Semantic context‐aware attention UNET for lung cancer segmentation and classification

Background: Advancements in technology have significantly improved the diagnosis of solitary pulmonary nodules in the lungs. Various computed tomography (CT) imaging techniques, including modern dual-energy computed tomography (DECT), have enhanced the ability to accurately classify pulmonary nodules as benign or malignant. In this study, three different dual-energy parameters — iodine load, contrast load, and visual assessment — were evaluated for their potential in characterizing pulmonary nodules. Objectives: The aim of this study was to assess the reliability and effectiveness of DECT in distinguishing benign from malignant pulmonary nodules using different parameters, including visual assessment, iodine concentration, and contrast load. Patients and Methods: This prospective study included patients who underwent contrast-enhanced thoracic DECT for solitary pulmonary nodules, had histopathological examination results, or had at least a two-year follow-up CT scan. Patients with nodules smaller than 6 mm or completely calcified nodules were excluded. Patients diagnosed with a suspicious solitary pulmonary nodule on chest radiography and subsequently underwent contrast-enhanced DECT, or those diagnosed with a lung nodule on routine non-contrast CT scans and later evaluated using DECT, were included in the study. Benign and malignant nodules were compared based on gender, age, contrast load, iodine load, and color map assessment. Nodule images were obtained 40 seconds after intravenous contrast administration using single-source DECT (120 kV split filter) with twin-beam technology. The visual enhancement and color map evaluation, including contrast and iodine load measurements, were separately calculated and recorded for each lung nodule. Results: A total of 59 patients [30 males (50.8%) and 29 females (49.2%)] with a solitary pulmonary nodule met the inclusion criteria. Among the 59 pulmonary nodules, 16 (27.1%) were malignant, and 43 (72.9%) were benign. Of the benign lesions, 23 (53.5%) were found in males and 20 (46.5%) in females. The mean age of patients with benign nodules was 53.5 ± 12 years (range: 25 - 73 years), while for those with malignant nodules, it was 69.2 ± 5.59 years (range: 57 - 75 years). There was no statistically significant difference in age between the two groups (P = 0.506). The median contrast load was 0.0 Hounsfield units (HU) [interquartile range (IQR: 64)] in benign nodules and 63 HU (IQR: 154) in malignant nodules. Malignant nodules had a significantly higher contrast load than benign nodules (P = 0.003). Using a cut-off value of 22 HU for contrast load in malignancy diagnosis, the sensitivity was 100%, specificity was 58.14%, positive predictive value (PPV) was 47.06%, and negative predictive value (NPV) was 100%. The area under the curve (AUC) was 0.746. The median iodine load was 0.0 mg/dL (IQR: 4.5) in benign nodules and 4.5 mg/dL (IQR: 11.8) in malignant nodules. Malignant nodules had a significantly higher iodine load than benign nodules (P < 0.001). Using a cut-off value of 1 mg/mL for malignancy diagnosis, the sensitivity was 100%, specificity was 62.79%, PPV was 50%, and NPV was 100% (AUC: 0.768). Conclusion: Dual-energy computed tomography provides valuable contributions in differentiating benign and malignant pulmonary nodules. In this study, the diagnostic value of three different approaches — visual iodine coverage color map, iodine concentration, and contrast load — was demonstrated in distinguishing these lesions.

Low-dose helical computed tomography (LDCT) is being applied as a modality for lung cancer screening. It may be difficult, however, for radiologists to distinguish malignant from benign nodules in LDCT. Our purpose in this study was to develop a computer-aided diagnostic (CAD) scheme for distinction between benign and malignant nodules in LDCT scans by use of a massive training artificial neural network (MTANN). The MTANN is a trainable, highly nonlinear filter based on an artificial neural network. To distinguish malignant nodules from six different types of benign nodules, we developed multiple MTANNs (multi-MTANN) consisting of six expert MTANNs that are arranged in parallel. Each of the MTANNs was trained by use of input CT images and teaching images containing the estimate of the distribution for the "likelihood of being a malignant nodule," i.e., the teaching image for a malignant nodule contains a two-dimensional Gaussian distribution and that for a benign nodule contains zero. Each MTANN was trained independently with ten typical malignant nodules and ten benign nodules from each of the six types. The outputs of the six MTANNs were combined by use of an integration ANN such that the six types of benign nodules could be distinguished from malignant nodules. After training of the integration ANN, our scheme provided a value related to the "likelihood of malignancy" of a nodule, i.e., a higher value indicates a malignant nodule, and a lower value indicates a benign nodule. Our database consisted of 76 primary lung cancers in 73 patients and 413 benign nodules in 342 patients, which were obtained from a lung cancer screening program on 7847 screenees with LDCT for three years in Nagano, Japan. The performance of our scheme for distinction between benign and malignant nodules was evaluated by use of receiver operating characteristic (ROC) analysis. Our scheme achieved an Az (area under the ROC curve) value of 0.882 in a round-robin test. Our scheme correctly identified 100% (76/76) of malignant nodules as malignant, whereas 48% (200/413) of benign nodules were identified correctly as benign. Therefore, our scheme may be useful in assisting radiologists in the diagnosis of lung nodules in LDCT.

10521 Background: There is no approved screening method for lung cancer and CT scanning has a high rate of false positives. Exhaled breath analysis for volatile organic compounds (VOCs) has the potential to distinguish between benign and malignant nodules. Recently, we showed that novel gold (Au) nanoparticles-based Artificial Olfactory System; NaNose, distinguishes between malignant (non-small lung cancer; NSCLC) and non-malignant human breaths and cell lines. In this study we incorporated the NaNose in our pulmonary “nodule clinics” where patients are evaluated for a suspicious lung nodule. Methods: 34 patients with lung nodules and 21 healthy subjects were tested for exhaled breath VOC profile. Patients were further evaluated as clinically appropriate. The exhaled breath was sampled by Eco Medics collecting system and the air passed through a Tenax SKC tube, which was analyzed for: (i) gas-chromatography/mass- spectrometry (GCMS) combined with solid phase micro-extraction (SPME) for determining the chemical nature of the VOCs; and by (ii) NaNose (Technion, Haifa Israel), for obtaining simple, real-time discriminations between the samples. For the latter, the electrical properties of the sensors were measured by a programmed time-related analyzer. Samples from healthy subjects were used to standardize the signals. Results: 25 patients had a malignant nodule (23 NSCLC; 12 adenocarcinomas, 8 squamous cell carcinomas, 3 undifferentiated and 2 SCLC) and 9 had benign nodules. Smoking history, comorbidity and nodule location were not different between the groups. Principle component analysis of the nanoparticle-based sensors yielded a significant discrimination between the malignant and the benign nodules (p < 0.007; sensitivity 88%; specificity 90%). The SPME/GCMS analysis identified 1000 different VOCs, but forward stepwise discrimination analysis produced different VOCs profile for the groups. VOCs that did not overlap between the malignant and the benign groups were isolated and selected as “malignant lung nodule” biomarkers. Conclusions: Non-invasive, exhaled breath analysis using the NaNose for VOCs profile discriminates between malignant and benign pulmonary nodules. No significant financial relationships to disclose.

Role of baseline nodule density and changes in density and nodule features in the discrimination between benign and malignant solid indeterminate pulmonary nodules

BACKGROUND: Cigarette smoking is closely related to both lung cancer and chronic obstructive pulmonary disease. The incidence of lung cancer is higher in patients with obstructive ventilatory impairment than in patients without obstructive ventilatory impairment regardless of smoking. So, obstructive ventilatory impairment is suspected as an independent risk factor of lung cancer. METHODS: For the evaluation of the role of obstructive ventilatory impairment as a risk factor of lung cancer, a total of 73 cases comprising 47 cases of malignant and 26 benign solitary pulmonary nodule were analyzed retrospectively. A comparative study of analysis of forced expiratory volume curves and frequencies of obstructive ventilatory impairment were made between cases with malignant and benign nodules. RESULTS: In comparison of vital capacity and parameters derived from forced expiratory volume curve between two groups, VC, FVC and FEV1 were not significantly different whereas FEV1/FVC% and FEF 25-75 % showed a significant decrease in the cases with malignant nodule. The frequency of obstructive ventilatory impairment determined by pulmonary function test was significantly higher in the cases with malignant nodule (23.4%) than in benign nodule(3.8%). When the risk for lung cancer was examined by the presence or absence of obstructive ventilatory impairment using the logistic regression analysis, the unadjusted relative risk for the lung cancer of obstructive ventilatory impairment was 17.17. When the effect of smoking and age were considered, the relative risk was to 8.13. CONCLUISON: These findings suggest that an obstructive ventilatory impairment is a risk factor of lung cancer.

The deadliest red and prevalent disease responsible for huge death cases every year is cancer. In various cancers, the highly predominant cancer-associated towards most incredible mortality ratio is lung cancer. Thereby, to identify or detect lung cancer, the utilization of computed tomography (CT) scans is essential as that presents a comprehensive image of tumor located in the body and its evolution tracking. However, even though CT prefers different imaging modalities, the visual interpretation of such CT scan images may result in erroneous function, causing lag in detecting lung cancer. Consequently, image processing methods have been extensively applied in the medical domain intended for the detection of lung tumor in formative years. Over the past years, extensive studies have been effectuated towards the CAD system for lung cancer detection employing CT images. Generally, the entire process involves four stages: pre-processing or lung segmentation, nodule detection, nodule segmentation, and classification. The study presents performance execution and investigation of the image processing technique for the detection of lung cancer. In this research, a detection technique of lung cancer attributed to image segmentation is proposed since it is halfway in image processing. Further, the approach is extended to Marker control watershed and region growing methodology for segmenting of CT scan image. With the image enhancement followed towards the phases of detection. In this light, the detection segments outcome using Gabor filter, image segmentation, and features extraction. With the assistance of experimental results, it is observed that the efficacy of the proposed approach has reached the highest mark for detecting foremost topographies of lung cancer through the watershed by masking technique attaining extreme precision and vigorous.

Lung cancer is a dangerous disease that taking human life rapidly worldwide. The death of the people is increasing exponentially because of lung cancer. In order to reduce the disease and save a human's life, the automated system is needed. The purpose of the lung cancer detection system is able to detect and provide reliable information to doctors and clinicians from the medical image. To minimize this problem, many systems have been proposed by using different image processing techniques, machine learning, and deep learning techniques. A computed tomography (CT) imaging modality is an efficient technique for medical screening used for lung cancer detection and diagnosis. Physician and radiologist use the CT scan images to analyze, interpret and diagnose the lung cancer from lung tissues. However, in most cases, obtaining an accurate diagnosis result without using the extra medical tool known as a computer- Aid detection and Diagnosis (CAD) system is tedious work for many physicians. To obtain an accurate result from computer-aided diagnosis system lung segmentation methods are basic once. So in this project, we have used different lung segmentation and nodules segmentation methods. Our work has consisted of preprocessing, and lung segmentation by using thresholding, and also used the U-net model for detection of the candidate nodules of the patient’s lung CT scan and classification methodology. We have used a convolutional neural network and designed a 3D CNN model that has a 0.77% accuracy performance.

BackgroundThe aim of the study was to derive and compare metabolic parameters relating to benign and malignant pulmonary nodules using dynamic 2-deoxy-2-[fluorine-18]fluoro-D-glucose (18F-FDG) PET/CT, and nodule perfusion parameters derived through perfusion computed tomography (CT).Patients and methodsTwenty patients with 21 pulmonary nodules incidentally detected on CT underwent a dynamic 18F-FDG PET/CT and a perfusion CT. The maximum standardized uptake value (SUVmax) was measured on conventional 18F-FDG PET/CT images. The influx constant (Ki) was calculated from the dynamic 18F-FDG PET/CT data using Patlak model. Arterial flow (AF) using the maximum slope model and blood volume (BV) using the Patlak plot method for each nodule were calculated from the perfusion CT data. All nodules were characterized as malignant or benign based on histopathology or 2 year follow up CT. All parameters were statistically compared between the two groups using the nonparametric Mann-Whitney test.ResultsTwelve malignant and 9 benign lung nodules were analysed (median size 20.1 mm, 9–29 mm) in 21 patients (male/female = 11/9; mean age ± SD: 65.3 ± 7.4; age range: 50–76 years). The average SUVmax values ± SD of the benign and malignant nodules were 2.2 ± 1.7 vs. 7.0 ± 4.5, respectively (p = 0.0148). Average Ki values in benign and malignant nodules were 0.0057 ± 0.0071 and 0.0230 ± 0.0155 min-1, respectively (p = 0.0311). Average BV for the benign and malignant nodules were 11.6857 ± 6.7347 and 28.3400 ± 15.9672 ml/100 ml, respectively (p = 0.0250). Average AF for the benign and malignant nodules were 74.4571 ± 89.0321 and 89.200 ± 49.8883 ml/100g/min, respectively (p = 0.1613).ConclusionsDynamic 18F-FDG PET/CT and perfusion CT derived blood volume had similar capability to differentiate benign from malignant lung nodules.

Pulmonary nodules are the main manifestations of early lung cancer. Non-small cell lung cancer is the most common histological type of lung cancer, and the main histological classification of non-small cell lung cancer is lung adenocarcinoma. The present study aimed to analyze the differentially expressed genes between patients with benign and malignant pulmonary nodules, and to identify potential therapeutic targets for lung adenocarcinoma. Sequencing data for benign and malignant pulmonary nodule samples and samples with no nodules were obtained from the National Center for Biotechnology Information Gene Expression Omnibus GSE135304 dataset. Differential gene analysis showed that S100 calcium binding protein P (S100P), ribonuclease A family member 2 (RNASE2), cytochrome c oxidase subunit 7C and mast cell expressed membrane protein 1 (C19orf59) were significantly upregulated among the blood samples collected from patients with malignant pulmonary nodules. Results from Kaplan-Meier plotter datasets showed that S100P, RNASE2 and C19orf59 were associated with the prognosis of lung cancer. RNASE2 expression was positively associated with nodule size and negatively associated with lung cancer prognosis. Moreover, RNASE2 was highly expressed in lung adenocarcinoma tissues compared with that in normal tissues. CCK-8 and Transwell assays indicated that overexpressed RNASE2 promoted the proliferation, migration and invasion of lung adenocarcinoma cells. In lung adenocarcinoma cells, RNASE2 was identified as a downstream target of microRNA (miR)-185-5p and was regulated by it. Inhibited cell proliferation, migration and invasion were observed following overexpression of miR-185-5p. Overexpression of RNASE2 reversed the inhibitory effect of miR-185-5p overexpression. In conclusion, in blood samples from patients with malignant pulmonary nodules and lung adenocarcinoma tissues, RNASE2 was found to be upregulated. High RNASE2 expression was associated with poor overall survival. miR-185-5p inhibited the proliferation, migration and invasion of lung adenocarcinoma cells by downregulating RNASE2 expression. These findings have implications for guiding therapeutic strategies.

The use of computed tomography in mediastinal staging of lung cancer relies on the premiss that malignant lymph nodes are larger than benign ones. This hypothesis was tested by linking node size and presence or absence of malignancy and looking at factors possibly influencing the size of benign nodes. All accessible mediastinal lymph nodes were taken from 56 consecutive patients with lung cancer who underwent thoracotomy. Nodes were measured and histologically examined. Resected cancer bearing lung from 44 of these patients was assessed for degree of acute and chronic inflammation. Lymph node size was not significantly related to the presence of metastatic disease, 58% of malignant and 43% of benign lymph nodes measuring over 15 mm. Similarly, there was no statistically significant relation between size of lymph nodes and the likelihood of malignancy, 20% of lymph nodes of 10 mm or more but also 15% of those less than 10 mm being malignant. Thresholds of 15 and 20 mm showed similar results. The maximum size of benign lymph nodes was significantly greater in those patients with histological evidence of acute pulmonary inflammation than in those without. The study shows that in patients with lung cancer (1) malignant mediastinal lymph nodes are not larger than benign nodes; (2) small mediastinal lymph nodes are not infrequently malignant; and (3) benign adenopathy is more common in patients with acute pulmonary inflammation.

Endobronchial ultrasound (EBUS) allows minimally invasive sampling of hilar and mediastinal lymph nodes and has an established role in non-small cell lung cancer (NSCLC) diagnosis and staging. Molecular biomarkers are being explored increasingly in lung cancer research. Gene expression profiling (GEP) is a microarray-based technology that comprehensively assesses genome-wide changes in gene expression that can provide tumour-specific molecular signatures with the potential to predict prognosis and treatment responsiveness. We assessed the feasibility of using EBUS-derived aspirates from benign and tumour-infiltrated lymph nodes for GEP. RNA was extracted from EBUS-directed transbronchial fine needle aspiration samples in routine clinical practice. GEP was subsequently performed in six patients with NSCLC, three of whom had tumour-infiltrated nodes and three who had benign lymph nodes; the differences in gene expression were then compared. RNA was successfully extracted in 29 of 32 patients, 12 of whom were diagnosed with NSCLC. RNA yield (median, 12.1 μg) and RNA integrity (median, 6.3) were sufficient after amplification for GEP. Benign and malignant nodes in adenocarcinoma were discriminated by principal component analysis and hierarchical clustering with different expression patterns between malignant and benign nodes. We have demonstrated the feasibility of RNA extraction and GEP on EBUS-derived transbronchial fine needle aspirates from benign and tumour-infiltrated lymph nodes in patients with known NSCLC in routine clinical practice. Further studies on larger patient cohorts are required to identify expression profiles that robustly differentiate benign from malignant lymph nodes in NSCLC.

Lung cancer is the first killer among the cancer deaths. Malignant lung nodules have extremely high mortality while some of the benign nodules don't need any treatment .Thus, the accuracy of diagnosis between benign or malignant nodules diagnosis is necessary. Notably, although currently additional invasive biopsy or second CT scan in 3 months later may help radiologists to make judgments, easier diagnosis approaches are imminently needed. In this paper, we propose a novel CAD method to distinguish the benign and malignant lung cancer from CT images directly, which can not only improve the efficiency of rumor diagnosis but also greatly decrease the pain and risk of patients in biopsy collecting process. Briefly, according to the state-of-the-art radiomics approach, 583 features were used at the first step for measurement of nodules' intensity, shape, heterogeneity and information in multi-frequencies. Further, with Random Forest method, we distinguish the benign nodules from malignant nodules by analyzing all these features. Notably, our proposed scheme was tested on all 79 CT scans with diagnosis data available in The Cancer Imaging Archive (TCIA) which contain 127 nodules and each nodule is annotated by at least one of four radiologists participating in the project. Satisfactorily, this method achieved 82.7% accuracy in classification of malignant primary lung nodules and benign nodules. We believe it would bring much value for routine lung cancer diagnosis in CT imaging and provide improvement in decision-support with much lower cost.

We aimed to evaluate the diagnostic values of conventional ultrasound (US), ultrasound contrast (UC) and ultrasound elastography (UE) in distinguishing the benign and malignant thyroid nodules. A total of 100 patients with thyroid nodules receiving operative treatment were selected; they underwent the conventional US, UE and UC examinations before operation, respectively. The nodules received pathological examination after operation to distinguish benign from malignant lesions. The sensitivity, specificity and diagnostic accordance rate of each diagnostic method was evaluated by receiver operating characteristic (ROC) curve, and the area under the curve (AUC) of ROC was calculated. The manifestations of malignant thyroid nodules in conventional US examination were mostly the hypoecho, heterogeneous echo, irregular shape, unclear boundary, aspect ratio <1, microcalcification and irregular peripheral echo halo, and there were statistically significant differences compared with the benign nodules (P<0.05). UE showed that the differences between benign and malignant nodules in 2, 3 and 4 points were statistically significant (P<0.05). The manifestations of malignant nodules in UC were mostly the irregular shape, obscure boundary, no obvious enhancement, heterogeneous enhancement and visible perfusion defects, and there were statistically significant differences compared with the benign nodules (P<0.05). ROC curve showed that both sensitivity and specificity of UE and UC were superior to those of conventional US. AUC was the largest (AUC = 0.908) and the diagnostic value was the highest in the conventional US combined with UE and UC. Conventional US combined with elastography and UC can significantly improve the sensitivity, specificity and accuracy of diagnosis of benign and malignant thyroid nodules.

Lung cancer is one of the leading causes of cancer-related deaths worldwide, necessitating accurate and early detection for effective treatment. In recent years, deep learning models, particularly Convolutional Neural Networks (CNNs), have shown significant promise in medical image analysis tasks, including lung classification. adenocarcinoma, It cancer classifies large detection as and normal, cell carcinoma, squamous cell carcinoma . Our model classifies the CT scan In this research paper, we present a comprehensive comparative study of six popular CNN architectures - AlexNet, GoogleNet, VGG16, VGG19, LeNet, and ResNet - for the automated detection and classification of lung cancer from medical imaging data. For each CNN architecture, we fine-tuned the pre-trained networks using transfer learning techniques . VGG19 showed high test accuracy of approximately 94.8 .

The early detection, early diagnosis, and early treatment of lung cancer are the best strategies to improve the 5-year survival rate. Logistic regression analysis can be a helpful tool in the early detection of high-risk groups of lung cancer. Convolutional neural network (CNN) could distinguish benign from malignant pulmonary nodules, which is critical for early precise diagnosis and treatment. Here, we developed a risk assessment model of lung cancer and a high-precision classification diagnostic model using these technologies so as to provide a basis for early screening of lung cancer and for intelligent differential diagnosis. A total of 355 lung cancer patients, 444 patients with benign lung disease and 472 healthy people from The First Affiliated Hospital of Zhengzhou University were included in this study. Moreover, the dataset of 607 lung computed tomography images was collected from the above patients. The logistic regression method was employed to screen the high-risk groups of lung cancer, and the CNN model was designed to classify pulmonary nodules into benign or malignant nodules. The area under the curve of the lung cancer risk assessment model in the training set and the testing set were 0.823 and 0.710, respectively. After finely optimizing the settings of the CNN, the area under the curve could reach 0.984. This performance demonstrated that the lung cancer risk assessment model could be used to screen for high-risk individuals with lung cancer and the CNN framework was suitable for the differential diagnosis of pulmonary nodules.