Super Resolution of Pulmonary Nodules Target Reconstruction Using a Two-Channel GAN Models.

RATIONALE AND OBJECTIVES: To develop a Dual generative-adversarial-network (GAN) Cascaded Network (DGCN) for generating super-resolution computed tomography (SRCT) images from normal-resolution CT (NRCT) images and evaluate the performance of DGCN in multi-center datasets. MATERIALS AND METHODS: This retrospective study included 278 patients with chest CT from two hospitals between January 2020 and June 2023, and each patient had all three NRCT (512×512 matrix CT images with a resolution of 0.70 mm, 0.70 mm,1.0 mm), high-resolution CT (HRCT, 1024×1024 matrix CT images with a resolution of 0.35 mm, 0.35 mm,1.0 mm), and ultra-high-resolution CT (UHRCT, 1024×1024 matrix CT images with a resolution of 0.17 mm, 0.17 mm, 0.5 mm) examinations. Initially, a deep chest CT super-resolution residual network (DCRN) was built to generate HRCT from NRCT. Subsequently, we employed the DCRN as a pre-trained model for the training of DGCN to further enhance resolution along all three axes, ultimately yielding SRCT. PSNR, SSIM, FID, subjective evaluation scores, and objective evaluation parameters related to pulmonary nodule segmentation in the testing set were recorded and analyzed. RESULTS: DCRN obtained a PSNR of 52.16, SSIM of 0.9941, FID of 137.713, and an average diameter difference of 0.0981 mm. DGCN obtained a PSNR of 46.50, SSIM of 0.9990, FID of 166.421, and an average diameter difference of 0.0981 mm on 39 testing cases. There were no significant differences between the SRCT and UHRCT images in subjective evaluation. CONCLUSION: Our model exhibited a significant enhancement in generating HRCT and SRCT images and outperformed established methods regarding image quality and clinical segmentation accuracy across both internal and external testing datasets.

Prognostic implications of synaptophysin, CD56, thyroid transcription factor-1, and Ki-67 in pulmonary high-grade neuroendocrine carcinomas.

BACKGROUND: The correlation between the expression of immunohistochemical markers and the clinicopathological characteristics of pulmonary high-grade neuroendocrine carcinomas (HGNEC) and its impact on the clinical outcomes of individuals with HGNEC has not yet been explored. METHODS: This study enrolled patients diagnosed with HGNEC between April 2015 and July 2023. Based on the expression levels of synaptophysin (Syn), the neural cell adhesion molecule (CD56), thyroid transcription factor-1 (TTF-1), and Ki-67, a comprehensive analysis was conducted. This involved a comparison of clinicopathological characteristics, chemosensitivity, overall survival (OS), and progression-free survival (PFS). Furthermore, the study identified prognostic factors associated with patient survival through univariate and multivariate analyses. RESULTS: Eighty-two patients were analyzed. Significant differences were identified in tumor stage (χ2 = 5.473, P = 0.019), lymphatic invasion (χ2 = 8.839, P = 0.003), and distant metastasis (χ2 = 5.473, P = 0.019), respectively, between the CD56 positive and negative groups. A significant difference in lymphatic invasion was observed (χ2 = 9.949, P = 0.002) between the CD56 positive and negative groups. A significant difference in vascular invasion was observed (χ2 = 5.106, P = 0.024) between the low and high Ki-67 groups. Compared to the Syn negative group, the Syn positive group had significantly shorter PFS (P = 0.006). Compared to the Syn negative group, the Syn positive group had significantly shorter OS (P = 0.004). The CD56 positive group also had significantly shorter OS than the CD56 negative group (P = 0.027). Univariate analysis revealed that tumor stage and Syn expression were associated with OS and PFS. Lymphatic invasion and CD56 expression were associated with OS. Multivariate analysis revealed that tumor stage was the strongest predictor of poor prognosis for OS (hazard ratio [HR] 0.551, 95 % confidence interval [CI] 0.328-0.927, P = 0.025) and PFS (HR 0.409, 95 % CI 0.247-0.676, P < 0.001). CONCLUSIONS: Positive expression of Syn was associated with reduced PFS and OS, while positive CD56 expression was correlated with a shorter OS in HGNEC. The TNM stage was an independent risk factor that significantly influenced PFS and OS in patients with HGNEC. More studies are needed to make further progress in future treatment.

Cost-effectiveness analysis of nivolumab versus placebo for relapsed malignant mesothelioma.

BACKGROUND: Although nivolumab has shown clinical benefits for relapsed malignant mesothelioma, its cost-effectiveness requires further investigation. AIM: This study aimed to evaluate the cost-effectiveness of nivolumab compared to placebo for relapsed malignant mesotheliomas from the perspective of the Chinese healthcare system. METHOD: A three-state Markov model was developed based on data from the phase 3 randomized CONFIRM clinical trial. The drug cost and utility values for the health state were obtained from the relevant literature. The measured outcomes included quality-adjusted life-years (QALYs) and incremental cost-effectiveness ratio (ICER). Probabilistic and one-way sensitivity analyses (OWSA) were performed to assess the uncertainty of the model. RESULTS: Patients receiving nivolumab gained more health benefits (0.65 QALYs vs. 0.43 QALYs). The cost was higher ($25,806.08 vs. $9,310.74) than for patients in the placebo group, resulting in an ICER of $75,805.11/QALY, which was above the willingness-to-pay (WTP) threshold of three times per capita GDP ($35,864.61) in China. The result of OWSA indicated that the cost of nivolumab, the utility of the disease progression, and the discount rate were the most significant factors. Probabilistic sensitivity analysis suggested that the probability that nivolumab was not cost-effective as was 100.00% above the specified WTP threshold. CONCLUSION: From the perspective of the Chinese healthcare system, nivolumab was not as cost-effective as placebo for relapsed malignant mesothelioma.

Automated Rib Fracture Detection on Chest X-Ray Using Contrastive Learning.

To develop a deep learning-based model for detecting rib fractures on chest X-Ray and to evaluate its performance based on a multicenter study. Chest digital radiography (DR) images from 18,631 subjects were used for the training, testing, and validation of the deep learning fracture detection model. We first built a pretrained model, a simple framework for contrastive learning of visual representations (simCLR), using contrastive learning with the training set. Then, simCLR was used as the backbone for a fully convolutional one-stage (FCOS) objective detection network to identify rib fractures from chest X-ray images. The detection performance of the network for four different types of rib fractures was evaluated using the testing set. A total of 127 images from Data-CZ and 109 images from Data-CH with the annotations for four types of rib fractures were used for evaluation. The results showed that for Data-CZ, the sensitivities of the detection model with no pretraining, pretrained ImageNet, and pretrained DR were 0.465, 0.735, and 0.822, respectively, and the average number of false positives per scan was five in all cases. For the Data-CH test set, the sensitivities of three different pretraining methods were 0.403, 0.655, and 0.748. In the identification of four fracture types, the detection model achieved the highest performance for displaced fractures, with sensitivities of 0.873 and 0.774 for the Data-CZ and Data-CH test sets, respectively, with 5 false positives per scan, followed by nondisplaced fractures, buckle fractures, and old fractures. A pretrained model can significantly improve the performance of the deep learning-based rib fracture detection based on X-ray images, which can reduce missed diagnoses and improve the diagnostic efficacy.

An AI-Based Image Quality Control Framework for Knee Radiographs.

Image quality control (QC) is crucial for the accurate diagnosis of knee diseases using radiographs. However, the manual QC process is subjective, labor intensive, and time-consuming. In this study, we aimed to develop an artificial intelligence (AI) model to automate the QC procedure typically performed by clinicians. We proposed an AI-based fully automatic QC model for knee radiographs using high-resolution net (HR-Net) to identify predefined key points in images. We then performed geometric calculations to transform the identified key points into three QC criteria, namely, anteroposterior (AP)/lateral (LAT) overlap ratios and LAT flexion angle. The proposed model was trained and validated using 2212 knee plain radiographs from 1208 patients and an additional 1572 knee radiographs from 753 patients collected from six external centers for further external validation. For the internal validation cohort, the proposed AI model and clinicians showed high intraclass consistency coefficients (ICCs) for AP/LAT fibular head overlap and LAT knee flexion angle of 0.952, 0.895, and 0.993, respectively. For the external validation cohort, the ICCs were also high, with values of 0.934, 0.856, and 0.991, respectively. There were no significant differences between the AI model and clinicians in any of the three QC criteria, and the AI model required significantly less measurement time than clinicians. The experimental results demonstrated that the AI model performed comparably to clinicians and required less time. Therefore, the proposed AI-based model has great potential as a convenient tool for clinical practice by automating the QC procedure for knee radiographs.

Clinical observation of Pemetrexed first-line treatment in advanced non-squamous lung cancer or non-small cell lung cancer without driver-mutations: a phase 2, single-arm trial.

BACKGROUND: Non-dominant population, which means patients with advanced non-squamous lung cancer or non-small cell lung cancer (NSCLC) without driver-mutations, who are excluded from clinical studies because of specific baseline conditions refractory to multiple treatments, have poor outcomes. We assessed the activity of pemetrexed first-line treatment for a non-dominant population, explore the safety and efficacy of pemetrexed therapy. METHODS: We did this two-phased, single-arm trial at two sites at the Fifth Affiliated Hospital of Sun Yat-sen University and Guangxi medical university cancer hospital. Pemetrexed 500 mg/m2, static drops on day 1; 21 days for a cycle, each treatment for at least two cycles and up to six cycles. Efficacy was assessed every two cycles. RESULTS: We counted the July 21, 2018 to 2020 on May 31, first diagnosed with IIIb-IV period (American Joint Committee on Cancer eighth edition) no drive genes, non-squamous cell carcinomas, 30 patients with non-small cell lung cancer, the follow-up to July 31, 2020, median follow-up time was 12 months. Most were elderly patients with poor general conditions (96.7% of patients had ECOG scores of 2-3) (median age 66 years). Median duration of maintenance treatment was 6 months. Median progression-free survival was 6.5 months. Median overall survival was 12 months. Patients with performance status =0-2 had a significantly higher median overall survival time (16 months) compared with patients with performance status =3 who had a median overall survival time of 7 months (P=0.001). Most treatment-related adverse events were grade 1 or grade 2. CONCLUSIONS: This study is the first to investigate the survival benefit and toxicity tolerance of pemetrexed treatment in non-dominant population in the real world, providing a new therapeutic possibility for those who failed to be enrolled in clinical studies.