conducted comprehensive evaluations for EGCCap including the quantitative and quality of performance, generalization, robustness, interpretability, and assistant value analyses. The commonly used metrics were BLEUs, CIDEr, METEOR, ROUGE, SPICE, accuracy, sensitivity, and specificity. Two-sided statistical tests were conducted, and statistical significance was determined when P < .05. RESULTS: EGCCap acquired satisfying captioning performance by outputting correctly and coherently clinically meaningful sentences in the internal test cohort (BLEU1 = 52.434, CIDEr = 36.734, METEOR = 27.823, ROUGE = 49.949, SPICE = 35.548) and maintained over 80% performance when applied to other centers or corrupted data. The diagnostic ability of endoscopists improved with the assistance of EGCCap, which was especially significant (P < .05) for junior endoscopists. Endoscopists gave EGCCap an average remarkable score of 7.182, showing acceptance of EGCCap. CONCLUSIONS: EGCCap exhibited promising captioning performance and was proven with satisfying generalization, robustness, and interpretability. Our study showed potential value in aiding and improving the diagnosis of EGC and facilitating the development of automated reporting in the future.

Responsiveness of the healthcare system in the Kingdom of Saudi Arabia: evidence from a nationally representative survey.

BACKGROUND: Responsiveness is one of the widely used metrics in assessing the performance of healthcare systems. An analysis of the determinants of health care demand and supply and how the Saudi health system responds to the needs of patients (inpatient and outpatient) is needed; hence the need for this study. METHODS: We analysed data from the Saudi Health Systems Responsiveness survey - a nationally representative survey of 10,000 households interviewed in 2017. Using this dataset, we descriptively analysed the level of responsiveness of inpatient and outpatient services (using the standard World Health Organization (WHO) responsiveness dimensions). Based on a logit modelling approach, the relationship between responsiveness and its key determinants was analysed in terms of healthcare demand and supply. RESULTS: Over four fifths of respondents are satisfied with the level of inpatient and outpatient responsiveness. Furthermore, we find that those in bad health tend to show lower levels of satisfaction with inpatient and outpatient care. We also find some evidence that age, gender, and to some extent nationality act as correlates of health system responsiveness. Specifically, we find evidence that Saudi nationals are less satisfied with health services compared to foreign nationals. CONCLUSION: Based on these findings improving the responsiveness of public healthcare facilities would need to be prioritized. Focusing on patients in worse health and lower socio-economic status should also be one of the main priorities.

Chest Radiographs Using a Context-Fusion Convolution Neural Network (CNN): Can It Distinguish the Etiology of Community-Acquired Pneumonia (CAP) in Children?

Clinical symptoms and inflammatory markers cannot reliably distinguish the etiology of CAP, and chest radiographs have abundant information related with CAP. Hence, we developed a context-fusion convolution neural network (CNN) to explore the application of chest radiographs to distinguish the etiology of CAP in children. This retrospective study included 1769 cases of pediatric pneumonia (viral pneumonia, n = 487; bacterial pneumonia, n = 496; and mycoplasma pneumonia, n = 786). The chest radiographs of the first examination, C-reactive protein (CRP), and white blood cell (WBC) were collected for analysis. All patients were stochastically divided into training, validation, and test cohorts in a 7:1:2 ratio. Automatic lung segmentation and hand-crafted pneumonia lesion segmentation were performed, from which three image-based models including a full-lung model, a local-lesion model, and a context-fusion model were built; two clinical characteristics were used to build a clinical model, while a logistic regression model combined the best CNN model and two clinical characteristics. Our experiments showed that the context-fusion model which integrated the features of the full-lung and local-lesion had better performance than the full-lung model and local-lesion model. The context-fusion model had area under curves of 0.86, 0.88, and 0.93 in identifying viral, bacterial, and mycoplasma pneumonia on the test cohort respectively. The addition of clinical characteristics to the context-fusion model obtained slight improvement. Mycoplasma pneumonia was more easily identified compared with the other two types. Using chest radiographs, we developed a context-fusion CNN model with good performance for noninvasively diagnosing the etiology of community-acquired pneumonia in children, which would help improve early diagnosis and treatment.

Expression of a Chlorophyll b Reductase Gene from Zoysia japonica Causes Changes in Leaf Color and Chlorophyll Morphology in Agrostis stolonifera.

The NYC-like (NOL) enzyme is considered as an essential enzyme for chlorophyll b degradation, which catalyzes the formation of 7-hydroxymethyl chlorophyll a from chlorophyll b. The ZjNOL gene was cloned from Zoysia japonica with a completed coding sequence of 981-bp in length, encoding 326 amino acids. ZjNOL was localized on the stroma side of the thylakoid membrane, and co-localized with ZjNYC in the chloroplasts. Multiple photoregulatory elements and hormone regulatory elements were identified in the promoter region of the ZjNOL gene, and the expression level of the ZjNOL gene was dramatically up-regulated in senescence leaves, which were regulated by a variety of plant hormones. ZjNOL's ectopic expression in creeping bentgrass produced yellow leaves, thicker cortex, and smaller vascular column cells. Additionally, transgenic plants exhibited morphological alterations in their chloroplast structure, and the number of grana and thylakoids per grana stack reduced dramatically. Transgenic plants also had a lower photosynthetic rate and Fm/Fv than the control. The transgenic plants displayed a decreased chlorophyll content and a greater rate of ion leakage. The properties and activities of ZjNOL will serve as a foundation for future research into gene functions and regulatory processes.

Expression of a Hydroxycinnamoyl-CoA Shikimate/Quinate Hydroxycinnamoyl Transferase 4 Gene from Zoysia japonica (ZjHCT4) Causes Excessive Elongation and Lignin Composition Changes in Agrostis stolonifera.

Hydroxycinnamoyl-CoA shikimate/quinate hydroxycinnamoyl transferase (HCT) is considered to be an essential enzyme for regulating the biosynthesis and composition of lignin. To investigate the properties and function of ZjHCT4, the ZjHCT4 gene was cloned from Zoysia japonica with a completed coding sequence of 1284-bp in length, encoding 428 amino acids. The ZjHCT4 gene promoter has several methyl jasmonate (MeJA) response elements. According to analysis of expression patterns, it was up-regulated by MeJA, GA3 (Gibberellin), and SA (Salicylic acid), and down-regulated by ABA (Abscisic acid). Ectopic ZjHCT4 expression in creeping bentgrass causes excessive plant elongation. In addition, the content of G-lingnin and H-lingnin fell in transgenic plants, whereas the level of S-lingnin increased, resulting in a considerable rise in the S/G unit ratio. Analysis of the expression levels of lignin-related genes revealed that the ectopic expression of ZjHCT4 altered the expression levels of a number of genes involved in the lignin synthesis pathway. Simultaneously, MeJA, SA, GA3, IAA, BR (Brassinosteroid), and other hormones were dramatically enhanced in transgenic plants relative to control plants, whereas ABA concentration was significantly decreased. Expression of ZjHCT4 impacted lignin composition and plant growth via altering the phenylpropionic acid metabolic pathway and hormone response, as revealed by transcriptome analysis. HCTs may influence plant lignin composition and plant development by altering hormone content. These findings contributed to a deeper comprehension of the lignin synthesis pathway and set the stage for further investigation and application of the HCTs gene.

Semi-supervised Long-tail Endoscopic Image Classification.

Objective To explore the semi-supervised learning (SSL) algorithm for long-tail endoscopic image classification with limited annotations. Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir, the largest gastrointestinal public dataset with 23 diverse classes. Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling. After splitting the training dataset and the test dataset at a ratio of 4:1, we sampled 20%, 50%, and 100% labeled training data to test the classification with limited annotations. Results The classification performance was evaluated by micro-average and macro-average evaluation metrics, with the Mathews correlation coefficient (MCC) as the overall evaluation. SSL algorithm improved the classification performance, with MCC increasing from 0.8761 to 0.8850, from 0.8983 to 0.8994, and from 0.9075 to 0.9095 with 20%, 50%, and 100% ratio of labeled training data, respectively. With a 20% ratio of labeled training data, SSL improved both the micro-average and macro-average classification performance; while for the ratio of 50% and 100%, SSL improved the micro-average performance but hurt macro-average performance. Through analyzing the confusion matrix and labeling bias in each class, we found that the pseudo-based SSL algorithm exacerbated the classifier's preference for the head class, resulting in improved performance in the head class and degenerated performance in the tail class. Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification, especially when the labeled data is extremely limited, which may benefit the building of assisted diagnosis systems for low-volume hospitals. However, the pseudo-labeling strategy may amplify the effect of class imbalance, which hurts the classification performance for the tail class.

A novel prognostic cancer-related lncRNA signature in papillary renal cell carcinoma.

BACKGROUND: Papillary renal cell carcinoma (pRCC) ranks second in renal cell carcinoma and the prognosis of pRCC remains poor. Here, we aimed to screen and identify a novel prognostic cancer-related lncRNA signature in pRCC. METHODS: The RNA-seq profile and clinical feature of pRCC cases were downloaded from TCGA database. Significant cancer-related lncRNAs were obtained from the Immlnc database. Differentially expressed cancer-related lncRNAs (DECRLs) in pRCC were screened for further analysis. Cox regression report was implemented to identify prognostic cancer-related lncRNAs and establish a prognostic risk model, and ROC curve analysis was used to evaluate its precision. The correlation between RP11-63A11.1 and clinical characteristics was further analyzed. Finally, the expression level and role of RP11-63A11.1 were studied in vitro. RESULTS: A total of 367 DECRLs were finally screened and 26 prognostic cancer-related lncRNAs were identified. Among them, ten lncRNAs (RP11-573D15.8, LINC01317, RNF144A-AS1, TFAP2A-AS1, LINC00702, GAS6-AS1, RP11-400K9.4, LUCAT1, RP11-63A11.1, and RP11-156L14.1) were independently associated with prognosis of pRCC. These ten lncRNAs were incorporated into a prognostic risk model. In accordance with the median value of the riskscore, pRCC cases were separated into high and low risk groups. Survival analysis indicated that there was a significant difference on overall survival (OS) rate between the two groups. The area under curve (AUC) in different years indicated that the model was of high efficiency in prognosis prediction. RP11-63A11.1 was mainly expressed in renal tissues and it correlated with the tumor stage, T, M, N classifications, OS, PFS, and DSS of pRCC patients. Consistent with the expression in pRCC tissue samples, RP11-63A11.1 was also down-regulated in pRCC cells. More importantly, up-regulation of RP11-63A11.1 attenuated cell survival and induced apoptosis. CONCLUSIONS: Ten cancer-related lncRNAs were incorporated into a powerful model for prognosis evaluation. RP11-63A11.1 functioned as a cancer suppressor in pRCC and it might be a potential therapeutic target for treating pRCC.

MRI-Based Deep-Learning Model for Distant Metastasis-Free Survival in Locoregionally Advanced Nasopharyngeal Carcinoma.

BACKGROUND: Distant metastasis is the primary cause of treatment failure in locoregionally advanced nasopharyngeal carcinoma (LANPC). PURPOSE: To develop a model to evaluate distant metastasis-free survival (DMFS) in LANPC and to explore the value of additional chemotherapy to concurrent chemoradiotherapy (CCRT) for different risk groups. STUDY TYPE: Retrospective. POPULATION: In all, 233 patients with biopsy-confirmed nasopharyngeal carcinoma (NPC) from two hospitals. FIELD STRENGTH: 1.5T and 3T. SEQUENCE: Axial T2 -weighted (T2 -w) and contrast-enhanced T1 -weighted (CET1 -w) images. ASSESSMENT: Deep learning was used to build a model based on MRI images (including axial T2 -w and CET1 -w images) and clinical variables. Hospital 1 patients were randomly divided into training (n = 169) and validation (n = 19) cohorts; Hospital 2 patients were assigned to a testing cohort (n = 45). LANPC patients were divided into low- and high-risk groups according to their DMFS (P < 0.05). Kaplan-Meier survival analysis was performed to compare the DMFS of different risk groups and subgroup analysis was performed to compare patients treated with CCRT alone and treated with additional chemotherapy to CCRT in different risk groups, respectively. STATISTICAL TESTS: Univariate analysis was performed to identify significant clinical variables. The area under the receiver operating characteristic (ROC) curve (AUC) was used to assess the model performance. RESULTS: Our deep-learning model integrating the deep-learning signature, node (N) stage (from TNM staging), plasma Epstein-Barr virus (EBV)-DNA, and treatment regimens yielded an AUC of 0.796 (95% confidence interval [CI]: 0.729-0.863), 0.795 (95% CI: 0.540-1.000), and 0.808 (95% CI: 0.654-0.962) in the training, internal validation, and external testing cohorts, respectively. Low-risk patients treated with CCRT alone had longer DMFS than patients treated with additional chemotherapy to CCRT (P < 0.05). DATA CONCLUSION: The proposed deep-learning model, based on MRI features and clinical variates, facilitated the prediction of DMFS in LANPC patients. LEVEL OF EVIDENCE: 3. TECHNICAL EFFICACY STAGE: 4.

Identifying early gastric cancer under magnifying narrow-band images with deep learning: a multicenter study.

BACKGROUND AND AIMS: Narrow-band imaging with magnifying endoscopy (ME-NBI) has shown advantages in the diagnosis of early gastric cancer (EGC). However, proficiency in diagnostic algorithms requires substantial expertise and experience. In this study, we aimed to develop a computer-aided diagnostic model for EGM (EGCM) to analyze and assist in the diagnosis of EGC under ME-NBI. METHODS: A total of 1777 ME-NBI images from 295 cases were collected from 3 centers. These cases were randomly divided into a training cohort (n = 170), an internal test cohort (ITC, n = 73), and an external test cohort (ETC, n = 52). EGCM based on VGG-19 architecture (Visual Geometry Group [VGG], Oxford University, Oxford, UK) with a single fully connected 2-classification layer was developed through fine-tuning and validated on all cohorts. Furthermore, we compared the model with 8 endoscopists with varying experience. Primary comparison measures included accuracy, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: EGCM acquired AUCs of .808 in the ITC and .813 in the ETC. Moreover, EGCM achieved similar predictive performance as the senior endoscopists (accuracy: .770 vs .755, P = .355; sensitivity: .792 vs .767, P = .183; specificity: .745 vs .742, P = .931) but better than the junior endoscopists (accuracy: .770 vs .728, P < .05). After referring to the results of EGCM, the average diagnostic ability of the endoscopists was significantly improved in terms of accuracy, sensitivity, PPV, and NPV (P < .05). CONCLUSIONS: EGCM exhibited comparable performance with senior endoscopists in the diagnosis of EGC and showed the potential value in aiding and improving the diagnosis of EGC by endoscopists.

Integrating No.3 lymph nodes and primary tumor radiomics to predict lymph node metastasis in T1-2 gastric cancer.

BACKGROUND: This study aimed to develope and validate a radiomics nomogram by integrating the quantitative radiomics characteristics of No.3 lymph nodes (LNs) and primary tumors to better predict preoperative lymph node metastasis (LNM) in T1-2 gastric cancer (GC) patients. METHODS: A total of 159 T1-2 GC patients who had undergone surgery with lymphadenectomy between March 2012 and November 2017 were retrospectively collected and divided into a training cohort (n = 80) and a testing cohort (n = 79). Radiomic features were extracted from both tumor region and No. 3 station LNs based on computed tomography (CT) images per patient. Then, key features were selected using minimum redundancy maximum relevance algorithm and fed into two radiomic signatures, respectively. Meanwhile, the predictive performance of clinical risk factors was studied. Finally, a nomogram was built by merging radiomic signatures and clinical risk factors and evaluated by the area under the receiver operator characteristic curve (AUC) as well as decision curve. RESULTS: Two radiomic signatures, reflecting phenotypes of the tumor and LNs respectively, were significantly associated with LN metastasis. A nomogram incorporating two radiomic signatures and CT-reported LN metastasis status showed good discrimination of LN metastasis in both the training cohort (AUC 0.915; 95% confidence interval [CI] 0.832-0.998) and testing cohort (AUC 0.908; 95% CI 0.814-1.000). The decision curve also indicated its potential clinical usefulness. CONCLUSIONS: The nomogram received favorable predictive accuracy in predicting No.3 LNM in T1-2 GC, and the nomogram showed positive role in predicting LNM in No.4 LNs. The nomogram may be used to predict LNM in T1-2 GC and could assist the choice of therapy.

Development and External Validation of Radiomics Approach for Nuclear Grading in Clear Cell Renal Cell Carcinoma.

BACKGROUND AND PURPOSE: Nuclear grades of clear cell renal cell carcinoma (ccRCC) are usually confirmed by invasive methods. Radiomics is a quantitative tool that uses non-invasive medical imaging for tumor diagnosis and prognosis. In this study, a radiomics approach was proposed to analyze the association between preoperative computed tomography (CT) images and nuclear grades of ccRCC. METHODS: Our dataset included 320 ccRCC patients from two centers and was divided into a training set (n = 124), an internal test set (n = 123), and an external test set (n = 73). A radiomic feature set was extracted from unenhanced, corticomedullary phase, and nephrographic phase CT images. The maximizing independent classification information criteria function and recursive feature elimination with cross-validation were used to select effective features. Random forests were used to build a final model for predicting nuclear grades, and area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of radiomic features and models. RESULTS: The radiomic features from the three CT phases could effectively distinguished the four nuclear grades. A combined model, merging radiomic features and clinical characteristics, obtained good predictive performances in the internal test set (AUC 0.77, 0.75, 0.79, and 0.85 for the four grades, respectively), and performance was further confirmed in the external test set, with AUCs of 0.75, 0.68, and 0.73 (no fourth-level data). CONCLUSION: The combination of CT radiomic features and clinical characteristics could discriminate the nuclear grades in ccRCC, which may help in assisting treatment decision making.

Noninvasive Prediction of High-Grade Prostate Cancer via Biparametric MRI Radiomics.

BACKGROUND: Gleason score (GS) is a histologic prognostic factor and the basis of treatment decision-making for prostate cancer (PCa). Treatment regimens between lower-grade (GS ≤7) and high-grade (GS >7) PCa differ largely and have great effects on cancer progression. PURPOSE: To investigate the use of different sequences in biparametric MRI (bpMRI) of the prostate gland for noninvasively distinguishing high-grade PCa. STUDY TYPE: Retrospective. POPULATION: In all, 489 patients (training cohort: N = 326; test cohort: N = 163) with PCa between June 2008 and January 2018. FIELD STRENGTH/SEQUENCE: 3.0T, pelvic phased-array coils, bpMRI including T2 -weighted imaging (T2 WI) and diffusion-weighted imaging (DWI); apparent diffusion coefficient map extracted from DWI. ASSESSMENT: The whole prostate gland was delineated. Radiomic features were extracted and selected using the Kruskal-Wallis test, the minimum redundancy-maximum relevance, and the sequential backward elimination algorithm. Two single-sequence radiomic (T2 WI, DWI) and two combined (T2 WI-DWI, T2 WI-DWI-Clinic) models were respectively constructed and validated via logistic regression. STATISTICAL TESTS: The Kruskal-Wallis test and chi-squared test were utilized to evaluate the differences among variable groups. P < 0.05 determined statistical significance. The area under the receiver operating characteristic curve (AUC), specificity, sensitivity, and accuracy were used to evaluate model performance. The Delong test was conducted to compare the differences between the AUCs of all models. RESULT: All radiomic models showed significant (P < 0.001) predictive performances. Between the single-sequence radiomic models, the DWI model achieved the most encouraging results, with AUCs of 0.801 and 0.787 in the training and test cohorts, respectively. For the combined models, the T2 WI-DWI models acquired an AUC of 0.788, which was almost the same with DWI in the test cohort, and no significant difference was found between them (training cohort: P = 0.199; test cohort: P = 0.924). DATA CONCLUSION: Radiomics based on bpMRI can noninvasively identify high-grade PCa before the operation, which is helpful for individualized diagnosis of PCa. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 2 J. Magn. Reson. Imaging 2020;52:1102-1109.

Multiparametric MRI Radiomic Model for Preoperative Predicting WHO/ISUP Nuclear Grade of Clear Cell Renal Cell Carcinoma.

BACKGROUND: Nuclear grade is of importance for treatment selection and prognosis in patients with clear cell renal cell carcinoma (ccRCC). PURPOSE: To develop and validate an MRI-based radiomic model for preoperative predicting WHO/ISUP nuclear grade in ccRCC. STUDY TYPE: Retrospective. POPULATION: In all, 379 patients with histologically confirmed ccRCC. Training cohort (n = 252) and validation cohort (n = 127) were randomly assigned. FIELD STRENGTH/SEQUENCE: Pretreatment 3.0T renal MRI. Imaging sequences were fat-suppressed T2 WI, contrast-enhanced T1 WI, and diffusion weighted imaging. ASSESSMENT: Three prediction models were developed using selected radiomic features, radiomic and clinicoradiologic characteristics, and a model containing only clinicoradiologic characteristics. Receiver operating characteristic (ROC) curves and area under the curve (AUC) were used to assess the predictive performance of these models in predicting high-grade ccRCC. STATISTICAL TESTS: The least absolute shrinkage and selection operator (LASSO) and minimum redundancy maximum relevance (mRMR) method were used for the selection of radiomic features and clinicoradiologic characteristics, respectively. Multivariable logistic regression analysis was used to develop the radiomic signature of radiomic features and clinicoradiologic model of clinicoradiologic characteristics. RESULTS: The radiomic signature showed good performance in discriminating high-grade (grades 3 and 4) from low-grade (grades 1 and 2) ccRCC, with sensitivity, specificity, and AUC of 77.3%, 80.0%, and 0.842, respectively, in the validation cohort. The radiomic model, combining radiomic signature and clinicoradiologic characteristics, displayed good predictive ability for high-grade with sensitivity, specificity, and accuracy of 63.6%, 93.3%, and 88.2%, respectively, in the validation cohort. The radiomic model showed a significantly better performance than the clinicoradiologic model (P < 0.05). DATA CONCLUSION: Multiparametric MRI-based radiomic model can predict WHO/ISUP grade in patients with ccRCC with satisfying performance, and thus could help the physician to improve treatment decisions. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Dual-energy CT-based deep learning radiomics can improve lymph node metastasis risk prediction for gastric cancer.

OBJECTIVES: To build a dual-energy CT (DECT)-based deep learning radiomics nomogram for lymph node metastasis (LNM) prediction in gastric cancer. MATERIALS AND METHODS: Preoperative DECT images were retrospectively collected from 204 pathologically confirmed cases of gastric adenocarcinoma (mean age, 58 years; range, 28-81 years; 157 men [mean age, 60 years; range, 28-81 years] and 47 women [mean age, 54 years; range, 28-79 years]) between November 2011 and October 2018, They were divided into training (n = 136) and test (n = 68) sets. Radiomics features were extracted from monochromatic images at arterial phase (AP) and venous phase (VP). Clinical information, CT parameters, and follow-up data were collected. A radiomics nomogram for LNM prediction was built using deep learning approach and evaluated in test set using ROC analysis. Its prognostic performance was determined with Harrell's concordance index (C-index) based on patients' outcomes. RESULTS: The dual-energy CT radiomics signature was associated with LNM in two sets (Mann-Whitney U test, p < 0.001) and an achieved area under the ROC curve (AUC) of 0.71 for AP and 0.76 for VP in test set. The nomogram incorporated the two radiomics signatures and CT-reported lymph node status exhibited AUCs of 0.84 in the training set and 0.82 in the test set. The C-indices of the nomogram for progression-free survival and overall survival prediction were 0.64 (p = 0.004) and 0.67 (p = 0.002). CONCLUSION: The DECT-based deep learning radiomics nomogram showed good performance in predicting LNM in gastric cancer. Furthermore, it was significantly associated with patients' prognosis. KEY POINTS: • This study investigated the value of deep learning dual-energy CT-based radiomics in predicting lymph node metastasis in gastric cancer. • The dual-energy CT-based radiomics nomogram outweighed the single-energy model and the clinical model. • The nomogram also exhibited a significant prognostic ability for patient survival and enriched radiomics studies.