Detection Of Pulmonary Nodules Research Articles

Virtual thoracoscopic imaging for accurate pulmonary nodule localization: clinical experience.

The increasing detection of small pulmonary nodules on computed tomography (CT) warrants simple and effective nodule localization methods. We describe our clinical experience using an experimental computer that displays virtual thoracoscopic images. This device constructs three-dimensional images from preoperative CT scans and simulates the deflated lung parenchyma in the lateral decubitus position. Five patients underwent lung resection using this technology. The device provided images that closely resembled actual thoracoscopic images in all cases. This method addresses the limitations of other localization techniques such as allergic reactions and mechanical marker-related complications. The method only requires preoperative CT images, and the process is semi-automatically performed by specifying the nodule location, thoracoscopic camera insertion site, and camera angle. This study is still in the preliminary phase and has several limitations. However, this method has the potential to accurately predict nodule locations and eliminate the many risks associated with other techniques.

NAS FD Lung: A novel lung assist diagnostic system based on neural architecture search

In the detection and recognition of lung nodules, pulmonary nodules vary in size and shape and contain many similar tissues and organs around them, leading to the problems of both missed detection and false detection in existing detection algorithms. Designing proprietary detection and recognition networks manually requires substantial professional expertise. This process is time-consuming and labour-intensive and leads to issues like parameter redundancy and improper feature selection. Therefore, this paper proposes a new pulmonary CAD (computer-aided diagnosis) system for pulmonary nodules, NAS FD Lung (Using the NAS approach to search deep FPN and DPN networks), that can automatically learn and generate a deep learning network tailored to pulmonary nodule detection and recognition task requirements. NAS FD Lung aims to use automatic search to generate deep learning networks in the auxiliary diagnosis of pulmonary nodules to replace the manual design of deep learning networks. NAS FD Lung comprises two automatic search networks: BM NAS-FPN (Using NAS methods to search for deep FPN structures with Binary operation and Matrix multiplication fusion methods) network for nodule detection and NAS-A-DPN (Using the NAS approach to search deep DPN networks with attention mechanism) for nodule identification. The proposed technique is tested on the LUNA16 dataset, and the experimental results show that the model is superior to many existing state-of-the-art approaches. The detection accuracy of lung nodules is 98.23%. Regarding the lung nodules classification, the accuracy, specificity, sensitivity, and AUC values achieved 96.32%,97.14%,95.82%, and 98.33%, respectively.

EP.04B.03 The Diagnostic Efficacy of Seven Lung Cancer Autoantibodies in Early Detection of Pulmonary Ground-Glass Nodules

EP.04B.03 The Diagnostic Efficacy of Seven Lung Cancer Autoantibodies in Early Detection of Pulmonary Ground-Glass Nodules

Leveraging artificial intelligence for timely detection and referral of incidental pulmonary nodules at a safety-net hospital.

422 Background: Incidental pulmonary nodules (IPNs) are commonly reported through a multitude of radiologic exams. A small number of these IPNs can harbor lung cancer (LC). To aide LC detection rates, hospitals must identify and validate the completion of appropriate follow-up regarding IPNs in a timely manner. The problem with timely referral and completion of work up is found to be amplified in safety-net settings with limited resources. John Peter Smith (JPS) hospital, a safety-net hospital, has developed a method to identify, track, and refer patients presenting with IPNs. Methods: JPS has created an algorithm to classify all IPNs by means of Thynk Health, an Artificial Intelligence (AI) platform that uses Natural Language Processing (NLP) to identify and track incidental findings and lung cancer screening patients (LCS). The algorithm created a scoring system by combining Fleischner Society (2017) and the American College of Radiology (ACR) LCS (Lung-RADS) guideline recommendations. The scoring system was designed to mimic Lung-RADS established by the ACR (1, 2, 3, 4A, and 4B). The assigned score creates a risk stratification to assist providers in the patient’s care plan. Using NLP, the project queried radiologic exams performed at JPS searching for key terminology relating to IPNs. Findings were then reviewed by radiology staff for validity and assigned a score based on the algorithm. Program exclusions, when identified in the radiology report, included: patient < 35 years, patient has known cancer or under surveillance of oncology team, abnormalities favoring infectious process, LCS patients and when nodule size is not reported in the radiologist’s dictation. Results: A current state analysis was completed from 3/25/24 to 4/25/24. The AI platform analyzed 5,276 CT exams (2049 abdomen, 1347 head/neck, and 1880 chest) involving partial or complete imaging of the lungs. A total of 727 (13.8%) IPNs were flagged for review. After excluding exams falling outside of the set program parameters, a total of 178 (3.4%) IPNs were identified. 21 (11.8%) of the IPNs identified received a score of 4A or 4B. Patients found to have a score of 4A (11, 6.2%) and 4B (10, 5.6%) underwent additional review. Conclusions: Our team has created a unique system that can be used as a model for other large health systems. By leveraging technology, we are able to successfully identify key factors associated with IPNs to help ensure patients receive the recommended care in a timely manner. Results of JPS incidental pulmonary nodule program: first monthly analysis. JPS Pulmonary Nodule Score 4A 4B Number of Patients (% of IPNs) 11 (6.2%) 10 (5.6%) Median Age (years) 70 68.5 JPS Assigned PCP 1 7 (63.6%) 7 (70%) Median Smoking History (PY) 2 6.4 24.5 Average Nodule Size (mm) 11.5 34.3 Pulmonary Referral 3/11 (27.3%) 7/10 (70%) Positive for Cancer 0 3/4 (75%) 1 Primary care provider. 2 Pack years.

Dual-energy subtraction radiography (DESR): a systematic review and meta-analysis of pulmonary nodule detection

PurposeThis study examined the literature to compare the accuracy, sensitivity, and specificity of dual-energy subtraction radiography (DESR) with conventional radiography (CR) in the detection of pulmonary nodules. To our knowledge, no meta-analysis has been conducted to compare DESR with CR. Material and MethodsThe authors searched Pubmed using the terms “Dual-energy subtraction radiography,” and “Dual-Energy Chest Radiography.” Only studies comparing the detection of pulmonary nodules between DESR and CR were included. Studies utilizing artificial intelligence were excluded. The primary study outcomes analyzed were the mean difference of Receiver Operating Characteristic Area under the Curve (ROC AUC), mean difference of sensitivity, and mean difference of specificity. ResultsTwenty-three studies between 1994 - 2022 were included. Of these twenty-three, eighteen reported ROC AUC statistics. The difference between DESR ROC AUC (mean = 0.7702, SD = 0.1361) and CR ROC AUC (mean = 0.7106, SD = 0.1183) was 0.0597 (p<0.001).Sensitivity data was reported for thirteen of the twenty-three selected studies. The difference between DESR sensitivity (mean = 0.5753, SD = 0.1546) and CR sensitivity (mean = 0.4391, SD = 0.1007) was 0.136 (p<0.001).Specificity data was reported for ten of the twenty-three selected studies. The difference between DESR specificity (mean = 0.753, SD = 0.1575) and CR specificity (mean = 0.764, SD = 0.1168) was -0.011 (p=0.767). This was not statistically significant. ConclusionDESR showed superior sensitivity and ROC AUC values compared to CR in detecting pulmonary nodules. There was no difference in specificity.

Impact of artificial intelligence assistance on pulmonary nodule detection and localization in chest CT: a comparative study among radiologists of varying experience levels

The study aimed to evaluate the impact of AI assistance on pulmonary nodule detection rates among radiology residents and senior radiologists, along with assessing the effectiveness of two different commercialy available AI software systems in improving detection rates and LungRADS classification in chest CT. The study cohort included 198 participants with 221 pulmonary nodules. Residents’ mean detection rate increased significantly from 64 to 77% with AI assist, while seniors’ detection rate remained largely unchanged (85% vs. 86%). Residents showed significant improvement in segmental nodule localization with AI assistance, seniors did not. Software 2 slightly outperformed software 1 in increasing detection rates (67–77% vs. 80–86%), but neither significantly affected LungRADS classification. The study suggests that clinical experience mitigates the need for additional AI software, with the combination of CAD with residents being the most beneficial approach. Both software systems performed similarly, with software 2 showing a slightly higher but non-significant increase in detection rates.

Genomic Landscape Features of Minimally Invasive Adenocarcinoma and Invasive Lung Adenocarcinoma

Abstract Background The widespread implementation of computed tomography has significantly increased the detection of small pulmonary nodules, including atypical adenomatous hyperplasia, minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC). Few studies have focused on the genomic differences between MIA and IAC. Methods We retrospectively analyzed patients with lung adenocarcinoma (LUAD) who underwent surgery from January 2020 to December 2023. Patients were categorized into MIA and IAC groups. The mutation status of common driver genes was assessed using next-generation sequencing. Results A total of 422 LUAD patients were included in the study, comprising 119 MIA cases and 303 IAC cases. MIA patients were younger and predominantly female compared with IAC patients. EGFR mutations were detected in 251 patients (59.5%), with the frequency of EGFR mutations increasing from 37.0% in MIA to 68.3% in IAC (p &lt; 0.001). TP53 mutations were found in 108 patients (25.6%), with 7 patients (5.9%) in MIA and 101 patients (33.3%) in IAC (p &lt; 0.001). ERBB2 mutations were identified in 23 MIA patients (19.3%) and 20 IAC patients (6.6%) (p &lt; 0.001). Additionally, CDKN2A mutations were detected in 23 IAC patients (7.6%), while no mutations in this gene were found in the MIA group. Moreover, ALK and RET gene fusions were identified in 11 patients, respectively. Conclusion ERBB2 mutations and RET fusions are early genomic events in LUAD, while TP53 and CDKN2A mutations and ALK fusions occur later. Genomic intratumor heterogeneity likely arises early, before invasive characteristics develop.

Data-driven risk stratification and precision management of pulmonary nodules detected on chest computed tomography.

The widespread implementation of low-dose computed tomography (LDCT) in lung cancer screening has led to the increasing detection of pulmonary nodules. However, precisely evaluating the malignancy risk of pulmonary nodules remains a formidable challenge. Here we propose a triage-driven Chinese Lung Nodules Reporting and Data System (C-Lung-RADS) utilizing a medical checkup cohort of 45,064 cases. The system was operated in a stepwise fashion, initially distinguishing low-, mid-, high- and extremely high-risk nodules based on their size and density. Subsequently, it progressively integrated imaging information, demographic characteristics and follow-up data to pinpoint suspicious malignant nodules and refine the risk scale. The multidimensional system achieved a state-of-the-art performance with an area under the curve (AUC) of 0.918 (95% confidence interval (CI) 0.918-0.919) on the internal testing dataset, outperforming the single-dimensional approach (AUC of 0.881, 95% CI 0.880-0.882). Moreover, C-Lung-RADS exhibited a superior sensitivity compared with Lung-RADS v2022 (87.1% versus 63.3%) in an independent cohort, which was screened using mobile computed tomography scanners to broaden screening accessibility in resource-constrained settings. With its foundation in precise risk stratification and tailored management, this system has minimized unnecessary invasive procedures for low-risk cases and recommended prompt intervention for extremely high-risk nodules to avert diagnostic delays. This approach has the potential to enhance the decision-making paradigm and facilitate a more efficient diagnosis of lung cancer during routine checkups as well as screening scenarios.

Effects of tube voltage, radiation dose and adaptive statistical iterative reconstruction strength level on the detection and characterization of pulmonary nodules in ultra-low-dose chest CT

ObjectiveTo explore the effects of tube voltage, radiation dose and adaptive statistical iterative reconstruction (ASiR-V) strength level on the detection and characterization of pulmonary nodules by an artificial intelligence (AI) software in ultra-low-dose chest CT (ULDCT).Materials and methodsAn anthropomorphic thorax phantom containing 12 spherical simulated nodules (Diameter: 12 mm, 10 mm, 8 mm, 5 mm; CT value: -800HU, -630HU, 100HU) was scanned with three ULDCT protocols: Dose-1 (70kVp:0.11mSv, 100kVp:0.10mSv), Dose-2 (70kVp:0.34mSv, 100kVp:0.32mSv), Dose-3 (70kVp:0.53mSv, 100kVp:0.51mSv). All scanning protocols were repeated five times. CT images were reconstructed using four different strength levels of ASiR-V (0%=FBP, 30%, 50%, 70%ASiR-V) with a slice thickness of 1.25 mm. The characteristics of the physical nodules were used as reference standards. All images were analyzed using a commercially available AI software to identify nodules for calculating nodule detection rate (DR) and to obtain their long diameter and short diameter, which were used to calculate the deformation coefficient (DC) and size measurement deviation percentage (SP) of nodules. DR, DC and SP of different imaging groups were statistically compared.ResultsImage noise decreased with the increase of ASiR-V strength level, and the 70 kV images had lower noise under the same strength level (mean-value 70 kV: 40.14 ± 7.05 (dose 1), 27.55 ± 7.38 (dose 2), 23.88 ± 6.98 (dose 3); 100 kV: 42.36 ± 7.62 (dose 1); 30.78 ± 6.87 (dose 2); 26.49 ± 6.61 (dose 3)). Under the same dose level, there were no differences in DR between 70 kV and 100 kV (dose 1: 58.76% vs. 58.33%; dose 2: 73.33% vs. 70.83%; dose 3: 75.42% vs. 75.42%, all p > 0.05). The DR of GGNs increased significantly at dose 2 and higher (70 kV: 38.12% (dose 1), 60.63% (dose 2), 64.38% (dose 3); 100 kV: 37.50% (dose 1), 59.38% (dose 2), 66.25% (dose 3)). In general, the use of ASiR-V at higher strength levels (> 50%) and 100 kV provided better (lower) DC and SP.ConclusionDetection rates are similar between 70 kV and 100 kV scans. The 70 kV images have better noise performance under the same ASiR-V level, while images of 100 kV and higher ASiR-V levels are better in preserving the nodule morphology (lower DC and SP); the dose levels above 0.33mSv provide high sensitivity for nodules detection, especially the simulated ground glass nodules.

Detection of Pulmonary Nodules on Ultra-low Dose Chest Computed Tomography With Deep-learning Image Reconstruction Algorithm.

To evaluate the accuracy of ultra-low dose (ULD) chest computed tomography (CT), with a radiation exposure equivalent to a 2-view chest x-ray, for pulmonary nodule detection using deep learning image reconstruction (DLIR). This prospective cross-sectional study included 60 patients referred to our institution for assessment or follow-up of solid pulmonary nodules. All patients underwent low-dose (LD) and ULD chest CT within the same examination session. LD CT data were reconstructed using Adaptive Statistical Iterative Reconstruction-V (ASIR-V), whereas ULD CT data were reconstructed using DLIR and ASIR-V. ULD CT images were reviewed by 2 readers and LD CT images were reviewed by an experienced thoracic radiologist as the reference standard. Quantitative image quality analysis was performed, and the detectability of pulmonary nodules was assessed according to their size and location. The effective radiation dose for ULD CT and LD CT were 0.13±0.01 and 1.16±0.6mSv, respectively. Over the whole population, LD CT revealed 733 nodules. At ULD, DLIR images significantly exhibited better image quality than ASIR-V images. The overall sensitivity of DLIR reconstruction for the detection of solid pulmonary nodules from the ULD CT series was 93% and 82% for the 2 readers, with a good to excellent agreement with LD CT (ICC=0.82 and 0.66, respectively). The best sensitivities were observed in the middle lobe (97% and 85%, respectively). At ULD, DLIR reconstructions, with minimal radiation exposure that could facilitate large-scale screening, allow the detection of pulmonary nodules with high sensitivity in an unrestricted BMI population.

Pulmonary Nodule Detection, Segmentation and Classification Using Deep Learning: A Comprehensive Literature Review

Lung cancer is a leading cause of cancer-related deaths worldwide, emphasizing the significance of early detection. Computer-aided diagnostic systems have emerged as valuable tools for aiding radiologists in the analysis of medical images, particularly in the context of lung cancer screening. A typical pipeline for lung cancer diagnosis involves pulmonary nodule detection, segmentation, and classification. Although traditional machine learning methods have been deployed in the previous years with great success, this literature review focuses on state-of-the-art deep learning methods. The objective is to extract key insights and methodologies from deep learning studies that exhibit high experimental results in this domain. This paper delves into the databases utilized, preprocessing steps applied, data augmentation techniques employed, and proposed methods deployed in studies with exceptional outcomes. The reviewed studies predominantly harness cutting-edge deep learning methodologies, encompassing traditional convolutional neural networks (CNNs) and advanced variants such as 3D CNNs, alongside other innovative approaches such as Capsule networks and transformers. The methods examined in these studies reflect the continuous evolution of deep learning techniques for pulmonary nodule detection, segmentation, and classification. The methodologies, datasets, and techniques discussed here collectively contribute to the development of more efficient computer-aided diagnostic systems, empowering radiologists and dfhealthcare professionals in the fight against this deadly disease.

Image quality and detection efficacy of zero echo time magnetic resonance imaging on Lung-RADS 2 pulmonary ground-glass nodules in comparison to thin-slice fat-saturated T2-weighted imaging.

Widely used computed tomography (CT) screening increases the detection of pulmonary pure ground-glass nodules (pGGNs), often classified as the second category of Lung Imaging Reporting and Data System (Lung-RADS 2). Despite their low malignancy risk, these nodules pose significant challenges and necessitate accurate assessment to minimize the risk of long-term follow-ups. This study investigated the detection efficacy of zero echo time (ZTE) magnetic resonance imaging (MRI) and thin-slice fat-saturated T2-weighted imaging (T2WI-FS) on 3.0 T MRI on the predictive accuracy of invasiveness for Lung-RADS 2 pGGNs. This prospective study enrolled 83 consecutive patients with 110 pGGNs who underwent preoperative CT and MRI scans. All CT images were assessed by artificial intelligence (AI) software and confirmed by a thoracic radiologist. Another two radiologists blind to pathology results assessed MRI for image quality (objective and subjective evaluations) and detection of pGGNs. Differences in nodule diameter, CT density and detection rate were compared within different pathological groups. The objective and subjective image quality scores were compared using the Wilcoxon signed rank test between ZTE and T2WI-FS. Interobserver agreement was calculated using the kappa coefficient. Receiver operating characteristic (ROC) curve analysis evaluated the diagnostic accuracy for distinguishing invasiveness. Among the 110 pGGNs evaluated, T2WI-FS demonstrated a higher detection rate (80.0%) compared to ZTE (51.8%). ZTE showed a superior signal-to-noise ratio (SNR) in the lung parenchyma, aorta, and peripheral lung structures, whereas T2WI-FS more effectively delineated tracheal walls and pulmonary nodules. Both observers rated ZTE higher for vascular and bronchial visibility, while T2WI-FS was better in terms of lower noise and fewer artifacts. Notably, ZTE visibility varied with pathological results, exhibiting a range from 0% in atypical adenomatous hyperplasia (AAH) to 94.1% in invasive adenocarcinoma (IAC). The key indicators for distinguishing invasive pGGNs from non-invasive ones were nodule diameter [area under the curve (AUC) =0.874], ZTE visibility (AUC =0.740), followed by CT values (AUC =0.682) and T2WI-FS visibility (AUC =0.678). MRI has the potential to detect and predict the invasiveness of pGGN. Both T2WI-FS and ZTE demonstrate reliable image quality in pulmonary imaging, each displaying strengths in visualizing pGGN. Thin-slice T2WI-FS has a superior detection rate, while ZTE better predicts histological invasiveness.

Application of artificial intelligence in lung cancer screening: A real-world study in a Chinese physical examination population.

With the rapid increase of chest computed tomography (CT) images, the workload faced by radiologists has increased dramatically. It is undeniable that the use of artificial intelligence (AI) image-assisted diagnosis system in clinical treatment is a major trend in medical development. Therefore, in order to explore the value and diagnostic accuracy of the current AI system in clinical application, we aim to compare the detection and differentiation of benign and malignant pulmonary nodules between AI system and physicians, so as to provide a theoretical basis for clinical application. Our study encompassed a cohort of 23 336 patients who underwent chest low-dose spiral CT screening for lung cancer at the Health Management Center of West China Hospital. We conducted a comparative analysis between AI-assisted reading and manual interpretation, focusing on the detection and differentiation of benign and malignant pulmonary nodules. The AI-assisted reading exhibited a significantly higher screening positive rate and probability of diagnosing malignant pulmonary nodules compared with manual interpretation (p < 0.001). Moreover, AI scanning demonstrated a markedly superior detection rate of malignant pulmonary nodules compared with manual scanning (97.2% vs. 86.4%, p < 0.001). Additionally, the lung cancer detection rate was substantially higher in the AI reading group compared with the manual reading group (98.9% vs. 90.3%, p < 0.001). Our findings underscore the superior screening positive rate and lung cancer detection rate achieved through AI-assisted reading compared with manual interpretation. Thus, AI exhibits considerable potential as an adjunctive tool in lung cancer screening within clinical practice settings.

Speed and efficiency: evaluating pulmonary nodule detection with AI-enhanced 3D gradient echo imaging.

Evaluating the diagnostic feasibility of accelerated pulmonary MR imaging for detection and characterisation of pulmonary nodules with artificial intelligence-aided compressed sensing. In this prospective trial, patients with benign and malignant lung nodules admitted between December 2021 and December 2022 underwent chest CT and pulmonary MRI. Pulmonary MRI used a respiratory-gated 3D gradient echo sequence, accelerated with a combination of parallel imaging, compressed sensing, and deep learning image reconstruction with three different acceleration factors (CS-AI-7, CS-AI-10, and CS-AI-15). Two readers evaluated image quality (5-point Likert scale), nodule detection and characterisation (size and morphology) of all sequences compared to CT in a blinded setting. Reader agreement was determined using the intraclass correlation coefficient (ICC). Thirty-seven patients with 64 pulmonary nodules (solid n = 57 [3-107 mm] part-solid n = 6 [ground glass/solid 8 mm/4-28 mm/16 mm] ground glass nodule n = 1 [20 mm]) were analysed. Nominal scan times were CS-AI-7 3:53 min; CS-AI-10 2:34 min; CS-AI-15 1:50 min. CS-AI-7 showed higher image quality, while quality remained diagnostic even for CS-AI-15. Detection rates of pulmonary nodules were 100%, 98.4%, and 96.8% for CS-AI factors 7, 10, and 15, respectively. Nodule morphology was best at the lowest acceleration and was inferior to CT in only 5% of cases, compared to 10% for CS-AI-10 and 23% for CS-AI-15. The nodule size was comparable for all sequences and deviated on average < 1 mm from the CT size. The combination of compressed sensing and AI enables a substantial reduction in the scan time of lung MRI while maintaining a high detection rate of pulmonary nodules. Incorporating compressed sensing and AI in pulmonary MRI achieves significant time savings without compromising nodule detection or characteristics. This advancement holds clinical promise, enhancing efficiency in lung cancer screening without sacrificing diagnostic quality. Lung cancer screening by MRI may be possible but would benefit from scan time optimisation. Significant scan time reduction, high detection rates, and preserved nodule characteristics were achieved across different acceleration factors. Integrating compressed sensing and AI in pulmonary MRI offers efficient lung cancer screening without compromising diagnostic quality.

Multiple representation contrastive self-supervised learning for pulmonary nodule detection✰

Self-supervised learning aims to create semantic-enriched representation from unannotated data. A prevalent strategy in this field involves training a unified representation space that is invariant to various transformation combinations. However, creating a single invariant representation to multiple transformations poses several challenges. The efficacy of such a representation space depends on factors such as the intensity, sequence, and various combination scenarios of transformations. As a result, features generated in single representation space may exhibit limited adaptability for subsequent tasks. In contrast to the conventional SSL training approach, we introduce a novel method that involves constructing multiple atomic transformation-invariant representation subspaces. Each subspace in the proposed method is invariant to a specific atomic transformation from a predefined reference set. Our method offers increased flexibility by enabling the downstream task to weigh every atomic transformation-invariant subspace based on the desired feature space. A series of experiments were conducted to compare our approach to traditional self-supervised learning methods in order to assess its effectiveness. This evaluation encompassed diverse data regimes, datasets, evaluation protocols, and perspectives on source-destination data distribution. Our results highlight the superiority of our method compared to training strategies based on single transformation-invariant representation spaces. Additionally, our proposed method demonstrated superior performance in reducing false positives in the context of pulmonary nodule detection when compared to several recent supervised and self-supervised approaches.

ICNoduleNet: Enhancing Pulmonary Nodule Detection Performance on Sharp Kernel CT Imaging.

Thoracic computed tomography (CT) currently plays the primary role in pulmonary nodule detection, where the reconstruction kernel significantly impacts performance in computer-aided pulmonary nodule detectors. The issue of kernel selection affecting performance has been overlooked in pulmonary nodule detection. This paper first introduces a novel pulmonary nodule detection dataset named Reconstruction Kernel Imaging for Pulmonary Nodule Detection (RKPN) for quantifying algorithm differences between the two imaging types. The dataset contains pairs of images taken from the same patient on the same date, featuring both smooth (B31f) and sharp kernel (B60f) reconstructions. All other imaging parameters and pulmonary nodule labels remain entirely consistent across these pairs. Extensive quantification reveals mainstream detectors perform better on smooth kernel imaging than on sharp kernel imaging. To address suboptimal detection on the sharp kernel imaging, we further propose an image conversion-based pulmonary nodule detector called ICNoduleNet. A lightweight 3D slice-channel converter (LSCC) module is introduced to convert sharp kernel images into smooth kernel images, which can sufficiently learn inter-slice and inter-channel feature information while avoiding introducing excessive parameters. We conduct thorough experiments that validate the effectiveness of ICNoduleNet, it takes sharp kernel images as input and can achieve comparable or even superior detection performance to the baseline that uses the smooth kernel images. The evaluation shows promising results and proves the effectiveness of ICNoduleNet.

Detection of pulmonary nodules in chest radiographs: novel cost function for effective network training with purely synthesized datasets

PurposeMany large radiographic datasets of lung nodules are available, but the small and hard-to-detect nodules are rarely validated by computed tomography. Such difficult nodules are crucial for training nodule detection methods. This lack of difficult nodules for training can be addressed by artificial nodule synthesis algorithms, which can create artificially embedded nodules. This study aimed to develop and evaluate a novel cost function for training networks to detect such lesions. Embedding artificial lesions in healthy medical images is effective when positive cases are insufficient for network training. Although this approach provides both positive (lesion-embedded) images and the corresponding negative (lesion-free) images, no known methods effectively use these pairs for training. This paper presents a novel cost function for segmentation-based detection networks when positive–negative pairs are available.MethodsBased on the classic U-Net, new terms were added to the original Dice loss for reducing false positives and the contrastive learning of diseased regions in the image pairs. The experimental network was trained and evaluated, respectively, on 131,072 fully synthesized pairs of images simulating lung cancer and real chest X-ray images from the Japanese Society of Radiological Technology dataset.ResultsThe proposed method outperformed RetinaNet and a single-shot multibox detector. The sensitivities were 0.688 and 0.507 when the number of false positives per image was 0.2, respectively, with and without fine-tuning under the leave-one-case-out setting.ConclusionTo our knowledge, this is the first study in which a method for detecting pulmonary nodules in chest X-ray images was evaluated on a real clinical dataset after being trained on fully synthesized images. The synthesized dataset is available at https://zenodo.org/records/10648433.

A human-in-the-loop method for pulmonary nodule detection in CT scans

Automated pulmonary nodule detection using computed tomography scans is vital in the early diagnosis of lung cancer. Although extensive well-performed methods have been proposed for this task, they suffer from the domain shift issue between training and test images. Unsupervised domain adaptation (UDA) methods provide a promising means to mitigate the domain variance; however, their performance is still limited since no target domain supervision is introduced. To make the pulmonary nodule detection algorithm more applicable in clinical practice and further boost the performance across domains, we propose a human-in-the-loop method in a semi-supervised fashion to enhance the model generalization ability when transferred from source domain to target domain. Specifically, we first train a detector model on source domain, and then the pre-trained detector is utilized with our proposed uncertainty-guided sample selection scheme (USSS) to find a few target domain samples worth annotating most and obtain their human annotations. Finally, the annotated and the rest unlabeled target domain samples are used together to refine the pre-trained model via our proposed zoom-in and zoom-out constraint (ZZC) strategy. We evaluate our method on the Nodule Analysis 2016 (LUNA16) and TianChi datasets. Experimental results show that our method surpasses recent competitive methods on source domain and also achieves surprising performance on target domain.

Deep learning in pulmonary nodule detection and segmentation: a systematic review.

The accurate detection and precise segmentation of lung nodules on computed tomography are key prerequisites for early diagnosis and appropriate treatment of lung cancer. This study was designed to compare detection and segmentation methods for pulmonary nodules using deep-learning techniques to fill methodological gaps and biases in the existing literature. This study utilized a systematic review with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, searching PubMed, Embase, Web of Science Core Collection, and the Cochrane Library databases up to May 10, 2023. The Quality Assessment of Diagnostic Accuracy Studies 2 criteria was used to assess the risk of bias and was adjusted with the Checklist for Artificial Intelligence in Medical Imaging. The study analyzed and extracted model performance, data sources, and task-focus information. After screening, we included nine studies meeting our inclusion criteria. These studies were published between 2019 and 2023 and predominantly used public datasets, with the Lung Image Database Consortium Image Collection and Image Database Resource Initiative and Lung Nodule Analysis 2016 being the most common. The studies focused on detection, segmentation, and other tasks, primarily utilizing Convolutional Neural Networks for model development. Performance evaluation covered multiple metrics, including sensitivity and the Dice coefficient. This study highlights the potential power of deep learning in lung nodule detection and segmentation. It underscores the importance of standardized data processing, code and data sharing, the value of external test datasets, and the need to balance model complexity and efficiency in future research. Deep learning demonstrates significant promise in autonomously detecting and segmenting pulmonary nodules. Future research should address methodological shortcomings and variability to enhance its clinical utility. Deep learning shows potential in the detection and segmentation of pulmonary nodules. There are methodological gaps and biases present in the existing literature. Factors such as external validation and transparency affect the clinical application.

Better performance of deep learning pulmonary nodule detection using chest radiography with pixel level labels in reference to computed tomography: data quality matters

Labeling errors can significantly impact the performance of deep learning models used for screening chest radiographs. The deep learning model for detecting pulmonary nodules is particularly vulnerable to such errors, mainly because normal chest radiographs and those with nodules obscured by ribs appear similar. Thus, high-quality datasets referred to chest computed tomography (CT) are required to prevent the misclassification of nodular chest radiographs as normal. From this perspective, a deep learning strategy employing chest radiography data with pixel-level annotations referencing chest CT scans may improve nodule detection and localization compared to image-level labels. We trained models using a National Institute of Health chest radiograph-based labeling dataset and an AI-HUB CT-based labeling dataset, employing DenseNet architecture with squeeze-and-excitation blocks. We developed four models to assess whether CT versus chest radiography and pixel-level versus image-level labeling would improve the deep learning model’s performance to detect nodules. The models' performance was evaluated using two external validation datasets. The AI-HUB dataset with image-level labeling outperformed the NIH dataset (AUC 0.88 vs 0.71 and 0.78 vs.0.73 in two external datasets, respectively; both p < 0.001). However, the AI-HUB data annotated at the pixel level produced the best model (AUC 0.91 and 0.86 in external datasets), and in terms of nodule localization, it significantly outperformed models trained with image-level annotation data, with a Dice coefficient ranging from 0.36 to 0.58. Our findings underscore the importance of accurately labeled data in developing reliable deep learning algorithms for nodule detection in chest radiography.