RESUMEN

BACKGROUND: Precise glioma segmentation from multi-parametric magnetic resonance (MR) images is essential for brain glioma diagnosis. However, due to the indistinct boundaries between tumor sub-regions and the heterogeneous appearances of gliomas in volumetric MR scans, designing a reliable and automated glioma segmentation method is still challenging. Although existing 3D Transformer-based or convolution-based segmentation networks have obtained promising results via multi-modal feature fusion strategies or contextual learning methods, they widely lack the capability of hierarchical interactions between different modalities and cannot effectively learn comprehensive feature representations related to all glioma sub-regions. PURPOSE: To overcome these problems, in this paper, we propose a 3D hierarchical cross-modality interaction network (HCMINet) using Transformers and convolutions for accurate multi-modal glioma segmentation, which leverages an effective hierarchical cross-modality interaction strategy to sufficiently learn modality-specific and modality-shared knowledge correlated to glioma sub-region segmentation from multi-parametric MR images. METHODS: In the HCMINet, we first design a hierarchical cross-modality interaction Transformer (HCMITrans) encoder to hierarchically encode and fuse heterogeneous multi-modal features by Transformer-based intra-modal embeddings and inter-modal interactions in multiple encoding stages, which effectively captures complex cross-modality correlations while modeling global contexts. Then, we collaborate an HCMITrans encoder with a modality-shared convolutional encoder to construct the dual-encoder architecture in the encoding stage, which can learn the abundant contextual information from global and local perspectives. Finally, in the decoding stage, we present a progressive hybrid context fusion (PHCF) decoder to progressively fuse local and global features extracted by the dual-encoder architecture, which utilizes the local-global context fusion (LGCF) module to efficiently alleviate the contextual discrepancy among the decoding features. RESULTS: Extensive experiments are conducted on two public and competitive glioma benchmark datasets, including the BraTS2020 dataset with 494 patients and the BraTS2021 dataset with 1251 patients. Results show that our proposed method outperforms existing Transformer-based and CNN-based methods using other multi-modal fusion strategies in our experiments. Specifically, the proposed HCMINet achieves state-of-the-art mean DSC values of 85.33% and 91.09% on the BraTS2020 online validation dataset and the BraTS2021 local testing dataset, respectively. CONCLUSIONS: Our proposed method can accurately and automatically segment glioma regions from multi-parametric MR images, which is beneficial for the quantitative analysis of brain gliomas and helpful for reducing the annotation burden of neuroradiologists.

RESUMEN

The classification problem concerning crisp-valued data has been well resolved. However, interval-valued data, where all of the observations' features are described by intervals, are also a common data type in real-world scenarios. For example, the data extracted by many measuring devices are not exact numbers but intervals. In this article, we focus on a highly challenging problem called learning from interval-valued data (LIND), where we aim to learn a classifier with high performance on interval-valued observations. First, we obtain the estimation error bound of the LIND problem based on the Rademacher complexity. Then, we give the theoretical analysis to show the strengths of multiview learning on classification problems, which inspires us to construct a new algorithm called multiview interval information extraction (Mv-IIE) approach for improving classification accuracy on interval-valued data. The experiment comparisons with several baselines on both synthetic and real-world datasets illustrate the superiority of the proposed framework in handling interval-valued data. Moreover, we describe an application of Mv-IIE that we can prevent data privacy leakage by transforming crisp-valued (raw) data into interval-valued data.

RESUMEN

Using cine magnetic resonance imaging (cine MRI) images to track cardiac motion helps users to analyze the myocardial strain, and is of great importance in clinical applications. At present, most of the automatic deep learning-based motion tracking methods compare two images without considering temporal information between MRI frames, which easily leads to the lack of consistency of the generated motion fields. Even though a small number of works take into account the temporal factor, they are usually computationally intensive or have limitations on image length. To solve this problem, we propose a bidirectional convolution neural network for motion tracking of cardiac cine MRI images. This network leverages convolutional blocks to extract spatial features from three-dimensional (3D) image registration pairs, and models the temporal relations through a bidirectional recurrent neural network to obtain the Lagrange motion field between the reference image and other images. Compared with previous pairwise registration methods, the proposed method can automatically learn spatiotemporal information from multiple images with fewer parameters. We evaluated our model on three public cardiac cine MRI datasets. The experimental results demonstrated that the proposed method can significantly improve the motion tracking accuracy. The average Dice coefficient between estimated segmentation and manual segmentation has reached almost 0.85 on the widely used Automatic Cardiac Diagnostic Challenge (ACDC) dataset.

Asunto(s)

RESUMEN

Objective. Sliding motion may occur between organs in anatomical regions due to respiratory motion and heart beating. This issue is often neglected in previous studies, resulting in poor image registration performance. A new approach is proposed to handle discontinuity at the boundary and improve registration accuracy.Approach. The proposed discontinuity-preserving regularization (DPR) term can maintain local discontinuities. It leverages the segmentation mask to find organ boundaries and then relaxes the displacement field constraints in these boundary regions. A weakly supervised method using mask dissimilarity loss (MDL) is also proposed. It employs a simple formula to calculate the similarity between the fixed image mask and the deformed moving image mask. These two strategies are added to the loss function during network training to guide the model better to update parameters. Furthermore, during inference time, no segmentation mask information is needed.Main results. Adding the proposed DPR term increases the Dice coefficients by 0.005, 0.009, and 0.081 for three existing registration neural networks CRNet, VoxelMorph, and ViT-V-Net, respectively. It also shows significant improvements in other metrics, including Hausdorff Distance and Average Surface Distance. All quantitative indicator results with MDL have been slightly improved within 1%. After applying these two regularization terms, the generated displacement field is more reasonable at the boundary, and the deformed moving image is closer to the fixed image.Significance. This study demonstrates that the proposed regularization terms can effectively handle discontinuities at the boundaries of organs and improve the accuracy of deep learning-based cardiac image registration methods. Besides, they are generic to be extended to other networks.

Asunto(s)

RESUMEN

BACKGROUND: Multi-modal learning is widely adopted to learn the latent complementary information between different modalities in multi-modal medical image segmentation tasks. Nevertheless, the traditional multi-modal learning methods require spatially well-aligned and paired multi-modal images for supervised training, which cannot leverage unpaired multi-modal images with spatial misalignment and modality discrepancy. For training accurate multi-modal segmentation networks using easily accessible and low-cost unpaired multi-modal images in clinical practice, unpaired multi-modal learning has received comprehensive attention recently. PURPOSE: Existing unpaired multi-modal learning methods usually focus on the intensity distribution gap but ignore the scale variation problem between different modalities. Besides, within existing methods, shared convolutional kernels are frequently employed to capture common patterns in all modalities, but they are typically inefficient at learning global contextual information. On the other hand, existing methods highly rely on a large number of labeled unpaired multi-modal scans for training, which ignores the practical scenario when labeled data is limited. To solve the above problems, we propose a modality-collaborative convolution and transformer hybrid network (MCTHNet) using semi-supervised learning for unpaired multi-modal segmentation with limited annotations, which not only collaboratively learns modality-specific and modality-invariant representations, but also could automatically leverage extensive unlabeled scans for improving performance. METHODS: We make three main contributions to the proposed method. First, to alleviate the intensity distribution gap and scale variation problems across modalities, we develop a modality-specific scale-aware convolution (MSSC) module that can adaptively adjust the receptive field sizes and feature normalization parameters according to the input. Secondly, we propose a modality-invariant vision transformer (MIViT) module as the shared bottleneck layer for all modalities, which implicitly incorporates convolution-like local operations with the global processing of transformers for learning generalizable modality-invariant representations. Third, we design a multi-modal cross pseudo supervision (MCPS) method for semi-supervised learning, which enforces the consistency between the pseudo segmentation maps generated by two perturbed networks to acquire abundant annotation information from unlabeled unpaired multi-modal scans. RESULTS: Extensive experiments are performed on two unpaired CT and MR segmentation datasets, including a cardiac substructure dataset derived from the MMWHS-2017 dataset and an abdominal multi-organ dataset consisting of the BTCV and CHAOS datasets. Experiment results show that our proposed method significantly outperforms other existing state-of-the-art methods under various labeling ratios, and achieves a comparable segmentation performance close to single-modal methods with fully labeled data by only leveraging a small portion of labeled data. Specifically, when the labeling ratio is 25%, our proposed method achieves overall mean DSC values of 78.56% and 76.18% in cardiac and abdominal segmentation, respectively, which significantly improves the average DSC value of two tasks by 12.84% compared to single-modal U-Net models. CONCLUSIONS: Our proposed method is beneficial for reducing the annotation burden of unpaired multi-modal medical images in clinical applications.

Asunto(s)

RESUMEN

Prostate cancer is one of the deadest cancers among human beings. To better diagnose the prostate cancer, prostate lesion segmentation becomes a very important work, but its progress is very slow due to the prostate lesions small in size, irregular in shape, and blurred in contour. Therefore, automatic prostate lesion segmentation from mp-MRI is a great significant work and a challenging task. However, the most existing multi-step segmentation methods based on voxel-level classification are time-consuming, may introduce errors in different steps and lead to error accumulation. To decrease the computation time, harness richer 3D spatial features, and fuse the multi-level contextual information of mp-MRI, we present an automatic segmentation method in which all steps are optimized conjointly as one step to form our end-to-end convolutional neural network. The proposed end-to-end network DMSA-V-Net consists of two parts: (1) a 3D V-Net is used as the backbone network, it is the first attempt in employing 3D convolutional neural network for CS prostate lesion segmentation, (2) a deep multi-scale attention mechanism is introduced into the 3D V-Net which can highly focus on the ROI while suppressing the redundant background. As a merit, the attention can adaptively re-align the context information between the feature maps at different scales and the saliency maps in high-levels. We performed experiments based on five cross-fold validation with data including 97 patients. The results show that the Dice and sensitivity are 0.7014 and 0.8652 respectively, which demonstrates that our segmentation approach is more significant and accurate compared to other methods.

Asunto(s)

RESUMEN

PURPOSE: Automatic liver segmentation from computed tomography (CT) images is an essential preprocessing step for computer-aided diagnosis of liver diseases. However, due to the large differences in liver shapes, low-contrast to adjacent tissues, and existence of tumors or other abnormalities, liver segmentation has been very challenging. This study presents an accurate and fast liver segmentation method based on a novel probabilistic active contour (PAC) model and its fast global minimization scheme (3D-FGMPAC), which is explainable as compared with deep learning methods. METHODS: The proposed method first constructs a slice-indexed-histogram to localize the volume of interest (VOI) and estimate the probability that a voxel belongs to the liver according its intensity. The probabilistic image would be used to initialize the 3D PAC model. Secondly, a new contour indicator function, which is a component of the model, is produced by combining the gradient-based edge detection and Hessian-matrix-based surface detection. Then, a fast numerical scheme derived for the 3D PAC model is performed to evolve the initial probabilistic image into the global minimizer of the model, which is a smoothed probabilistic image showing a distinctly highlighted liver. Next, a simple region-growing strategy is applied to extract the whole liver mask from the smoothed probabilistic image. Finally, a B-spline surface is constructed to fit the patch of the rib cage to prevent possible leakage into adjacent intercostal tissues. RESULTS: The proposed method is evaluated on two public datasets. The average Dice score, volume overlap error, volume difference, symmetric surface distance and volume processing time are 0.96, 7.35%, 0.02%, 1.17 mm and 19.8 s for the Sliver07 dataset, and 0.95, 8.89%, - 0.02 % $-0.02\%$ , 1.45 mm and 23.08 s for the 3Dircadb dataset, respectively. CONCLUSIONS: The proposed fully-automatic approach can effectively segment the liver from low-contrast and complex backgrounds. The quantitative and qualitative results demonstrate that the proposed segmentation method outperforms state-of-the-art traditional automatic liver segmentation algorithms and achieves very competitive performance compared with recent deep leaning-based methods.

Asunto(s)

RESUMEN

BACKGROUND Non-small cell lung cancer (NSCLC) is one of the leading causes of cancer-related death in the world and its poor prognosis is a major concern. Periostin was found to be associated with the prognosis of NSCLC. However, the research results were inconsistent. This meta-analysis evaluated the correlation between periostin expression and the prognosis of NSCLC. MATERIAL AND METHODS A meta-analysis was performed on data acquired from PubMed, EMBASE, the Cochrane Library, China National Knowledge Infrastructure (CNKI), and Wanfang Database from inception to 18 June 2022. Published and unpublished studies investigating the correlation between periostin expression and the prognosis of NSCLC were included in this meta-analysis. Eligible studies reported at least 1 of the following clinical outcome measures: overall survival, progression-free survival, cancer-specific survival, relapse-free survival, disease-free survival, or other clinical parameters of prognosis. Pooled hazard ratios (HR) with 95% confidence interval (CI) were calculated using the random-effects model. Sensitivity and subgroup analyses and assessment of publication bias were also conducted. RESULTS This meta-analysis enrolled 2504 NSCLC cases from 12 eligible studies. The hazard ratio for the overall survival was 1.761 (95% CI: 1.022-3.033, P=0.041). Heterogeneity was significant among the studies, but publication bias was lacking. Subgroup analyses were performed based on different issues, such as districts, antibodies and methods for periostin detection. CONCLUSIONS Overexpression of periostin is a negative prognostic factor and is associated with worse overall survival (OS) in NSCLC patients. Periostin may serve as a prognostic biomarker for NSCLC patients.

Asunto(s)

RESUMEN

The theoretical analysis of multiclass classification has proved that the existing multiclass classification methods can train a classifier with high classification accuracy on the test set, when the instances are precise in the training and test sets with same distribution and enough instances can be collected in the training set. However, one limitation with multiclass classification has not been solved: how to improve the classification accuracy of multiclass classification problems when only imprecise observations are available. Hence, in this article, we propose a novel framework to address a new realistic problem called multiclass classification with imprecise observations (MCIMO), where we need to train a classifier with fuzzy-feature observations. First, we give the theoretical analysis of the MCIMO problem based on fuzzy Rademacher complexity. Then, two practical algorithms based on support vector machine and neural networks are constructed to solve the proposed new problem. The experiments on both synthetic and real-world datasets verify the rationality of our theoretical analysis and the efficacy of the proposed algorithms.

RESUMEN

SHP2, a protein tyrosine phosphatase, plays a critical role in fully activating oncogenic signaling pathways such as Ras/MAPK downstream of cell surface tyrosine receptors (e.g., EGFR), which are often activated in human cancers, and thus has emerged as an attractive cancer therapeutic target. This study focused on evaluating the therapeutic potential of the novel SHP2 degrader, SHP2-D26 (D26), either alone or in combination, against non-small cell lung cancer (NSCLC) cells. While all tested NSCLC cell lines responded to D26 with IC50s of < 8 µM, a few cell lines (4/14) were much more sensitive than others with IC50s of ≤ 4 µM. There was no clear association between basal levels of SHP2 and cell sensitivities to D26. Moreover, D26 rapidly and potently decreased SHP2 levels in different NSCLC cell lines in a sustained way regardless of cell sensitivities to D26, suggesting that additional factors may impact cell response to D26. We noted that suppression of p70S6K/S6, but not ERK1/2, was associated with cell responses to D26. In the sensitive cell lines, D26 effectively increased Bim levels while decreasing Mcl-1 levels accompanied with the induction of apoptosis. When combined with the third generation EGFR inhibitor, osimertinib (AZD9291), synergistic effects on decreasing the survival of different osimertinib-resistant cell lines were observed with enhanced induction of apoptosis. Although D26 alone exerted moderate inhibition of the growth of NSCLC xenografts, the combination of osimertinib and D26 effectively inhibited the growth of osimertinib-resistant xenografts, suggesting promising efficacy in overcoming acquired resistance to osimertinib.

Asunto(s)

RESUMEN

Lung cancer remains the leading cause of cancer deaths worldwide despite advances in knowledge in cancer biology and options of various targeted therapies. Efforts in identifying innovative and effective therapies are still highly appreciated. Targeting bromodomain and extra terminal (BET) proteins that function as epigenetic readers and master transcription coactivators is now a potential cancer therapeutic strategy. The current study evaluates the therapeutic efficacies of the novel BET degrader, QCA570, in lung cancer and explores its underlying mechanisms. QCA570 at low nanomolar ranges effectively decreased the survival of a panel of human lung cancer cell lines with induction of apoptosis in vitro. As expected, it potently induced degradation of BET proteins including BRD4, BRD3 and BRD2. Moreover, it potently decreased Mcl-1 levels due to transcriptional suppression and protein degradation; this event is critical for mediating apoptosis induced by QCA570. Moreover, QCA570 synergized with osimertinib in suppressing the growth of osimertinib-resistant cells in vitro and in vivo, suggesting potential in overcoming acquired resistance to osimertinib. These preclinical findings support the potential of QCA570 in treatment of lung cancer either as a single agent or in combination with others.

RESUMEN

This paper presents an automatic Couinaud segmentation method based on deep learning of key point detection. Assuming that the liver mask has been extracted, the proposed method can automatically divide the liver into eight anatomical segments according to Couinaud's definition. Firstly, an attentive residual hourglass-based cascaded network (ARH-CNet) is proposed to identify six key bifurcation points of the hepatic vascular system. Subsequently, the detected points are used to derive the planes that divide the liver into different functional units, and the caudate lobe is segmented slice-by-slice based on the circles defined by the detected points. We comprehensively evaluate our method on a public dataset from MICCAI 2018. Experiments firstly demonstrate the effectiveness of our landmark detection network ARH-CNet, which is superior to that of two baseline methods, also robust to noisy data. The average error distance of all predicted key points is 4.68 ± 3.17 mm, and the average accuracy of all points is 90% with the detection error distance of 7 mm. We also verify that summation of the corresponding heat-maps can improve the accuracy of point localization. Furthermore, the overlap-based accuracy and the Dice score of our landmark-derived Couinaud segmentation are respectively 91% and 84%, which are better than the performance of the direct segmentation approach and the traditional plane-based method, thus our method can be regarded as a good alternative for automatic Couinaud segmentation.

Asunto(s)

RESUMEN

Treatment of EGFR-mutant non-small cell lung cancer (NSCLC) with mutation-selective third-generation EGFR-tyrosine kinase inhibitors (EGFR-TKIs) such as osimertinib has achieved remarkable success in the clinic. However, the immediate challenge is the emergence of acquired resistance, limiting the long-term remission of patients. This study suggests a novel strategy to overcome acquired resistance to osimertinib and other third-generation EGFR-TKIs through directly targeting the intrinsic apoptotic pathway. We found that osimertinib, when combined with Mcl-1 inhibition or Bax activation, synergistically decreased the survival of different osimertinib-resistant cell lines, enhanced the induction of intrinsic apoptosis, and inhibited the growth of osimertinib-resistant tumor in vivo. Interestingly, the triple-combination of osimertinib with Mcl-1 inhibition and Bax activation exhibited the most potent activity in decreasing the survival and inducing apoptosis of osimertinib-resistant cells and in suppressing the growth of osimertinib-resistant tumors. These effects were associated with increased activation of the intrinsic apoptotic pathway evidenced by augmented mitochondrial cytochrome C and Smac release. Hence, this study convincingly demonstrates a novel strategy for overcoming acquired resistance to osimertinib and other 3rd generation EGFR-TKIs by targeting activation of the intrinsic apoptotic pathway through Mcl-1 inhibition, Bax activation or both, warranting further clinical validation of this strategy.

Asunto(s)

RESUMEN

Background: The tumor microenvironment evidently affects treatment response and clinical outcome. This study aims to construct a tumor microenvironment-based crosstalk between immunotherapy and epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI) in lung adenocarcinoma. Methods: We used ESTIMATE algorithm to calculate stromal and immune scores. Differentially expressed genes (DEGs) were extracted based on the comprehensive analysis of immune score groups and EGFR-TKI resistance samples. The independent prognostic value of the five selected genes was assessed by univariate/multivariate Cox regression analysis, survival analysis and the receiver operating characteristic (ROC) curve. Correlation analysis was performed using Spearman's rho value through TIMER 2.0. Results: The Kaplan-Meier survival curve show that patients with higher immune scores have significantly better overall survival. We identified 1328 DEGs from immune score groups and 806 DEGs from the EGFR-TKI resistance cohort GSE123066. A total of 19 co-regulated genes were found, and the Cox regression model produced a significant statistical prognosis for five genes (CENPF, CYSLTR1, GLDN, PIGR and SCGB3A1). Multivariate Cox regression analysis showed that the selected five gene signatures could be used as independent prognostic indicators. Furthermore, GSEA and correlation analysis demonstrated that CENPF was positively correlated to the signalling pathway which related to EGFR-TKI resistance and the well-known bypass gene. Conclusion: Our findings indicate that CENPF, CYSLTR1, GLDN, PIGR and SCGB3A1 are independent prognostic biomarkers associated with acquired EGFR-TKI resistance and tumor immune cell infiltration in lung adenocarcinoma, and CENPF may be a potential target that can improve immunotherapy efficacy and overcome the acquired EGFR-TKI resistance.

RESUMEN

Brain tissue segmentation in multi-modal magnetic resonance (MR) images is significant for the clinical diagnosis of brain diseases. Due to blurred boundaries, low contrast, and intricate anatomical relationships between brain tissue regions, automatic brain tissue segmentation without prior knowledge is still challenging. This paper presents a novel 3D fully convolutional network (FCN) for brain tissue segmentation, called APRNet. In this network, we first propose a 3D anisotropic pyramidal convolutional reversible residual sequence (3DAPC-RRS) module to integrate the intra-slice information with the inter-slice information without significant memory consumption; secondly, we design a multi-modal cross-dimension attention (MCDA) module to automatically capture the effective information in each dimension of multi-modal images; then, we apply 3DAPC-RRS modules and MCDA modules to a 3D FCN with multiple encoded streams and one decoded stream for constituting the overall architecture of APRNet. We evaluated APRNet on two benchmark challenges, namely MRBrainS13 and iSeg-2017. The experimental results show that APRNet yields state-of-the-art segmentation results on both benchmark challenge datasets and achieves the best segmentation performance on the cerebrospinal fluid region. Compared with other methods, our proposed approach exploits the complementary information of different modalities to segment brain tissue regions in both adult and infant MR images, and it achieves the average Dice coefficient of 87.22% and 93.03% on the MRBrainS13 and iSeg-2017 testing data, respectively. The proposed method is beneficial for quantitative brain analysis in the clinical study, and our code is made publicly available.

Asunto(s)

RESUMEN

BACKGROUND: The preoperative systemic immune-inflammation index (SII) is correlated with prognosis in several malignancies. The aim of this study was to investigate the prognosis value of SII in patients with resected breast cancer. MATERIALS AND METHODS: A total of 784 breast cancer patients who underwent surgical resection were consecutively investigated. The optimal cutoff value of SII was evaluated using the receiver operating characteristic (ROC) curve. The collection of SII with clinicopathological characteristic and prognosis was further evaluated. RESULTS: The optimal cutoff value for SII in the prediction of survival was 514 according to ROC curve analysis. A high SII was significantly correlated with younger age (P = 0.037), PR status (P < 0.001), and HER2 status (P = 0.035). Univariate analysis revealed that SII (P < 0.001), T-stage (P < 0.001), lymph node involvement post-surgery (P = 0.024), and histological grade (P < 0.001) were significantly related to DFS, and SII (P < 0.001), T-stage (P = 0.003), lymph node involvement post-surgery (P = 0.006), and histological grade (P < 0.001) were significantly associated with OS. In multivariate analysis, a high SII was an independent worse prognostic factor for DFS (HR, 4.530; 95% CI, 3.279-6.258; P < 0.001) and OS (HR, 3.825; 95% CI, 2.594-5.640; P < 0.001) in all the enrolled patients. Furthermore, subgroup analysis of molecular subtype revealed that SII was significantly associated with prognosis in all subtypes. CONCLUSION: Preoperative SII is a simple and useful prognostic factor for predicting long-term outcomes for breast cancer patients undergoing surgery.

RESUMEN

PURPOSE: Deformable image registration (DIR) of lung four-dimensional computed tomography (4DCT) plays a vital role in a wide range of clinical applications. Most of the existing deep learning-based lung 4DCT DIR methods focus on pairwise registration which aims to register two images with large deformation. However, the temporal continuities of deformation fields between phases are ignored. This paper proposes a fast and accurate deep learning-based lung 4DCT DIR approach that leverages the temporal component of 4DCT images. METHODS: We present Lung-CRNet, an end-to-end convolutional recurrent registration neural network for lung 4DCT images and reformulate 4DCT DIR as a spatiotemporal sequence predicting problem in which the input is a sequence of three-dimensional computed tomography images from the inspiratory phase to the expiratory phase in a respiratory cycle. The first phase in the sequence is selected as the only reference image and the rest as moving images. Multiple convolutional gated recurrent units (ConvGRUs) are stacked to capture the temporal clues between images. The proposed network is trained in an unsupervised way using a spatial transformer layer. During inference, Lung-CRNet is able to yield the respective displacement field for each reference-moving image pair in the input sequence. RESULTS: We have trained the proposed network using a publicly available lung 4DCT dataset and evaluated performance on the widely used the DIR-Lab dataset. The mean and standard deviation of target registration error are 1.56 ± 1.05 mm on the DIR-Lab dataset. The computation time for each forward prediction is less than 1 s on average. CONCLUSIONS: The proposed Lung-CRNet is comparable to the existing state-of-the-art deep learning-based 4DCT DIR methods in both accuracy and speed. Additionally, the architecture of Lung-CRNet can be generalized to suit other groupwise registration tasks which align multiple images simultaneously.

Asunto(s)

RESUMEN

The occurrence of ureteral metastasis from distant primary tumors is uncommon, and appears to be especially rare when it originates from the lungs. In the case presented here, a patient with lumbago and left hydronephrosis was diagnosed with left ureteral metastasis of pulmonary adenocarcinoma after a CT-guided percutaneous transthoracic needle biopsy of the lung and retroperitoneal laparoscopic left nephroureterectomy. He accepted the targeted therapy because the lung tumor epidermal growth factor receptor mutation (exon19 deletion) was positive, and preoperative staging of lung adenocarcinoma was stage IVA. After an 8-month follow-up, he is still alive and well, with no local recurrence or distant metastases. The therapy outcome assessment is stable disease. Although rare, our case has demonstrated that pulmonary adenocarcinoma has the possibility of metastasizing to the ureter, a risk that should be considered in some lung cancer patients.

Asunto(s)