LUNA16 Dataset Research Articles

Fully Automated Neural Network Framework for Pulmonary Nodules Detection and Segmentation

Lung cancer is the leading cause of cancer death worldwide, and most patients are diagnosed with advanced stages for lack of symptoms in the early stages of the disease, leading to poor prognosis. It is thus of great importance to detect lung cancer in the early stages which can reduce mortality and improve patient survival significantly. Although there are many computer aided diagnosis (CAD) systems used for detecting pulmonary nodules, there are still few CAD systems for detection and segmentation, and their performance on small nodules is not ideal. Thus, in this paper, we propose a deep cascaded multitask framework called mobilenet split-attention Yolo unet, the mobilenet split-attention Yolo(Msa-yolo) greatly enhance the feature of small nodules and boost up their performance, the overall result shows that the mean accuracy precision (mAP) of our Msa-Yolo compared to Yolox has increased from 85.10% to 86.64% on LUNA16 dataset, and from 90.13% to 94.15% on LCS dataset compared to YoloX. Besides, we get only 8.35 average number of candidates per scan with 96.32% sensitivity on LUNA16 dataset, which greatly outperforms other existing systems. At the segmentation stage, the mean intersection over union (mIOU) of our CAD system has increased from 71.66% to 76.84% on LCS dataset comparing to baseline. Conclusion: A fast, accurate and robust CAD system for nodule detection, segmentation and classification is proposed in this paper. And it is confirmed by the experimental results that the proposed system possesses the ability to detect and segment small nodules.

A semantic segmentation of the lung nodules using a shape attention-guided contextual residual network

Objective. The early diagnosis of lung cancer depends on the precise segmentation of lung nodules. However, the variable size, uneven intensity, and blurred borders of lung nodules bring many challenges to the precise segmentation of lung nodules. Approach. We propose a shape attention-guided contextual residual network to address the difficult problem in lung nodule segmentation. Firstly, we establish a selective kernel convolution residual module to replace the original encoder and decoder. This module incorporates selective kernel convolution, which automatically selects convolutions with different receptive fields to acquire multi-scale spatial features. Secondly, we construct a multi-scale contextual attention module to assist the network in extracting multi-scale contextual features of local feature maps. Finally, we develop a shape attention-guided module to assist the network to restore details such as the boundary and shape of lung nodules during the upsampling phase. Main results. The proposed network is comprehensively analyzed using the publicly available LUNA16 data set, and an ablation experiment is designed to validate the effectiveness of each individual component. Ultimately, the dice similarity coefficient of the experimental results reaches 87.39% on the test set. Compared to other state-of-the-art segmentation methods, the proposed network achieves superior performance in lung nodule segmentation. Significance. Our proposed network improves the accuracy of lung nodule segmentation, which provides an important support for physicians to subsequently develop treatment plans.

A dual-task region-boundary aware neural network for accurate pulmonary nodule segmentation

Recently, the performance of pulmonary nodule segmentation has improved fast because of the development of deep learning-based methods. However, existing CNN-based methods still don’t solve the two issues, leading to poor segmentation: (1) The information of small nodules lost in continuous down-sampling operation; (2) Discriminative features can’t be extracted from non-solid nodules because whose gray values are close to the surrounding environment. This study proposes a novel dual-task region-boundary aware deep convolutional neural network to solve the problems above. A hierarchical feature module is proposed to capture multi-scale information, improving small nodules' segmentation accuracy. Boundary guided module is introduced to extract edge features and predict nodule boundaries directly. In addition, a feature aggregation module is proposed to aggregate features at different levels. Besides, to better optimize the segment results and reduce overfitting, the region-boundary aware loss function is proposed. The method is trained and tested on the LIDC-IDRI dataset and the LUNA16 dataset, and the results demonstrate that our method is efficient. More importantly, our method is suitable for the segmentation of various nodules, especially small nodules, GGO nodules, and part-solid nodules.

Optimal Thresholding for Multi-Window Computed Tomography (CT) to Predict Lung Cancer

Lung cancer is the world’s second-largest cause of cancer mortality. Patients’ lives can be saved if this malignancy is detected early. Doctors, however, encounter difficulties in detecting cancer in computed tomography (CT) images. In recent years, significant research has been devoted to producing automated lung nodule detection methods that can help radiologists. Most of them use only the lung window in their analysis and generally do not consider the mediastinal windows, which, according to recent research, carry important information. In this paper, we propose a simple yet effective algorithm to analyze multi-window CT images for lung nodules. The algorithm works in three steps. First, the CT image is preprocessed to suppress any noise and improve the image quality. Second, the lungs are extracted from the preprocessed image. Based on the histogram analysis of the lung windows, we propose a multi-Otsu-based approach for lung segmentation in lung windows. The case of mediastinal windows is rather difficult due to irregular patterns in the histograms. To this end, we propose a global–local-mean-based thresholding technique for lung detection. In the final step, the nodule candidates are extracted from the segmented lungs using simple intensity-based thresholding. The radius of the extracted objects is computed to separate the nodule from the bronchioles and blood vessels. The proposed algorithm is evaluated on the benchmark LUNA16 dataset and achieves accuracy of over 94% for lung tumor detection, surpassing that of existing similar methods.

3DAGNet: 3D Deep Attention and Global Search Network for Pulmonary Nodule Detection

In traditional clinical medicine, respiratory physicians or radiologists often identify the location of lung nodules by highlighting targets in consecutive CT slices, which is labor-intensive and easy-to-misdiagnose work. To achieve intelligent detection and diagnosis of CT lung nodules, we designed a 3D convolutional neural network, called 3DAGNet, for pulmonary nodule detection. Inspired by the diagnostic process of lung nodule localization by physicians, the 3DGNet includes a spatial attention and a global search module. A multi-scale cascade module has also been introduced to enhance the model detection using attention enhancement, global information search, and contextual feature fusion. The experimental results showed that the proposed network achieved accurate detection of lung nodule information, and our method achieves a high sensitivity of 88.08% of the average FROC score on the LUNA16 dataset. In addition, ablation experiments also demonstrated the effectiveness of our method.

Multi-scale detection of pulmonary nodules by integrating attention mechanism

The detection of pulmonary nodules has a low accuracy due to the various shapes and sizes of pulmonary nodules. In this paper, a multi-scale detection network for pulmonary nodules based on the attention mechanism is proposed to accurately predict pulmonary nodules. During data processing, the pseudo-color processing strategy is designed to enhance the gray image and introduce more contextual semantic information. In the feature extraction network section, this paper designs a basic module of ResSCBlock integrating attention mechanism for feature extraction. At the same time, the feature pyramid structure is used for feature fusion in the network, and the problem of the detection of small-size nodules which are easily lost is solved by multi-scale prediction method. The proposed method is tested on the LUNA16 data set, with an 83% mAP value. Compared with other detection networks, the proposed method achieves an improvement in detecting pulmonary nodules.

Detection and classification of lung cancer computed tomography images using a novel improved deep belief network with Gabor filters

The computer-aided diagnosis (CAD) method plays a considerable role in the automated recognition of medical images, considering the increasing numbers of lung cancer patients. Pulmonary nodules are a type of lung irregularity that can be detected early in the course of a patient's life using CAD-based pulmonary patient diagnosis. For several classification methods of lung CT images, the existing method has a lower performance in early cancer diagnosis and a longer processing time. To improve the performance of the classification method in terms of processing time and accuracy, we propose a novel method to classify lung CT images. In the proposed method of lung cancer classification, we use Gabor filters with an enhanced Deep Belief Network (E-DBN) with multiple classification methods. In this E-DBN, we use two cascaded RBMs, Gaussian-Bernoulli (GB) and Bernoulli–Bernoulli (BB) RBMs. A support vector machine (SVM) gives the best performance parameters of all applied methods. Our proposed model uses a support vector machine with an E-DBN to classify lung CT images and improve performance parameters like accuracy, sensitivity, specificity, F-1 score, false positive rate (FPR), false negative rate (FNR), and ROC curve. The proposed approaches are tested and evaluated using three publicly available datasets: the LIDC-IDRI and LUNA-16 datasets.

Lung Cancer Segmentation with Three-Parameter Logistic Type Distribution燤odel

Lung cancer is the leading cause of mortality in the world affecting both men and women equally. When a radiologist just focuses on the patient’s body, it increases the amount of strain on the radiologist and the likelihood of missing pathological information such as abnormalities are increased. One of the primary objectives of this research work is to develop computer-assisted diagnosis and detection of lung cancer. It also intends to make it easier for radiologists to identify and diagnose lung cancer accurately. The proposed strategy which was based on a unique image feature, took into consideration the spatial interaction of voxels that were next to one another. Using the U-NET+Three parameter logistic distribution-based technique, we were able to replicate the situation. The proposed technique had an average Dice co-efficient (DSC) of 97.3%, a sensitivity of 96.5% and a specificity of 94.1% when tested on the Luna-16 dataset. This research investigates how diverse lung segmentation, juxta pleural nodule inclusion, and pulmonary nodule segmentation approaches may be applied to create Computer Aided Diagnosis (CAD) systems. When we compared our approach to four other lung segmentation methods, we discovered that ours was the most successful. We employed 40 patients from Luna-16 datasets to evaluate this. In terms of DSC performance, the findings demonstrate that the suggested technique outperforms the other strategies by a significant margin.

Pulmonary nodule detection based on IR-UNet + + .

Lung cancer is one of the cancers with the highest incidence rate and death rate worldwide. An initial lesion of the lung appears as nodules in the lungs on CT images, and early and timely diagnosis can greatly improve the survival rate. Automatic detection of lung nodules can greatly improve work efficiency and accuracy rate. However, owing to the three-dimensional complex structure of lung CT data and the variation in shapes and appearances of lung nodules, high-precision detection of pulmonary nodules remains challenging. To address the problem, a new 3D framework IR-UNet + + is proposed for automatic pulmonary nodule detection in this paper. First, the Inception Net and ResNet are combined as the building blocks. Second, the squeeze-and-excitation structure is introduced into building blocks for better feature extraction. Finally, two short skip pathways are redesigned based on the U-shaped network. To verify the effectiveness of our algorithm, systematic experiments are conducted on the LUNA16 dataset. Experimental results show that the proposed network performs better than several existing lung nodule detection methods with the sensitivity of 1 FP/scan, 4 FPs/scan, and 8 FPs/scan being 90.13%, 94.77%, and 95.78%, respectively. Therefore, it comes to the conclusion that our proposed model has achieved superior performance for lung nodule detection.

Robust and accurate pulmonary nodule detection with self-supervised feature learning on domain adaptation.

Medical imaging data annotation is expensive and time-consuming. Supervised deep learning approaches may encounter overfitting if trained with limited medical data, and further affect the robustness of computer-aided diagnosis (CAD) on CT scans collected by various scanner vendors. Additionally, the high false-positive rate in automatic lung nodule detection methods prevents their applications in daily clinical routine diagnosis. To tackle these issues, we first introduce a novel self-learning schema to train a pre-trained model by learning rich feature representatives from large-scale unlabeled data without extra annotation, which guarantees a consistent detection performance over novel datasets. Then, a 3D feature pyramid network (3DFPN) is proposed for high-sensitivity nodule detection by extracting multi-scale features, where the weights of the backbone network are initialized by the pre-trained model and then fine-tuned in a supervised manner. Further, a High Sensitivity and Specificity (HS) network is proposed to reduce false positives by tracking the appearance changes among continuous CT slices on Location History Images (LHI) for the detected nodule candidates. The proposed method's performance and robustness are evaluated on several publicly available datasets, including LUNA16, SPIE-AAPM, LungTIME, and HMS. Our proposed detector achieves the state-of-the-art result of sensitivity at false positive per scan on the LUNA16 dataset. The proposed framework's generalizability has been evaluated on three additional datasets (i.e., SPIE-AAPM, LungTIME, and HMS) captured by different types of CT scanners.

Cross attention guided multi-scale feature fusion for false-positive reduction in pulmonary nodule detection

False-positive reduction is a crucial step of computer-aided diagnosis (CAD) system for pulmonary nodules detection and it plays an important role in lung cancer diagnosis. In this paper, we propose a novel cross attention guided multi-scale feature fusion method for false-positive reduction in pulmonary nodule detection. Specifically, a 3D SENet50 fed with a candidate nodule cube is applied as the backbone to acquire multi-scale coarse features. Then, the coarse features are refined and fused by the multi-scale fusion part to achieve a better feature extraction result. Finally, a 3D spatial pyramid pooling module is used to enhance receptive field and a distributed aligned linear classifier is applied to get the confidence score. In addition, each of the five nodule cubes with different sizes centering on every testing nodule position is fed into the proposed framework to obtain a confidence score separately and a weighted fusion method is used to improve the generalization performance of the model. Extensive experiments are conducted to demonstrate the effectiveness of the classification performance of the proposed model. The data used in our work is from the LUNA16 pulmonary nodule detection challenge. In this data set, the number of true-positive pulmonary nodules is 1,557, while the number of false-positive ones is 753,418. The new method is evaluated on the LUNA16 dataset and achieves the score of the competitive performance metric (CPM) 84.8%.

A Cascaded Multi-Stage Framework for Automatic Detection and Segmentation of Pulmonary Nodules in Developing Countries.

Lung cancer has the highest mortality rate among all malignancies. Non-micro pulmonary nodules are the primary manifestation of early-stage lung cancer. If patients can be detected with nodules in the early stage and receive timely treatment, their survival rate can be improved. Due to the large number of patients and limited medical resources, doctors take a longer time to make a diagnosis, which reduces efficiency and accuracy. Besides, there are no suitable approaches for developing countries. Therefore, we propose a 2.5D-based cascaded multi-stage framework for automatic detection and segmentation (DS-CMSF) of pulmonary nodules. The first three stages of the framework are used to discover lesions, and the latter stage is used to segment them. The first locating stage introduces the classical 2D-based Yolov5 model to locate the nodules roughly on axial slices. The second aggregation stage proposes a candidate nodule selection (CNS) algorithm to locate further and reduce redundant candidate nodules. The third classification stage uses a multi-size 3D-based fusion model to accommodate nodules of varying sizes and shapes for false-positive reducing. The last segmentation stage introduces multi-scale and attention modules into 3D-based UNet autoencoder to segment the nodular regions finely. Our proposed framework achieves 95.95% sensitivity and 89.50% CPM for nodules detection on the LUNA16 dataset, and 86.75% DSC for nodules segmentation on the LIDC-IDRI dataset. Moreover, our approach also achieves the accuracy-complexity trade-off, which can effectively realize the auxiliary diagnosis of pulmonary nodules in developing countries.

A Lower False Positive Pulmonary Nodule Detection Approach for Early Lung Cancer Screening.

Pulmonary nodule detection with low-dose computed tomography (LDCT) is indispensable in early lung cancer screening. Although existing methods have achieved excellent detection sensitivity, nodule detection still faces challenges such as nodule size variation and uneven distribution, as well as excessive nodule-like false positive candidates in the detection results. We propose a novel two-stage nodule detection (TSND) method. In the first stage, a multi-scale feature detection network (MSFD-Net) is designed to generate nodule candidates. This includes a proposed feature extraction network to learn the multi-scale feature representation of candidates. In the second stage, a candidate scoring network (CS-Net) is built to estimate the score of candidate patches to realize false positive reduction (FPR). Finally, we develop an end-to-end nodule computer-aided detection (CAD) system based on the proposed TSND for LDCT scans. Experimental results on the LUNA16 dataset show that our proposed TSND obtained an excellent average sensitivity of 90.59% at seven predefined false positives (FPs) points: 0.125, 0.25, 0.5, 1, 2, 4, and 8 FPs per scan on the FROC curve introduced in LUNA16. Moreover, comparative experiments indicate that our CS-Net can effectively suppress false positives and improve the detection performance of TSND.

Data augmentation based on multiple oversampling fusion for medical image segmentation

A high-performance medical image segmentation model based on deep learning depends on the availability of large amounts of annotated training data. However, it is not trivial to obtain sufficient annotated medical images. Generally, the small size of most tissue lesions, e.g., pulmonary nodules and liver tumours, could worsen the class imbalance problem in medical image segmentation. In this study, we propose a multidimensional data augmentation method combining affine transform and random oversampling. The training data is first expanded by affine transformation combined with random oversampling to improve the prior data distribution of small objects and the diversity of samples. Secondly, class weight balancing is used to avoid having biased networks since the number of background pixels is much higher than the lesion pixels. The class imbalance problem is solved by utilizing weighted cross-entropy loss function during the training of the CNN model. The LUNA16 and LiTS17 datasets were introduced to evaluate the performance of our works, where four deep neural network models, Mask-RCNN, U-Net, SegNet and DeepLabv3+, were adopted for small tissue lesion segmentation in CT images. In addition, the small tissue segmentation performance of the four different deep learning architectures on both datasets could be greatly improved by incorporating the data augmentation strategy. The best pixelwise segmentation performance for both pulmonary nodules and liver tumours was obtained by the Mask-RCNN model, with DSC values of 0.829 and 0.879, respectively, which were similar to those of state-of-the-art methods.

Deep learning-based growth prediction for sub-solid pulmonary nodules on CT images.

BackgroundEstimating the growth of pulmonary sub-solid nodules (SSNs) is crucial to the successful management of them during follow-up periods. The purpose of this study is to (1) investigate the measurement sensitivity of diameter, volume, and mass of SSNs for identifying growth and (2) seek to establish a deep learning-based model to predict the growth of SSNs.MethodsA total of 2,523 patients underwent at least 2-year examination records retrospectively collected with sub-solid nodules. A total of 2,358 patients with 3,120 SSNs from the NLST dataset were randomly divided into training and validation sets. Patients from the Yibicom Health Management Center and Guangdong Provincial People’s Hospital were collected as an external test set (165 patients with 213 SSN). Trained models based on LUNA16 and Lndb19 datasets were employed to automatically obtain the diameter, volume, and mass of SSNs. Then, the increase rate in measurements between cancer and non-cancer groups was studied to evaluate the most appropriate way to identify growth-associated lung cancer. Further, according to the selected measurement, all SSNs were classified into two groups: growth and non-growth. Based on the data, the deep learning-based model (SiamModel) and radiomics model were developed and verified.ResultsThe double time of diameter, volume, and mass were 711 vs. 963 days (P = 0.20), 552 vs. 621 days (P = 0.04) and 488 vs. 623 days (P< 0.001) in the cancer and non-cancer groups, respectively. Our proposed SiamModel performed better than the radiomics model in both the NLST validation set and external test set, with an AUC of 0.858 (95% CI 0.786–0.921) and 0.760 (95% CI 0.646–0.857) in the validation set and 0.862 (95% CI 0.789–0.927) and 0.681 (95% CI 0.506–0.841) in the external test set, respectively. Furthermore, our SiamModel could use the data from first-time CT to predict the growth of SSNs, with an AUC of 0.855 (95% CI 0.793–0.908) in the NLST validation set and 0.821 (95% CI 0.725–0.904) in the external test set.ConclusionMass increase rate can reflect more sensitively the growth of SSNs associated with lung cancer than diameter and volume increase rates. A deep learning-based model has a great potential to predict the growth of SSNs.

A bi-directional deep learning architecture for lung nodule semantic segmentation.

Lung nodules are abnormal growths and lesions may exist. Both lungs may have nodules. Most lung nodules are harmless (not cancerous/malignant). Pulmonary nodules are rare in lung cancer. X-rays and CT scans identify the lung nodules. Doctors may term the growth a lung spot, coin lesion, or shadow. It is necessary to obtain properly computed tomography (CT) scans of the lungs to get an accurate diagnosis and a good estimate of the severity of lung cancer. This study aims to design and evaluate a deep learning (DL) algorithm for identifying pulmonary nodules (PNs) using the LUNA-16 dataset and examine the prevalence of PNs using DB-Net. The paper states that a new, resource-efficient deep learning architecture is called for, and it has been given the name of DB-NET. When a physician orders a CT scan, they need to employ an accurate and efficient lung nodule segmentation method because they need to detect lung cancer at an early stage. However, segmentation of lung nodules is a difficult task because of the nodules' characteristics on the CT image as well as the nodules' concealed shape, visual quality, and context. The DB-NET model architecture is presented as a resource-efficient deep learning solution for handling the challenge at hand in this paper. Furthermore, it incorporates the Mish nonlinearity function and the mask class weights to improve segmentation effectiveness. In addition to the LUNA-16 dataset, which contained 1200 lung nodules collected during the LUNA-16 test, the LUNA-16 dataset was extensively used to train and assess the proposed model. The DB-NET architecture surpasses the existing U-NET model by a dice coefficient index of 88.89%, and it also achieves a similar level of accuracy to that of human experts.

Two-stage lung nodule detection framework using enhanced UNet and convolutional LSTM networks in CT images

Lung cancer is one of the leading causes of cancer deaths globally, and lung nodules are the primary indicators that aid in early detection. The computer-aided detection (CADe) system acts as a second reader, reducing the variability in lung cancer risk assessment across physicians. This work aims to improve the performance of CADe systems by developing high sensitive and resilient detection networks using deep learning. This paper proposes a novel CADe framework to detect nodules from CT scans using an enhanced UNet in conjunction with a pyramid dilated convolutional long short term memory (PD-CLSTM) network. The proposed CADe system works in two stages: nodule detection and false nodule elimination. In the first stage, a modified UNet-based model, Atrous UNet+, is proposed to detect nodule candidates from axial slices using dilation and ensemble mechanisms. Dilated convolution is a powerful technique for dense prediction by incorporating larger context information without increasing the computation load. Ensemble skip connections fuse multilevel semantic features that help detect nodules of diverse sizes. In the second stage, The pyramid dilated convolutional LSTM network is proposed to identify true nodules using inter-slice and intra-slice spatial features of 3D nodule patches. In this work, a novel idea of applying convolution long short-term memory (ConvLSTM) is attempted to categorize true nodules from false nodules and help to eliminate false nodules. Experimental results on the LUNA16 dataset show that our proposed CADe system achieves the best average sensitivity of 0.930 at seven predefined FPRs: 1/8, 1/4, 1/2, 1, 2, 4, and 8 FPs per scan. Also, the proposed CADe system detects small nodules in the range of 5–9 mm with a sensitivity of 0.92 and other nodules (>10 mm) with a sensitivity of 0.93, resulting in a high detection rate in recognizing nodules of diverse sizes.

Performance Analysis of State-of-the-Art CNN Architectures for LUNA16.

The convolutional neural network (CNN) has become a powerful tool in machine learning (ML) that is used to solve complex problems such as image recognition, natural language processing, and video analysis. Notably, the idea of exploring convolutional neural network architecture has gained substantial attention as well as popularity. This study focuses on the intrinsic various CNN architectures: LeNet, AlexNet, VGG16, ResNet-50, and Inception-V1, which have been scrutinized and compared with each other for the detection of lung cancer using publicly available LUNA16 datasets. Furthermore, multiple performance optimizers: root mean square propagation (RMSProp), adaptive moment estimation (Adam), and stochastic gradient descent (SGD), were applied for this comparative study. The performances of the three CNN architectures were measured for accuracy, specificity, sensitivity, positive predictive value, false omission rate, negative predictive value, and F1 score. The experimental results showed that the CNN AlexNet architecture with the SGD optimizer achieved the highest validation accuracy for CT lung cancer with an accuracy of 97.42%, misclassification rate of 2.58%, 97.58% sensitivity, 97.25% specificity, 97.58% positive predictive value, 97.25% negative predictive value, false omission rate of 2.75%, and F1 score of 97.58%. AlexNet with the SGD optimizer was the best and outperformed compared to the other state-of-the-art CNN architectures.

MSANet: Multiscale Aggregation Network Integrating Spatial and Channel Information for Lung Nodule Detection.

Improving the detection accuracy of pulmonary nodules plays an important role in the diagnosis and early treatment of lung cancer. In this paper, a multiscale aggregation network (MSANet), which integrates spatial and channel information, is proposed for 3D pulmonary nodule detection. MSANet is designed to improve the network's ability to extract information and realize multiscale information fusion. First, multiscale aggregation interaction strategies are used to extract multilevel features and avoid feature fusion interference caused by large resolution differences. These strategies can effectively integrate the contextual information of adjacent resolutions and help to detect different sized nodules. Second, the feature extraction module is designed for efficient channel attention and self-calibrated convolutions (ECA-SC) to enhance the interchannel and local spatial information. ECA-SC also recalibrates the features in the feature extraction process, which can realize adaptive learning of feature weights and enhance the information extraction ability of features. Third, the distribution ranking (DR) loss is introduced as the classification loss function to solve the problem of imbalanced data between positive and negative samples. The proposed MSANet is comprehensively compared with other pulmonary nodule detection networks on the LUNA16 dataset, and a CPM score of 0.920 is obtained. The results show that the sensitivity for detecting pulmonary nodules is improved and that the average number of false-positives is effectively reduced. The proposed method has advantages in pulmonary nodule detection and can effectively assist radiologists in pulmonary nodule detection.

Automatic Detection and Localization of Pulmonary Nodules in CT Images Based on YOLOv5

&lt;p&gt;Lung cancer has always threatening human health and life. As small pulmonary nodules are main early features of lung cancer, early screening for small pulmonary nodules through computed tomography (CT) imaging is essential for the treatment of lung cancer. In this paper, the YOLOv5 model is improved to improve the ability of detection and recognition of small pulmonary nodules in complex CT lung images. Firstly, the preprocessing step is put into effect to obtain the lung parenchyma in CT images. Then, the backbone structure of YOLOv5 is improved by iResNet to improve the ability of feature extraction, and the feature fusion network is improved by BiFPN to improve the detection ability of small pulmonary nodules. Finally, the strategy of group normalization is used to improve the model performance under small batch size training condition. The experimental results on LUNA16 data set show that the detection AP of the improved model reach 94.8%, the competitive index score is 0.895, and the sensitivity is 78.1%, 94.4%, under 1/8 and 1/4 FPs, respectively. Compared with other two-dimensional target detection models, the improved yolov5 model has better detection ability of small pulmonary nodules. And, the results are better than most other two-dimensional pulmonary nodule detection methods. In addition, compared with other three-dimensional pulmonary nodule detection methods.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;