Which is a real valuable screening tool for lung cancer and measure thoracic diseases, chest radiography or low-dose computed tomography?: A review on the current status of Japan and other countries.

Chest radiography (CR) has been used as a screening tool for lung cancer and the use of low-dose computed tomography (LDCT) is not recommended in Japan. We need to reconsider whether CR really contributes to the early detection of lung cancer. In addition, we have not well discussed about other major thoracic disease detection by CR and LDCT compared with lung cancer despite of its high frequency. We review the usefulness of CR and LDCT as veridical screening tools for lung cancer and other thoracic diseases. In the case of lung cancer, many studies showed that LDCT has capability of early detection and improving outcomes compared with CR. Recent large randomized trial also supports former results. In the case of chronic obstructive pulmonary disease (COPD), LDCT contributes to early detection and leads to the implementation of smoking cessation treatments. In the case of pulmonary infections, LDCT can reveal tiny inflammatory changes that are not observed on CR, though many of these cases improve spontaneously. Therefore, LDCT screening for pulmonary infections may be less useful. CR screening is more suitable for the detection of pulmonary infections. In the case of cardiovascular disease (CVD), CR may be a better screening tool for detecting cardiomegaly, whereas LDCT may be a more useful tool for detecting vascular changes. Therefore, the current status of thoracic disease screening is that LDCT may be a better screening tool for detecting lung cancer, COPD, and vascular changes. CR may be a suitable screening tool for pulmonary infections and cardiomegaly.

Automated thorax disease diagnosis using multi-branch residual attention network.

Chest X-ray (CXR) is an extensively utilized radiological modality for supporting the diagnosis of chest diseases. However, existing research approaches suffer from limitations in effectively integrating multi-scale CXR image features and are also hindered by imbalanced datasets. Therefore, there is a pressing need for further advancement in computer-aided diagnosis (CAD) of thoracic diseases. To tackle these challenges, we propose a multi-branch residual attention network (MBRANet) for thoracic disease diagnosis. MBRANet comprises three components. Firstly, to address the issue of inadequate extraction of spatial and positional information by the convolutional layer, a novel residual structure incorporating a coordinate attention (CA) module is proposed to extract features at multiple scales. Next, based on the concept of a Feature Pyramid Network (FPN), we perform multi-scale feature fusion in the following manner. Thirdly, we propose a novel Multi-Branch Feature Classifier (MFC) approach, which leverages the class-specific residual attention (CSRA) module for classification instead of relying solely on the fully connected layer. In addition, the designed BCEWithLabelSmoothing loss function improves the generalization ability and mitigates the problem of class imbalance by introducing a smoothing factor. We evaluated MBRANet on the ChestX-Ray14, CheXpert, MIMIC-CXR, and IU X-Ray datasets and achieved average AUCs of 0.841, 0.895, 0.805, and 0.745, respectively. Our method outperformed state-of-the-art baselines on these benchmark datasets.

Ultrasound in the Study of Thoracic Diseases: Innovative Aspects

Thoracic ultrasound (TU) has rapidly gained popularity over the past 10 years. This is in part because ultrasound equipment is available in many settings, more training programmes are educating trainees in this technique, and ultrasound can be done rapidly without exposure to radiation.The aim of this review is to present the most interesting and innovative aspects of the use of TU in the study of thoracic diseases.In pleural diseases, TU has been a real revolution. It helps to differentiate between different types of pleural effusions, guides the performance of pleural biopsies when necessary and is more cost-effective under these conditions, and assists in the decision to remove thoracic drainage after talc pleurodesis.With the advent of COVID19, the use of TU has increased for the study of lung involvement. Nowadays it helps in the diagnosis of pneumonias, tumours and interstitial diseases, and its use is becoming more and more widespread in the Pneumology ward.In recent years, TU guided biopsies have been shown to be highly cost-effective, with other advantages such as the absence of radiation and the possibility of being performed at bedside. The use of contrast in ultrasound to increase the cost-effectiveness of these biopsies is very promising.In the study of the mediastinum and peripheral pulmonary nodules, the introduction of echobronchoscopy has brought about a radical change. It is a fully established technique in the study of lung cancer patients. The introduction of elastography may help to further improve its cost-effectiveness.In critically-ill patients, diaphragmatic ultrasound helps in the assessment of withdrawal of mechanical ventilation, and is now an indispensable tool in the management of these patients. (AU)

Robust Stochastic Neural Ensemble Learning With Noisy Labels for Thoracic Disease Classification.

Chest radiography is the most common radiology examination for thoracic disease diagnosis, such as pneumonia. A tremendous number of chest X-rays prompt data-driven deep learning models in constructing computer-aided diagnosis systems for thoracic diseases. However, in realistic radiology practice, a deep learning-based model often suffers from performance degradation when trained on data with noisy labels possibly caused by different types of annotation biases. To this end, we present a novel stochastic neural ensemble learning (SNEL) framework for robust thoracic disease diagnosis using chest X-rays. The core idea of our method is to learn from noisy labels by constructing model ensembles and designing noise-robust loss functions. Specifically, we propose a fast neural ensemble method that collects parameters simultaneously across model instances and along optimization trajectories. Moreover, we propose a loss function that both optimizes a robust measure and characterizes a diversity measure of ensembles. We evaluated our proposed SNEL method on three publicly available hospital-scale chest X-ray datasets. The experimental results indicate that our method outperforms competing methods and demonstrate the effectiveness and robustness of our method in learning from noisy labels. Our code is available at https://github.com/hywang01/SNEL.

Spectrum of Thoracic Imaging Findings in the Setting of Substance Abuse.

ABSTRACT: Substance abuse continues to be prevalent nationwide and can lead to a myriad of chest pathologies. Imaging findings are vast and can include nodules, masses, ground-glass opacities, airspace disease, and cysts. Radiologists with awareness of these manifestations can assist in early identification of disease in situations where information is unable to be obtained from the patient. This review focuses on thoracic imaging findings associated with various forms of substance abuse, which are organized by portal of entry into the thorax: inhalation, ingestion, and injection.

Thoracic Applications of Spectral CT Scan.

TOPIC IMPORTANCE: Thoracic imaging with CT scan has become an essential component in the evaluation of respiratory and thoracic diseases. Providers have historically used conventional single-energy CT; however, prevalence of dual-energy CT (DECT) is increasing, and as such, it is important for thoracic physicians to recognize the utility and limitations of this technology. REVIEW FINDINGS: The technical aspects of DECT are presented, and practical approaches to using DECT are provided. Imaging at multiple energy spectra allows for postprocessing of the data and the possibility of creating multiple distinct image reconstructions based on the clinical question being asked. The data regarding utility of DECT in pulmonary vascular disorders, ventilatory defects, and thoracic oncology are presented. A pictorial essay is provided to give examples of the strengths associated with DECT. SUMMARY: DECT has been most heavily studied in chronic thromboembolic pulmonary hypertension; however, it is increasingly being used across a wide spectrum of thoracic diseases. DECT combines morphologic and functional assessments in a single imaging acquisition, providing clinicians with a powerful diagnostic tool. Its role in the evaluation and treatment of thoracic diseases will likely continue to expand in the coming years as clinicians become more experienced with the technology.

Ultrasound in the Study of Thoracic Diseases: Innovative Aspects.

Thoracic ultrasound (TU) has rapidly gained popularity over the past 10 years. This is in part because ultrasound equipment is available in many settings, more training programmes are educating trainees in this technique, and ultrasound can be done rapidly without exposure to radiation. The aim of this review is to present the most interesting and innovative aspects of the use of TU in the study of thoracic diseases. In pleural diseases, TU has been a real revolution. It helps to differentiate between different types of pleural effusions, guides the performance of pleural biopsies when necessary and is more cost-effective under these conditions, and assists in the decision to remove thoracic drainage after talc pleurodesis. With the advent of COVID19, the use of TU has increased for the study of lung involvement. Nowadays it helps in the diagnosis of pneumonias, tumours and interstitial diseases, and its use is becoming more and more widespread in the Pneumology ward. In recent years, TU guided biopsies have been shown to be highly cost-effective, with other advantages such as the absence of radiation and the possibility of being performed at bedside. The use of contrast in ultrasound to increase the cost-effectiveness of these biopsies is very promising. In the study of the mediastinum and peripheral pulmonary nodules, the introduction of echobronchoscopy has brought about a radical change. It is a fully established technique in the study of lung cancer patients. The introduction of elastography may help to further improve its cost-effectiveness. In critically-ill patients, diaphragmatic ultrasound helps in the assessment of withdrawal of mechanical ventilation, and is now an indispensable tool in the management of these patients. In neuromuscular patients, ultrasound is a good predictor of impaired lung function. Currently, in Neuromuscular Disease Units, TU is an indispensable tool. Ultrasound study of the intercostal musculature is also effective in the study of respiratory function, and is widely used in Respiratory Rehabilitation. In Intermediate Care Units, thoracic ultrasound is indispensable for patient management. In these units there are ultrasound protocols for the management of patients with acute dyspnoea that have proven to be very effective.

CheXNet and feature pyramid network: a fusion deep learning architecture for multilabel chest X-Ray clinical diagnoses classification.

The existing multilabel X-Ray image learning tasks generally contain much information on pathology co-occurrence and interdependency, which is very important for clinical diagnosis. However, the challenging part of this subject is to accurately diagnose multiple diseases that occurred in a single X-Ray image since multiple levels of features are generated in the images, and create different features as in single label detection. Various works were developed to address this challenge with proposed deep learning architectures to improve classification performance and enrich diagnosis results with multi-probability disease detection. The objective is to create an accurate result and a faster inference system to support a quick diagnosis in the medical system. To contribute to this state-of-the-art, we designed a fusion architecture, CheXNet and Feature Pyramid Network (FPN), to classify and discriminate multiple thoracic diseases from chest X-Rays. This concept enables the model to extract while creating a pyramid of feature maps with different spatial resolutions that capture low-level and high-level semantic information to encounter multiple features. The model's effectiveness is evaluated using the NIH ChestXray14 dataset, with the Area Under Curve (AUC) and accuracy metrics used to compare the results against other cutting-edge approaches. The overall results demonstrate that our method outperforms other approaches and has become promising for multilabel disease classification in chest X-Rays, with potential applications in clinical practice. The result demonstrated that we achieved an average AUC of 0.846 and an accuracy of 0.914. Further, our proposed architecture diagnoses images in 0.013 s, faster than the latest approaches.

Canadian Association of Radiologists Thoracic Imaging Referral Guideline.

The Canadian Association of Radiologists (CAR) Thoracic Expert Panel consists of radiologists, respirologists, emergency and family physicians, a patient advisor, and an epidemiologist/guideline methodologist. After developing a list of 24 clinical/diagnostic scenarios, a rapid scoping review was undertaken to identify systematically produced referral guidelines that provide recommendations for one or more of these clinical/diagnostic scenarios. Recommendations from 30 guidelines and contextualization criteria in the Grading of Recommendations, Assessment, Development, and Evaluations (GRADE) for guidelines framework were used to develop 48 recommendation statements across the 24 scenarios. This guideline presents the methods of development and the referral recommendations for screening/asymptomatic individuals, non-specific chest pain, hospital admission for non-thoracic conditions, long-term care admission, routine pre-operative imaging, post-interventional chest procedure, upper respiratory tract infection, acute exacerbation of asthma, acute exacerbation of chronic obstructive pulmonary disease, suspect pneumonia, pneumonia follow-up, immunosuppressed patient with respiratory symptoms/febrile neutropenia, chronic cough, suspected pneumothorax (non-traumatic), clinically suspected pleural effusion, hemoptysis, chronic dyspnea of non-cardiovascular origin, suspected interstitial lung disease, incidental lung nodule, suspected mediastinal lesion, suspected mediastinal lymphadenopathy, and elevated diaphragm on chest radiograph.

MRChexNet: Multi-modal bridge and relational learning for thoracic disease recognition in chest X-rays.

While diagnosing multiple lesion regions in chest X-ray (CXR) images, radiologists usually apply pathological relationships in medicine before making decisions. Therefore, a comprehensive analysis of labeling relationships in different data modes is essential to improve the recognition performance of the model. However, most automated CXR diagnostic methods that consider pathological relationships treat different data modalities as independent learning objects, ignoring the alignment of pathological relationships among different data modalities. In addition, some methods that use undirected graphs to model pathological relationships ignore the directed information, making it difficult to model all pathological relationships accurately. In this paper, we propose a novel multi-label CXR classification model called MRChexNet that consists of three modules: a representation learning module (RLM), a multi-modal bridge module (MBM) and a pathology graph learning module (PGL). RLM captures specific pathological features at the image level. MBM performs cross-modal alignment of pathology relationships in different data modalities. PGL models directed relationships between disease occurrences as directed graphs. Finally, the designed graph learning block in PGL performs the integrated learning of pathology relationships in different data modalities. We evaluated MRChexNet on two large-scale CXR datasets (ChestX-Ray14 and CheXpert) and achieved state-of-the-art performance. The mean area under the curve (AUC) scores for the 14 pathologies were 0.8503 (ChestX-Ray14) and 0.8649 (CheXpert). MRChexNet effectively aligns pathology relationships in different modalities and learns more detailed correlations between pathologies. It demonstrates high accuracy and generalization compared to competing approaches. MRChexNet can contribute to thoracic disease recognition in CXR.

Deep reinforcement learning framework for thoracic diseases classification via prior knowledge guidance.

The chest X-ray is commonly employed in the diagnosis of thoracic diseases. Over the years, numerous approaches have been proposed to address the issue of automatic diagnosis based on chest X-rays. However, the limited availability of labeled data for related diseases remains a significant challenge in achieving accurate diagnoses. This paper focuses on the diagnostic problem of thorax diseases and presents a novel deep reinforcement learning framework. This framework incorporates prior knowledge to guide the learning process of diagnostic agents, and the model parameters can be continually updated as more data becomes available, mimicking a person's learning process. Specifically, our approach offers two key contributions: (1) prior knowledge can be acquired from pre-trained models using old data or similar data from other domains, effectively reducing the dependence on target domain data; and (2) the reinforcement learning framework enables the diagnostic agent to be as exploratory as a human, leading to improved diagnostic accuracy through continuous exploration. Moreover, this method effectively addresses the challenge of learning models with limited data, enhancing the model's generalization capability. We evaluate the performance of our approach using the well-known NIH ChestX-ray 14 and CheXpert datasets, and achieve competitive results. More importantly, in clinical application, we make considerable progress. The source code for our approach can be accessed at the following URL: https://github.com/NeaseZ/MARL.

PediCXR: An open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children.

Computer-aided diagnosis systems in adult chest radiography (CXR) have recently achieved great success thanks to the availability of large-scale, annotated datasets and the advent of high-performance supervised learning algorithms. However, the development of diagnostic models for detecting and diagnosing pediatric diseases in CXR scans is undertaken due to the lack of high-quality physician-annotated datasets. To overcome this challenge, we introduce and release PediCXR, a new pediatric CXR dataset of 9,125 studies retrospectively collected from a major pediatric hospital in Vietnam between 2020 and 2021. Each scan was manually annotated by a pediatric radiologist with more than ten years of experience. The dataset was labeled for the presence of 36 critical findings and 15 diseases. In particular, each abnormal finding was identified via a rectangle bounding box on the image. To the best of our knowledge, this is the first and largest pediatric CXR dataset containing lesion-level annotations and image-level labels for the detection of multiple findings and diseases. For algorithm development, the dataset was divided into a training set of 7,728 and a test set of 1,397. To encourage new advances in pediatric CXR interpretation using data-driven approaches, we provide a detailed description of the PediCXR data sample and make the dataset publicly available on https://physionet.org/content/vindr-pcxr/1.0.0/ .

Lipoma intratorácico. Manejo expectante. A propósito de un caso / Intrathoracic lipoma. Expectant management. About a case

El lipoma intratorácico es un tumor benigno poco frecuente, que pasa inadvertido hasta que es bastante voluminoso y se detectan en la radiografía de tórax por otro motivo. Suelen ser asintomáticos, aunque en casos de gran tamaño pueden producir síntomas como tos, disnea o síntomas compresivos. En la radiografía de tórax aparece como una masa de bordes bien definidos, aunque suele ser necesaria la realización de una tomografía computerizada para determinar mejor la lesión. Actualmente, no existe una estrategia homogénea para el manejo de los pacientes con lipomas intratorácicos asintomáticos, por lo que una opción es el manejo expectante. (AU)

Intrathoracic lipoma is a rare benign tumor, which goes unnoticed until they are quite bulky and detected on chest X-ray for another reason. They are usually asymptomatic, although in large cases they can produce symptoms such as cough, dyspnea, or compressive symptoms. On chest X-ray it appears as a mass with well-defined borders, although a computerized tomography is usually necessary to better determine the lesion. Currently, there is no homogeneous strategy for the management of patients with asymptomatic intrathoracic lipomas. Therefore, expectant management can be chosen. (AU)

PCAN: Pixel-wise classification and attention network for thoracic disease classification and weakly supervised localization.

Automatic chest X-ray (CXR) disease classification has drawn increasing public attention as CXR is widely used in thoracic disease diagnosis. Existing classification networks typically employ a global average pooling layer to produce the final feature for the subsequent classifier. This limits the classification performance owing to the characteristics of lesions in CXR images, including small relative sizes, varied absolute sizes, and different occurrence locations. In this study, we propose a pixel-wise classification and attention network (PCAN) to simultaneously perform disease classification and weakly supervised localization, which provides interpretability for disease classification. The PCAN comprises a backbone network for extracting mid-level features, a pixel-wise classification branch (pc-branch) for generating pixel-wise diagnoses, and a pixel-wise attention branch (pa-branch) for producing pixel-wise weights. The pc-branch is capable of explicitly detecting small lesions, and the pa-branch is capable of adaptively focusing on different regions when classifying different thoracic diseases. Then, the pixel-wise diagnoses are multiplied with the pixel-wise weights to obtain the disease localization map, which provides the sizes and locations of lesions in a manner of weakly supervised learning. The final image-wise diagnosis is obtained by summing up the disease localization map at the spatial dimension. Comprehensive experiments conducted on the ChestX-ray14 and CheXpert datasets demonstrate the effectiveness of the proposed PCAN, which has great potential for thoracic disease diagnosis and treatment. The source codes are available at https://github.com/fzfs/PCAN.

Evaluation of chest radiography and low-dose computed tomography as valuable screening tools for thoracic diseases.

BACKGROUND: Recent studies have shown that low-dose computed tomography (LDCT) is effective for the early detection of lung cancer. However, the utility of chest radiography (CR) and LDCT for other thoracic diseases has not been as well investigated as it has been for lung cancer. This study aimed to clarify the usefulness of the veridical method in the screening of various thoracic diseases. METHODS: Among individuals who had received general health checkups over a 10-year period, those who had undergone both CR and LDCT were selected for analysis. The present study included 4317 individuals (3146 men and 1171 women). We investigated cases in which abnormal opacity was detected on CR and/or LDCT. RESULTS: A total of 47 and 124 cases had abnormal opacity on CR and LDCT, respectively. Among these, 41 cases in which the abnormal opacity was identified by both methods contained 20 treated cases. Six cases had abnormalities only on CR, and none of the cases required further treatment. Eighty-three cases were identified using LDCT alone. Of these, many cases, especially those over the age of 50 years, were diagnosed with thoracic tumors and chronic obstructive pulmonary disease, which required early treatment. In contrast, many cases of pulmonary infections have improved spontaneously, without any treatment. CONCLUSION: These results revealed that LDCT allowed early detection of thoracic tumors and chronic obstructive pulmonary disease, especially in individuals over the age of 50 years. CR is still a useful imaging modality for other thoracic diseases, especially in individuals under the age of 49 years.

Automatic Localization and Identification of Thoracic Diseases from Chest X-rays with Deep Learning.

BACKGROUND: There are numerous difficulties in using deep learning to automatically locate and identify diseases in chest X-rays (CXR). The most prevailing two are the lack of labeled data of disease locations and poor model transferability between different datasets. This study aims to tackle these problems. METHODS: We built a new form of bounding box dataset and developed a two-stage model for disease localization and identification of CXRs based on deep learning. The dataset marks anomalous regions in CXRs but not the corresponding diseases, different from all previous datasets. The advantages of this design are reduced labor of annotation and fewer possible errors associated with image labeling. The two-stage model combines the robustness of the region proposal network, feature pyramid network, and multi-instance learning techniques. We trained and validated our model with the new bounding box dataset and the CheXpert dataset. Then, we tested its classification and localization performance on an external dataset, which is the official split test set of ChestX-ray14. RESULTS: For classification result, the mean area under the receiver operating characteristic curve (AUC) metrics of our model on the CheXpert validation dataset was 0.912, which was 0.021, superior to the baseline model. The mean AUC of our model on an external testing set was 0.784, whereas the state-of-the-art model got 0.773. The localization results showed comparable performance to the stateof- the-art models. CONCLUSION: Our model exhibits a good transferability between datasets. The new bounding box dataset is proven to be useful and shows an alternative technique for compiling disease localization datasets.

State-of-the-art MR Imaging for Thoracic Diseases.

Since thoracic MR imaging was first used in a clinical setting, it has been suggested that MR imaging has limited clinical utility for thoracic diseases, especially lung diseases, in comparison with x-ray CT and positron emission tomography (PET)/CT. However, in many countries and states and for specific indications, MR imaging has recently become practicable. In addition, recently developed pulmonary MR imaging with ultra-short TE (UTE) and zero TE (ZTE) has enhanced the utility of MR imaging for thoracic diseases in routine clinical practice. Furthermore, MR imaging has been introduced as being capable of assessing pulmonary function. It should be borne in mind, however, that these applications have so far been academically and clinically used only for healthy volunteers, but not for patients with various pulmonary diseases in Japan or other countries. In 2020, the Fleischner Society published a new report, which provides consensus expert opinions regarding appropriate clinical indications of pulmonary MR imaging for not only oncologic but also pulmonary diseases. This review article presents a brief history of MR imaging for thoracic diseases regarding its technical aspects and major clinical indications in Japan 1) in terms of what is currently available, 2) promising but requiring further validation or evaluation, and 3) developments warranting research investigations in preclinical or patient studies. State-of-the-art MR imaging can non-invasively visualize lung structural and functional abnormalities without ionizing radiation and thus provide an alternative to CT. MR imaging is considered as a tool for providing unique information. Moreover, prospective, randomized, and multi-center trials should be conducted to directly compare MR imaging with conventional methods to determine whether the former has equal or superior clinical relevance. The results of these trials together with continued improvements are expected to update or modify recommendations for the use of MRI in near future.

Clinical Artificial Intelligence Applications in Radiology: Chest and Abdomen.

Organ segmentation, chest radiograph classification, and lung and liver nodule detections are some of the popular artificial intelligence (AI) tasks in chest and abdominal radiology due to the wide availability of public datasets. AI algorithms have achieved performance comparable to humans in less time for several organ segmentation tasks, and some lesion detection and classification tasks. This article introduces the current published articles of AI applied to chest and abdominal radiology, including organ segmentation, lesion detection, classification, and predicting prognosis.