Lung Segmentation Research Articles

3D Segmentation of Whole Lung and Metastatic Lung Nodules Using Adaptive Region Growing and Shape-based Morphology.

Early diagnosis of primary and metastatic lung nodules is critical for effective therapeutic planning. Manual delineation of lung nodules is not time-efficient and is prone to human error as well as interobserver and intraobserver variability. This study aimed to address the unmet need for an open-source computer-aided detection (CAD) system for 3D segmentation of lung and metastatic lung nodules along with radiomic feature extraction. The proposed adaptive region-growing-based lung nodule segmentation (RGLNS) tool was developed in-house, requiring only manual input to select a seed point within the nodule on computed tomography (CT) images. A total of 230 CT scans from 100 patients with sarcomas were screened. Lung nodules were present in 200 CT scans, which were further analyzed. The accuracy of the lung and nodule segmentation was evaluated qualitatively using a 5-point Likert scale (uninterpretable: 1; poor: 2; fair: 3; good: 4; excellent: 5) and quantitatively using the Dice coefficient and Jaccard index. A total of 200 CT scans comprising 12,000 CT slices were analyzed, among which 786 lung nodules were identified. Quantitative lung segmentation accuracies (n=2400 slices) yielded a Dice coefficient of 0.92±0.06 and a Jaccard index of 0.85±0.05. Qualitative scores (n=9600 slices) for lung boundary correction (4.56±1.18) and inclusion of pulmonary vessels (4.75±0.72) were rated as good to excellent. Quantitative nodule segmentation (n=142 nodules) accuracies were as follows: dice coefficient=0.92±0.03, 0.88±0.04, 0.86±0.03, 0.85±0.03, 084±0.04 and Jaccard index=0.84±0.03, 0.81±0.04, 0.78±0.04, 0.78±0.02, 0.76±0.04 for solitary (n=73), juxtapleural (n=32), juxtavascular (n=28), fissure-attached (n=6), and ground-glass (n=6) nodules, respectively. Qualitative scores (n=644 nodules) for nodule-boundary were good to excellent [solitary (n=342): 4.97±0.15; juxtapleural (n=155): 4.45±0.60; juxtavascular (n=127): 4.40±0.65; fissure-attached (n=9): 4.40±0.70; ground-glass (n=11): 4.25±0.75] and for exclusion of pulmonary vessels/pleura from nodules were good [juxtapleural (n=155): 4.10±0.66; juxtavascular (n=127): 4.08±0.64; fissure-attached (n=9): 4.30±0.67]. The proposed semiautomated CAD system, RGLNS, requiring minimal manual input, demonstrated robust, and promising segmentation results for the whole lung and various types of metastatic lung nodules.

Staged Approach: The Role of Delayed Repair Following Complete Unifocalization of Major Aortopulmonary Collateral Arteries with Ventricular Septal Defect and Pulmonary Atresia.

The presentation of pulmonary vasculature in pulmonary atresia with ventricular septal defect and major aortopulmonary collateral arteries (PA/VSD/MAPCA) is highly variable-as is the number, size and position of the MAPCAs and their relationship with the native pulmonary artery system. The priority in the management of this disease should be attaining timely and complete unifocalization, as opposed to single-stage full repair in every case. The merit of early unifocalization is that it secures the pulmonary vascular bed by (a) avoiding loss of lung segments from progressive stenosis/atresia of MAPCA origins, (b) preventing lung injury from high pressure/flow in areas fed by large, unobstructed MAPCAs, and (c) restoring central continuity of the pulmonary vasculature. Furthermore, there are a small but important group of patients with poorly developed vessels (about 10%-15% of the population) and/or diminutive native pulmonary artery vasculature that require initial shunt procedures to promote rehabilitation and growth of vessels before unifocalization can be attempted. During unifocalization, patients not suitable for single stage repair can be identified by intraoperative flow studies and can be successfully managed with staged strategies that provide time for growth and reinterventions on the pulmonary vasculature. Over 85% of patients can achieve unifocalization. Deferring closure of the VSD to a subsequent procedure is safe and these cases have similar survival to primary repair. Some patients (15%-20%) may never achieve VSD closure with this strategy but can still maintain a good quality of life with a restrictive right ventricular to pulmonary artery conduit and open VSD.

SVMVGGNet-16: A Novel Machine and Deep Learning Based Approaches for Lung Cancer Detection Using Combined SVM and VGGNet-16.

Lung cancer remains a leading cause of cancer-related mortality worldwide, necessitating early and accurate detection methods. Our study aims to enhance lung cancer detection by integrating VGGNet-16 form of Convolutional Neural Networks (CNNs) and Support Vector Machines (SVM) into a hybrid model (SVMVGGNet-16), leveraging the strengths of both models for high accuracy and reliability in classifying lung cancer types in different 4 classes such as adenocarcinoma (ADC), large cell carcinoma (LCC), Normal, and squamous cell carcinoma (SCC). Using the LIDC-IDRI dataset, we pre-processed images with a median filter and histogram equalization, segmented lung tumors through thresholding and edge detection, and extracted geometric features such as area, perimeter, eccentricity, compactness, and circularity. VGGNet-16 and SVM employed for feature extraction and classification, respectively. Performance matrices were evaluated using accuracy, AUC, recall, precision, and F1-score. Both VGGNet-16 and SVM underwent comparative analysis during the training, validation, and testing phases. The SVMVGGNet-16 model outperformed both, with a training accuracy (97.22%), AUC (99.42%), recall (94.22%), precision (95.28%), and F1- score (94.68%). In testing, our SVMVGGNet-16 model maintained high accuracy (96.72%), with an AUC (96.87%), recall (84.67%), precision (87.40%), and F1-score (85.73%). Our experimental results demonstrate the potential of SVMVGGNet-16 in improving diagnostic performance, leading to earlier detection and better treatment outcomes. Future work includes refining the model, expanding datasets, conducting clinical trials, and integrating the system into clinical practice to ensure practical usability.

Usefulness of bronchial sputum aspirate specimens for the diagnosis of Non-tuberculous mycobacterial pulmonary disease.

The usefulness of bronchoscopy for the diagnosis of NTM pulmonary disease (NTM-PD) has been reported. However, performing bronchoscopy for aspirated sputum and airway secretion specimens (sputum aspirate specimens) in the region extending from the trachea down to the orifice of each segmental bronchus has been poorly documented. We evaluated the diagnostic yield of sputum aspirate specimens collected from the central airway using bronchoscopy. We reviewed the medical records of 114 patients with clinically suspected NTM-PD on chest computed tomography (CT) who underwent bronchoscopy. Patients for whom sputum aspirate and bronchial washing specimens were obtained using a thin bronchoscope were included. Positive culture acid-fast bacilli yield was compared between sputum aspirate specimens obtained during bronchial luminal examination and bronchial washing specimens obtained by wedging the tip of the bronchoscope into bronchi with the most affected lung segment. Among the 69 NTM culture-positive patients, culture positivity yield for sputum aspirate and bronchial washing specimens was 94.2% (65/69) and 88.4% (61/69), respectively. While 8 (11.6%) patients were culture-positive for only sputum aspirate specimens, 4 (5.8%) patients were culture-positive for only bronchial washing specimens. Comparison of chest CT findings and bronchoscopy procedure showed no difference between patients with positive cultures from both sputum aspirate and bronchial washing specimens and those with positive cultures on only one of either specimen. In diagnosing NTM-PD using thin bronchoscopy, the diagnostic yield of sputum aspirate specimens from the central airway was comparable to that of bronchial washing specimens obtained from the peripheral airway.

Automated Deep Learning-Based Detection and Segmentation of Lung Tumors at CT.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Background Detection and segmentation of lung tumors on CT scans are critical for monitoring cancer progression, evaluating treatment responses, and planning radiation therapy; however, manual delineation is labor-intensive and subject to physician variability. Purpose To develop and evaluate an ensemble deep learning model for automating identification and segmentation of lung tumors on CT scans. Materials and Methods A retrospective study was conducted between July 2019 and November 2024 using a large dataset of CT simulation scans and clinical lung tumor segmentations from radiotherapy plans. This dataset was used to train a 3D U-Net-based, image-multiresolution ensemble model to detect and segment lung tumors on CT scans. Model performance was evaluated on internal and external test sets composed of CT simulation scans and lung tumor segmentations from two affiliated medical centers, including single primary and metastatic lung tumors. Performance metrics included sensitivity, specificity, false positive rate, and Dice similarity coefficient (DSC). Model-predicted tumor volumes were compared with physician-delineated volumes. Group comparisons were made with Wilcoxon signed-rank test or one-way ANOVA. P < 0.05 indicated statistical significance. Results The model, trained on 1,504 CT scans with clinical lung tumor segmentations, achieved 92% sensitivity (92/100) and 82% specificity (41/50) in detecting lung tumors on the combined 150-CT scan test set. For a subset of 100 CT scans with a single lung tumor each, the model achieved a median model-physician DSC of 0.77 (IQR: 0.65-0.83) and an interphysician DSC of 0.80 (IQR: 0.72-0.86). Segmentation time was shorter for the model than for physicians (mean 76.6 vs. 166.1-187.7 seconds; p<0.001). Conclusion Routinely collected radiotherapy data were useful for model training. The key strengths of the model include a 3D U-Net ensemble approach for balancing volumetric context with resolution, robust tumor detection and segmentation performance, and the ability to generalize to an external site.

Comparative Analysis of Edge Detection Operators Using a Threshold Estimation Approach on Medical Noisy Images with Different Complexities

The manuscript conducts a comparative analysis to assess the impact of noise on medical images using a proposed threshold value estimation approach. It applies an innovative method for edge detection on images of varying complexity, considering different noise types and concentrations of noise. Five edges are evaluated on images with low, medium, and high detail levels. This study focuses on medical images from three distinct datasets: retinal images, brain tumor segmentation, and lung segmentation from CT scans. The importance of noise analysis is heightened in medical imaging, as noise can significantly obscure the critical features and potentially lead to misdiagnoses. Images are categorized based on the complexity, providing a multidimensional view of noise’s effect on edge detection. The algorithm utilized the grid search (GS) method and random search with nine values (RS9). The results demonstrate the effectiveness of the proposed approach, especially when using the Canny operator, across diverse noise types and intensities. Laplace operators are most affected by noise, yet significant improvements are observed with the new approach, particularly when using the grid search method. The obtained results are compared with the most popular techniques for edge detection using deep learning like AlexNet, ResNet, VGGNet, MobileNetv2, and Inceptionv3. The paper presents the results via graphs and edge images, along with a detailed analysis of each operator’s performance with noisy images using the proposed approach.

Safety and efficacy of anatomical tunneling technique for precise lung segment resection in complex anatomical settings

BackgroundThoracoscopic segmentectomy is the main surgical method for the treatment of earlylung cancer. With the promotion of technology and increasingly accurate criteria for lung subsegments, lung nodules with complex positions involving intersegmental and multisegments have become technical bottlenecks. This study aimed to verify whether seeking anatomical conditions for creating a fissure by tunneling techniques with precise resection of lung segments could solve this bottleneck problem.MethodsThe clinical data of patients with lung nodules ≤ 2 cm located in the complex position in the Department of Thoracic Surgery of Jiangsu Provincial People's Hospital from January 2019 to August 2023 were collected. Date analyzed the characteristics of patients who underwent seeking anatomical conditions for creating a fissure by tunneling techniques with precise resection of lung segments (segment group) at complex setting and compared the surgical outcomes and complications between these lobectomy patients (lobectomy group) at similar locations.ResultsA total of 22 patients were included segment group and 47 patients were included lobectomy group. Except for the depth ratio or tumor size or consolidation tumor ratio (CTR), there were no significant differences in the other baseline data between the two groups. All patients in segment group received a satisfactory surgical margin. Compared to the lobectomy group, surgical outcomes were better in segment group (p < 0.05 for postoperative hospital stay and the counts of resected subsegments).ConclusionSeeking anatomical conditions for creating a fissure by tunneling techniques is a promising technique for performing precise resection of lung segments with a safe resection margin for patients with lung nodules at complex positions involving multiple segments. It can be used as a precise resection of lung segments technique.

Leveraging anatomical constraints with uncertainty for pneumothorax segmentation.

Pneumothorax is a medical emergency caused by the abnormal accumulation of air in the pleural space-the potential space between the lungs and chest wall. On 2D chest radiographs, pneumothorax occurs within the thoracic cavity and outside of the mediastinum, and we refer to this area as "lung + space." While deep learning (DL) has increasingly been utilized to segment pneumothorax lesions in chest radiographs, many existing DL models employ an end-to-end approach. These models directly map chest radiographs to clinician-annotated lesion areas, often neglecting the vital domain knowledge that pneumothorax is inherently location-sensitive. We propose a novel approach that incorporates the lung + space as a constraint during DL model training for pneumothorax segmentation on 2D chest radiographs. To circumvent the need for additional annotations and to prevent potential label leakage on the target task, our method utilizes external datasets and an auxiliary task of lung segmentation. This approach generates a specific constraint of lung + space for each chest radiograph. Furthermore, we have incorporated a discriminator to eliminate unreliable constraints caused by the domain shift between the auxiliary and target datasets. Our results demonstrated considerable improvements, with average performance gains of 4.6%, 3.6%, and 3.3% regarding intersection over union, dice similarity coefficient, and Hausdorff distance. These results were consistent across six baseline models built on three architectures (U-Net, LinkNet, or PSPNet) and two backbones (VGG-11 or MobileOne-S0). We further conducted an ablation study to evaluate the contribution of each component in the proposed method and undertook several robustness studies on hyper-parameter selection to validate the stability of our method. The integration of domain knowledge in DL models for medical applications has often been underemphasized. Our research underscores the significance of incorporating medical domain knowledge about the location-specific nature of pneumothorax to enhance DL-based lesion segmentation and further bolster clinicians' trust in DL tools. Beyond pneumothorax, our approach is promising for other thoracic conditions that possess location-relevant characteristics.

Comparing Different Data Partitioning Strategies for Segmenting Areas Affected by COVID-19 in CT Scans.

According to the World Health Organization, the gold standard for diagnosing COVID-19 is the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. However, to confirm the diagnosis in patients who have negative results but still show symptoms, imaging tests, especially computed tomography (CT), are used. In this study, using convolutional neural networks, we compared the following topics using manual and automatic lung segmentation methods: (1) the performance of an automatic segmentation of COVID-19 areas using two strategies for data partitioning, CT scans, and slice strategies; (2) the performance of an automatic segmentation method of COVID-19 when there was interobserver agreement between two groups of radiologists; and (3) the performance of the area affected by COVID-19. Two datasets and two deep neural network architectures are used to evaluate the automatic segmentation of lungs and COVID-19 areas. The performance of the U-Net architecture is compared with the performance of a new architecture proposed by the research group. With automatic lung segmentation, the Dice metrics for the segmentation of the COVID-19 area were 73.01 ± 9.47% and 84.66 ± 5.41% for the CT-scan strategy and slice strategy, respectively. With manual lung segmentation, the Dice metrics for the automatic segmentation of COVID-19 were 74.47 ± 9.94% and 85.35 ± 5.41% for the CT-scan and the slice strategy, respectively. The main conclusions were as follows: COVID-19 segmentation was slightly better for the slice strategy than for the CT-scan strategy; a comparison of the performance of the automatic COVID-19 segmentation and the interobserver agreement, in a group of 7 CT scans, revealed that there was no statistically significant difference between any metric.

New Approaches to AI Methods for Screening Cardiomegaly on Chest Radiographs

Background: Cardiothoracic ratio (CTR) and transverse cardiac diameter (TCD) are parameters that are used to assess cardiac size on chest radiographs (CXRs). We aimed to investigate the performance and efficiency of artificial intelligence (AI) in screening for cardiomegaly on CXRs. Methods: The U-net architecture was designed for lung and heart segmentation. The CTR and TCD were then calculated using these labels and a mathematical algorithm. For the training set, we retrospectively included 65 randomly selected patients who underwent CXRs, while for the testing set, we chose 50 patients who underwent cardiac magnetic resonance (CMR) imaging and had available CXRs in the medical documentation. Results: Using U-net for the training set, the Dice coefficient for the lung was 0.984 ± 0.003 (min. 0.977), while for the heart it was 0.983 ± 0.004 (min. 0.972). For the testing set, the Dice coefficient for the lung was 0.970 ± 0.012 (min. 0.926), while for the heart it was 0.950 ± 0.021 (min. 0.871). The mean CTR and TCD measurements were slightly greater when calculated from either manual or automated segmentation than when manually read. Receiver operating characteristic analyses showed that both the CTR and TCD measurements calculated from either manual or automated segmentation, or when manually read, were good predictors of cardiomegaly diagnosed in CMR. However, McNemar tests have shown that diagnoses made with TCD, rather than CTR, were more consistent with CMR diagnoses. According to a different definition of cardiomegaly based on CMR imaging, accuracy for CTR measurements ranged from 62.0 to 74.0% for automatic segmentation (for TCD it ranged from 64.0 to 72.0%). Conclusion: The use of AI may optimize the screening process for cardiomegaly on CXRs. Future studies should focus on improving the accuracy of AI algorithms and on assessing the usefulness both of CTR and TCD measurements in screening for cardiomegaly.

Fully automatic quantification of pulmonary fat attenuation volume by CT: an exploratory pilot study

BackgroundNon-malignant chronic diseases remain a major public health concern. Given the alterations in lipid metabolism and deposition in the lung and its association with fibrotic interstitial lung disease (fILD) and chronic obstructive pulmonary disease (COPD), this study aimed to detect those alterations using computed tomography (CT)-based analysis of pulmonary fat attenuation volume (CTpfav).MethodsThis observational retrospective single-center study involved 716 chest CT scans from three subcohorts: control (n = 279), COPD (n = 283), and fILD (n = 154). Fully automated quantification of CTpfav based on lung segmentation and HU-thresholding. The pulmonary fat index (PFI) was derived by normalizing CTpfav to the CT lung volume. Statistical analyses were conducted using Kruskal–Wallis with Dunn’s post hoc tests.ResultsPatients with fILDs demonstrated a significant increase in CTpfav (median 71.0 mL, interquartile range [IQR] 59.7 mL, p < 0.001) and PFI (median 1.9%, IQR 2.4%, p < 0.001) when compared to the control group (CTpfav median 43.6 mL, IQR 16.94 mL; PFI median 0.9%, IQR 0.5%). In contrast, individuals with COPD exhibited significantly reduced CTpfav (median 36.2 mL, IQR 11.4 mL, p < 0.001) and PFI (median 0.5%, IQR 0.2%, p < 0.001).ConclusionThe study underscores the potential of CTpfav and PFI as imaging biomarkers for detecting changes in lung lipid metabolism and deposition and demonstrates a possibility of tracking these alterations in patients with COPD and ILDs. Further research is needed to validate these findings and explore the clinical relevance of CTpfav and PFI in lung disease management.Relevance statementThis study introduces a fully automated method for quantifying CTpfav, potentially establishing it as a new imaging biomarker for chronic lung diseases.Key PointsThis retrospective observational study employed an open-source, automated algorithm for the quantification of CT pulmonary fat attenuation volume (CTpfav).Patients with fibrotic interstitial lung disease (fILD) showed a significantly higher CTpfav and pulmonary fat index (PFI), i.e., CTpfav/CT lung volume, compared to a control group.Patients with chronic obstructive pulmonary disease (COPD) showed significantly lower CTpfav and PFI compared to the control group.CTpfav and PFI may each serve as imaging biomarkers for various lung diseases and warrant further investigation.Graphical

Indocyanine Green-Guided Pulmonary Resection for Lung Cancer With Anomalous Systemic Arterial Supply to the Basal Segment.

A 78-year-old male who was undergoing treatment for diabetes was referred to our department after a chest X-ray revealed an abnormal shadow in the left upper lung field. A chest contrast-enhanced CT showed a tumor in the left upper lobe and a cystic lesion in the left lower lobe. Two aberrant arteries branching from the aorta were identified near the cyst. The patient was diagnosed with lung cancer and anomalous systemic arterial supply to the basal segment of the left lung (ABLL), necessitating surgical intervention. Thoracoscopic surgery was performed, with the left upper segmentectomy guided by Indocyanine green (ICG) to facilitate precise intersegmental plane identification. The two aberrant arteries were resected, and the perfusion area supplied by these arteries was excised using repeated ICG intravenous injection. This case of lung cancer with ABLL demonstrates that the repeated use of ICG can enable not only a precise upper segmentectomy but also accurate visualization and resection of a perfusion area supplied by aberrant arteries.

Major Aortopulmonary Collateral Arteries and Their Effects on Perioperative Parameters and Mortality of Children with Tetralogy of Fallot: A Case-control Study.

Inadequate pulmonary blood flow in tetralogy of Fallot (TOF) can lead to the development of major aortopulmonary collateral arteries (MAPCA), which interferes with surgical repair. The present study evaluated the features of MAPCAs among patients with TOF and their treatment approaches. Besides, perioperative parameters and mortality rates of our TOF patients with and without MAPCA were compared. This retrospective case-control study was conducted from 2011 to 2020 at Namazi and Shahid Faghihi Hospitals, affiliated with Shiraz University of Medical Sciences, Shiraz, Iran. The significant aspects of MAPCAs, including their quantity, the presence of dual or single supply lung segments, and the employed devices for closure were evaluated. The patients were divided into three groups: TOF patients without MAPCAs as the control group, those with preoperative percutaneous MAPCA closure (Closed MAPCA), and those with small MAPCAs deemed unsuitable for percutaneous closure (Open MAPCA). A comparative analysis, encompassing hospital and surgical data, such as the presence of MAPCA, blood transfusion volume, intubation time, ICU stay, and mortality rates during and post-surgery, was performed among the aforementioned groups. The Chi square, Mann-Whitney, and Kruskal-Wallis tests were used to analyze the data. 59 patients were enrolled, with a mean age of 27.98±24.19 months. The control group included 34 patients with no collaterals, the closed MAPCA group had 12 patients with occluded collaterals, and the open MAPCA group had 13 patients with small collaterals unsuitable for closure. Blood transfusion volume and intensive care unit (ICU) stay were significantly higher in the open MAPCA group than the control group (P=0.01 and P=0.04, respectively). The highest mortality rate was seen in the Iranian Journal of Medical Sciences group (P<0.001). In TOF patients, percutaneous MAPCA closure prior to surgical repair was recommended. This approach could potentially decrease the occurrence of complications both during and post-surgery.

Lung image quality assessment and diagnosis using generative autoencoders in unsupervised ensemble learning

The lung is a critical organ for blood gas exchange. Early lung disease detection is often hindered by subtle symptoms. The diagnosis typically requires expert analysis of lung image scans, where both conventional methods and advanced machine learning (ML) and deep learning (DL) techniques are employed for scan segmentation and disease detection. However, it is a challenge to develop reliable computational models, due to the scarcity of high-quality data. With a major emphasis on lung disease classification and segmentation performance, this work presents a novel data quality assessment technique specifically designed for lung image datasets. The proposed pipeline combines ensemble learning, unsupervised learning, and generative autoencoders with attention mechanisms (GAME). By including attentional mechanisms in the generative autoencoders, we improve the tool’s ability to locate and prioritise areas of interest in lung images and extract the right features, which increases the accuracy of our algorithms. The pipeline automates quality checks and reduces the need for high-quality data, while reducing human oversight. Because it’s crucial to validate the robustness of the algorithms in our tool, we tested it using lung scans from the NIH-ChestXray and CheXpert datasets, and obtained IOU scores of 0.88 and 0.86, F1 scores of 0.95 and 0.95, and accuracy scores of 0.96 and 0.95, respectively, which shows they can be used as a classification tool as well as a segmentation tool. Given the challenging conditions in which the early diagnosis of lung disease is made, this is a significant step forward in the development of self-sustaining and accurate disease detection systems. The proposed model is made available to the public and the same is accessible via https://github.com/harshivchandra/LungDataQualityAssessment.

Short-term outcomes of robotic- vs. television-assisted thoracoscopic segmental lung resection for early-stage non-small-cell lung cancer in the day surgery models.

At present, few articles compare the differences between robot-assisted thoracic surgeries (RATSs) and video-assisted thoracic surgeries (VATSs) in the day surgery model and there is also little literature on what factors influence delayed discharge from day surgery. This study aims to compare short-term outcomes between RATS and VATS for segmental lung resection in a day surgery setting, and to identify risk factors for delayed discharge. A retrospective analysis was performed on 204 patients with early-stage non-small-cell lung cancer (NSCLC) who underwent segmental lung resection via RATS or VATS at the First People's Hospital of Changzhou City from January 2021 to December 2023. The clinical data and short-term efficacy of the two groups were compared, and the patients were divided into two subgroups based on whether the patients were discharged within 48 hours. One group was day surgery patients who were discharged within 48 hours, and the other group was day surgery patients with delayed discharge, so as to explore the factors affecting the delayed discharge of day surgery. Compared to the VATS group, the RATS group had a shorter average surgery duration (58.59±12.20 vs. 66.12±21.56 min, P<0.001), less intraoperative blood loss (98.77±51.50 vs. 128.87±65.79 mL, P=0.02), lower total postoperative drainage (185.44±109.14 vs. 268.70±147.99 mL, P=0.007), and a shorter postoperative drainage duration (1.74±0.30 vs. 2.29±0.98 days, P=0.045). The patients experienced less pain, with lower total drug dose of intramuscular diclofenac sodium lidocaine injection and oral celecoxib capsules (111.76±40.52 vs. 167.74±67.20 mg, P<0.001) and reduced pain scores (3.29±0.66 vs. 4.31±0.81, P=0.003). Fewer patients in the RATS group experienced delayed discharges (11 vs. 39, P<0.001), and the incidence of postoperative complications was lower (nausea and vomiting: 3.9% vs. 3.9%, fever: 4.9% vs. 13.5%, pulmonary atelectasis: 0% vs. 2.0%, infection: 1.0% vs. 2.9%, air leakage: 6.9% vs. 8.8%, abnormal drainage fluid: 0% vs. 8.8%, P=0.23; recovery: P=0.27). Meanwhile, subgroup analysis revealed that the four indicators of 24-hour postoperative analgesic medication, operation time, intraoperative bleeding, and tumor history were statistically significant (tumor history: P=0.04; intraoperative bleeding: P=0.005; use of analgesic medication in the 24-hour postoperative period: P=0.001; duration of surgery: P=0.008). In the surgery setting, RATSs showed better outcomes compared to VATSs, including shorter surgical duration, reduced intraoperative blood loss, lower postoperative drainage volume, shorter drainage duration, and fewer postoperative complications. History of tumor, intraoperative bleeding, use of analgesic medication in the 24-hour postoperative period, and duration of surgery were risk factors for delayed discharge from day surgery.

Enhanced Lung Segmentation in DICOM CT Images Using a Hybrid K-Means Clustering and Region Growing Technique

Enhanced Lung Segmentation in DICOM CT Images Using a Hybrid K-Means Clustering and Region Growing Technique

A Novel Method for 3D Lung Tumor Reconstruction Using Generative Models.

Lung cancer remains a significant health concern, and the effectiveness of early detection significantly enhances patient survival rates. Identifying lung tumors with high precision is a challenge due to the complex nature of tumor structures and the surrounding lung tissues. To address these hurdles, this paper presents an innovative three-step approach that leverages Generative Adversarial Networks (GAN), Long Short-Term Memory (LSTM), and VGG16 algorithms for the accurate reconstruction of three-dimensional (3D) lung tumor images. The first challenge we address is the accurate segmentation of lung tissues from CT images, a task complicated by the overwhelming presence of non-lung pixels, which can lead to classifier imbalance. Our solution employs a GAN model trained with a reinforcement learning (RL)-based algorithm to mitigate this imbalance and enhance segmentation accuracy. The second challenge involves precisely detecting tumors within the segmented lung regions. We introduce a second GAN model with a novel loss function that significantly improves tumor detection accuracy. Following successful segmentation and tumor detection, the VGG16 algorithm is utilized for feature extraction, preparing the data for the final 3D reconstruction. These features are then processed through an LSTM network and converted into a format suitable for the reconstructive GAN. This GAN, equipped with dilated convolution layers in its discriminator, captures extensive contextual information, enabling the accurate reconstruction of the tumor's 3D structure. The effectiveness of our method is demonstrated through rigorous evaluation against established techniques using the LIDC-IDRI dataset and standard performance metrics, showcasing its superior performance and potential for enhancing early lung cancer detection. This study highlights the benefits of combining GANs, LSTM, and VGG16 into a unified framework. This approach significantly improves the accuracy of detecting and reconstructing lung tumors, promising to enhance diagnostic methods and patient results in lung cancer treatment.

Automated lung segmentation on chest MRI in children with cystic fibrosis.

Segmentation of lung structures in medical imaging is crucial for the application of automated post-processing steps on lung diseases like cystic fibrosis (CF). Recently, machine learning methods, particularly neural networks, have demonstrated remarkable improvements, often outperforming conventional segmentation methods. Nonetheless, challenges still remain when attempting to segment various imaging modalities and diseases, especially when the visual characteristics of pathologic findings significantly deviate from healthy tissue. Our study focuses on imaging of pediatric CF patients [mean age, standard deviation (7.50 ± 4.6)], utilizing deep learning-based methods for automated lung segmentation from chest magnetic resonance imaging (MRI). A total of 165 standardized annual surveillance MRI scans from 84 patients with CF were segmented using the nnU-Net framework. Patient cases represented a range of disease severities and ages. The nnU-Net was trained and evaluated on three MRI sequences (BLADE, VIBE, and HASTE), which are highly relevant for the evaluation of CF induced lung changes. We utilized 40 cases for training per sequence, and tested with 15 cases per sequence, using the Sørensen-Dice-Score, Pearson's correlation coefficient (r), a segmentation questionnaire, and slice-based analysis. The results demonstrated a high level of segmentation performance across all sequences, with only minor differences observed in the mean Dice coefficient: BLADE (0.96 ± 0.05), VIBE (0.96 ± 0.04), and HASTE (0.95 ± 0.05). Additionally, the segmentation quality was consistent across different disease severities, patient ages, and sizes. Manual evaluation identified specific challenges, such as incomplete segmentations near the diaphragm and dorsal regions. Validation on a separate, external dataset of nine toddlers (2-24 months) demonstrated generalizability of the trained model achieving a Dice coefficient of 0.85 ± 0.03. Overall, our study demonstrates the feasibility and effectiveness of using nnU-Net for automated segmentation of lung halves in pediatric CF patients, showing promising directions for advanced image analysis techniques to assist in clinical decision-making and monitoring of CF lung disease progression. Despite these achievements, further improvements are needed to address specific segmentation challenges and enhance generalizability.

The effectiveness of deep learning model in differentiating benign and malignant pulmonary nodules on spiral CT.

Pulmonary nodule, one of the most common clinical phenomena, is an irregular circular lesion with a diameter of ⩽ 3 cm in the lungs, which can be classified as benign or malignant. Differentiating benign and malignant pulmonary nodules has an essential effect on clinical medical diagnosis. To explore the clinical value and diagnostic effects of the lung nodule classification and segmentation algorithm based on deep learning in differentiating benign and malignant pulmonary nodules. A deep learning model with a fine-grained classification manner for the discrimination of pulmonary models in Dr.Wise Lung Analyzer. This study retrospectively enrolled 120 patients with pulmonary nodules detected by chest spiral CT from March 2021 to September 2022 in the radiology department of Ninghai First Hospital. The DL-based method and physicians' accuracy, sensitivity, and specificity results were compared using the pathological results as the gold standard. The ROC curve of the deep learning model was plotted, and the AUCs were calculated. On 120 CT images, pathologically diagnosed 81 malignant nodules and 122 benign modules. The AUCs of radiologists' diagnostic approach and DL-base method for differentiating patients were 0.62 and 0.81; radiologists' diagnostic approach and DL-base method achieved AUCs of 0.75 and 0.90 for benign and malignant pulmonary nodules differentiate. The accuracy, sensitivity, and specificity with the deep learning model were 73.33%, 78.75%, and 62.50%, respectively, while the accuracy, sensitivity, and specificity with the physician's diagnosis were 63.33%, 66.25%, and 57.500. There was no significant difference between the diagnosis results of the proposed DL-based method and the radiologists' diagnostic approach in differentiating benign and malignant lung nodules on spiral CT (P< 0.05).

Multi-level digital-twin models of pulmonary mechanics: correlation analysis of 3D CT lung volume and 2D Chest motion

Creating multi-level digital-twin models for mechanical ventilation requires a detailed estimation of regional lung volume. An accurate generic map between 2D chest surface motion and 3D regional lung volume could provide improved regionalisation and clinically acceptable estimates localising lung damage. This work investigates the relationship between CT lung volumes and the forced vital capacity (FVC) a surrogate of tidal volume proven linked to 2D chest motion. In particular, a convolutional neural network (CNN) with U-Net architecture is employed to build a lung segmentation model using a benchmark CT scan dataset. An automated thresholding method is proposed for image morphology analysis to improve model performance. Finally, the trained model is applied to an independent CT dataset with FVC measurements for correlation analysis of CT lung volume projection to lung recruitment capacity. Model training results show a clear improvement of lung segmentation performance with the proposed automated thresholding method compared to a typically suggested fixed value selection, achieving accuracy greater than 95% for both training and independent validation sets. The correlation analysis for 160 patients shows a good correlation ofRsquared value of 0.73 between the proposed 2D volume projection and the FVC value, which indicates a larger and denser projection of lung volume relative to a greater FVC value and lung recruitable capacity. The overall results thus validate the potential of using non-contact, non-invasive 2D measures to enable regionalising lung mechanics models to equivalent 3D models with a generic map based on the good correlation. The clinical impact of improved lung mechanics digital twins due to regionalising the lung mechanics and volume to specific lung regions could be very high in managing mechanical ventilation and diagnosing or locating lung injury or dysfunction based on regular monitoring instead of intermittent and invasive lung imaging modalities.