Feature Reconstruction‐Guided Multi‐Scale Attention Network for Non‐Significant Lung Nodule Detection

Lung cancer is the most common cause of cancer-related death globally. Currently, lung nodule detection and classification are performed by radiologist-assisted computer-aided diagnosis systems. However, emerged artificially intelligent techniques such as neural network, support vector machine, and HMM have improved the detection and classification process of cancer in any part of the human body. Such automated methods and their possible combinations could be used to assist radiologists at early detection of lung nodules that could reduce treatment cost, death rate. Literature reveals that classification based on voting of classifiers exhibited better performance in the detection and classification process. Accordingly, this article presents an automated approach for lung nodule detection and classification that consists of multiple steps including lesion enhancement, segmentation, and features extraction from each candidate's lesion. Moreover, multiple classifiers logistic regression, multilayer perceptron, and voted perceptron are tested for the lung nodule classification using k-fold cross-validation process. The proposed approach is evaluated on the publically available Lung Image Database Consortium benchmark data set. Based on the performance evaluation, it is observed that the proposed method performed better in the stateof the art and achieved an overall accuracy rate of 100%.

Early detection of lung nodules is of great importance in lung cancer screening. Existing research recognizes the critical role played by CAD systems in early detection and diagnosis of lung nodules. However, many CAD systems, which are used as cancer detection tools, produce a lot of false positives (FP) and require a further FP reduction step. Furthermore, guidelines for early diagnosis and treatment of lung cancer are consist of different shape and volume measurements of abnormalities. Segmentation is at the heart of our understanding of nodules morphology making it a major area of interest within the field of computer aided diagnosis systems. This study set out to test the hypothesis that joint learning of false positive (FP) nodule reduction and nodule segmentation can improve the computer aided diagnosis (CAD) systems' performance on both tasks. To support this hypothesis we propose a 3D deep multi-task CNN to tackle these two problems jointly. We tested our system on LUNA16 dataset and achieved an average dice similarity coefficient (DSC) of 91% as segmentation accuracy and a score of nearly 92% for FP reduction. As a proof of our hypothesis, we showed improvements of segmentation and FP reduction tasks over two baselines. Our results support that joint training of these two tasks through a multi-task learning approach improves system performance on both. We also showed that a semi-supervised approach can be used to overcome the limitation of lack of labeled data for the 3D segmentation task.

Lung cancer is one of the most serious cancer-related diseases in Vietnam and all over the world. Early detection of lung nodules can help to increase the survival rate of lung cancer patients. Computer-aided diagnosis (CAD) systems are proposed in the literature for early detection of lung nodules. However, most of the current CAD systems are based on the building of high-quality machine learning models for a fixed dataset rather than taking into account the dataset properties which are very important for the lung cancer diagnosis. In this paper, we follow the direction of data-centric approach for lung nodule detection by proposing a data-centric method to improve detection performance of lung nodules on CT scans. Our method takes into account the dataset-specific features (nodule sizes and aspect ratios) to train detection models as well as add more training data from local Vietnamese hospital. We experiment our method on the three widely used object detection networks (Faster R-CNN, YOLOv3 and RetinaNet). The experimental results show that our proposed method improves detection sensitivity of these object detection models up to 4.24%.

In this paper, a computer-aided detection system is developed to detect lung nodules at an early stage using Computed Tomography (CT) scan images where lung nodules are one of the most important indicators to predict lung cancer. The developed system consists of four stages. First, the raw Computed Tomography lung images were preprocessed to enhance the image contrast and eliminate noise. Second, an automatic segmentation procedure for human's lung and pulmonary nodule canddates (nodules, blood vessels) using a two-level thresholding technique and morphological operations. Third, a feature fusion technique that fuses four feature extraction techniques: the statistical features of first and second order, value histogram features, histogram of oriented gradients features, and texture features of gray level co-occurrence matrix based on wavelet coefficients was utilised to extract the main features. The fourth stage is the classifier. Three classifiers were used and their performance was compared in order to obtain the highest classification accuracy. These are; multi-layer feed-forward neural network, radial basis function neural network and support vector machine. The performance of the proposed system was assessed using three quantitative parameters. These are: the classification accuracy rate, the sensitivity and the specificity. Forty standard computed tomography images containing 320 regions of interest obtained from an early lung cancer action project association were used to test and evaluate the developed system. The images consists of 40 computed tomography scan images. The results have shown that the fused features vector resulting from genetic algorithm as a feature selection technique and the support vector machine classifier give the highest classification accuracy rate, sensitivity and specificity values of 99.6%, 100% and 99.2%, respectively.

Lung cancer is the leading cause of cancer-related mortality worldwide, and early detection of lung nodules is crucial for improving patient survival rates. Computed tomography (CT) is a widely used screening tool for lung cancer, effectively capturing the morphological characteristics of lung nodules. However, the diversity and complexity of lung nodules present challenges for clinical detection and diagnosis. With advancements in deep learning and the availability of large annotated datasets, computer-aided detection (CADe) tools have shown high robustness, sensitivity, and low false-positive rates in lung nodule detection, gradually establishing themselves as mainstream methods in cancer screening. This review summarizes recent research advancements, current trends, and future challenges in automatic lung nodule detection within CT scans, covering studies published up to February 2024. The paper focuses on the techniques involved in various stages of automated lung nodule detection, including commonly used lung parenchyma segmentation methods, lung nodule detection, and false-positive reduction techniques. Finally, the article discusses the challenges faced by current methods and outlines potential future research directions. This review aims to provide researchers with the latest insights into the field of automatic lung nodule detection, advancing the development of early lung cancer diagnosis and treatment.

Lung nodules are an early manifestation of lung cancer. Early detection of lung nodules plays a vital role in improving the survival rate of patients. Computed tomography (CT) has fast scanning speed, high image size, and can capture tiny areas. The application of CT for clinical diagnosis is an effective method. We use convolutional neural network (CNN) to study the algorithm of lung nodule detection and diagnosis based on CT images. This paper is based on a lung nodule segmentation network combining VGG-16 and dilated convolution. And compared with traditional lung nodule segmentation methods and Inception v2, XOR evaluation coefficient, Hausdorff distance, Jaccard similarity coefficient, accuracy, sensitivity and specificity were used as segmentation evaluation indexes. VGG-16 is superior to traditional image processing methods in all indicators. The accuracy of VGG-16 is as high as 0.971, the false detection rate is only 0.101, and the missed detection rate is only 0.074. The segmented image result is closest to Ground Truth, and there is no problem of incorrect segmentation of lung parenchyma and lung nodules. The VGG-16 proposed in this paper improves the accuracy of segmenting lung nodules, and is superior to traditional image processing methods in various performance indicators, which can effectively help experts diagnose lung nodules.

Early detection increases overall survival among patients with lung cancer. This study formulated a machine learning method that processes chest X-rays (CXRs) to detect lung cancer early. After we preprocessed our dataset using monochrome and brightness correction, we used different kinds of preprocessing methods to enhance image contrast and then used U-net to perform lung segmentation. We used 559 CXRs with a single lung nodule labeled by experts to train a You Only Look Once version 4 (YOLOv4) deep-learning architecture to detect lung nodules. In a testing dataset of 100 CXRs from patients at Taipei Veterans General Hospital and 154 CXRs from the Japanese Society of Radiological Technology dataset, the sensitivity of the AI model using a combination of different preprocessing methods performed the best at 79%, with 3.04 false positives per image. We then tested the AI by using 383 sets of CXRs obtained in the past 5 years prior to lung cancer diagnoses. The median time from detection to diagnosis for radiologists assisted with AI was 46 (3-523) days, longer than that for radiologists (8 (0-263) days). The AI model can assist radiologists in the early detection of lung nodules.

Simple SummaryThe early detection of lung nodules is important for patient treatment and follow-up. Many researchers are investigating deep-learning-based lung nodule detection to ease the burden of lung nodule detection by radiologists. The purpose of this paper is to provide guidelines for collecting lung nodule data to facilitate research. We collected chest computed tomography scans reviewed by radiologists at three hospitals. In addition, several experiments were conducted using the large-scale open dataset, LUNA16. As a result of the experiment, it was possible to prove the value of using the collected data compared to using LUNA16. We also demonstrated the effectiveness of transfer learning from pre-trained learning weights in LUNA16. Finally, our study provides information on the amount of lung nodule data that must be collected to stabilize lung nodule detection performance.Early detection of lung nodules is essential for preventing lung cancer. However, the number of radiologists who can diagnose lung nodules is limited, and considerable effort and time are required. To address this problem, researchers are investigating the automation of deep-learning-based lung nodule detection. However, deep learning requires large amounts of data, which can be difficult to collect. Therefore, data collection should be optimized to facilitate experiments at the beginning of lung nodule detection studies. We collected chest computed tomography scans from 515 patients with lung nodules from three hospitals and high-quality lung nodule annotations reviewed by radiologists. We conducted several experiments using the collected datasets and publicly available data from LUNA16. The object detection model, YOLOX was used in the lung nodule detection experiment. Similar or better performance was obtained when training the model with the collected data rather than LUNA16 with large amounts of data. We also show that weight transfer learning from pre-trained open data is very useful when it is difficult to collect large amounts of data. Good performance can otherwise be expected when reaching more than 100 patients. This study offers valuable insights for guiding data collection in lung nodules studies in the future.

This paper is a review of the literature on detection of lung cancer using medical content based image retrieval. Lung cancer is prominent cancer as it states large number of deaths of more than a million every year. It creates need of detecting the lung nodule at early stage in Computer Tomography medical images. So to detect the occurrence of cancer nodule at early stage, the requirement of methods and techniques is increasing. There are different methods and techniques existing but none of them provide a better accuracy of detection. This provides content based image retrieval Computer Aided Diagnosis System (CAD) for early detection of lung nodules from the Chest Computer Tomography (CT) images. There are various phases described in the proposed CAD system. These are extraction of lung region from chest computer tomography (CT) images, segmentation of the lung region, feature extraction from the segmented region, and the classification of occurrence and non-occurrence of cancer in the lung. This paper describes the available literature and the techniques used for the detection of lung cancer.

Abstract— The robust nodule detection challenge in lung cancer identification has become difficult due to the variability of lung nodules and the complexity of the surrounding environment. Early detection of lung nodules is crucial for lung cancer survival and is an effective strategy to reduce patient mortality. The proposed method for identifying lung nodules from CT images utilizes VGG-16 convolutional neural networks, eliminating the need for manual feature extraction, as per previous feedback. The network is fed with raw lung CT images from publicly available LIDC-IDRI dataset. The VGG-16 convolutional neural network successfully classified lung CT images into benign and malignant categories, achieving 86% accuracy and reducing false positive rates. Keywords— VGG-16, Lung Cancer, Computed Tomography, Classification

Lung cancer is the most common cause of cancer-related death globally. As a preventive measure, the United States Preventive Services Task Force (USPSTF) recommends annual screening of high risk individuals with low-dose computed tomography (CT). The resulting volume of CT scans from millions of people will pose a significant challenge for radiologists to interpret. To fill this gap, computer-aided detection (CAD) algorithms may prove to be the most promising solution. A crucial first step in the analysis of lung cancer screening results using CAD is the detection of pulmonary nodules, which may represent early-stage lung cancer. The objective of this work is to develop and validate a reinforcement learning model based on deep artificial neural networks for early detection of lung nodules in thoracic CT images. Inspired by the AlphaGo system, our deep learning algorithm takes a raw CT image as input and views it as a collection of states, and output a classification of whether a nodule is present or not. The dataset used to train our model is the LIDC/IDRI database hosted by the lung nodule analysis (LUNA) challenge. In total, there are 888 CT scans with annotations based on agreement from at least three out of four radiologists. As a result, there are 590 individuals having one or more nodules, and 298 having none. Our training results yielded an overall accuracy of 99.1% [sensitivity 99.2%, specificity 99.1%, positive predictive value (PPV) 99.1%, negative predictive value (NPV) 99.2%]. In our test, the results yielded an overall accuracy of 64.4% (sensitivity 58.9%, specificity 55.3%, PPV 54.2%, and NPV 60.0%). These early results show promise in solving the major issue of false positives in CT screening of lung nodules, and may help to save unnecessary follow-up tests and expenditures.

Lung cancer has ranked first in incidence and mortality among all malignant tumors. Lung nodules are one of the early features of lung cancer. The early detection of lung nodules can help reduce the mortality rate of lung cancer. However, the detection performance of lung nodules is low due to their diverse shapes and small size. In this paper, an improved YOLOv5 method is proposed for lung nodule detection. By adding an attention mechanism to the feature extraction network, the feature expression capability is effectively improved. The method of feature fusion has also changed to make feature fusion more adequate. The experiments are conducted using the publicly available dataset provided by the Lung Image Database Consortium (LIDC). The experimental results show that the improved network has stronger feature expression and more adequate feature fusion capability compared with the original YOLOv5 network. The index of AP is improved by 1.4%.

The accurate and consistent border segmentation plays an important role in the tumor volume estimation and its treatment in the field of Medical Image Segmentation. Globally, Lung cancer is one of the leading causes of death and the early detection of lung nodules is essential for the early cancer diagnosis and survival rate of patients. The goal of this study was to demonstrate the feasibility of Deephealth toolkit including PyECVL and PyEDDL libraries to precisely segment lung nodules. Experiments for lung nodules segmentation has been carried out on UniToChest using PyECVL and PyEDDL, for data pre-processing as well as neural network training. The results depict accurate segmentation of lung nodules across a wide diameter range and better accuracy over a traditional detection approach. The datasets and the code used in this paper are publicly available as a baseline reference. KeywordsMedical image segmentationDeep learningU-NetDatasetChest CT scanLung nodulesDeepHealth

Early detection of lung nodules (LNs) is critical for prevention and treatment of lung cancer. However, current noninvasive diagnostic methods face significant challenges in reliably distinguishing benign from malignant nodules. Thus, there is an urgent need for novel molecular biomarkers or pathways to facilitate accurate identification of truly malignant LNs. Using the Gene Expression Omnibus (GEO) database and the “limma” package, we identified differentially expressed genes (DEGs) in lung nodules (LNs) by comparing benign and malignant samples. The oxidative stress-related genes were downloaded from the GenCards database. Subsequently, genes associated with immunity and oxidative stress were analyzed using weighted gene co-expression network analysis (WGCNA). A protein–protein interaction (PPI) network was constructed and hub genes were extracted using 12 centrality-based algorithms in the CytoHubba plugin. Shared DEGs from these analyses were subjected to functional enrichment analysis. To develop a diagnostic model for LNs, we investigated 113 combinations of 12 machine-learning algorithms, employing 10-fold cross-validation on the training set, followed by external validation of the test set. A total of 31 shared differentially expressed genes associated with immunity and oxidative stress were identified, including two hub genes, CDK2 and MCL1. Immune infiltration analysis revealed distinct patterns of immune cell infiltration in malignant LNs compared to those in benign controls. A promising 11-gene diagnostic signature was developed, which exhibited superior performance to existing LNs diagnostic models in both training and testing cohorts. This study developed a diagnostic model for malignant LNs, focusing on the shared genes associated with immunity and oxidative stress pathways. Furthermore, the identified hub genes facilitate a deeper understanding of the pathobiological mechanisms underlying the different types of LNs.

71PD Emergency department incidental lung nodule follow up: A best practice initiative