Automatic nodule detection for lung cancer in CT images: A review

SaraNet: Semantic aggregation reverse attention network for pulmonary nodule segmentation

Accurate segmentation of pulmonary nodule is essential for subsequent pathological analysis and diagnosis. However, current U-Net architectures often rely on a simple skip connection scheme, leading to the fusion of feature maps with different semantic information, which can have a negative impact on the segmentation model. In response to this challenge, this study introduces a novel U-shaped model specifically designed for pulmonary nodule segmentation. The proposed model incorporates features such as the U-Net backbone, semantic aggregation feature pyramid module, and reverse attention module. The semantic aggregation module combines semantic information with multi-scale features, addressing the semantic gap between the encoder and decoder. The reverse attention module explores missing object parts and captures intricate details by erasing the currently predicted salient regions from side-output features. The proposed model is evaluated using the LIDC-IDRI dataset. Experimental results reveal that the proposed method achieves a dice similarity coefficient of 89.11%and a sensitivity of 90.73 %, outperforming state-of-the-art approaches comprehensively.

Uncertainty-aware image classification on 3D CT lung

Early detection is crucial for lung cancer to prolong the patient's survival. Existing model architectures used in such systems have shown promising results. However, they lack reliability and robustness in their predictions and the models are typically evaluated on a single dataset, making them overconfident when a new class is present. With the existence of uncertainty, uncertain images can be referred to medical experts for a second opinion. Thus, we propose an uncertainty-aware framework that includes three phases: data preprocessing and model selection and evaluation, uncertainty quantification (UQ), and uncertainty measurement and data referral for the classification of benign and malignant nodules using 3D CT images. To quantify the uncertainty, we employed three approaches; Monte Carlo Dropout (MCD), Deep Ensemble (DE), and Ensemble Monte Carlo Dropout (EMCD). We evaluated eight different deep learning models consisting of ResNet, DenseNet, and the Inception network family, all of which achieved average F1 scores above 0.832, and the highest average value of 0.845 was obtained using InceptionResNetV2. Furthermore, incorporating the UQ demonstrated significant improvement in the overall model performance. Upon evaluation of the uncertainty estimate, MCD outperforms the other UQ models except for the metric, URecall, where DE and EMCD excel, implying that they are better at identifying incorrect predictions with higher uncertainty levels, which is vital in the medical field. Finally, we show that using a threshold for data referral can greatly improve the performance further, increasing the accuracy up to 0.959.

Robust explanation supervision for false positive reduction in pulmonary nodule detection

BACKGROUND

Lung cancer is the deadliest and second most common cancer in the United States due to the lack of symptoms for early diagnosis. Pulmonary nodules are small abnormal regions that can be potentially correlated to the occurrence of lung cancer. Early detection of these nodules is critical because it can significantly improve the patient's survival rates. Thoracic thin-sliced computed tomography (CT) scanning has emerged as a widely used method for diagnosing and prognosis lung abnormalities.

PURPOSE

The standard clinical workflow of detecting pulmonary nodules relies on radiologists to analyze CT images to assess the risk factors of cancerous nodules. However, this approach can be error-prone due to the various nodule formation causes, such as pollutants and infections. Deep learning (DL) algorithms have recently demonstrated remarkable success in medical image classification and segmentation. As an ever more important assistant to radiologists in nodule detection, it is imperative ensure the DL algorithm and radiologist to better understand the decisions from each other. This study aims to develop a framework integrating explainable AI methods to achieve accurate pulmonary nodule detection.

METHODS

A robust and explainable detection (RXD) framework is proposed, focusing on reducing false positives in pulmonary nodule detection. Its implementation is based on an explanation supervision method, which uses nodule contours of radiologists as supervision signals to force the model to learn nodule morphologies, enabling improved learning ability on small dataset, and enable small dataset learning ability. In addition, two imputation methods are applied to the nodule region annotations to reduce the noise within human annotations and allow the model to have robust attributions that meet human expectations. The 480, 265, and 265 CT image sets from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset are used for training, validation, and testing.

RESULTS

Using only 10, 30, 50, and 100 training samples sequentially, our method constantly improves the classification performance and explanation quality of baseline in terms of Area Under the Curve (AUC) and Intersection over Union (IoU). In particular, our framework with a learnable imputation kernel improves IoU from baseline by 24.0% to 80.0%. A pre-defined Gaussian imputation kernel achieves an even greater improvement, from 38.4% to 118.8% from baseline. Compared to the baseline trained on 100 samples, our method shows less drop in AUC when trained on fewer samples. A comprehensive comparison of interpretability shows that our method aligns better with expert opinions.

CONCLUSIONS

A pulmonary nodule detection framework was demonstrated using public thoracic CT image datasets. The framework integrates the robust explanation supervision (RES) technique to ensure the performance of nodule classification and morphology. The method can reduce the workload of radiologists and enable them to focus on the diagnosis and prognosis of the potential cancerous pulmonary nodules at the early stage to improve the outcomes for lung cancer patients.

Diagnosis and detection of pneumonia using weak-label based on X-ray images: a multi-center study

PURPOSE

Development and assessment the deep learning weakly supervised algorithm for the classification and detection pneumonia via X-ray.

METHODS

This retrospective study analyzed two publicly available dataset that contain X-ray images of pneumonia cases and normal cases. The first dataset from Guangzhou Women and Children's Medical Center. It contains a total of 5,856 X-ray images, which are divided into training, validation, and test sets with 8:1:1 ratio for algorithm training and testing. The deep learning algorithm ResNet34 was employed to build diagnostic model. And the second public dataset were collated by researchers from Qatar University and the University of Dhaka along with collaborators from Pakistan and Malaysia and some medical doctors. A total of 1,300 images of COVID-19 positive cases, 1,300 normal images and 1,300 images of viral pneumonia for external validation. Class activation map (CAM) were used to location the pneumonia lesions.

RESULTS

The ResNet34 model for pneumonia detection achieved an AUC of 0.9949 [0.9910-0.9981] (with an accuracy of 98.29% a sensitivity of 99.29% and a specificity of 95.57%) in the test dataset. And for external validation dataset, the model obtained an AUC of 0.9835[0.9806-0.9864] (with an accuracy of 94.62%, a sensitivity of 92.35% and a specificity of 99.15%). Moreover, the CAM can accurately locate the pneumonia area.

CONCLUSION

The deep learning algorithm can accurately detect pneumonia and locate the pneumonia area based on weak supervision information, which can provide potential value for helping radiologists to improve their accuracy of detection pneumonia patients through X-ray images.

On-cloud decision-support system for non-small cell lung cancer histology characterization from thorax computed tomography scans

Non-Small Cell Lung Cancer (NSCLC) accounts for about 85% of all lung cancers. Developing non-invasive techniques for NSCLC histology characterization may not only help clinicians to make targeted therapeutic treatments but also prevent subjects from undergoing lung biopsy, which is challenging and could lead to clinical implications. The motivation behind the study presented here is to develop an advanced on-cloud decision-support system, named LUCY, for non-small cell LUng Cancer histologY characterization directly from thorax Computed Tomography (CT) scans. This aim was pursued by selecting thorax CT scans of 182 LUng ADenocarcinoma (LUAD) and 186 LUng Squamous Cell carcinoma (LUSC) subjects from four openly accessible data collections (NSCLC-Radiomics, NSCLC-Radiogenomics, NSCLC-Radiomics-Genomics and TCGA-LUAD), in addition to the implementation and comparison of two end-to-end neural networks (the core layer of whom is a convolutional long short-term memory layer), the performance evaluation on test dataset (NSCLC-Radiomics-Genomics) from a subject-level perspective in relation to NSCLC histological subtype location and grade, and the dynamic visual interpretation of the achieved results by producing and analyzing one heatmap video for each scan. LUCY reached test Area Under the receiver operating characteristic Curve (AUC) values above 77% in all NSCLC histological subtype location and grade groups, and a best AUC value of 97% on the entire dataset reserved for testing, proving high generalizability to heterogeneous data and robustness. Thus, LUCY is a clinically-useful decision-support system able to timely, non-invasively and reliably provide visually-understandable predictions on LUAD and LUSC subjects in relation to clinically-relevant information.

A survey and taxonomy of 2.5D approaches for lung segmentation and nodule detection in CT images

CAD systems for lung cancer diagnosis and detection can significantly offer unbiased, infatiguable diagnostics with minimal variance, decreasing the mortality rate and the five-year survival rate. Lung segmentation and lung nodule detection are critical steps in the lung cancer CAD system pipeline. Literature on lung segmentation and lung nodule detection mostly comprises techniques that process 3-D volumes or 2-D slices and surveys. However, surveys that highlight 2.5D techniques for lung segmentation and lung nodule detection still need to be included. This paper presents a background and discussion on 2.5D methods to fill this gap. Further, this paper also gives a taxonomy of 2.5D approaches and a detailed description of the 2.5D approaches. Based on the taxonomy, various 2.5D techniques for lung segmentation and lung nodule detection are clustered into these 2.5D approaches, which is followed by possible future work in this direction.

Hyperparameter optimization and development of an advanced CNN-based technique for lung nodule assessment

Objective. This paper aims to propose an advanced methodology for assessing lung nodules using automated techniques with computed tomography (CT) images to detect lung cancer at an early stage.Approach. The proposed methodology utilizes a fixed-size 3 × 3 kernel in a convolution neural network (CNN) for relevant feature extraction. The network architecture comprises 13 layers, including six convolution layers for deep local and global feature extraction. The nodule detection architecture is enhanced by incorporating a transfer learning-based EfficientNetV_2 network (TLEV2N) to improve training performance. The classification of nodules is achieved by integrating the EfficientNet_V2 architecture of CNN for more accurate benign and malignant classification. The network architecture is fine-tuned to extract relevant features using a deep network while maintaining performance through suitable hyperparameters.Main results. The proposed method significantly reduces the false-negative rate, with the network achieving an accuracy of 97.56% and a specificity of 98.4%. Using the 3 × 3 kernel provides valuable insights into minute pixel variation and enables the extraction of information at a broader morphological level. The continuous responsiveness of the network to fine-tune initial values allows for further optimization possibilities, leading to the design of a standardized system capable of assessing diversified thoracic CT datasets.Significance. This paper highlights the potential of non-invasive techniques for the early detection of lung cancer through the analysis of low-dose CT images. The proposed methodology offers improved accuracy in detecting lung nodules and has the potential to enhance the overall performance of early lung cancer detection. By reconfiguring the proposed method, further advancements can be made to optimize outcomes and contribute to developing a standardized system for assessing diverse thoracic CT datasets.

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.

Path planning for percutaneous lung biopsy based on the loose-Pareto and adaptive heptagonal optimization method

Lung cancer has is highly prevalent worldwide and is the leading cause of cancer-related deaths. In the clinic, a biopsy sample of the lesion is taken to determine whether a lung mass is benign or malignant. CT-guided percutaneous lung biopsy is a minimally invasive intervention and is commonly used to diagnose lung cancer. Path planning before surgery plays a crucial role in percutaneous lung biopsy. Traditionally, path planning for lung biopsy is performed manually by physicians based on CT images of the patient, which demands knowledge and extensive clinical experience of the operating physicians. In this work, a computer-assisted path planning system for percutaneous lung biopsy is proposed based on clinical objectives. Five constraints are presented to remove unqualified skin entry points and determine a feasible entry region based on clinical criteria. Inspired by the Pareto principle and the concept of geometric weighting, the loose-Pareto and adaptive heptagonal optimization (LPHO) method is introduced to plan the optimal puncture path. CT images of 29 patients were collected from Zigong First People's Hospital. Retrospective experiments and test experiments were conducted to evaluate the effectiveness of the algorithm. The planning paths obtained using the proposed method were clinically feasible for 89.7% of patients, demonstrating the applicability and robustness of the system in surgical path planning for lung biopsy.

Harris hawks optimization for COVID-19 diagnosis based on multi-threshold image segmentation

Digital image processing techniques and algorithms have become a great tool to support medical experts in identifying, studying, diagnosing certain diseases. Image segmentation methods are of the most widely used techniques in this area simplifying image representation and analysis. During the last few decades, many approaches have been proposed for image segmentation, among which multilevel thresholding methods have shown better results than most other methods. Traditional statistical approaches such as the Otsu and the Kapur methods are the standard benchmark algorithms for automatic image thresholding. Such algorithms provide optimal results, yet they suffer from high computational costs when multilevel thresholding is required, which is considered as an optimization matter. In this work, the Harris hawks optimization technique is combined with Otsu's method to effectively reduce the required computational cost while maintaining optimal outcomes. The proposed approach is tested on a publicly available imaging datasets, including chest images with clinical and genomic correlates, and represents a rural COVID-19-positive (COVID-19-AR) population. According to various performance measures, the proposed approach can achieve a substantial decrease in the computational cost and the time to converge while maintaining a level of quality highly competitive with the Otsu method for the same threshold values.

Computational Methods for the Analysis and Prediction of EGFR-Mutated Lung Cancer Drug Resistance: Recent Advances in Drug Design, Challenges and Future Prospects

Lung cancer is a major cause of cancer deaths worldwide, and has a very low survival rate. Non-small cell lung cancer (NSCLC) is the largest subset of lung cancers, which accounts for about 85% of all cases. It has been well established that a mutation in the epidermal growth factor receptor (EGFR) can lead to lung cancer. EGFR Tyrosine Kinase Inhibitors (TKIs) are developed to target the kinase domain of EGFR. These TKIs produce promising results at the initial stage of therapy, but the efficacy becomes limited due to the development of drug resistance. In this paper, we provide a comprehensive overview of computational methods, for understanding drug resistance mechanisms. The important EGFR mutants and the different generations of EGFR-TKIs, with the survival and response rates are discussed. Next, we evaluate the role of important EGFR parameters in drug resistance mechanism, including structural dynamics, hydrogen bonds, stability, dimerization, binding free energies, and signaling pathways. Personalized drug resistance prediction models, drug response curve, drug synergy, and other data-driven methods are also discussed. Recent advancements in deep learning; such as AlphaFold2, deep generative models, big data analytics, and the applications of statistics and permutation are also highlighted. We explore limitations in the current methodologies, and discuss strategies to overcome them. We believe this review will serve as a reference for researchers; to apply computational techniques for precision medicine, analyzing structures of protein-drug complexes, drug discovery, and understanding the drug response and resistance mechanisms in lung cancer patients.

Practice toward standardized performance testing of computer-aided detection algorithms for pulmonary nodule

This study aimed at implementing practice to build a standardized protocol to test the performance of computer-aided detection (CAD) algorithms for pulmonary nodules. A test dataset was established according to a standardized procedure, including data collection, curation and annotation. Six types of pulmonary nodules were manually annotated as reference standard. Three specific rules to match algorithm output with reference standard were applied and compared. These rules included: (1) "center hit" [whether the center of algorithm highlighted region of interest (ROI) hit the ROI of reference standard]; (2) "center distance" (whether the distance between algorithm highlighted ROI center and reference standard center was below a certain threshold); (3) "area overlap" (whether the overlap between algorithm highlighted ROI and reference standard was above a certain threshold). Performance metrics were calculated and the results were compared among ten algorithms under test (AUTs). The test set currently consisted of CT sequences from 593 patients. Under "center hit" rule, the average recall rate, average precision, and average F₁ score of ten algorithms under test were 54.68, 38.19, and 42.39%, respectively. Correspondingly, the results under "center distance" rule were 55.43, 38.69, and 42.96%, and the results under "area overlap" rule were 40.35, 27.75, and 31.13%. Among the six types of pulmonary nodules, the AUTs showed the highest miss rate for pure ground-glass nodules, with an average of 59.32%, followed by pleural nodules and solid nodules, with an average of 49.80 and 42.21%, respectively. The algorithm testing results changed along with specific matching methods adopted in the testing process. The AUTs showed uneven performance on different types of pulmonary nodules. This centralized testing protocol supports the comparison between algorithms with similar intended use, and helps evaluate algorithm performance.

Artificial Intelligence in Lung Cancer Imaging: Unfolding the Future

Lung cancer is one of the malignancies with higher morbidity and mortality. Imaging plays an essential role in each phase of lung cancer management, from detection to assessment of response to treatment. The development of imaging-based artificial intelligence (AI) models has the potential to play a key role in early detection and customized treatment planning. Computer-aided detection of lung nodules in screening programs has revolutionized the early detection of the disease. Moreover, the possibility to use AI approaches to identify patients at risk of developing lung cancer during their life can help a more targeted screening program. The combination of imaging features and clinical and laboratory data through AI models is giving promising results in the prediction of patients’ outcomes, response to specific therapies, and risk for toxic reaction development. In this review, we provide an overview of the main imaging AI-based tools in lung cancer imaging, including automated lesion detection, characterization, segmentation, prediction of outcome, and treatment response to provide radiologists and clinicians with the foundation for these applications in a clinical scenario.

Cloud-YLung for Non-Small Cell Lung Cancer Histology Classification from 3D Computed Tomography Whole-Lung Scans

Non-Small Cell Lung Cancer (NSCLC) represents up to 85% of all malignant lung nodules. Adenocarcinoma and squamous cell carcinoma account for 90% of all NSCLC histotypes. The standard diagnostic procedure for NSCLC histotype characterization implies cooperation of 3D Computed Tomography (CT), especially in the form of low-dose CT, and lung biopsy. Since lung biopsy is invasive and challenging (especially for deeply-located lung cancers and for those close to blood vessels or airways), there is the necessity to develop non-invasive procedures for NSCLC histology classification. Thus, this study aims to propose Cloud-YLung for NSCLC histology classification directly from 3D CT whole-lung scans. With this aim, data were selected from the openly-accessible NSCLC-Radiomics dataset and a modular pipeline was designed. Automatic feature extraction and classification were accomplished by means of a Convolutional Long Short-Term Memory (ConvLSTM)-based neural network trained from scratch on a scalable GPU cloud service to ensure a machine-independent reproducibility of the entire framework. Results show that Cloud- YLung performs well in discriminating both NSCLC histotypes, achieving a test accuracy of 75% and AUC of 84%. Cloud-YLung is not only lung nodule segmentation free but also the first that makes use of a ConvLSTM-based neural network to automatically extract high-throughput features from 3D CT whole-lung scans and classify them. Clinical relevance- Cloud-YLung is a promising framework to non-invasively classify NSCLC histotypes. Preserving the lung anatomy, its application could be extended to other pulmonary pathologies using 3D CT whole-lung scans.

Lung nodule diagnosis and cancer histology classification from computed tomography data by convolutional neural networks: A survey

Lung cancer is among the deadliest cancers. Besides lung nodule classification and diagnosis, developing non-invasive systems to classify lung cancer histological types/subtypes may help clinicians to make targeted treatment decisions timely, having a positive impact on patients' comfort and survival rate. As convolutional neural networks have proven to be responsible for the significant improvement of the accuracy in lung cancer diagnosis, with this survey we intend to: show the contribution of convolutional neural networks not only in identifying malignant lung nodules but also in classifying lung cancer histological types/subtypes directly from computed tomography data; point out the strengths and weaknesses of slice-based and scan-based approaches employing convolutional neural networks; and highlight the challenges and prospective solutions to successfully apply convolutional neural networks for such classification tasks. To this aim, we conducted a comprehensive analysis of relevant Scopus-indexed studies involved in lung nodule diagnosis and cancer histology classification up to January 2022, dividing the investigation in convolutional neural network-based approaches fed with planar or volumetric computed tomography data. Despite the application of convolutional neural networks in lung nodule diagnosis and cancer histology classification is a valid strategy, some challenges raised, mainly including the lack of publicly-accessible annotated data, together with the lack of reproducibility and clinical interpretability. We believe that this survey will be helpful for future studies involved in lung nodule diagnosis and cancer histology classification prior to lung biopsy by means of convolutional neural networks.

Application of Surface-Enhanced Raman Spectroscopy in the Screening of Pulmonary Adenocarcinoma Nodules

This study is aimed at evaluating the feasibility of a screening method for the pulmonary adenocarcinoma nodules through surface-enhanced Raman spectroscopy (SERS). Objective. Using SERS to measure serum from pulmonary nodules and healthy subjects, intraoperative biopsy pathological diagnosis was regarded as the gold standard for labeling serum samples. To explore the application value of SERS in the differential diagnosis of pulmonary adenocarcinoma nodules, benign nodules, and healthy, we build a machine learning model. Method. We collected 116 serum samples from patients. Radiographically confirmed nodules less than 3 cm in maximum diameter in all patients, including 58 cancer (pathologic diagnosis: adenocarcinoma nodules, labeled as cancer) patients, 58 pathologic diagnoses as benign nodule (labeled as benign) patients, and 63 healthy (labeled as normal) people from the clinical laboratory of Sichuan Cancer Hospital. Gold nanorods were employed as SERS substrates. Support vector machine (SVM) was used to classify the normal, benign, and cancer sample groups, and SVM model evaluated using cross-validation. Results. The average SERS spectra of serum were significantly different between the normal group and the cancer/benign group. While the average SERS spectra of the cancer group and the benign group differed slightly, for the cancer, benign, and normal groups, SVM models can predict with 93.33% accuracy. Conclusion. This exploratory study demonstrates that the SERS technique based on nanoparticles in conjunction with SVM has great potential as a clinical auxiliary diagnosis and screening for pulmonary adenocarcinoma nodules.

Development and Validation of a Risk Stratification Model of Pulmonary Ground-Glass Nodules Based on Complementary Lung-RADS 1.1 and Deep Learning Scores

Purpose

To assess the value of novel deep learning (DL) scores combined with complementary lung imaging reporting and data system 1.1 (cLung-RADS 1.1) in managing the risk stratification of ground-glass nodules (GGNs) and therefore improving the efficiency of lung cancer (LC) screening in China.

Materials and Methods

Overall, 506 patients with 561 GGNs on routine computed tomography images, obtained between January 2017 and March 2021, were enrolled in this single-center, retrospective Chinese study. Moreover, the cLung-RADS 1.1 was previously validated, and the DL algorithms were based on a multi-stage, three-dimensional DL-based convolutional neural network. Therefore, the DL-based cLung-RADS 1.1 model was created using a combination of the risk scores of DL and category of cLung-RADS 1.1. The recall rate, precision, accuracy, per-class F1 score, weighted average F1 score (F1_weighted), Matthews correlation coefficient (MCC), and area under the curve (AUC) were used to evaluate the performance of DL-based cLung-RADS 1.1.

Results

The percentage of neoplastic lesions appeared as GGNs in our study was 95.72% (537/561) after long-period follow-up.Compared to cLung-RADS 1.1 model or DL model, The DL-based cLung-RADS 1.1 model achieved the excellent performance with F1 scores of 95.96% and 95.58%, F1_weighted values of 97.49 and 96.62%, accuracies of 92.38 and 91.77%, and MCCs of 32.43 and 37.15% in the training and validation tests, respectively. The combined model achieved the best AUCs of 0.753 (0.526–0.980) and 0.734 (0.585–0.884) for the training and validation tests, respectively.

Conclusion

The DL-based cLung-RADS 1.1 model shows the best performance in risk stratification management of GGNs, which demonstrates substantial promise for developing a more effective personalized lung neoplasm management paradigm for LC screening in China.

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

Advancements in the development of computer-aided decision (CAD) systems for clinical routines provide unquestionable benefits in connecting human medical expertise with machine intelligence, to achieve better quality healthcare. Considering the large number of incidences and mortality numbers associated with lung cancer, there is a need for the most accurate clinical procedures; thus, the possibility of using artificial intelligence (AI) tools for decision support is becoming a closer reality. At any stage of the lung cancer clinical pathway, specific obstacles are identified and "motivate" the application of innovative AI solutions. This work provides a comprehensive review of the most recent research dedicated toward the development of CAD tools using computed tomography images for lung cancer-related tasks. We discuss the major challenges and provide critical perspectives on future directions. Although we focus on lung cancer in this review, we also provide a more clear definition of the path used to integrate AI in healthcare, emphasizing fundamental research points that are crucial for overcoming current barriers.

Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT

Objectives

1) To develop a deep learning (DL) pipeline allowing quantification of COVID-19 pulmonary lesions on low-dose computed tomography (LDCT). 2) To assess the prognostic value of DL-driven lesion quantification.

Methods

This monocentric retrospective study included training and test datasets taken from 144 and 30 patients, respectively. The reference was the manual segmentation of 3 labels: normal lung, ground-glass opacity(GGO) and consolidation(Cons). Model performance was evaluated with technical metrics, disease volume and extent. Intra- and interobserver agreement were recorded. The prognostic value of DL-driven disease extent was assessed in 1621 distinct patients using C-statistics. The end point was a combined outcome defined as death, hospitalization>10 days, intensive care unit hospitalization or oxygen therapy.

Results

The Dice coefficients for lesion (GGO+Cons) segmentations were 0.75±0.08, exceeding the values for human interobserver (0.70±0.08; 0.70±0.10) and intraobserver measures (0.72±0.09). DL-driven lesion quantification had a stronger correlation with the reference than inter- or intraobserver measures. After stepwise selection and adjustment for clinical characteristics, quantification significantly increased the prognostic accuracy of the model (0.82 vs. 0.90; p<0.0001).

Conclusions

A DL-driven model can provide reproducible and accurate segmentation of COVID-19 lesions on LDCT. Automatic lesion quantification has independent prognostic value for the identification of high-risk patients.

Lung Segmentation in CT Images: A Residual U-Net Approach on a Cross-Cohort Dataset

Lung cancer is one of the most common causes of cancer-related mortality, and since the majority of cases are diagnosed when the tumor is in an advanced stage, the 5-year survival rate is dismally low. Nevertheless, the chances of survival can increase if the tumor is identified early on, which can be achieved through screening with computed tomography (CT). The clinical evaluation of CT images is a very time-consuming task and computed-aided diagnosis systems can help reduce this burden. The segmentation of the lungs is usually the first step taken in image analysis automatic models of the thorax. However, this task is very challenging since the lungs present high variability in shape and size. Moreover, the co-occurrence of other respiratory comorbidities alongside lung cancer is frequent, and each pathology can present its own scope of CT imaging appearances. This work investigated the development of a deep learning model, whose architecture consists of the combination of two structures, a U-Net and a ResNet34. The proposed model was designed on a cross-cohort dataset and it achieved a mean dice similarity coefficient (DSC) higher than 0.93 for the 4 different cohorts tested. The segmentation masks were qualitatively evaluated by two experienced radiologists to identify the main limitations of the developed model, despite the good overall performance obtained. The performance per pathology was assessed, and the results confirmed a small degradation for consolidation and pneumocystis pneumonia cases, with a DSC of 0.9015 ± 0.2140 and 0.8750 ± 0.1290, respectively. This work represents a relevant assessment of the lung segmentation model, taking into consideration the pathological cases that can be found in the clinical routine, since a global assessment could not detail the fragilities of the model.

LungSeek: 3D Selective Kernel residual network for pulmonary nodule diagnosis

Early detection and diagnosis of pulmonary nodules is the most promising way to improve the survival chances of lung cancer patients. This paper proposes an automatic pulmonary cancer diagnosis system, LungSeek. LungSeek is mainly divided into two modules: (1) Nodule detection, which detects all suspicious nodules from computed tomography (CT) scan; (2) Nodule Classification, classifies nodules as benign or malignant. Specifically, a 3D Selective Kernel residual network (SK-ResNet) based on the Selective Kernel Network and 3D residual network is located. A deep 3D region proposal network with SK-ResNet is designed for detection of pulmonary nodules while a multi-scale feature fusion network is designed for the nodule classification. Both networks use the SK-Net module to obtain different receptive field information, thereby effectively learning nodule features and improving diagnostic performance. Our method has been verified on the luna16 data set, reaching 89.06, 94.53% and 97.72% when the average number of false positives is 1, 2 and 4, respectively. Meanwhile, its performance is better than the state-of-the-art method and other similar networks and experienced doctors. This method has the ability to adaptively adjust the receptive field according to multiple scales of the input information, so as to better detect nodules of various sizes. The framework of LungSeek based on 3D SK-ResNet is proposed for nodule detection and nodule classification from chest CT. Our experimental results demonstrate the effectiveness of the proposed method in the diagnosis of pulmonary nodules.

Deep Learning Applications in Computed Tomography Images for Pulmonary Nodule Detection and Diagnosis: A Review

Lung cancer has one of the highest mortality rates of all cancers and poses a severe threat to people’s health. Therefore, diagnosing lung nodules at an early stage is crucial to improving patient survival rates. Numerous computer-aided diagnosis (CAD) systems have been developed to detect and classify such nodules in their early stages. Currently, CAD systems for pulmonary nodules comprise data acquisition, pre-processing, lung segmentation, nodule detection, false-positive reduction, segmentation, and classification. A number of review articles have considered various components of such systems, but this review focuses on segmentation and classification parts. Specifically, categorizing segmentation parts based on lung nodule type and network architectures, i.e., general neural network and multiview convolution neural network (CNN) architecture. Moreover, this work organizes related literature for classification of parts based on nodule or non-nodule and benign or malignant. The essential CT lung datasets and evaluation metrics used in the detection and diagnosis of lung nodules have been systematically summarized as well. Thus, this review provides a baseline understanding of the topic for interested readers.

A radiomics approach for lung nodule detection in thoracic CT images based on the dynamic patterns of morphological variation

OBJECTIVES

To propose and evaluate a set of radiomic features, called morphological dynamics features, for pulmonary nodule detection, which were rooted in the dynamic patterns of morphological variation and needless precise lesion segmentation.

MATERIALS AND METHODS

Two datasets were involved, namely, university hospital (UH) and LIDC datasets, comprising 72 CT scans (360 nodules) and 888 CT scans (2230 nodules), respectively. Each nodule was annotated by multiple radiologists. Denoted the category of nodules identified by at least k radiologists as ALk. A nodule detection algorithm, called CAD-MD algorithm, was proposed based on the morphological dynamics radiomic features, characterizing a lesion by ten sets of the same features with different values extracted from ten different thresholding results. Each nodule candidate was classified by a two-level classifier, including ten decision trees and a random forest, respectively. The CAD-MD algorithm was compared with a deep learning approach, the N-Net, using the UH dataset.

RESULTS

On the AL1 and AL2 of the UH dataset, the AUC of the AFROC curves were 0.777 and 0.851 for the CAD-MD algorithm and 0.478 and 0.472 for the N-Net, respectively. The CAD-MD algorithm achieved the sensitivities of 84.4% and 91.4% with 2.98 and 3.69 FPs/scan and the N-Net 74.4% and 80.7% with 3.90 and 4.49 FPs/scan, respectively. On the LIDC dataset, the CAD-MD algorithm attained the sensitivities of 87.6%, 89.2%, 92.2%, and 95.0% with 4 FPs/scan for AL1-AL4, respectively.

CONCLUSION

The morphological dynamics radiomic features might serve as an effective set of radiomic features for lung nodule detection.

KEY POINTS

• Texture features varied with such CT system settings as reconstruction kernels of CT images, CT scanner models, and parameter settings, and so on. • Shape and first-order statistics were shown to be the most robust features against variation in CT imaging parameters. • The morphological dynamics radiomic features, which mainly characterized the dynamic patterns of morphological variation, were shown to be effective for lung nodule detection.

Anomaly Segmentation Based on Depth Image for Quality Inspection Processes in Tire Manufacturing

This paper introduces and implements an efficient training method for deep learning–based anomaly area detection in the depth image of a tire. A depth image of 16 bit integer size is used in various fields, such as manufacturing, industry, and medicine. In addition, the advent of the 4th Industrial Revolution and the development of deep learning require deep learning–based problem solving in various fields. Accordingly, various research efforts use deep learning technology to detect errors, such as product defects and diseases, in depth images. However, a depth image expressed in grayscale has limited information, compared with a three-channel image with potential colors, shapes, and brightness. In addition, in the case of tires, despite the same defect, they often have different sizes and shapes, making it difficult to train deep learning. Therefore, in this paper, the four-step process of (1) image input, (2) highlight image generation, (3) image stacking, and (4) image training is applied to a deep learning segmentation model that can detect atypical defect data. Defect detection aims to detect vent spews that occur during tire manufacturing. We compare the training results of applying the process proposed in this paper and the general training result for experiment and evaluation. For evaluation, we use intersection of union (IoU), which compares the pixel area where the actual error is located in the depth image and the pixel area of the error inferred by the deep learning network. The results of the experiment confirmed that the proposed methodology improved the mean IoU by more than 7% and the IoU for the vent spew error by more than 10%, compared to the general method. In addition, the time it takes for the mean IoU to remain stable at 60% is reduced by 80%. The experiments and results prove that the methodology proposed in this paper can train efficiently without losing the information of the original depth data.

Accurate segmentation for different types of lung nodules on CT images using improved U-Net convolutional network

ABSTRACT

Since lung nodules on computed tomography images can have different shapes, contours, textures or locations and may be attached to neighboring blood vessels or pleural surfaces, accurate segmentation is still challenging. In this study, we propose an accurate segmentation method based on an improved U-Net convolutional network for different types of lung nodules on computed tomography images.The first phase is to segment lung parenchyma and correct the lung contour by applying α-hull algorithm. The second phase is to extract image pairs of patches containing lung nodules in the center and the corresponding ground truth and build an improved U-Net network with introduction of batch normalization.A large number of experiments manifest that segmentation performance of Dice loss has superior results than mean square error and Binary_crossentropy loss. The α-hull algorithm and batch normalization can improve the segmentation performance effectively. Our best result for Dice similar coefficient (0.8623) is also more competitive than other state-of-the-art segmentation algorithms.In order to segment different types of lung nodules accurately, we propose an improved U-Net network, which can improve the segmentation accuracy effectively. Moreover, this work also has practical value in helping radiologists segment lung nodules and diagnose lung cancer.

A survey of computer-aided diagnosis of lung nodules from CT scans using deep learning

Lung cancer has one of the highest mortalities of all cancers. According to the National Lung Screening Trial, patients who underwent low-dose computed tomography (CT) scanning once a year for 3 years showed a 20% decline in lung cancer mortality. To further improve the survival rate of lung cancer patients, computer-aided diagnosis (CAD) technology shows great potential. In this paper, we summarize existing CAD approaches applying deep learning to CT scan data for pre-processing, lung segmentation, false positive reduction, lung nodule detection, segmentation, classification and retrieval. Selected papers are drawn from academic journals and conferences up to November 2020. We discuss the development of deep learning, describe several important aspects of lung nodule CAD systems and assess the performance of the selected studies on various datasets, which include LIDC-IDRI, LUNA16, LIDC, DSB2017, NLST, TianChi, and ELCAP. Overall, in the detection studies reviewed, the sensitivity of these techniques is found to range from 61.61% to 98.10%, and the value of the FPs per scan is between 0.125 and 32. In the selected classification studies, the accuracy ranges from 75.01% to 97.58%. The precision of the selected retrieval studies is between 71.43% and 87.29%. Based on performance, deep learning based CAD technologies for detection and classification of pulmonary nodules achieve satisfactory results. However, there are still many challenges and limitations remaining including over-fitting, lack of interpretability and insufficient annotated data. This review helps researchers and radiologists to better understand CAD technology for pulmonary nodule detection, segmentation, classification and retrieval. We summarize the performance of current techniques, consider the challenges, and propose directions for future high-impact research.

Clinical evaluation of a deep-learning-based computer-aided detection system for the detection of pulmonary nodules in a large teaching hospital

AIM

To evaluate a deep-learning-based computer-aided detection (DL-CAD) software system for pulmonary nodule detection on computed tomography (CT) images and assess its added value in the clinical practice of a large teaching hospital.

MATERIALS AND METHODS

A retrospective analysis was performed of 145 chest CT examinations by comparing the output of the DL-CAD software with a reference standard based on the consensus reading of three radiologists. For every nodule in each scan, the location, composition, and maximum diameter in the axial plane were recorded. The subgroup of chest CT examinations (n = 97) without any nodules was used to determine the negative predictive value at the given clinical sensitivity threshold setting.

RESULTS

The radiologists found 91 nodules and the CAD system 130 nodules of which 80 were true positive. The measured sensitivity was 88% and the mean false-positive rate was 1.04 false positives/scan. The negative predictive value was 95%. For 23 nodules, there was a size discrepancy of which 19 (83%) were measured smaller by the radiologist. The agreement of nodule composition between the CAD results and the reference standard was 95%.

CONCLUSIONS

The present study found a sensitivity of 88% and a false-positive rate of 1.04 false positives/scan, which match the vendor specification. Together with the measured negative predictive value of 95% the system performs very well; however, these rates are still not good enough to replace the radiologist, even for the specific task of nodule detection. Furthermore, a surprisingly high rate of overestimation of nodule size was observed, which can lead to too many follow-up examinations.

Detection of Lung Nodules in Micro-CT Imaging Using Deep Learning

We are developing imaging methods for a co-clinical trial investigating synergy between immunotherapy and radiotherapy. We perform longitudinal micro-computed tomography (micro-CT) of mice to detect lung metastasis after treatment. This work explores deep learning (DL) as a fast approach for automated lung nodule detection. We used data from control mice both with and without primary lung tumors. To augment the number of training sets, we have simulated data using real augmented tumors inserted into micro-CT scans. We employed a convolutional neural network (CNN), trained with four competing types of training data: (1) simulated only, (2) real only, (3) simulated and real, and (4) pretraining on simulated followed with real data. We evaluated our model performance using precision and recall curves, as well as receiver operating curves (ROC) and their area under the curve (AUC). The AUC appears to be almost identical (0.76-0.77) for all four cases. However, the combination of real and synthetic data was shown to improve precision by 8%. Smaller tumors have lower rates of detection than larger ones, with networks trained on real data showing better performance. Our work suggests that DL is a promising approach for fast and relatively accurate detection of lung tumors in mice.

Lung Nodule Detectability of Artificial Intelligence-assisted CT Image Reading in Lung Cancer Screening

BACKGROUND

Artificial intelligence (AI)-based automatic lung nodule detection system improves the detection rate of nodules. It is important to evaluate the clinical value of AI system by comparing AI-assisted nodule detection with actu-al radiology reports.

OBJECTIVE

To compare the detection rate of lung nodules between the actual radiology reports and AI-assisted reading in lung cancer CT screening.

METHODS

Participants in chest CT screening from November to December 2019 were retrospectively included. In the real-world radiologist observation, 14 residents and 15 radiologists participated to finalize radiology reports. In AI-assisted reading, one resident and one radiologist reevaluated all subjects with the assistance of an AI system to lo-cate and measure the detected lung nodules. A reading panel determined the type and number of detected lung nodules between these two methods.

RESULTS

In 860 participants (57±7 years), the reading panel confirmed 250 patients with >1 solid nodule, while radiolo-gists observed 131, lower than 247 by AI-assisted reading (p<0.001). The panel confirmed 111 patients with >1 non-solid nodule, whereas radiologist observation identified 28, lower than 110 by AI-assisted reading (p<0.001). The accuracy and sensitivity of radiologist observation for solid nodules were 86.2% and 52.4%, lower than 99.1% and 98.8% by AI-assisted reading, respectively. These metrics were 90.4% and 25.2% for non-solid nodules, lower than 98.8% and 99.1% by AI-assisted reading, respectively.

CONCLUSION

Comparing with the actual radiology reports, AI-assisted reading greatly improves the accuracy and sensi-tivity of nodule detection in chest CT, which benefits lung nodule detection, especially for non-solid nodules.

An Efficient DA-Net Architecture for Lung Nodule Segmentation

A typical growth of cells inside tissue is normally known as a nodular entity. Lung nodule segmentation from computed tomography (CT) images becomes crucial for early lung cancer diagnosis. An issue that pertains to the segmentation of lung nodules is homogenous modular variants. The resemblance among nodules as well as among neighboring regions is very challenging to deal with. Here, we propose an end-to-end U-Net-based segmentation framework named DA-Net for efficient lung nodule segmentation. This method extracts rich features by integrating compactly and densely linked rich convolutional blocks merged with Atrous convolutions blocks to broaden the view of filters without dropping loss and coverage data. We first extract the lung’s ROI images from the whole CT scan slices using standard image processing operations and k-means clustering. This reduces the search space of the model to only lungs where the nodules are present instead of the whole CT scan slice. The evaluation of the suggested model was performed through utilizing the LIDC-IDRI dataset. According to the results, we found that DA-Net showed good performance, achieving an 81% Dice score value and 71.6% IOU score.

Attention-embedded complementary-stream CNN for false positive reduction in pulmonary nodule detection

False positive reduction plays a key role in computer-aided detection systems for pulmonary nodule detection in computed tomography (CT) scans. However, this remains a challenge owing to the heterogeneity and similarity of anisotropic pulmonary nodules. In this study, a novel attention-embedded complementary-stream convolutional neural network (AECS-CNN) is proposed to obtain more representative features of nodules for false positive reduction. The proposed network comprises three function blocks: 1) attention-guided multi-scale feature extraction, 2) complementary-stream block with an attention module for feature integration, and 3) classification block. The inputs of the network are multi-scale 3D CT volumes due to variations in nodule sizes. Subsequently, a gradual multi-scale feature extraction block with an attention module was applied to acquire more contextual information regarding the nodules. A subsequent complementary-stream integration block with an attention module was utilized to learn the significantly complementary features. Finally, the candidates were classified using a fully connected layer block. An exhaustive experiment on the LUNA16 challenge dataset was conducted to verify the effectiveness and performance of the proposed network. The AECS-CNN achieved a sensitivity of 0.92 with 4 false positives per scan. The results indicate that the attention mechanism can improve the network performance in false positive reduction, the proposed AECS-CNN can learn more representative features, and the attention module can guide the network to learn the discriminated feature channels and the crucial information embedded in the data, thereby effectively enhancing the performance of the detection system.

Recognizing lung cancer and stages using a self-developed electronic nose system

Exhaled breath contains thousands of gaseous volatile organic compounds (VOCs) that could be used as non-invasive biomarkers of lung cancer. Breath-based lung cancer screening has attracted wide attention on account of its convenience, low cost and easy popularization. In this paper, the research of lung cancer detection and staging is conducted by the self-developed electronic nose (e-nose) system. In order to investigate the performance of the device in distinguishing lung cancer patients from healthy controls, two feature extraction methods and two different classification models were adopted. Among all the models, kernel principal component analysis (KPCA) combined with extreme gradient boosting (XGBoost) achieved the best results among 235 breath samples. The accuracy, sensitivity and specificity of e-nose system were 93.59%, 95.60% and 91.09%, respectively. Meanwhile, the device could innovatively classify stages of 90 lung cancer patients (i.e., 44 stage III and 46 stage IV). Experimental results indicated that the recognition accuracy of lung cancer stages was more than 80%. Further experiments of this research also showed that the combination of sensor array and pattern recognition algorithms could identify and distinguish the expiratory characteristics of lung cancer, smoking and other respiratory diseases.

Hessian-MRLoG: Hessian information and multi-scale reverse LoG filter for pulmonary nodule detection

Computer-aided detection (CADe) of pulmonary nodules is an effective approach for early detection of lung cancer. However, due to the low contrast of lung computed tomography (CT) images, the interference of blood vessels and classifications, CADe has the problems of low detection rate and high false-positive rate (FPR). To solve these problems, a novel method using Hessian information and multi-scale reverse Laplacian of Gaussian (LoG) (Hessian-MRLoG) is proposed and developed in this work. Also, since the intensity distribution of the LoG operator and the lung nodule in CT images are inconsistent, and their shapes are mismatched, a multi-scale reverse Laplacian of Gaussian (MRLoG) is constructed. In addition, in order to enhance the effectiveness of target detection, the second-order partial derivatives of MRLoG are partially adjusted by introducing an adjustment factor. On this basis, the Hessian-MRLoG model is developed, and a novel elliptic filter is designed. Ultimately, in this study, the method of Hessian-MRLoG filtering is proposed and developed for pulmonary nodule detection. To verify its effectiveness and accuracy, the proposed method was used to analyze the LUNA16 dataset. The experimental results revealed that the proposed method had an accuracy of 93.6% and produced 1.0 false positives per scan (FPs/scan), indicating that the proposed method can improve the detection rate and significantly reduce the FPR. Therefore, the proposed method has the potential for application in the detection, localization and labeling of other lesion areas.

Lung cancer histology classification from CT images based on radiomics and deep learning models

Adenocarcinoma (AC) and squamous cell carcinoma (SCC) are frequent reported cases of non-small cell lung cancer (NSCLC), responsible for a large fraction of cancer deaths worldwide. In this study, we aim to investigate the potential of NSCLC histology classification into AC and SCC by applying different feature extraction and classification techniques on pre-treatment CT images. The employed image dataset (102 patients) was taken from the publicly available cancer imaging archive collection (TCIA). We investigated four different families of techniques: (a) radiomics with two classifiers (kNN and SVM), (b) four state-of-the-art convolutional neural networks (CNNs) with transfer learning and fine tuning (Alexnet, ResNet101, Inceptionv3 and InceptionResnetv2), (c) a CNN combined with a long short-term memory (LSTM) network to fuse information about the spatial coherency of tumor's CT slices, and (d) combinatorial models (LSTM + CNN + radiomics). In addition, the CT images were independently evaluated by two expert radiologists. Our results showed that the best CNN was Inception (accuracy = 0.67, auc = 0.74). LSTM + Inception yielded superior performance than all other methods (accuracy = 0.74, auc = 0.78). Moreover, LSTM + Inception outperformed experts by 7-25% (p < 0.05). The proposed methodology does not require detailed segmentation of the tumor region and it may be used in conjunction with radiological findings to improve clinical decision-making. Lung cancer histology classification from CT images based on CNN + LSTM.

Development of CAD System for Automatic Lung Nodule Detection: A Review

Lung cancer is a type of cancer that spreads rapidly and is the leading cause of mortality globally. The Computer-Aided Detection (CAD) system for automatic lung cancer detection has a significant influence on human survival. In this article, we report the summary of relevant literature on CAD systems for lung cancer detection. The CAD system includes preprocessing techniques, segmentation, lung nodule detection, and false-positive reduction with feature extraction. In evaluating some of the work on this topic, we used a search of selected literature, the dataset used for method validation, the number of cases, the image size, several techniques in nodule detection, feature extraction, sensitivity, and false-positive rates. The best performance CAD systems of our analysis results show the sensitivity value is high with low false positives and other parameters for lung nodule detection. Furthermore, it also uses a large dataset, so the further systems have improved accuracy and precision in detection. CNN is the best lung nodule detection method and need to develop, it is preferable because this method has witnessed various growth in recent years and has yielded impressive outcomes. We hope this article will help professional researchers and radiologists in developing CAD systems for lung cancer detection.

Artificial intelligence solution to classify pulmonary nodules on CT

PURPOSE

The purpose of this study was to create an algorithm to detect and classify pulmonary nodules in two categories based on their volume greater than 100 mm³ or not, using machine learning and deep learning techniques.

MATERIALS AND METHOD

The dataset used to train the model was provided by the organization team of the SFR (French Radiological Society) Data Challenge 2019. An asynchronous and parallel 3-stages pipeline was developed to process all the data (a data "pre-processing" stage; a "nodule detection" stage; a "classifier" stage). Lung segmentation was achieved using 3D U-NET algorithm; nodule detection was done using 3D Retina-UNET and classifier stage with a support vector machine algorithm on selected features. Performances were assessed using area under receiver operating characteristics curve (AUROC).

RESULTS

The pipeline showed good performance for pathological nodule detection and patient diagnosis. With the preparation dataset, an AUROC of 0.9058 (95% confidence interval [CI]: 0.8746-0.9362) was obtained, 87% yielding accuracy (95% CI: 84.83%-91.03%) for the "nodule detection" stage, corresponding to 86% specificity (95% CI: 82%-92%) and 89% sensitivity (95% CI: 84.83%-91.03%).

CONCLUSION

A fully functional pipeline using 3D U-NET, 3D Retina-UNET and classifier stage with a support vector machine algorithm was developed, resulting in high capabilities for pulmonary nodule classification.

PleThora: Pleural effusion and thoracic cavity segmentations in diseased lungs for benchmarking chest CT processing pipelines

This manuscript describes a dataset of thoracic cavity segmentations and discrete pleural effusion segmentations we have annotated on 402 computed tomography (CT) scans acquired from patients with non-small cell lung cancer. The segmentation of these anatomic regions precedes fundamental tasks in image analysis pipelines such as lung structure segmentation, lesion detection, and radiomics feature extraction. Bilateral thoracic cavity volumes and pleural effusion volumes were manually segmented on CT scans acquired from The Cancer Imaging Archive "NSCLC Radiomics" data collection. Four hundred and two thoracic segmentations were first generated automatically by a U-Net based algorithm trained on chest CTs without cancer, manually corrected by a medical student to include the complete thoracic cavity (normal, pathologic, and atelectatic lung parenchyma, lung hilum, pleural effusion, fibrosis, nodules, tumor, and other anatomic anomalies), and revised by a radiation oncologist or a radiologist. Seventy-eight pleural effusions were manually segmented by a medical student and revised by a radiologist or radiation oncologist. Interobserver agreement between the radiation oncologist and radiologist corrections was acceptable. All expert-vetted segmentations are publicly available in NIfTI format through The Cancer Imaging Archive at https://doi.org/10.7937/tcia.2020.6c7y-gq39. Tabular data detailing clinical and technical metadata linked to segmentation cases are also available. Thoracic cavity segmentations will be valuable for developing image analysis pipelines on pathologic lungs - where current automated algorithms struggle most. In conjunction with gross tumor volume segmentations already available from "NSCLC Radiomics," pleural effusion segmentations may be valuable for investigating radiomics profile differences between effusion and primary tumor or training algorithms to discriminate between them.

Multi-level 3D Densenets for False-positive Reduction in Lung Nodule Detection Based on Chest Computed Tomography

OBJECTIVE

False-positive nodule reduction is a crucial part of a computer-aided detection (CADe) system, which assists radiologists in accurate lung nodule detection. In this research, a novel scheme using multi-level 3D DenseNet framework is proposed to implement false-positive nodule reduction task.

METHODS

Multi-level 3D DenseNet models were extended to differentiate lung nodules from falsepositive nodules. First, different models were fed with 3D cubes with different sizes for encoding multi-level contextual information to meet the challenges of the large variations of lung nodules. In addition, image rotation and flipping were utilized to upsample positive samples which consisted of a positive sample set. Furthermore, the 3D DenseNets were designed to keep low-level information of nodules, as densely connected structures in DenseNet can reuse features of lung nodules and then boost feature propagation. Finally, the optimal weighted linear combination of all model scores obtained the best classification result in this research.

RESULTS

The proposed method was evaluated with LUNA16 dataset which contained 888 thin-slice CT scans. The performance was validated via 10-fold cross-validation. Both the Free-response Receiver Operating Characteristic (FROC) curve and the Competition Performance Metric (CPM) score show that the proposed scheme can achieve a satisfactory detection performance in the falsepositive reduction track of the LUNA16 challenge.

CONCLUSION

The result shows that the proposed scheme can be significant for false-positive nodule reduction task.

Machine-learning-based multiple abnormality prediction with large-scale chest computed tomography volumes

Machine learning models for radiology benefit from large-scale data sets with high quality labels for abnormalities. We curated and analyzed a chest computed tomography (CT) data set of 36,316 volumes from 19,993 unique patients. This is the largest multiply-annotated volumetric medical imaging data set reported. To annotate this data set, we developed a rule-based method for automatically extracting abnormality labels from free-text radiology reports with an average F-score of 0.976 (min 0.941, max 1.0). We also developed a model for multi-organ, multi-disease classification of chest CT volumes that uses a deep convolutional neural network (CNN). This model reached a classification performance of AUROC >0.90 for 18 abnormalities, with an average AUROC of 0.773 for all 83 abnormalities, demonstrating the feasibility of learning from unfiltered whole volume CT data. We show that training on more labels improves performance significantly: for a subset of 9 labels - nodule, opacity, atelectasis, pleural effusion, consolidation, mass, pericardial effusion, cardiomegaly, and pneumothorax - the model's average AUROC increased by 10% when the number of training labels was increased from 9 to all 83. All code for volume preprocessing, automated label extraction, and the volume abnormality prediction model is publicly available. The 36,316 CT volumes and labels will also be made publicly available pending institutional approval.

The natural language explanation algorithms for the lung cancer computer-aided diagnosis system

Two algorithms for explaining decisions of a lung cancer computer-aided diagnosis system are proposed. Their main peculiarity is that they produce explanations of diseases in the form of special sentences via natural language. The algorithms consist of two parts. The first part is a standard local post-hoc explanation model, for example, the well-known LIME, which is used for selecting important features from a special feature representation of the segmented lung suspicious objects. This part is identical for both algorithms. The second part is a model which aims to connect selected important features and to transform them to explanation sentences in natural language. This part is implemented differently for both algorithms. The training phase of the first algorithm uses a special vocabulary of simple phrases which produce sentences and their embeddings. The second algorithm significantly simplifies some parts of the first algorithm and reduces the explanation problem to a set of simple classifiers. The basic idea behind the improvement is to represent every simple phrase from vocabulary as a class of the "sparse" histograms. An implementation of the second algorithm is shown in detail.

Implementation of an Artificial Intelligence-Based Double Read System in Capturing Pulmonary Nodule Discrepancy in CT Studies

Studies show that up to 80% of all radiology errors are due to errors in perception. Early detection is critical for good outcomes in patients with primary lung cancer and lung metastasis. However, pulmonary nodules can be easily missed due to their small size. We prospectively applied a machine vision algorithm to CT studies containing lung parenchyma to detect pulmonary nodules, as well as a natural language processing algorithm to the text of the report to identify documentation of pulmonary nodules. Apparent discrepancies in perception - instances where a pulmonary nodule was not reported - were flagged for a secondary review by a radiologist. Four thousand and nine hundred studies were prospectively processed, of which 450 cases with potential discrepancies were detected. Preliminary manual analysis was performed to analyze the base error rate and to optimize thresholds for the machine vision and natural language processing algorithms, and 104 cases were flagged for final review. Of these 104 cases, 50 cases contained undocumented pulmonary nodules. Among these cases, 7 cases were classified as likely to be significant, where report addendums were done and the clinicians notified. We have successfully implemented an automated double read system to detect pulmonary nodule discrepancies, with minimal disruption to the radiology workflow and while keeping personal health information on-premises. This successful implementation demonstrates the viability of using an automated and secure radiology double-read system to improve patient safety in radiology workflows, either at a health system or an independent radiology practice.

Deep learning applications in pulmonary medical imaging: recent updates and insights on COVID-19

Shortly after deep learning algorithms were applied to Image Analysis, and more importantly to medical imaging, their applications increased significantly to become a trend. Likewise, deep learning applications (DL) on pulmonary medical images emerged to achieve remarkable advances leading to promising clinical trials. Yet, coronavirus can be the real trigger to open the route for fast integration of DL in hospitals and medical centers. This paper reviews the development of deep learning applications in medical image analysis targeting pulmonary imaging and giving insights of contributions to COVID-19. It covers more than 160 contributions and surveys in this field, all issued between February 2017 and May 2020 inclusively, highlighting various deep learning tasks such as classification, segmentation, and detection, as well as different pulmonary pathologies like airway diseases, lung cancer, COVID-19 and other infections. It summarizes and discusses the current state-of-the-art approaches in this research domain, highlighting the challenges, especially with COVID-19 pandemic current situation.

Optical Flow Methods for Lung Nodule Segmentation on LIDC-IDRI Images

Lung nodule segmentation is an essential step in any CAD system for lung cancer detection and diagnosis. Traditional approaches for image segmentation are mainly morphology based or intensity based. Motion-based segmentation techniques tend to use the temporal information along with the morphology and intensity information to perform segmentation of regions of interest in videos. CT scans comprise of a sequence of dicom 2-D image slices similar to videos which also comprise of a sequence of image frames ordered on a timeline. In this work, Farneback, Horn-Schunck and Lucas-Kanade optical flow methods have been used for processing the dicom slices. The novelty of this work lies in the usage of optical flow methods, generally used in motion-based segmentation tasks, for the segmentation of nodules from CT images. Since thin-sliced CT scans are the imaging modality considered, they closely approximate the motion videos and are the primary motivation for using optical flow for lung nodule segmentation. This paper also provides a detailed comparative analysis and validates the effectiveness of using optical flow methods for segmentation. Finally, we propose methods to further improve the efficiency of segmentation using optical flow methods on CT scans.

Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks

Fast diagnostic methods can control and prevent the spread of pandemic diseases like coronavirus disease 2019 (COVID-19) and assist physicians to better manage patients in high workload conditions. Although a laboratory test is the current routine diagnostic tool, it is time-consuming, imposing a high cost and requiring a well-equipped laboratory for analysis. Computed tomography (CT) has thus far become a fast method to diagnose patients with COVID-19. However, the performance of radiologists in diagnosis of COVID-19 was moderate. Accordingly, additional investigations are needed to improve the performance in diagnosing COVID-19. In this study is suggested a rapid and valid method for COVID-19 diagnosis using an artificial intelligence technique based. 1020 CT slices from 108 patients with laboratory proven COVID-19 (the COVID-19 group) and 86 patients with other atypical and viral pneumonia diseases (the non-COVID-19 group) were included. Ten well-known convolutional neural networks were used to distinguish infection of COVID-19 from non-COVID-19 groups: AlexNet, VGG-16, VGG-19, SqueezeNet, GoogleNet, MobileNet-V2, ResNet-18, ResNet-50, ResNet-101, and Xception. Among all networks, the best performance was achieved by ResNet-101 and Xception. ResNet-101 could distinguish COVID-19 from non-COVID-19 cases with an AUC of 0.994 (sensitivity, 100%; specificity, 99.02%; accuracy, 99.51%). Xception achieved an AUC of 0.994 (sensitivity, 98.04%; specificity, 100%; accuracy, 99.02%). However, the performance of the radiologist was moderate with an AUC of 0.873 (sensitivity, 89.21%; specificity, 83.33%; accuracy, 86.27%). ResNet-101 can be considered as a high sensitivity model to characterize and diagnose COVID-19 infections, and can be used as an adjuvant tool in radiology departments.

A CT-guided robotic needle puncture method for lung tumours with respiratory motion

PURPOSE

Percutaneous interventions rely on needle puncture to deliver medical devices into lesions. For lung tumours, respiratory motion makes effective puncture procedures difficult to achieve. To address this issue, a needle puncture method considering respiration is proposed to improve the accuracy of lung puncture.

METHODS

The accuracy of puncture is ensured by visualization and needle guidance. Dynamic visualization of the respiratory motion is developed for needle path planning based on four-dimensional computed tomography (4DCT) images. The rendered image is synchronized with the actual breathing by using respiratory signals. A robotic needle insertion strategy for velocity adjustment based on these respiratory signals is designed to guide the needle towards the moving tumour.

RESULTS

The dynamic visualization was tested on multiple 4DCT datasets and achieved a frame rate of over 32 frames per second (FPS). A computer simulation was carried out to verify the feasibility of the needle insertion strategy. Needle puncture was performed on a phantom, and a mean accuracy of 1.34±0.18 mm was achieved.

CONCLUSIONS

In this paper, an efficient and robust method is proposed to improve the visualization and targeting of lung puncture, which reduces the impact of respiratory motion on the accuracy.