Lung image database consortium: developing a resource for the medical imaging research community

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.

ADGAN: Attribute-Driven Generative Adversarial Network for Synthesis and Multiclass Classification of Pulmonary Nodules

Lung cancer is the leading cause of cancer-related deaths worldwide. According to the American Cancer Society, early diagnosis of pulmonary nodules in computed tomography (CT) scans can improve the five-year survival rate up to 70% with proper treatment planning. In this article, we propose an attribute-driven Generative Adversarial Network (ADGAN) for synthesis and multiclass classification of Pulmonary Nodules. A self-attention U-Net (SaUN) architecture is proposed to improve the generation mechanism of the network. The generator is designed with two modules, namely, self-attention attribute module (SaAM) and a self-attention spatial module (SaSM). SaAM generates a nodule image based on given attributes whereas SaSM specifies the nodule region of the input image to be altered. A reconstruction loss along with an attention localization loss (AL) is used to produce an attention map prioritizing the nodule regions. To avoid resemblance between a generated image and a real image, we further introduce an adversarial loss containing a regularization term based on KL divergence. The discriminator part of the proposed model is designed to achieve the multiclass nodule classification task. Our proposed approach is validated over two challenging publicly available datasets, namely LIDC-IDRI and LUNGX. Exhaustive experimentation on these two datasets clearly indicate that we have achieved promising classification accuracy as compared to other state-of-the-art methods.

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.

Diffusion models in medical imaging: A comprehensive survey

Denoising diffusion models, a class of generative models, have garnered immense interest lately in various deep-learning problems. A diffusion probabilistic model defines a forward diffusion stage where the input data is gradually perturbed over several steps by adding Gaussian noise and then learns to reverse the diffusion process to retrieve the desired noise-free data from noisy data samples. Diffusion models are widely appreciated for their strong mode coverage and quality of the generated samples in spite of their known computational burdens. Capitalizing on the advances in computer vision, the field of medical imaging has also observed a growing interest in diffusion models. With the aim of helping the researcher navigate this profusion, this survey intends to provide a comprehensive overview of diffusion models in the discipline of medical imaging. Specifically, we start with an introduction to the solid theoretical foundation and fundamental concepts behind diffusion models and the three generic diffusion modeling frameworks, namely, diffusion probabilistic models, noise-conditioned score networks, and stochastic differential equations. Then, we provide a systematic taxonomy of diffusion models in the medical domain and propose a multi-perspective categorization based on their application, imaging modality, organ of interest, and algorithms. To this end, we cover extensive applications of diffusion models in the medical domain, including image-to-image translation, reconstruction, registration, classification, segmentation, denoising, 2/3D generation, anomaly detection, and other medically-related challenges. Furthermore, we emphasize the practical use case of some selected approaches, and then we discuss the limitations of the diffusion models in the medical domain and propose several directions to fulfill the demands of this field. Finally, we gather the overviewed studies with their available open-source implementations at our GitHub.1 We aim to update the relevant latest papers within it regularly.

Impact of localized fine tuning in the performance of segmentation and classification of lung nodules from computed tomography scans using deep learning

Background

Algorithm malfunction may occur when there is a performance mismatch between the dataset with which it was developed and the dataset on which it was deployed.

Methods

A baseline segmentation algorithm and a baseline classification algorithm were developed using public dataset of Lung Image Database Consortium to detect benign and malignant nodules, and two additional external datasets (i.e., HB and XZ) including 542 cases and 486 cases were involved for the independent validation of these two algorithms. To explore the impact of localized fine tuning on the individual segmentation and classification process, the baseline algorithms were fine tuned with CT scans of HB and XZ datasets, respectively, and the performance of the fine tuned algorithms was tested to compare with the baseline algorithms.

Results

The proposed baseline algorithms of both segmentation and classification experienced a drop when directly deployed in external HB and XZ datasets. Comparing with the baseline validation results in nodule segmentation, the fine tuned segmentation algorithm obtained better performance in Dice coefficient, Intersection over Union, and Average Surface Distance in HB dataset (0.593 vs. 0.444; 0.450 vs. 0.348; 0.283 vs. 0.304) and XZ dataset (0.601 vs. 0.486; 0.482 vs. 0.378; 0.225 vs. 0.358). Similarly, comparing with the baseline validation results in benign and malignant nodule classification, the fine tuned classification algorithm had improved area under the receiver operating characteristic curve value, accuracy, and F1 score in HB dataset (0.851 vs. 0.812; 0.813 vs. 0.769; 0.852 vs. 0.822) and XZ dataset (0.724 vs. 0.668; 0.696 vs. 0.617; 0.737 vs. 0.668).

Conclusions

The external validation performance of localized fine tuned algorithms outperformed the baseline algorithms in both segmentation process and classification process, which showed that localized fine tuning may be an effective way to enable a baseline algorithm generalize to site-specific use.

A survey on the utilization of Superpixel image for clustering based image segmentation

Superpixel become increasingly popular in image segmentation field as it greatly helps image segmentation techniques to segment the region of interest accurately in noisy environment and also reduces the computation effort to a great extent. However, selection of proper superpixel generation techniques and superpixel image segmentation techniques play a very crucial role in the domain of different kinds of image segmentation. Clustering is a well-accepted image segmentation technique and proved their effective performance over various image segmentation field. Therefore, this study presents an up-to-date survey on the employment of superpixel image in combined with clustering techniques for the various image segmentation. The contribution of the survey has four parts namely (i) overview of superpixel image generation techniques, (ii) clustering techniques especially efficient partitional clustering techniques, their issues and overcoming strategies, (iii) Review of superpixel combined with clustering strategies exist in literature for various image segmentation, (iv) lastly, the comparative study among superpixel combined with partitional clustering techniques has been performed over oral pathology and leaf images to find out the efficacy of the combination of superpixel and partitional clustering approaches. Our evaluations and observation provide in-depth understanding of several superpixel generation strategies and how they apply to the partitional clustering method.

Medical matting: Medical image segmentation with uncertainty from the matting perspective

High-quality manual labeling of ambiguous and complex-shaped targets with binary masks can be challenging. The weakness of insufficient expression of binary masks is prominent in segmentation, especially in medical scenarios where blurring is prevalent. Thus, reaching a consensus among clinicians through binary masks is more difficult in multi-person labeling cases. These inconsistent or uncertain areas are related to the lesions' structure and may contain anatomical information conducive to providing an accurate diagnosis. However, recent research focuses on uncertainties of model training and data labeling. None of them has investigated the influence of the ambiguous nature of the lesion itself. Inspired by image matting, this paper introduces a soft mask called alpha matte to medical scenes. It can describe the lesions with more details better than a binary mask. Moreover, it can also be used as a new uncertainty quantification method to represent uncertain areas, filling the gap in research on the uncertainty of lesion structure. In this work, we introduce a multi-task framework to generate binary masks and alpha mattes, which outperforms all state-of-the-art matting algorithms compared. The uncertainty map is proposed to imitate the trimap in matting methods, which can highlight fuzzy areas and improve matting performance. We have created three medical datasets with alpha mattes to address the lack of available matting datasets in medical fields and evaluated the effectiveness of our proposed method on them comprehensively. Furthermore, experiments demonstrate that the alpha matte is a more effective labeling method than the binary mask from both qualitative and quantitative aspects.

Trustworthy learning with (un)sure annotation for lung nodule diagnosis with CT

Recent evolution in deep learning has proven its value for CT-based lung nodule classification. Most current techniques are intrinsically black-box systems, suffering from two generalizability issues in clinical practice. First, benign-malignant discrimination is often assessed by human observers without pathologic diagnoses at the nodule level. We termed these data as "unsure-annotation data". Second, a classifier does not necessarily acquire reliable nodule features for stable learning and robust prediction with patch-level labels during learning. In this study, we construct a sure-annotation dataset with pathologically-confirmed labels and propose a collaborative learning framework to facilitate sure nodule classification by integrating unsure-annotation data knowledge through nodule segmentation and malignancy score regression. A loss function is designed to learn reliable features by introducing interpretability constraints regulated with nodule segmentation maps. Furthermore, based on model inference results that reflect the understanding from both machine and experts, we explore a new nodule analysis method for similar historical nodule retrieval and interpretable diagnosis. Detailed experimental results demonstrate that our approach is beneficial for achieving improved performance coupled with trustworthy model reasoning for lung cancer prediction with limited data. Extensive cross-evaluation results further illustrate the effect of unsure-annotation data for deep-learning based methods in lung nodule classification.

Performance analyses of five neural network classifiers on nodule classification in lung CT images using WEKA: a comparative study

In this report, we are presenting our work on performance analyses of five different neural network classifiers viz. MLP, DL4JMLP, logistic regression, SGD and simple logistic classifier in lung nodule detection using WEKA interface. To the best of our knowledge, this report demonstrates first use of WEKA for comparative performance analyses of neural network classifiers in identifying lung nodules from lung CT-images. A total of 624 handcrafted features from 52 numbers of lung CT-images collected randomly from Lung Image Database Consortium (LIDC) were fed into WEKA to evaluate the performances of the classifiers under four different categories of computation. Performances of the classifiers were observed in terms of 11 important parameters viz. accuracy, kappa statistic, root mean squared error, TPR, FPR, precision, sensitivity, F-measurement, MCC, ROC area and PRC area. Results show 86.53%, 77.77%, 55.55%, 94.44% & 88.88% accuracy as well as 0.91, 0.86, 0.68, 0.91 & 0.93 ROC area for MLP, DL4JMLP, logistic, SGD and simple logistic classifier respectively at tenfold cross-validation by taking 66% of the data set for training and 34% for testing and validation purpose. SGDClassifier has been found the best performing followed by simple logistic classifier for the purpose.

Computer-Aided Diagnosis of Pulmonary Nodules in Rheumatoid Arthritis

(1) Background: Rheumatoid arthritis (RA) is considered a systemic inflammatory pathology characterized by symmetric polyarthritis associated with extra-articular manifestations, such as lung disease. The purpose of the present study is to use CAD in the detection of rheumatoid pulmonary nodules. In addition, we aim to identify the characteristics and associations between clinical, laboratory and imaging data in patients with rheumatoid arthritis and lung nodules. (2) Methods: The study included a number of 42 patients diagnosed with rheumatoid arthritis according to the 2010 American College of Rheumatology (ACR)/European League Against Rheumatism (EULAR) criteria, examined from January 2017 to November 2022 in the Departments of Rheumatology and Radiology and Medical Imaging of the University of Medicine and Pharmacy of Craiova. Medical records were reviewed. A retrospective blinded review of CT for biopsy-proven pulmonary nodules in RA using Veolity LungCAD software was performed (MeVis Medical Solutions AG, Bremen, Germany). Imaging was also reviewed by a senior radiologist. (3) Results: The interobserver agreement proved to be moderate (κ = 0.478) for the overall examined cases. CAD interpretation resulted in false positive results in the case of 12 lung nodules, whereas false negative results were reported in the case of 8 lung nodules. The mean time it took for the detection of lung nodules using CAD was 4.2 min per patient, whereas the detection of lung nodules by the radiologist was 8.1 min per patient. This resulted in a faster interpretation of lung CT scans, almost reducing the detection time by half (p < 0.001). (4) Conclusions: The CAD software is useful in identifying lung nodules, in shortening the interpretation time of the CT examination and also in aiding the radiologist in better assessing all the pulmonary lung nodules. However, the CAD software cannot replace the human eye yet due to the relative high rate of false positive and false negative results.

3D matting: A benchmark study on soft segmentation method for pulmonary nodules applied in computed tomography

Usually, lesions are not isolated but are associated with the surrounding tissues. For example, the growth of a tumour can depend on or infiltrate into the surrounding tissues. Due to the pathological nature of the lesions, it is challenging to distinguish their boundaries in medical imaging. However, these uncertain regions may contain diagnostic information. Therefore, the simple binarization of lesions by traditional binary segmentation can result in the loss of diagnostic information. In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i.e., a soft mask, to describe lesions in a 3D medical image. The traditional soft mask acted as a training trick to compensate for the easily mislabelled or under-labelled ambiguous regions. In contrast, 3D matting uses soft segmentation to characterize the uncertain regions more finely, which means that it retains more structural information for subsequent diagnosis and treatment. The current study of image matting methods in 3D is limited. To address this issue, we conduct a comprehensive study of 3D matting, including both traditional and deep-learning-based methods. We adapt four state-of-the-art 2D image matting algorithms to 3D scenes and further customize the methods for CT images to calibrate the alpha matte with the radiodensity. Moreover, we propose the first end-to-end deep 3D matting network and implement a solid 3D medical image matting benchmark. Its efficient counterparts are also proposed to achieve a good performance-computation balance. Furthermore, there is no high-quality annotated dataset related to 3D matting, slowing down the development of data-driven deep-learning-based methods. To address this issue, we construct the first 3D medical matting dataset. The validity of the dataset was verified through clinicians' assessments and downstream experiments. The dataset and codes will be released to encourage further research.1.

The federated tumor segmentation (FeTS) tool: an open-source solution to further solid tumor research

Objective.De-centralized data analysis becomes an increasingly preferred option in the healthcare domain, as it alleviates the need for sharing primary patient data across collaborating institutions. This highlights the need for consistent harmonized data curation, pre-processing, and identification of regions of interest based on uniform criteria.Approach.Towards this end, this manuscript describes theFederatedTumorSegmentation (FeTS) tool, in terms of software architecture and functionality.Main results.The primary aim of the FeTS tool is to facilitate this harmonized processing and the generation of gold standard reference labels for tumor sub-compartments on brain magnetic resonance imaging, and further enable federated training of a tumor sub-compartment delineation model across numerous sites distributed across the globe, without the need to share patient data.Significance.Building upon existing open-source tools such as the Insight Toolkit and Qt, the FeTS tool is designed to enable training deep learning models targeting tumor delineation in either centralized or federated settings. The target audience of the FeTS tool is primarily the computational researcher interested in developing federated learning models, and interested in joining a global federation towards this effort. The tool is open sourced athttps://github.com/FETS-AI/Front-End.

Unsupervised knowledge-transfer for learned image reconstruction

Deep learning-based image reconstruction approaches have demonstrated impressive empirical performance in many imaging modalities. These approaches usually require a large amount of high-quality paired training data, which is often not available in medical imaging. To circumvent this issue we develop a novel unsupervised knowledge-transfer paradigm for learned reconstruction within a Bayesian framework. The proposed approach learns a reconstruction network in two phases. The first phase trains a reconstruction network with a set of ordered pairs comprising of ground truth images of ellipses and the corresponding simulated measurement data. The second phase fine-tunes the pretrained network to more realistic measurement data without supervision. By construction, the framework is capable of delivering predictive uncertainty information over the reconstructed image. We present extensive experimental results on low-dose and sparse-view computed tomography showing that the approach is competitive with several state-of-the-art supervised and unsupervised reconstruction techniques. Moreover, for test data distributed differently from the training data, the proposed framework can significantly improve reconstruction quality not only visually, but also quantitatively in terms of PSNR and SSIM, when compared with learned methods trained on the synthetic dataset only.

Validation of a deep learning computer aided system for CT based lung nodule detection, classification, and growth rate estimation in a routine clinical population

OBJECTIVE

In this study, we evaluated a commercially available computer assisted diagnosis system (CAD). The deep learning algorithm of the CAD was trained with a lung cancer screening cohort and developed for detection, classification, quantification, and growth of actionable pulmonary nodules on chest CT scans. Here, we evaluated the CAD in a retrospective cohort of a routine clinical population.

MATERIALS AND METHODS

In total, a number of 337 scans of 314 different subjects with reported nodules of 3-30 mm in size were included into the evaluation. Two independent thoracic radiologists alternately reviewed scans with or without CAD assistance to detect, classify, segment, and register pulmonary nodules. A third, more experienced, radiologist served as an adjudicator. In addition, the cohort was analyzed by the CAD alone. The study cohort was divided into five different groups: 1) 178 CT studies without reported pulmonary nodules, 2) 95 studies with 1-10 pulmonary nodules, 23 studies from the same patients with 3) baseline and 4) follow-up studies, and 5) 18 CT studies with subsolid nodules. A reference standard for nodules was based on majority consensus with the third thoracic radiologist as required. Sensitivity, false positive (FP) rate and Dice inter-reader coefficient were calculated.

RESULTS

After analysis of 470 pulmonary nodules, the sensitivity readings for radiologists without CAD and radiologist with CAD, were 71.9% (95% CI: 66.0%, 77.0%) and 80.3% (95% CI: 75.2%, 85.0%) (p < 0.01), with average FP rate of 0.11 and 0.16 per CT scan, respectively. Accuracy and kappa of CAD for classifying solid vs sub-solid nodules was 94.2% and 0.77, respectively. Average inter-reader Dice coefficient for nodule segmentation was 0.83 (95% CI: 0.39, 0.96) and 0.86 (95% CI: 0.51, 0.95) for CAD versus readers. Mean growth percentage discrepancy of readers and CAD alone was 1.30 (95% CI: 1.02, 2.21) and 1.35 (95% CI: 1.01, 4.99), respectively.

CONCLUSION

The applied CAD significantly increased radiologist's detection of actionable nodules yet also minimally increasing the false positive rate. The CAD can automatically classify and quantify nodules and calculate nodule growth rate in a cohort of a routine clinical population. Results suggest this Deep Learning software has the potential to assist chest radiologists in the tasks of pulmonary nodule detection and management within their routine clinical practice.

A holistic overview of deep learning approach in medical imaging

Medical images are a rich source of invaluable necessary information used by clinicians. Recent technologies have introduced many advancements for exploiting the most of this information and use it to generate better analysis. Deep learning (DL) techniques have been empowered in medical images analysis using computer-assisted imaging contexts and presenting a lot of solutions and improvements while analyzing these images by radiologists and other specialists. In this paper, we present a survey of DL techniques used for variety of tasks along with the different medical image's modalities to provide critical review of the recent developments in this direction. We have organized our paper to provide significant contribution of deep leaning traits and learn its concepts, which is in turn helpful for non-expert in medical society. Then, we present several applications of deep learning (e.g., segmentation, classification, detection, etc.) which are commonly used for clinical purposes for different anatomical site, and we also present the main key terms for DL attributes like basic architecture, data augmentation, transfer learning, and feature selection methods. Medical images as inputs to deep learning architectures will be the mainstream in the coming years, and novel DL techniques are predicted to be the core of medical images analysis. We conclude our paper by addressing some research challenges and the suggested solutions for them found in literature, and also future promises and directions for further developments.

Lung Nodule Detection from Feature Engineering to Deep Learning in Thoracic CT Images: a Comprehensive Review

This paper presents a systematic review of the literature focused on the lung nodule detection in chest computed tomography (CT) images. Manual detection of lung nodules by the radiologist is a sequential and time-consuming process. The detection is subjective and depends on the radiologist's experiences. Owing to the variation in shapes and appearances of a lung nodule, it is very difficult to identify the proper location of the nodule from a huge number of slices generated by the CT scanner. Small nodules (< 10 mm in diameter) may be missed by this manual detection process. Therefore, computer-aided diagnosis (CAD) system acts as a "second opinion" for the radiologists, by making final decision quickly with higher accuracy and greater confidence. The goal of this survey work is to present the current state of the artworks and their progress towards lung nodule detection to the researchers and readers in this domain. This review paper has covered the published works from 2009 to April 2018. Different nodule detection approaches are described elaborately in this work. Recently, it is observed that deep learning (DL)-based approaches are applied extensively for nodule detection and characterization. Therefore, emphasis has been given to convolutional neural network (CNN)-based DL approaches by describing different CNN-based networks.

Artificial intelligence in oncology: From bench to clinic

In the past few years, Artificial Intelligence (AI) techniques have been applied to almost every facet of oncology, from basic research to drug development and clinical care. In the clinical arena where AI has perhaps received the most attention, AI is showing promise in enhancing and automating image-based diagnostic approaches in fields such as radiology and pathology. Robust AI applications, which retain high performance and reproducibility over multiple datasets, extend from predicting indications for drug development to improving clinical decision support using electronic health record data. In this article, we review some of these advances. We also introduce common concepts and fundamentals of AI and its various uses, along with its caveats, to provide an overview of the opportunities and challenges in the field of oncology. Leveraging AI techniques productively to provide better care throughout a patient's medical journey can fuel the predictive promise of precision medicine.

5K+ CT Images on Fractured Limbs: A Dataset for Medical Imaging Research

Imaging techniques widely use Computed Tomography (CT) scans for various purposes, such as screening, diagnosis, and decision-making. Of all, it holds true for bone injuries. To build fully automated Computer-Aided Detection (CADe) and Diagnosis (CADx) tools and techniques, it requires fairly large amount of data (with gold standard). Therefore, in this paper, since state-of-the-art works relied on small dataset, we introduced a CT image dataset on limbs that is designed to understand bone injuries. Our dataset is a collection of 24 patient-specific CT cases having fractures at upper and lower limbs. From upper limbs, 8 cases were collected from bones in/around the shoulder (left and right). Similarly, from lower limbs, 16 cases were collected from knees (left and right). Altogether, 5684 CT images (upper limbs: 2057 and lower limbs: 3627) were collected. Each patient-specific CT case is composed of maximum 257 scans/slices in average. Of all, clinically approved annotations were made on every 10th slices, resulting in 1787 images. Importantly, no fractured limbs were missed in our annotation. Besides, to avoid privacy and confidential issues, patient-related information were deleted. The proposed dataset could be a promising resource for the medical imaging research community, where imaging techniques are employed for various purposes. To the best of our knowledge, this is the first time 5K⁺ CT images on fractured limbs are provided for research and educational purposes.

Research on Application of Ultrasound Medical Imaging Technology in Big Data Mining of Regional Medical Imaging

Ultrasound medical imaging technology is one of the main methods of medical non-invasive diagnosis, and it is the focus of research in the medical field at home and abroad. Medical images have a large amount of data and contain a wealth of image feature information and rules, which need to be studied and understood. Therefore, the research of data mining technique for reading medical images has become a very important field in the interdisciplinary research of medical and computer science. The high resolution of medical images, the mass of data, and the complexity of image feature expressions make the research of data mining technology in medical images of great academic value and broad application prospects. At present, research on data mining for medical images has just started, and there are still many problems in the direct application of existing data mining methods. Researching and exploring the theoretical and practical problems of medical image data mining, such as data mining methods and algorithms suitable for medical image, which has significant and crucial value, and it is of great importance to help physicians in clinical diagnosis of medical images. This article introduces the background, definition and basic process of data mining technology, the characteristics of medical imaging data and the key techniques of medical image data mining. In view of the data mining research of human abdominal medical images is a completely new field, human abdominal imaging is the most complicated part of medical images. Solving the problem of abdominal imaging is of great value to the entire medical image. For regional medical image big data mining, we can use ultrasound images of the human abdomen. The clustering feature extraction algorithm and its implementation based on the approximate density structure of medical images proposed in this article, and innovative research results such as classification rule mining methods, are used to mine medical image data research, automatic diagnosis of clinical medical images, and early diagnosis of clinical medicine are of great significance.

Transfer-to-Transfer Learning Approach for Computer Aided Detection of COVID-19 in Chest Radiographs

The coronavirus disease 2019 (COVID-19) global pandemic has severely impacted lives across the globe. Respiratory disorders in COVID-19 patients are caused by lung opacities similar to viral pneumonia. A Computer-Aided Detection (CAD) system for the detection of COVID-19 using chest radiographs would provide a second opinion for radiologists. For this research, we utilize publicly available datasets that have been marked by radiologists into two-classes (COVID-19 and non-COVID-19). We address the class imbalance problem associated with the training dataset by proposing a novel transfer-to-transfer learning approach, where we break a highly imbalanced training dataset into a group of balanced mini-sets and apply transfer learning between these. We demonstrate the efficacy of the method using well-established deep convolutional neural networks. Our proposed training mechanism is more robust to limited training data and class imbalance. We study the performance of our algorithm(s) based on 10-fold cross validation and two hold-out validation experiments to demonstrate its efficacy. We achieved an overall sensitivity of 0.94 for the hold-out validation experiments containing 2265 and 2139 marked as COVID-19 chest radiographs, respectively. For the 10-fold cross validation experiment, we achieve an overall Area under the Receiver Operating Characteristic curve (AUC) value of 0.996 for COVID-19 detection. This paper serves as a proof-of-concept that an automated detection approach can be developed with a limited set of COVID-19 images, and in areas with scarcity of trained radiologists.

The State of Radiology AI: Considerations for Purchase Decisions and Current Market Offerings

Purpose

To provide an overview of important factors to consider when purchasing radiology artificial intelligence (AI) software and current software offerings by type, subspecialty, and modality.

Materials and Methods

Important factors for consideration when purchasing AI software, including key decision makers, data ownership and privacy, cost structures, performance indicators, and potential return on investment are described. For the market overview, a list of radiology AI companies was aggregated from the Radiological Society of North America and the Society for Imaging Informatics in Medicine conferences (November 2016-June 2019), then narrowed to companies using deep learning for imaging analysis and diagnosis. Software created for image enhancement, reporting, or workflow management was excluded. Software was categorized by task (repetitive, quantitative, explorative, and diagnostic), modality, and subspecialty.

Results

A total of 119 software offerings from 55 companies were identified. There were 46 algorithms that currently have Food and Drug Administration and/or Conformité Européenne approval (as of November 2019). Of the 119 offerings, distribution of software targets was 34 of 70 (49%), 21 of 70 (30%), 14 of 70 (20%), and one of 70 (1%) for diagnostic, quantitative, repetitive, and explorative tasks, respectively. A plurality of companies are focused on nodule detection at chest CT and two-dimensional mammography. There is very little activity in certain subspecialties, including pediatrics and nuclear medicine. A comprehensive table is available on the website hitilab.org/pages/ai-companies.

Conclusion

The radiology AI marketplace is rapidly maturing, with an increase in product offerings. Radiologists and practice administrators should educate themselves on current product offerings and important factors to consider before purchase and implementation.© RSNA, 2020See also the invited commentary by Sala and Ursprung in this issue.

Deep learning-based pulmonary nodule detection: Effect of slab thickness in maximum intensity projections at the nodule candidate detection stage

BACKGROUND AND OBJECTIVE

To investigate the effect of the slab thickness in maximum intensity projections (MIPs) on the candidate detection performance of a deep learning-based computer-aided detection (DL-CAD) system for pulmonary nodule detection in CT scans.

METHODS

The public LUNA16 dataset includes 888 CT scans with 1186 nodules annotated by four radiologists. From those scans, MIP images were reconstructed with slab thicknesses of 5 to 50 mm (at 5 mm intervals) and 3 to 13 mm (at 2 mm intervals). The architecture in the nodule candidate detection part of the DL-CAD system was trained separately using MIP images with various slab thicknesses. Based on ten-fold cross-validation, the sensitivity and the F₂ score were determined to evaluate the performance of using each slab thickness at the nodule candidate detection stage. The free-response receiver operating characteristic (FROC) curve was used to assess the performance of the whole DL-CAD system that took the results combined from 16 MIP slab thickness settings.

RESULTS

At the nodule candidate detection stage, the combination of results from 16 MIP slab thickness settings showed a high sensitivity of 98.0% with 46 false positives (FPs) per scan. Regarding a single MIP slab thickness of 10 mm, the highest sensitivity of 90.0% with 8 FPs/scan was reached before false positive reduction. The sensitivity increased (82.8% to 90.0%) for slab thickness of 1 to 10 mm and decreased (88.7% to 76.6%) for slab thickness of 15-50 mm. The number of FPs was decreasing with increasing slab thickness, but was stable at 5 FPs/scan at a slab thickness of 30 mm or more. After false positive reduction, the DL-CAD system, utilizing 16 MIP slab thickness settings, had the sensitivity of 94.4% with 1 FP/scan.

CONCLUSIONS

The utilization of multi-MIP images could improve the performance at the nodule candidate detection stage, even for the whole DL-CAD system. For a single slab thickness of 10 mm, the highest sensitivity for pulmonary nodule detection was reached at the nodule candidate detection stage, similar to the slab thickness usually applied by radiologists.

W. L. Aerts H, Kikinis R, Prior F. DICOM re-encoding of volumetrically annotated Lung Imaging Database Consortium (LIDC) nodules

PURPOSE

The dataset contains annotations for lung nodules collected by the Lung Imaging Data Consortium and Image Database Resource Initiative (LIDC) stored as standard DICOM objects. The annotations accompany a collection of computed tomography (CT) scans for over 1000 subjects annotated by multiple expert readers, and correspond to "nodules ≥ 3 mm", defined as any lesion considered to be a nodule with greatest in-plane dimension in the range 3-30 mm regardless of presumed histology. The present dataset aims to simplify reuse of the data with the readily available tools, and is targeted towards researchers interested in the analysis of lung CT images.

ACQUISITION AND VALIDATION METHODS

Open source tools were utilized to parse the project-specific XML representation of LIDC-IDRI annotations and save the result as standard DICOM objects. Validation procedures focused on establishing compliance of the resulting objects with the standard, consistency of the data between the DICOM and project-specific representation, and evaluating interoperability with the existing tools.

DATA FORMAT AND USAGE NOTES

The dataset utilizes DICOM Segmentation objects for storing annotations of the lung nodules, and DICOM Structured Reporting objects for communicating qualitative evaluations (nine attributes) and quantitative measurements (three attributes) associated with the nodules. The total of 875 subjects contain 6859 nodule annotations. Clustering of the neighboring annotations resulted in 2651 distinct nodules. The data are available in TCIA at https://doi.org/10.7937/TCIA.2018.h7umfurq.

POTENTIAL APPLICATIONS

The standardized dataset maintains the content of the original contribution of the LIDC-IDRI consortium, and should be helpful in developing automated tools for characterization of lung lesions and image phenotyping. In addition to those properties, the representation of the present dataset makes it more FAIR (Findable, Accessible, Interoperable, Reusable) for the research community, and enables its integration with other standardized data collections.

Learning Latent Spiculated Features for Lung Nodule Characterization

Computer-aided Diagnosis (CAD) systems have long aimed to be used in clinical practice to help doctors make decisions by providing a second opinion. However, most machine learning based CAD systems make predictions without explicitly showing how their predictions were generated. Since the cognitive process of the diagnostic imaging interpretation involves various visual characteristics of the region of interest, the explainability of the results should leverage those characteristics. We encode visual characteristics of the region of interest based on pairs of similar images rather than the image content by itself. Using a Siamese convolutional neural network (SCNN), we first learn the similarity among nodules, then encode image content using the SCNN similarity-based feature representation, and lastly, we apply the K-nearest neighbor (KNN) approach to make diagnostic characterizations using the Siamese-based image features. We demonstrate the feasibility of our approach on spiculation, a visual characteristic that radiologists consider when interpreting the degree of cancer malignancy, and the NIH/NCI Lung Image Database Consortium (LIDC) dataset that contains both spiculation and malignancy characteristics for lung nodules.Clinical Relevance - This establishes that spiculation can be quantified to automate the diagnostic characterization of lung nodules in Computed Tomography images.

A Clinical Decision-Support System Based on Three-Stage Integrated Image Analysis for Diagnosing Lung Disease

Thoracic computed tomography (CT) technology has been used for lung cancer screening in high-risk populations, and this technique is highly effective in the identification of early lung cancer. With the rapid development of intelligent image analysis in the field of medical science and technology, many researchers have proposed computer-aided automatic diagnosis methods for facilitating medical experts in detecting lung nodules. This paper proposes an advanced clinical decision-support system for analyzing chest CT images of lung disease. Three advanced methods are utilized in the proposed system: the three-stage automated segmentation method (TSASM), the discrete wavelet packets transform (DWPT) with singular value decomposition (SVD), and the algorithms of the rough set theory, which comprise a classification-based method. Two collected medical CT image datasets were prepared to evaluate the proposed system. The CT image datasets were labeled (nodule, non-nodule, or inflammation) by experienced radiologists from a regional teaching hospital. According to the results, the proposed system outperforms other classification methods (trees, naïve Bayes, multilayer perception, and sequential minimal optimization) in terms of classification accuracy and can be employed as a clinical decision-support system for diagnosing lung disease.

Lung Nodule Detection in CT Images Using Statistical and Shape-Based Features

The lung tumor is among the most detrimental kinds of malignancy. It has a high occurrence rate and a high death rate, as it is frequently diagnosed at the later stages. Computed Tomography (CT) scans are broadly used to distinguish the disease; computer aided systems are being created to analyze the ailment at prior stages productively. In this paper, we present a fully automatic framework for nodule detection from CT images of lungs. A histogram of the grayscale CT image is computed to automatically isolate the lung locale from the foundation. The results are refined using morphological operators. The internal structures are then extracted from the parenchyma. A threshold-based technique is proposed to separate the candidate nodules from other structures, e.g., bronchioles and blood vessels. Different statistical and shape-based features are extracted for these nodule candidates to form nodule feature vectors which are classified using support vector machines. The proposed method is evaluated on a large lungs CT dataset collected from the Lung Image Database Consortium (LIDC). The proposed method achieved excellent results compared to similar existing methods; it achieves a sensitivity rate of 93.75%, which demonstrates its effectiveness.

An Appraisal of Nodule Diagnosis for Lung Cancer in CT Images

As "the second eyes" of radiologists, computer-aided diagnosis systems play a significant role in nodule detection and diagnosis for lung cancer. In this paper, we aim to provide a systematic survey of state-of-the-art techniques (both traditional techniques and deep learning techniques) for nodule diagnosis from computed tomography images. This review first introduces the current progress and the popular structure used for nodule diagnosis. In particular, we provide a detailed overview of the five major stages in the computer-aided diagnosis systems: data acquisition, nodule segmentation, feature extraction, feature selection and nodule classification. Second, we provide a detailed report of the selected works and make a comprehensive comparison between selected works. The selected papers are from the IEEE Xplore, Science Direct, PubMed, and Web of Science databases up to December 2018. Third, we discuss and summarize the better techniques used in nodule diagnosis and indicate the existing future challenges in this field, such as improving the area under the receiver operating characteristic curve and accuracy, developing new deep learning-based diagnosis techniques, building efficient feature sets (fusing traditional features and deep features), developing high-quality labeled databases with malignant and benign nodules and promoting the cooperation between medical organizations and academic institutions.

Effective and Reliable Framework for Lung Nodules Detection from CT Scan Images

Lung cancer is considered more serious among other prevailing cancer types. One of the reasons for it is that it is usually not diagnosed until it has spread and by that time it becomes very difficult to treat. Early detection of lung cancer can significantly increase the chances of survival of a cancer patient. An effective nodule detection system can play a key role in early detection of lung cancer thus increasing the chances of successful treatment. In this research work, we have proposed a novel classification framework for nodule classification. The framework consists of multiple phases that include image contrast enhancement, segmentation, optimal feature extraction, followed by employment of these features for training and testing of Support Vector Machine. We have empirically tested the efficacy of our technique by utilizing the well-known Lung Image Consortium Database (LIDC) dataset. The empirical results suggest that the technique is highly effective for reducing the false positive rates. We were able to receive an impressive sensitivity rate of 97.45%.

Detection of pulmonary ground-glass opacity based on deep learning computer artificial intelligence

Background

A deep learning computer artificial intelligence system is helpful for early identification of ground glass opacities (GGOs).

Methods

Images from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) database were used in AlexNet and GoogLeNet to detect pulmonary nodules, and 221 GGO images provided by Xinhua Hospital were used in ResNet50 for detecting GGOs. We used computed tomography image radial reorganization to create the input image of the three-dimensional features, and used the extracted features for deep learning, network training, testing, and analysis.

Results

In the final evaluation results, we found that the accuracy of identification of lung nodule could reach 88.0%, with an F-score of 0.891. In terms of performance and accuracy, our method was better than the existing solutions. The GGO nodule classification achieved the best F-score of 0.87805. We propose a preprocessing method of red, green, and blue (RGB) superposition in the region of interest to effectively increase the differentiation between nodules and normal tissues, and that is the innovation of our research.

Conclusions

The method of deep learning proposed in this study is more sensitive than other systems in recent years, and the average false positive is lower than that of others.

CT screening for lung cancer: comparison of three baseline screening protocols

PURPOSE

Clinical management decisions arising from the baseline round for lung cancer screening are the most challenging, as findings have accumulated over a lifetime and may be of no clinical concern. To minimize unnecessary harms and costs of workup prior to the first, annual repeat screening, workup should be limited to participants with the highest suspicion of lung cancer while still aiming to identify small, early lung cancers.

METHODS

We compared recommendations for immediate, delayed (by 3 or 6 months) workup to assess growth at a malignant rate, and the resulting overall and potential biopsies of three baseline screening protocols: I-ELCAP, the two scenarios of ACR-LungRADS, and the European Consortium. For each protocol, the efficiency ratio (ER) of each recommendation was calculated by dividing the number of participants recommended for that workup by the number of resulting lung cancer diagnoses. The ER for potential biopsies was calculated, assuming that biopsies were performed on all participants recommended for immediate workup as well as those diagnosed with lung cancer after delayed workup.

RESULTS

For I-ELCAP, ACR-LungRADS Scenario 1, ACR-LungRADS Scenario 2, and the European consortium, the overall ER was 13.9, 18.3, 18.3, and 31.9, respectively, and for potential biopsies, it was 2.2, 8.1, 3.2, and 4.4, respectively. ER for immediate workup was 2.9, 8.6, 3.9, and 5.6, respectively, and for delayed workup was 36.1, 160.3, 57.8, and 111.9, respectively.

CONCLUSIONS

I-ELCAP recommendations had the lowest ER values for overall, immediate, and delayed workup, and for potential biopsies.

KEY POINTS

• Small differences in protocol thresholds can lead to many unnecessary diagnostic workups. • I-ELCAP recommendations were the most efficient for immediate and overall workup, and potential biopsies. • Definition of a "positive result" and recommendations for further workup in the baseline round needs to be continually reevaluated and updated.

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

Automatic lung nodule detection has great significance for treating lung cancer and increasing patient survival. This work summarizes a critical review of recent techniques for automatic lung nodule detection in computed tomography images. This review indicates the current tendency and obtained progress as well as future challenges in this field. This research covered the databases including Web of Science, PubMed, and the Press, including IEEE Xplore and Science Direct, up to May 2018. Each part of the paper is summarized carefully in terms of the method and validation results for better comparison. Based on the results, some techniques show better performance for lung nodule detection. However, researchers should pay attention to the existing challenges, such as high sensitivity with a low false positive rate, large and different patient databases, developing or optimizing the detection technique of various types of lung nodules with different sizes, shapes, textures and locations, combining electronic medical records and picture archiving and communication systems, building efficient feature sets for better classification and promoting the cooperation and communication between academic institutions and medical organizations. We believe that automatic computer-aided detection systems will be developed with strong robustness, high efficiency and security assurance. This review will be helpful for professional researchers and radiologists to further learn about the latest techniques in computer-aided detection systems.

A Computer-Aided Pipeline for Automatic Lung Cancer Classification on Computed Tomography Scans

Lung cancer is one of the most common cancer types. For the survival of the patient, early detection of lung cancer with the best treatment method is crucial. In this study, we propose a novel computer-aided pipeline on computed tomography (CT) scans for early diagnosis of lung cancer thanks to the classification of benign and malignant nodules. The proposed pipeline is composed of four stages. In preprocessing steps, CT images are enhanced, and lung volumes are extracted from the image with the help of a novel method called lung volume extraction method (LUVEM). The significance of the proposed pipeline is using LUVEM for extracting lung region. In nodule detection stage, candidate nodules are determined according to the circular Hough transform- (CHT-) based method. Then, lung nodules are segmented with self-organizing maps (SOM). In feature computation stage, intensity, shape, texture, energy, and combined features are used for feature extraction, and principal component analysis (PCA) is used for feature reduction step. In the final stage, probabilistic neural network (PNN) classifies benign and malign nodules. According to the experiments performed on our dataset, the proposed pipeline system can classify benign and malign nodules with 95.91% accuracy, 97.42% sensitivity, and 94.24% specificity. Even in cases of small-sized nodules (3-10 mm), the proposed system can determine the nodule type with 94.68% accuracy.

Opportunities and challenges to utilization of quantitative imaging: Report of the AAPM practical big data workshop

BACKGROUND

This article is a summary of the quantitative imaging subgroup of the 2017 AAPM Practical Big Data Workshop (PBDW-2017) on progress and challenges in big data applied to cancer treatment and research supplemented by a draft white paper following an American Association of Physicists in Medicine FOREM meeting on Imaging Genomics in 2014.

AIMS

The goal of PBDW-2017 was to close the gap between theoretical vision and practical experience with encountering and solving challenges in curating and analyzing data.

CONCLUSIONS

Recommendations based on the meetings are summarized.

Development of a pulmonary imaging biomarker pipeline for phenotyping of chronic lung disease

We designed and generated pulmonary imaging biomarker pipelines to facilitate high-throughput research and point-of-care use in patients with chronic lung disease. Image processing modules and algorithm pipelines were embedded within a graphical user interface (based on the .NET framework) for pulmonary magnetic resonance imaging (MRI) and x-ray computed-tomography (CT) datasets. The software pipelines were generated using C++ and included: (1) inhaled He3/Xe129 MRI ventilation and apparent diffusion coefficients, (2) CT-MRI coregistration for lobar and segmental ventilation and perfusion measurements, (3) ultrashort echo-time H1 MRI proton density measurements, (4) free-breathing Fourier-decomposition H1 MRI ventilation/perfusion and free-breathing H1 MRI specific ventilation, (5) multivolume CT and MRI parametric response maps, and (6) MRI and CT texture analysis and radiomics. The image analysis framework was implemented on a desktop workstation/tablet to generate biomarkers of regional lung structure and function related to ventilation, perfusion, lung tissue texture, and integrity as well as multiparametric measures of gas trapping and airspace enlargement. All biomarkers were generated within 10 min with measurement reproducibility consistent with clinical and research requirements. The resultant pulmonary imaging biomarker pipeline provides real-time and automated lung imaging measurements for point-of-care and high-throughput research.

Discovery radiomics via evolutionary deep radiomic sequencer discovery for pathologically proven lung cancer detection

While lung cancer is the second most diagnosed form of cancer in men and women, a sufficiently early diagnosis can be pivotal in patient survival rates. Imaging-based, or radiomics-driven, detection methods have been developed to aid diagnosticians, but largely rely on hand-crafted features that may not fully encapsulate the differences between cancerous and healthy tissue. Recently, the concept of discovery radiomics was introduced, where custom abstract features are discovered from readily available imaging data. We propose an evolutionary deep radiomic sequencer discovery approach based on evolutionary deep intelligence. Motivated by patient privacy concerns and the idea of operational artificial intelligence, the evolutionary deep radiomic sequencer discovery approach organically evolves increasingly more efficient deep radiomic sequencers that produce significantly more compact yet similarly descriptive radiomic sequences over multiple generations. As a result, this framework improves operational efficiency and enables diagnosis to be run locally at the radiologist's computer while maintaining detection accuracy. We evaluated the evolved deep radiomic sequencer (EDRS) discovered via the proposed evolutionary deep radiomic sequencer discovery framework against state-of-the-art radiomics-driven and discovery radiomics methods using clinical lung CT data with pathologically proven diagnostic data from the LIDC-IDRI dataset. The EDRS shows improved sensitivity (93.42%), specificity (82.39%), and diagnostic accuracy (88.78%) relative to previous radiomics approaches.

Feature fusion for lung nodule classification

PURPOSE

This article examines feature-based nodule description for the purpose of nodule classification in chest computed tomography scanning.

METHODS

Three features based on (i) Gabor filter, (ii) multi-resolution local binary pattern (LBP) texture features and (iii) signed distance fused with LBP which generates a combinational shape and texture feature are utilized to provide feature descriptors of malignant and benign nodules and non-nodule regions of interest. Support vector machines (SVMs) and k-nearest neighbor (kNN) classifiers in serial and two-tier cascade frameworks are optimized and analyzed for optimal classification results of nodules.

RESULTS

A total of 1191 nodule and non-nodule samples from the Lung Image Data Consortium database is used for analysis. Classification using SVM and kNN classifiers is examined. The classification results from the two-tier cascade SVM using Gabor features showed overall better results for identifying non-nodules, malignant and benign nodules with average area under the receiver operating characteristics (AUC-ROC) curves of 0.99 and average f1-score of 0.975 over the two tiers.

CONCLUSION

In the results, higher overall AUCs and f1-scores were obtained for the non-nodules cases using any of the three features, showing the greatest distinguishability over nodules (benign/malignant). SVM and kNN classifiers were used for benign, malignant and non-nodule classification, where Gabor proved to be the most effective of the features for classification. The cascaded framework showed the greatest distinguishability between benign and malignant nodules.

Automatic Scoring of Multiple Semantic Attributes With Multi-Task Feature Leverage: A Study on Pulmonary Nodules in CT Images

The gap between the computational and semantic features is the one of major factors that bottlenecks the computer-aided diagnosis (CAD) performance from clinical usage. To bridge this gap, we exploit three multi-task learning (MTL) schemes to leverage heterogeneous computational features derived from deep learning models of stacked denoising autoencoder (SDAE) and convolutional neural network (CNN), as well as hand-crafted Haar-like and HoG features, for the description of 9 semantic features for lung nodules in CT images. We regard that there may exist relations among the semantic features of "spiculation", "texture", "margin", etc., that can be explored with the MTL. The Lung Image Database Consortium (LIDC) data is adopted in this study for the rich annotation resources. The LIDC nodules were quantitatively scored w.r.t. 9 semantic features from 12 radiologists of several institutes in U.S.A. By treating each semantic feature as an individual task, the MTL schemes select and map the heterogeneous computational features toward the radiologists' ratings with cross validation evaluation schemes on the randomly selected 2400 nodules from the LIDC dataset. The experimental results suggest that the predicted semantic scores from the three MTL schemes are closer to the radiologists' ratings than the scores from single-task LASSO and elastic net regression methods. The proposed semantic attribute scoring scheme may provide richer quantitative assessments of nodules for better support of diagnostic decision and management. Meanwhile, the capability of the automatic association of medical image contents with the clinical semantic terms by our method may also assist the development of medical search engine.

Fuzzy Clustering Applied to ROI Detection in Helical Thoracic CT Scans with a New Proposal and Variants

The detection of pulmonary nodules is one of the most studied problems in the field of medical image analysis due to the great difficulty in the early detection of such nodules and their social impact. The traditional approach involves the development of a multistage CAD system capable of informing the radiologist of the presence or absence of nodules. One stage in such systems is the detection of ROI (regions of interest) that may be nodules in order to reduce the space of the problem. This paper evaluates fuzzy clustering algorithms that employ different classification strategies to achieve this goal. After characterising these algorithms, the authors propose a new algorithm and different variations to improve the results obtained initially. Finally it is shown as the most recent developments in fuzzy clustering are able to detect regions that may be nodules in CT studies. The algorithms were evaluated using helical thoracic CT scans obtained from the database of the LIDC (Lung Image Database Consortium).

Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans

This paper performs a comprehensive study on the deep-learning-based computer-aided diagnosis (CADx) for the differential diagnosis of benign and malignant nodules/lesions by avoiding the potential errors caused by inaccurate image processing results (e.g., boundary segmentation), as well as the classification bias resulting from a less robust feature set, as involved in most conventional CADx algorithms. Specifically, the stacked denoising auto-encoder (SDAE) is exploited on the two CADx applications for the differentiation of breast ultrasound lesions and lung CT nodules. The SDAE architecture is well equipped with the automatic feature exploration mechanism and noise tolerance advantage, and hence may be suitable to deal with the intrinsically noisy property of medical image data from various imaging modalities. To show the outperformance of SDAE-based CADx over the conventional scheme, two latest conventional CADx algorithms are implemented for comparison. 10 times of 10-fold cross-validations are conducted to illustrate the efficacy of the SDAE-based CADx algorithm. The experimental results show the significant performance boost by the SDAE-based CADx algorithm over the two conventional methods, suggesting that deep learning techniques can potentially change the design paradigm of the CADx systems without the need of explicit design and selection of problem-oriented features.

The importance of the regimen of screening in maximizing the benefit and minimizing the harms

BACKGROUND

In CT screening for lung cancer, the regimen of screening is critical in diagnosing lung cancer early while limiting unnecessary tests and invasive procedures. The International Early Lung Cancer Action Program (I-ELCAP) has developed a regimen based on evidence collected in the I-ELCAP cohort of more than 70,000 participants.

METHODS

Important in the development of the regimen is the recognition of the profound difference between the first, baseline round of screening and all subsequent rounds of repeat screening. For each person undergoing screening, the baseline round happens only once while repeat rounds will be performed annually for many years. This difference needs to be clearly recognized as it is these annual rounds which allow for identification of small, early, yet aggressive, lung cancers which have high cure rates despite their aggressiveness. The importance of nodule consistency and size are key factors in the regimen. The regimen needs to be continuously updated by incorporating advances in technology and knowledge.

RESULTS

The use of the I-ELCAP regimen reduces the workup of participants in the screening program to less than 10% in the baseline round and less than 6% in the annual repeat rounds. By use of this regimen, estimated cure rate of lung cancers diagnosed under screening is 80% or higher in both baseline and annual repeat rounds.

CONCLUSIONS

The I-ELCAP collaboration provides a new paradigm that answers the 2002 NCI call for multiple approaches to address relevant questions about screening and the Institute of Medicine (IOM) Roundtable on Evidence-based Medicine from the National Academy of Science's call for a "new clinical research paradigm that takes better advantage of data generated in the course of healthcare delivery would speed and improve the development of evidence for real-world decision making".

Computer-aided detection of pulmonary nodules: a comparative study using the public LIDC/IDRI database

Objectives

To benchmark the performance of state-of-the-art computer-aided detection (CAD) of pulmonary nodules using the largest publicly available annotated CT database (LIDC/IDRI), and to show that CAD finds lesions not identified by the LIDC’s four-fold double reading process.

Methods

The LIDC/IDRI database contains 888 thoracic CT scans with a section thickness of 2.5 mm or lower. We report performance of two commercial and one academic CAD system. The influence of presence of contrast, section thickness, and reconstruction kernel on CAD performance was assessed. Four radiologists independently analyzed the false positive CAD marks of the best CAD system.

Results

The updated commercial CAD system showed the best performance with a sensitivity of 82 % at an average of 3.1 false positive detections per scan. Forty-five false positive CAD marks were scored as nodules by all four radiologists in our study.

Conclusions

On the largest publicly available reference database for lung nodule detection in chest CT, the updated commercial CAD system locates the vast majority of pulmonary nodules at a low false positive rate. Potential for CAD is substantiated by the fact that it identifies pulmonary nodules that were not marked during the extensive four-fold LIDC annotation process.

Key Points

• CAD systems should be validated on public, heterogeneous databases.

• The LIDC/IDRI database is an excellent database for benchmarking nodule CAD.

• CAD can identify the majority of pulmonary nodules at a low false positive rate.

• CAD can identify nodules missed by an extensive two-stage annotation process.

Semantic characteristics prediction of pulmonary nodule using Artificial Neural Networks

Since it is difficult to choose which computer calculated features are effective to predict the malignancy of pulmonary nodules, in this study, we add a semantic-level of Artificial Neural Networks (ANNs) structure to improve intuition of features selection. The works of this study include two: 1) seeking the relationships between computer-calculated features and medical semantic concepts which could be understood by human; 2) providing an objective assessment method to predict the malignancy from semantic characteristics. We used 60 thoracic CT scans collected from the Lung Image Database Consortium (LIDC) database, in which the suspicious lesions had been delineated and annotated by 4 radiologists independently. Corresponding to the two works of this study, correlation analysis experiment and agreement experiment were performed separately.

INTEGRATION OF MULTIPLE CLASSIFIERS FOR COMPUTERIZED DETECTION OF LUNG NODULES IN CT

The purpose of this study was to investigate the usefulness of various classifier combination methods for improving the performance of a computer-aided diagnosis (CAD) system for pulmonary nodule detection in computed tomography (CT). We employed 85 CT scans with 110 nodules in the publicly available Lung Image Database Consortium (LIDC) dataset. We first applied our CAD scheme trained previously to the LIDC cases for identifying initial nodule candidates, and extracting 18 features for each nodule candidate. We used eight individual classifiers for false positives (FPs) reduction, including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), Naïve Bayes, simple logistic, artificial neural network (ANN) and support vector machines (SVMs) with three different kernels. Five classifier combination methods were then employed to integrate the outputs of the eight individual classifiers for improving detection performance. The five combination methods included two supervised (a likelihood ratio (LR) method and a probability method based on the output scores of the eight individual classifiers) and three unsupervised ones (the sum, the product and the majority voting of the output scores from the eight individual classifiers). Leave-one-case-out approach was employed to train and test individual classifiers and supervised combination methods. At a sensitivity of 80%, the numbers of FPs per CT scan for the eight individual classifiers were 6.1 for LDA, 19.9 for QDA, 10.8 for Naïve Bayes, 8.4 for simple logistic, 8.6 for ANN, 23.7 for SVM-dot, 17.0 for SVM-poly, and 23.4 for SVM-anova; the numbers of FPs per CT scan for the five combination methods were 3.3 for the majority voting method, 5.0 for the sum, 4.6 for the product, 65.7 for the LR and 3.9 for the probability method. Compared to the best individual classifier, the majority voting method reduced 45% of FPs at 80% sensitivity. The performance of our CAD can be improved by combining multiple classifiers. The majority voting method achieved higher performance levels than other combination methods and all individual classifiers.