Lung Nodules Research Articles

Artificial Intelligence: Can It Save Lives, Hospitals, and Lung Screening?

BackgroundEarly detection is essential in lung cancer survival. Lung screening or incidental detection on unrelated imaging holds the most promise for early detection. With the large volume of imaging performed today, management of incidental pulmonary nodules can be difficult. We hypothesized an artificial intelligence (AI) tool could reliably read all imaging reports, detect, and effectively triage indeterminate pulmonary nodules without adding additional personnel, helping save lives. MethodsAn incidental lung nodule clinic (ILNC) was created using AI and an existing nurse practitioner. Over 26 months, the software read all radiology reports, visualizing any lung tissue. Patients with nodules >3 mm and considered indeterminate by the nurse practitioner were referred to the ILNC. High-risk patients with benign nodules were offered entry into the lung screening program. ResultsOf 502,632 imaging reports analyzed, 22,136 (4.4%) had positive findings. Follow-up data were lacking in 11,797 (2.3%), 911 (7.7%) were verified lost, and 518 (4.4%) were referred to the ILNC. There were 393 patients with benign nodules and accepted enrollment in the lung screening program. Mean age of enrolled patients was 61 years, and 53% were men. Workup included 499 diagnostic computed tomographic scans, 39 positron emission tomographic scans, and 27 biopsy samples that identified 15 malignancies (2.9%), with 14 lung cancers (8 stage I, 4 stage III, and 2 stage IV). Treatment included 5 lobectomies, and 4 underwent stereotactic body radiation therapy. Financials were favorable. ConclusionsAI software can supplement practitioners, help diagnose lung cancer earlier, save lives, and generate value-based revenue for the hospital.

Phase 2 Clinical Trial of VGT-309 for Intraoperative Molecular Imaging During Pulmonary Resection

BackgroundAdvances in intraoperative molecular imaging (IMI) may improve surgical outcomes when resecting tumors in the lung. A single-center trial was conducted using VGT-309, a cathepsin-targeted near-infrared imaging agent that causes lung nodules to fluoresce during surgical resection. The end point of this phase 2 study was to evaluate the frequency that IMI with VGT-309 resulted in a clinically significant event (CSE): localization of pulmonary nodules, discovery of unsuspected additional cancers, or identification of positive margins. MethodsPatients undergoing surgical resection for known or suspected cancer in the lung received VGT-309 (0.32 mg/kg) preoperatively. During the surgical procedure, localization and resection of the nodules were performed using standard surgical techniques. Near-infrared imaging was then used to localize nodules, seek occult lesions, and assess resection margins. Efficacy was measured by the frequency of CSEs. ResultsOf the 40 patients who underwent pulmonary resection with VGT-309, 17 (42.5%) had at least 1 CSE. Near-infrared imaging identified lesions not found by standard surgical methods in 16 patients, additional cancers not found by preoperative imaging in 1 patient, and margins within 5 mm of the closest staple line in 2 patients. VGT-309 performance was tested across a broad range of tumor types and commercial near-infrared imaging systems. VGT-309 appeared safe, well-tolerated, with no infusion reactions, and no drug-related serious adverse events. ConclusionsThis phase 2 study demonstrated the utility of IMI with VGT-309 in localizing pulmonary nodules, recognizing synchronous lesions, and identifying positive margins. A multi-institutional study will further evaluate the efficacy of VGT-309.

Robot-Assisted Bronchoscopy for Identification of Lung Nodules During Minimally Invasive Pulmonary Resection.

Small pulmonary nodules can be difficult to identify during minimally invasive surgical (MIS) resection. Previous investigators have reported using standard bronchoscopy with electromagnetic navigation to identify small pulmonary nodules. Robot-assisted bronchoscopy has been introduced into clinical practice and has shown utility for the biopsy of small lesions. We report our experience using robot-assisted bronchoscopy with dye marking to aid in minimally invasive pulmonary resection. Patients with peripheral pulmonary nodules underwent robot-assisted bronchoscopy before a planned minimally invasive resection. Indocyanine green or methylene blue was injected directly into the targeted lesion. Surgical resection was then immediately performed. Success was defined as dye visualization leading to sublobar resection of the target nodule without the need for lobectomy or thoracotomy. Thirty patients with a single targeted nodule underwent robot-assisted bronchoscopy followed by MIS resection. The median lesion size was 9 mm (4 to 25 mm), and the median distance from the pleura was 5 mm (1 to 32 mm). The success rate was 83.3% (25 of 30). There were 3 cases in which the dye was not visualized, and in 2 cases there was free extravasation of dye. The targeted nodule was identified in these 5 patients without the need for thoracotomy or lobectomy. Pathology revealed non-small cell lung cancer (n = 13, 43.3%), metastatic disease (n = 11, 36.7%), and benign disease (n = 6, 20%). There were no complications related to the use of robot-assisted bronchoscopy. Robot-assisted bronchoscopy with dye marking is safe and effective for guiding minimally invasive resection of small peripheral pulmonary nodules.

Accuracy Study on Deep Learning-Based CT Image Analysis for Lung Nodule Detection and Classification

Accuracy Study on Deep Learning-Based CT Image Analysis for Lung Nodule Detection and Classification

Lung Cancer Detection Using CNN VGG19 + Model

In the last many years, lung cancer has become a major public health concern. To examine cell breakdown in the lungs in its starting stages, doctors often use imaging modalities such as X-ray chest films, CT scans, MRIs, etc. The timing of diagnosis determines the course of therapy. Artificial intelligence (AI) is a hotspot for developing computational models of human intellect. In this research, we aim to enhance the detection and classification of lung nodules from CT images using a novel deep learning approach. Our study builds upon an extensive review of existing lung cancer detection methods, highlighting their strengths and weaknesses. This LIDC/IDRI dataset has been used in over half of the most recent research on lung cancer diagnosis. While several Convolutional Neural Networks (CNNs) architecture are adequate to process medical field data using technology solutions to discover and diagnose Lung cancer, here we proposed model VGG-19+ model. It is known for its strong feature extraction capabilities. It outflanks the ongoing model on a few exhibition measures, including exactness, accuracy, responsiveness/review, and f1-score.This research using VGG-19+ model could lead to more widespread utilization in cancer diagnosis by enhancing early lung cancer detection and developing the field of medical image analysis.

Second opinion for pulmonary and pleural cytology is valuable for patient care

IntroductionThoracic cytology can be challenging due to limited procured material or overlapping morphology between benign and malignant entities. In such cases, expert consultation might be sought. This study aimed to characterize all pulmonary and pleural cytology consult cases submitted to our practice and provide recommendations on approaching difficult cases. Materials and MethodsAll thoracic (pulmonary and pleural) cytology cases submitted for expert consultation to the University of Michigan (MLabs) from 2013 to mid-2022 were reviewed. Cases where cytology was only part of a hematopathology or surgical pathology consult were excluded. Patient demographics, specimen location, procedure performed, referring diagnosis, and our diagnoses were recorded for each case. Diagnoses were categorized according to the Papanicolaou Society of Cytopathology recommendations for pulmonary and effusion cytology. Discordant diagnoses were stratified as major or minor. Data was analyzed using Chi-Square analysis and logistic models. ResultsWe received 784 thoracic cytology consult cases, including 530 exfoliative samples and 307 fine needle aspirations (FNAs). The most common anatomic locations sampled were the bronchial wall (n=194, 23%), lung nodule (n=322, 38%), and pleura (n=296, 35%). 413 cases had a diagnostic discrepancy (48.3%), with 274 (66%) minor and 139 (34%) major discrepancies. By location, pleural effusion specimens had the highest probability of a discrepant diagnosis (p=0.003). By specimen type, FNA samples were significantly more likely to have a discrepant diagnosis (p=0.06). ConclusionNearly half of the thoracic cytology cases submitted for expert second opinion had diagnostic discrepancies. Consequently, consulting a tertiary medical care center with cytopathology expertise for challenging thoracic cytology diagnoses is beneficial.

Diagnostic Value of Immunostaining for Thyroid Transcription Factor 1 (TTF1) and Paired Box 8 (PAX8) in Distinguishing Pulmonary Metastases of Mesonephric and Mesonephric-like Adenocarcinomas from Primary Lung Adenocarcinomas.

Both mesonephric adenocarcinoma (MA) and mesonephric-like adenocarcinoma (MLA) express thyroid transcription factor 1 (TTF1). TTF1 is also considered a highly sensitive and specific diagnostic marker for primary lung adenocarcinoma (PLA). However, distinguishing PLA from pulmonary metastatic MA/MLA (PMM) based on the expression of TTF1 alone can be difficult. This study aimed to investigate the expression of TTF1 and paired box 8 (PAX8) and assess their value in distinguishing PMM from PLA. We reviewed the electronic medical records and pathology slides of eight PMM cases. We conducted immunostaining for TTF1 and PAX8 in 6, 8, and 21 cases of primary MA/MLA, PMM, and PLA, respectively. Two patients with stage IB uterine MLA developed lung metastases at 5 and 57 months after hysterectomy. Solitary pulmonary nodules were suspected to be primary lung cancer in two patients. Compared to primary tumors, all matched PMMs exhibited reduced TTF1 immunoreactivity. In contrast, the majority of PLAs showed uniform and intense TTF1 expression. All except one PMM exhibited diffuse and strong PAX8 expression, while only one PLA showed focal and weak PAX8 expression. Immunostaining for TTF1 and PAX8 can help in distinguishing PMM from PLA in the diagnosis of pulmonary lesions detected in patients with a history of MA/MLA.

Low-grade undifferentiated sarcoma with MEIS1::NCOA2-rearrangement primary to the lung: a case report

BackgroundMEIS1::NCOA2 is a rare fusion gene that has been recently described in a subset of spindle cell rhabdomyosarcomas and multiple low-grade undifferentiated spindle cell sarcomas predominantly arising in the genitourinary and gynecologic tracts with no specific line of differentiation. We present the first documented case of this neoplasm arising as a lung primary tumor.Case PresentationA 74-year-old woman with a 40-year smoking history presented with a 2.1 × 1.7 cm lung nodule discovered on computed tomography (CT) scan. A biopsy and subsequent lobe resection were performed, as well as an extensive metastatic work up, which revealed no additional masses. No specific line of differentiation was found by immunohistochemical staining, and an RNA-based fusion panel revealed a MEIS1::NCOA2 fusion, at which point a diagnosis of Low-Grade Undifferentiated Sarcoma with MEIS1::NCOA2-Rearrangement was rendered.ConclusionsThis report represents the first diagnosis of this tumor primary to the lung, and provides additional insight into the origin and localization of these rare tumors.

Nodule-CLIP: Lung nodule classification based on multi-modal contrastive learning

The latest developments in deep learning have demonstrated the importance of CT medical imaging for the classification of pulmonary nodules. However, challenges remain in fully leveraging the relevant medical annotations of pulmonary nodules and distinguishing between the benign and malignant labels of adjacent nodules. Therefore, this paper proposes the Nodule-CLIP model, which deeply mines the potential relationship between CT images, complex attributes of lung nodules, and benign and malignant attributes of lung nodules through a comparative learning method, and optimizes the model in the image feature extraction network by using its similarities and differences to improve its ability to distinguish similar lung nodules. Firstly, we segment the 3D lung nodule information by U-Net to reduce the interference caused by the background of lung nodules and focus on the lung nodule images. Secondly, the image features, class features, and complex attribute features are aligned by contrastive learning and loss function in Nodule-CLIP to achieve lung nodule image optimization and improve classification ability. A series of testing and ablation experiments were conducted on the public dataset LIDC-IDRI, and the final benign and malignant classification rate was 90.6%, and the recall rate was 92.81%. The experimental results show the advantages of this method in terms of lung nodule classification as well as interpretability.

Clinical and Radiological Assessment of Patients with Lung Cancer Using Chest CT Scan: An Observational Study in a Barcelona Hospital, Spain

Introduction: Lung cancer is one of the most common and deadliest types of cancer in the world. Chest CT scan is an important diagnostic tool for detecting and evaluating lung cancer. This study aimed to assess the clinical and radiological characteristics of patients with lung cancer who underwent chest CT scans at Barcelona Hospital, Spain. Methods: This research is a retrospective observational study involving 1059 patients diagnosed with lung cancer who underwent chest CT scans between 2018-2023. Patient data were collected from electronic medical records, including demographic information, clinical symptoms, CT scan findings, and histopathological diagnosis results. Results: The most common clinical symptom was cough (83.0%), followed by shortness of breath (58.8%), chest pain (45.6%), coughing up blood (20.3%), and weight loss (17, 9%). The most common CT scan finding was lung nodules (80.6%), followed by consolidation (39.7%) and pleural effusion (26.9%). The most common histopathologic diagnosis was adenocarcinoma (40.4%), followed by squamous cell carcinoma (29.5%), large cell carcinoma (17.9%), and neuroendocrine cell carcinoma (12.3%). Conclusion: This study provides an overview of the clinical and radiological characteristics of patients with lung cancer who underwent chest CT scans at the Barcelona Hospital, Spain. The findings of this study may help doctors in diagnosing and managing patients with lung cancer.

APPLICATION VALUE OF CT INDEXES COMBINED WITH TUMOR MARKERS AND 7-TAAB IN THE DIAGNOSIS OF INVASIVE LUNG CANCER BASED ON IMPROVED ARTIFICIAL INTELLIGENCE TECHNOLOGY

Objective: To investigate the efficacy of artificially intelligent CT metrics combined with tumor markers and 7-TAABs in predicting the infiltrative nature of mixed ground-glass nodules in the lungs to provide a basis for rational clinical decision-making. Materials and Methods: The clinical data of patients admitted to Changshu Hospital affiliated with Soochow University (Hospital 1) and the Eighth People’s Hospital of Tongzhou District, Nantong City (Hospital 2) from January 2022 to June 2023 were retrospectively analyzed, and a total of 427 cases were included in the study based on the nadir criteria. Three hundred twenty cases from Hospital 1 were randomly grouped into a training set ([Formula: see text]) and an internal validation set ([Formula: see text]), and 107 cases from Hospital 2 were used for the external validation set. The correlations between patients’ clinicoradiological characteristics, tumor markers, and seven tumor autoantibodies (7-TAABs) were analyzed by the Mantel test and further by univariate and multivariate logistic regression analyses to screen the risk factors for the development of infiltrative tumors in the ground-glass nodes and to establish a joint model, which was combined with the clinicoradiological model and the model of the serological indexes in the internal and external validation sets were performed to compare the subject work characteristics (ROC) curves, clinical calibration curves, and clinical decision curves to evaluate their predictive efficacy and clinical utility. Results: Of the 427 cases included, 174 were in the noninfiltrating group, and 253 were in the infiltrating group. There was a significant relationship between tumor markers, seven tumor autoantibodies, and lung cancer infiltrability, and after multifactorial logistic regression analysis, a bronchial air sign, probability of malignancy, nodule diameter, percentage of solidity, VEGF, proGRP, GAGE7, and 7-TAABs were the risk factors for determining the development of infiltrative lesions in early-stage lung nodules. The clinicoradiological model was superior to the serological index model on both internal and external validation sets (AUC values were: 0.926 versus 0.839, [Formula: see text]; 0.895 versus 0.751, [Formula: see text]), and the combined model was slightly superior to the clinicoradiological model on both internal and external validation sets (AUC values were: 0.928 versus 0.926, [Formula: see text]; 0.914 versus 0.895, [Formula: see text]). The combined model performed optimally in terms of calibration accuracy and net clinical benefit, suggesting that a model constructed based on AI CT metrics combined with tumor markers and 7-TAABs would be beneficial to clinicians in predicting the infiltrative nature of early-stage lung cancer. Conclusion: The column-line diagram model built based on CT indexes improved by artificial intelligence technology combined with tumor markers and 7-TAAB can better predict the infiltration of lung tumors, which has specific clinical application value.

Use of CT-derived radiomic features to preoperatively identify invasive mucinous adenocarcinoma in solitary pulmonary nodules ≤3 cm

ObjectiveIn this study, we aimed to utilize computed tomography (CT)-derived radiomics and various machine learning approaches to differentiate between invasive mucinous adenocarcinoma (IMA) and invasive non-mucinous adenocarcinoma (INMA) preoperatively in solitary pulmonary nodules (SPN) ≤3 cm. MethodsA total of 538 patients with SPNs measuring ≤3 cm were enrolled, categorized into either the IMA group (n = 50) or INMA group (n = 488) based on postoperative pathology. Radiomic features were extracted from non-contrast-enhanced CT scans and identified using the least absolute shrinkage and selection operator (LASSO) algorithm. In constructing radiomics-based models, logistic regression, support vector machines, classification and regression trees, and k-nearest neighbors were employed. Additionally, a clinical model was developed, focusing on CT radiological features. Subsequently, this clinical model was integrated with the most effective radiomic model to create a combined model. Performance assessments of these models were conducted, utilizing metrics such as the area under the receiver operating characteristic curve (AUC), DeLong's test, net reclassification index (NRI), and integrated discrimination improvement (IDI). ResultsThe support vector machine approach showed superior predictive efficiency, with AUCs of 0.829 and 0.846 in the training and test cohorts, respectively. The clinical model had AUCs of 0.760 and 0.777 in the corresponding cohorts. The combined model had AUCs of 0.847 and 0.857 in the corresponding cohorts. Furthermore, compared to the radiomic model, the combined model significantly improved performance in both the training (DeLong test P = 0.045, NRI 0.206, IDI 0.024) and test cohorts (P = 0.029, NRI 0.125, IDI 0.032), as well as compared to the clinical model in both the training (P = 0.01, NRI 0.310, IDI 0.09) and test cohorts (P = 0.047, NRI 0.382, IDI 0.085). Conclusionthe combined model exhibited excellent performance in distinguishing between IMA and INMA in SPNs ≤3 cm.

Pulmonary Nodule Segmentation Network Based on Res Select Kernel Contextual U-Net

Abstract U-Net network is widely used in the field of medical image segmentation. The automatic segmentation and detection of lung nodules can help in the early detection of lung cancer. Therefore, in this paper, to solve the problems of small proportion of nodules in computer tomography (CT) images, complex features, and insufficient segmentation accuracy, an improved U-Net network based on residual network and attention mechanism was proposed. The feature extraction part of Res select Kernel Contextual U-Net (RkcU-Net) network is based on Res2net, a variant of Resnet, and on which a feature extraction module with automatic selection of convolution kernel size is designed to perform multiscale convolution inside the feature layer to form perceptual fields of different sizes. This module selects the appropriate convolution kernel size to extract lung nodule features in the face of different fine-grained lung nodules. Second, the contextual supplementary (CS) block is designed to use the information of adjacent upper and lower layers to correct for the upper layer features, eliminating the discrepancy in the fusion of features at different levels. In this paper, the LUNA16 dataset was selected as the basis for lung nodule segmentation experiments. The method used in this dataset can achieve an intersection ratio (IoU) of 80.59% and a dice similarity coefficient (DSC) score of 89.25%. The network effectively improves the accuracy of lung nodule segmentation compared with other models. The results show that the method enhances the feature extraction ability of the network and improves the segmentation effect. In addition, the contribution of jump connections to information recovery should be noted.

MRUNet-3D: A multi-stride residual 3D UNet for lung nodule segmentation

Obtaining an accurate segmentation of the pulmonary nodules in computed tomography (CT) images is challenging. This is due to: (1) the heterogeneous nature of the lung nodules; (2) comparable visual characteristics between the nodules and their surroundings. A robust multi-scale feature extraction mechanism that can effectively obtain multi-scale representations at a granular level can improve segmentation accuracy. As the most commonly used network in lung nodule segmentation, UNet, its variants, and other image segmentation methods lack this robust feature extraction mechanism. In this study, we propose a multi-stride residual 3D UNet (MRUNet-3D) to improve the segmentation accuracy of lung nodules in CT images. It incorporates a multi-slide Res2Net block (MSR), which replaces the simple sequence of convolution layers in each encoder stage to effectively extract multi-scale features at a granular level from different receptive fields and resolutions while conserving the strengths of 3D UNet. The proposed method has been extensively evaluated on the publicly available LUNA16 dataset. Experimental results show that it achieves competitive segmentation performance with an average dice similarity coefficient of 83.47 % and an average surface distance of 0.35 mm on the dataset. More notably, our method has proven to be robust to the heterogeneity of lung nodules. It has also proven to perform better at segmenting small lung nodules. Ablation studies have shown that the proposed MSR and RFIA modules are fundamental to improving the performance of the proposed model.

The application of Raman spectroscopy for the diagnosis and monitoring of lung tumors.

Raman spectroscopy is an optical technique that uses inelastic light scattering in response to vibrating molecules to produce chemical fingerprints of tissues, cells, and biofluids. Raman spectroscopy strategies produce high levels of chemical specificity without requiring extensive sample preparation, allowing for the use of advanced optical tools such as microscopes, fiber optics, and lasers that operate in the visible and near-infrared spectral range, making them increasingly suitable for a wide range of medical diagnostic applications. Metal nanoparticles and nonlinear optical effects can improve Raman signals, and optimized fiber optic Raman probes can make real-time, in vivo, single-point observations. Furthermore, diagnostic speed and spatial accuracy can be improved through the multimodal integration of Raman measurements and other technologies. Recent studies have significantly contributed to the improvement of diagnostic speed and accuracy, making them suitable for clinical application. Lung cancer is a prevalent type of respiratory malignancy. However, the use of computed tomography for detection and screening frequently reveals numerous smaller lung nodules, which makes the diagnostic process more challenging from a clinical perspective. While the majority of small nodules detected are benign, there are currently no direct methods for identifying which nodules represent very early-stage lung cancer. Positron emission tomography and other auxiliary diagnostic methods for non-surgical biopsy samples from these small nodules yield low detection rates, which might result in significant expenses and the possibility of complications for patients. While certain subsets of patients can undergo curative treatment, other individuals have a less favorable prognosis and need alternative therapeutic interventions. With the emergence of new methods for treating cancer, such as immunotherapies, which can potentially extend patient survival and even lead to a complete cure in certain instances, it is crucial to determine the most suitable biomarkers and metrics for assessing the effectiveness of these novel compounds. This will ensure that significant treatment outcomes are accurately measured. This review provides a comprehensive overview of the prospects of Raman spectroscopy and its applications in the diagnosis and analysis of lung tumors.

Cross-spectral vision transformer for lung nodule detection with improved moth flame algorithm using deep learning

The second-leading cause of cancer-related deaths globally is lung cancer. A patient's life may be saved if this cancer is discovered early. Cancer can be difficult to detect on computed tomography (CT) images, according to physicians. Strong nodule segmentation is a difficulty because to the variety of pulmonary nodules and the visual similarities between nodules and their surroundings. Preprocessing, feature extraction, and classification are the three phases of the approach. Gather databases first from open source platforms. Unwanted noise in acquired CT images reduces the effectiveness of classification. In order to remove undesired noise from the input image, preprocessing techniques like filtering and contrast enhancement might be taken into consideration. The essential segmentation of the image is then carried out using optimization approaches like Automatic Lung Parenchyma Mining and Remora Concavity (ALPM & RC). Cross Spectral Visual Transformer and Improved Moth Flame Optimization (CSViT-IMFO) are the two classifiers that are being suggested. For multi-process optimization in CSViT, like structural and hyperparameter optimization, IMFO is used. Utilizing performance matrices like accuracy, precision, recall, specificity, sensitivity, and F_Measure, the proposed method is put into practice in MATLAB. On the LIDC dataset, our suggested solution outperforms cutting-edge learning-based methods with a classification accuracy of 99.5 %.

Does obstructive sleep apnea–induced intermittent hypoxia increase the incidence of solitary pulmonary nodules, thyroid nodules, and other disorders? A retrospective study based on 750 cardiovascular disease patients

BackgroundObstructive sleep apnea (OSA) has been shown to be an important risk factor for cardiovascular disease (CVD), and intermittent hypoxia is an important pathogenetic factor for it. In the clinic, it was found that most CVD patients combined with OSA were also combined with solitary pulmonary nodules (SPN) or thyroid nodules (TN). Are these disorders related to intermittent hypoxia? One study showed that intermittent hypoxia is a pathogenic factor for lung cancer in mice, but there have been no clinical reports. So we conducted a retrospective study to explore whether intermittent hypoxia caused by OSA increases the incidence of SPN, TN, and other disorders.MethodsWe selected 750 patients with cardiovascular disease (CVD), who were divided into the control group and the OSA group according to the result of portable sleep monitoring. Retrospectively analyzed the comorbidities that patients with OSA are prone to and explored the correlation between OSA and those comorbidities.ResultsThe incidence of SPN, TN, cervical spondylosis, and carotid-artery plaques was higher in the OSA group than in the control group. These diseases are significantly associated with OSA (p < 0.05), and their incidence increased with an elevated apnea–hypopnea index. After excluding interference from age, gender, BMI, smoking history, history of lung disease, and history of tumors, OSA showed a significant correlation with SPN. After excluding age, gender, BMI, and thyroid disease, OSA was associated with TN. Patients with comorbidities have lower nocturnal oxygen saturation and more extended periods of apnea. Logistic multiple regression results revealed that male, advanced age, obesity, CS, and nasal septum deviation were independent risk factors for OSA.ConclusionsPatients combined with OSA may further develop more comorbidities, such as SPN, TN, and carotid-artery plaques. It may be related to intermittent hypoxia caused by OSA.

Semi-supervised lung nodule detection with adversarial learning

Semi-supervised lung nodule detection with adversarial learning

Transformation with Yolo Tiny Network Architecture for Multimodal Fusion in Lung Disease Classification

This article focuses on the crucial task of identifying lung diseases through the analysis and processing of medical images, aiming to aid medical professionals in the diagnostic process. Image fusion technologies, employed in prospective remedies, enhance diagnostic precision and reliability by amalgamating radiological information from diverse sources. The study introduces a Yolo Tiny network-based medical imaging fusion technique, yielding fused images with enhanced clarity and diverse physical information. The proposed method involves the integration of an adaptive pre-processing module, YOLO Tiny for efficient classification, discrete wavelet transform for feature combination, and a novel adaptive image fusion technique based on a classifier, contributing to improved diagnostic accuracy. Addressing challenges like uneven illumination and poor contrast in medical images, the comprehensive workflow enhances image quality, facilitating effective classification in medical imaging. Experimental results showcase the efficacy of the proposed scheme in CT imaging signs retrieval and classification, specifically for lung nodule detection. The system exhibits high accuracy, specificity, sensitivity, and recall, outperforming existing systems in terms of SSIM, PSNR, MSE, and overall accuracy for both single-modal and multi-modal datasets. The incorporation of YOLO and YOLO Tiny networks underscores improved performance in image processing and classification tasks across diverse medical imaging modalities. The hybrid model, suggested in this study, effectively preserves rich specific information from source images, yielding esthetically pleasing visuals for medical practitioners and enhancing the diagnostic process.

Performance changes due to differences among annotating radiologists for training data in computerized lesion detection

PurposeThe quality and bias of annotations by annotators (e.g., radiologists) affect the performance changes in computer-aided detection (CAD) software using machine learning. We hypothesized that the difference in the years of experience in image interpretation among radiologists contributes to annotation variability. In this study, we focused on how the performance of CAD software changes with retraining by incorporating cases annotated by radiologists with varying experience.MethodsWe used two types of CAD software for lung nodule detection in chest computed tomography images and cerebral aneurysm detection in magnetic resonance angiography images. Twelve radiologists with different years of experience independently annotated the lesions, and the performance changes were investigated by repeating the retraining of the CAD software twice, with the addition of cases annotated by each radiologist. Additionally, we investigated the effects of retraining using integrated annotations from multiple radiologists.ResultsThe performance of the CAD software after retraining differed among annotating radiologists. In some cases, the performance was degraded compared to that of the initial software. Retraining using integrated annotations showed different performance trends depending on the target CAD software, notably in cerebral aneurysm detection, where the performance decreased compared to using annotations from a single radiologist.ConclusionsAlthough the performance of the CAD software after retraining varied among the annotating radiologists, no direct correlation with their experience was found. The performance trends differed according to the type of CAD software used when integrated annotations from multiple radiologists were used.