Assessment of artificial intelligence-aided computed tomography in lung cancer screening (original) (raw)
Related papers
Current Medical Imaging Formerly Current Medical Imaging Reviews
Background: Every year, lung cancer contributes to a high percentage deaths in the world. Early detection of lung cancer is important for its effective treatment, and non-invasive rapid methods are usually used for diagnosis. Introduction: In this study, we aimed to detect lung cancer using deep learning methods and determine the contribution of deep learning to the classification of lung carcinoma using a convolutional neural network (CNN). Methods: A total of 301 patients diagnosed with lung carcinoma pathologies in our hospital were included in the study. In the thorax, Computed Tomography (CT) was performed for diagnostic purposes prior to the treatment. After tagging the section images, tumor detection, small and non-small cell lung carcinoma differentiation, adenocarcinoma-squamous cell lung carcinoma differentiation, and adenocarcinoma-squamous cell-small cell lung carcinoma differentiation were sequentially performed using deep CNN methods. Result: In total, 301 lung carcino...
Development and clinical application of deep learning model for lung nodules screening on CT images
Scientific Reports, 2020
Lung cancer screening based on low-dose CT (LDCT) has now been widely applied because of its effectiveness and ease of performance. Radiologists who evaluate a large LDCT screening images face enormous challenges, including mechanical repetition and boring work, the easy omission of small nodules, lack of consistent criteria, etc. It requires an efficient method for helping radiologists improve nodule detection accuracy with efficiency and cost-effectiveness. Many novel deep neural network-based systems have demonstrated the potential for use in the proposed technique to detect lung nodules. However, the effectiveness of clinical practice has not been fully recognized or proven. Therefore, the aim of this study to develop and assess a deep learning (DL) algorithm in identifying pulmonary nodules (PNs) on LDCT and investigate the prevalence of the PNs in China. Radiologists and algorithm performance were assessed using the FROC score, ROC-AUC, and average time consumption. Agreement ...
Japanese Journal of Radiology, 2020
Purpose To evaluate the performance of a deep learning-based computer-aided diagnosis (CAD) system at detecting pulmonary nodules on CT by comparing radiologists' readings with and without CAD. Materials and methods A total of 120 chest CT images were randomly selected from patients with suspected lung cancer. The gold standard of nodules ≥ 3 mm was established by a panel of three expert radiologists. Two less experienced radiologists read the images without and afterward with CAD system. Their reading times were recorded. Results The radiologists' sensitivity increased from 20.9% to 38.0% with the introduction of CAD. The positive predictive value (PPV) decreased from 70.5% to 61.8%, and the F1-score increased from 32.2% to 47.0%. The sensitivity significantly increased from 13.7% to 32.4% for small nodules (3-6 mm) and from 33.3% to 47.6% for medium nodules (6-10 mm). CAD alone showed a sensitivity of 70.3%, a PPV of 57.9%, and an F1-score of 63.5%. Reading time decreased by 11.3% with the use of CAD. Conclusion CAD improved the less experienced radiologists' sensitivity in detecting pulmonary nodules of all sizes, especially including a significant improvement in the detection of clinically important-sized medium nodules (6-10 mm) as well as small nodules (3-6 mm) and reduced their reading time.
Towards radiologist-level cancer risk assessment in CT lung screening using deep learning
Computerized Medical Imaging and Graphics
How does a deep learning model for Lung Cancer Screening perform as compared to radiologists, how well do deep learning algorithms generalize across multiple datasets and how should we train these algorithms? Finding: A deep learning model demonstrates stable performance across three low-dose lung cancer screening datasets (NLST, LHMC, and Kaggle competition data), better performance than the widely used PanCan model, improved performance compared to the state-of-the-art represented by the winners of the Kaggle Data Science Bowl challenge on lung cancer screening, and comparable performance to a panel of six radiologists. Our findings also demonstrate the importance of a good nodule detector and confirms that the training for nodule detection and malignancy score prediction can be two separate processes. Meaning: The results suggest that a deep learning algorithm may be helpful to radiologists in their practice as a decision support tool or second opinion, but this will require further validation in a clinical setting.
International Journal of Engineering Research and Technology (IJERT), 2021
https://www.ijert.org/efficient-identification-of-lung-cancer-on-computed-tomography-images-by-using-methodology-classification-based-on-deep-learning https://www.ijert.org/research/efficient-identification-of-lung-cancer-on-computed-tomography-images-by-using-methodology-classification-based-on-deep-learning-IJERTCONV9IS05021.pdf Deep learning is associate AI feature that mimics the human brain's operations within the process of knowledge for object detection, speech recognition, language translation, and higher cognitive process. The prediction of cancer at earlier stages in recent years is mandatory to maximize the probability of the sufferer's survival. Lung cancer, which is known as one of the most prevalent diseases in humans worldwide, is the most dreadful type. As high-resolution images are made, medical image processing is very capable and offers key developments in current three-dimensional (3-D) medical imaging science and medicine. A major area of technical imaging needs to be developed due to developments in computer-assisted diagnosis and continued advancement in the field of computerized medical image visualization. Since lung cancer is a very common cancer, there are several forms of cancer. The classification of computed tomography (CT) images has increased the early identification of lung cancer, enabling victims to access early treatment. The resolution of the CT images has been used for the model's precision in different ways. Besides, early diagnosis has been significantly assisted by the identification of lumps or abnormalities in the photos. In deep learning models, classification plays a crucial role in sorting out the input images as positive and negative based on the model attribute created. However, the precision of the corresponding models developed has been diminished by the generalization of classifiers. An optimized classification strategy to predict lung cancer from the CT images is used to improve the precision and performance of the deep learning algorithm. The goal of optimization here will allow the model to adjust the stipulated method of extraction of features to the input images to feed into the network. Provided any resolution of the images, the model will be trained for predicting purposes.
Lung cancer is considered as the common cancerous neoplasms across the globe. In 2018, the World Health Organization (WHO) statistics approximated 2.09 million lung cancer cases with 1.76 million deaths globally. Early identification is an important aspect of providing the greatest chance of healing the patients. The objective of this manuscript was to explore how Deep Learning (DL) performs when the method is evaluated on datasets that are not from LUNA 16 for detection of pulmonary nodule and categorization of computed tomography scans. This report covered only peer-reviewed, original research papers using DL technology, and only findings were included from testing on datasets other than LUNA-16 and LIDC-IDRI. Deep learning utilizes Computed-Tomography (CT) to automatically improve the precision of an initial diagnosis of lung cancer. Consequently, this manuscript presents a short yet important review of DL methods to solve the extraordinary challenges of detecting lung cancer. In...
Enhancing Lung Cancer Detection with Deep Learning: A CT Image Classification Approach
IRJET, 2023
Lung cancer is a highly perilous illness ranking as one of the primary causes of disease and death, particularly when diagnosed in its initial stages. It presents significant challenges, as it is often only discernible after it has already diffused. This study proposes a lung cancer prognostication framework that uses deep learning to enhance the accuracy of cancer forecasting and disease determination, thereby enabling personalized treatment approaches based on disease severity. It consists of various steps, including image preprocessing and segmentation of lung CT image features extracted from the segmented images. Three different models, namely a DCNN model, a DCDNN model, and an ANN model, were employed for image classification, and a deep convolutional neural network (DCNN) was employed to detect lung diagnosis based on the extracted feature evaluation results showing the best accuracy of 99.41% in accurately discerning the presence or absence of lung cancer. The GAN model generates realistic lung CT scan images by training a generator to produce authentic images, and a discriminator to distinguish between real and fake images. The outcome of the system depends on the quality of the data, and a well-trained DCNN through training, validation, and testing on diverse datasets is crucial to ensure the reliability and generalizability of the model.
PLOS ONE, 2022
In this study, we evaluated a commercially available computer assisted diagnosis system (CAD). The deep learning algorithm of the CAD was trained with a lung cancer screening cohort and developed for detection, classification, quantification, and growth of actionable pulmonary nodules on chest CT scans. Here, we evaluated the CAD in a retrospective cohort of a routine clinical population. Materials and methods In total, a number of 337 scans of 314 different subjects with reported nodules of 3-30 mm in size were included into the evaluation. Two independent thoracic radiologists alternately reviewed scans with or without CAD assistance to detect, classify, segment, and register pulmonary nodules. A third, more experienced, radiologist served as an adjudicator. In addition, the cohort was analyzed by the CAD alone. The study cohort was divided into five different groups: 1) 178 CT studies without reported pulmonary nodules, 2) 95 studies with 1-10 pulmonary nodules, 23 studies from the same patients with 3) baseline and 4) followup studies, and 5) 18 CT studies with subsolid nodules. A reference standard for nodules was based on majority consensus with the third thoracic radiologist as required. Sensitivity, false positive (FP) rate and Dice inter-reader coefficient were calculated. Results After analysis of 470 pulmonary nodules, the sensitivity readings for radiologists without CAD and radiologist with CAD, were 71.9% (95% CI: 66.0%, 77.0%) and 80.3% (95% CI: 75.2%, 85.0%) (p < 0.01), with average FP rate of 0.11 and 0.16 per CT scan, respectively. Accuracy and kappa of CAD for classifying solid vs sub-solid nodules was 94.2% and 0.77, respectively. Average inter-reader Dice coefficient for nodule segmentation was 0.83 (95% CI: 0.39, 0.96) and 0.86 (95% CI: 0.51, 0.95) for CAD versus readers. Mean growth
2021
Deep learning is associate AI feature that mimics the human brain's operations within the process of knowledge for object detection, speech recognition, language translation, and higher cognitive process. The prediction of cancer at earlier stages in recent years is mandatory to maximize the probability of the sufferer's survival. Lung cancer, which is known as one of the most prevalent diseases in humans worldwide, is the most dreadful type. As high-resolution images are made, medical image processing is very capable and offers key developments in current three-dimensional (3D) medical imaging science and medicine. A major area of technical imaging needs to be developed due to developments in computer-assisted diagnosis and continued advancement in the field of computerized medical image visualization. Since lung cancer is a very common cancer, there are several forms of cancer. The classification of computed tomography (CT) images has increased the early identification of ...
European radiology, 2024
Purpose To compare the diagnostic performance of standalone deep learning (DL) algorithms and human experts in lung cancer detection on chest computed tomography (CT) scans. Materials and methods This study searched for studies on PubMed, Embase, and Web of Science from their inception until November 2023. We focused on adult lung cancer patients and compared the efficacy of DL algorithms and expert radiologists in disease diagnosis on CT scans. Quality assessment was performed using QUADAS-2, QUADAS-C, and CLAIM. Bivariate random-effects and subgroup analyses were performed for tasks (malignancy classification vs invasiveness classification), imaging modalities (CT vs low-dose CT [LDCT] vs high-resolution CT), study region, software used, and publication year. Results We included 20 studies on various aspects of lung cancer diagnosis on CT scans. Quantitatively, DL algorithms exhibited superior sensitivity (82%) and specificity (75%) compared to human experts (sensitivity 81%, specificity 69%). However, the difference in specificity was statistically significant, whereas the difference in sensitivity was not statistically significant. The DL algorithms' performance varied across different imaging modalities and tasks, demonstrating the need for tailored optimization of DL algorithms. Notably, DL algorithms matched experts in sensitivity on standard CT, surpassing them in specificity, but showed higher sensitivity with lower specificity on LDCT scans. Conclusion DL algorithms demonstrated improved accuracy over human readers in malignancy and invasiveness classification on CT scans. However, their performance varies by imaging modality, underlining the importance of continued research to fully assess DL algorithms' diagnostic effectiveness in lung cancer. Clinical relevance statement DL algorithms have the potential to refine lung cancer diagnosis on CT, matching human sensitivity and surpassing in specificity. These findings call for further DL optimization across imaging modalities, aiming to advance clinical diagnostics and patient outcomes. Key Points • Lung cancer diagnosis by CT is challenging and can be improved with AI integration. • DL shows higher accuracy in lung cancer detection on CT than human experts. • Enhanced DL accuracy could lead to improved lung cancer diagnosis and outcomes.