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)

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.

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.

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.

An Approach for Thoracic Syndrome Classification with Convolutional Neural Networks.

There have been remarkable changes in our lives and the way we perceive the world with advances in computing technology. Healthcare sector is evolving with the intervention of the latest computer-driven technology and has made a remarkable change in the diagnosis and treatment of various diseases. Due to many governing factors including air pollution, there is a rapid rise in chest-related diseases and the number of such patients is rising at an alarming rate. In this research work, we have employed machine learning approach for the detecting various chest-related problems using convolutional neural networks (CNN) on an open dataset of chest X-rays. The method has an edge over the traditional approaches for image segmentation including thresholding, k-means clustering, and edge detection. The CNN cannot scan and process the whole image at an instant; it needs to recursively scan small pixel spots until it has scanned the whole image. Spatial transformation layers and VGG19 have been used for the purpose of feature extraction, and ReLU activation function has been employed due to its inherent low complexity and high computation efficiency; finally, stochastic gradient descent has been used as an optimizer. The main advantage of the current method is that it retains the essential features of the image for prediction along with incorporating a considerable dimensional reduction. The model delivered substantial improvement over existing research in terms of precision, f-score, and accuracy of prediction. This model if used precisely can be very effective for healthcare practitioners in determining the thoracic or pneumonic symptoms in the patient at an early stage thus guiding the practitioner to start the treatment immediately leading to fast improvement in the health status of the patient.

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.

Comparison of Radiation Dose and Image Quality Between Split-Filter Twin Beam Dual-Energy Images and Single-Energy Images in Single-Source Contrast-Enhanced Chest Computed Tomography.

OBJECTIVE: To compare image quality and radiation dose of split-filter TwinBeam dual-energy (SF-TBDE) with those of single-energy images (SECT) in the contrast-enhanced chest computed tomography (CT). METHODS: Two hundred patients who underwent SF-TBDE (n = 100) and SECT (n = 100) contrast-enhanced chest scanning were retrospectively analyzed. The contrast-to-noise ratio (CNR) and figure of merit (FOM)-CNR of 5 structures (lung, aorta, pulmonary artery, thyroid, and erector spinae) were calculated and subjectively evaluated by 2 independent radiologists. Radiation dose was compared using volume CT dose index and size-specific dose estimate. RESULTS: The CNR and FOM-CNR of lung and erector spinae in SF-TBDE were higher than those of SECT (P < 0.001). The differences in the subjective image quality between the 2 groups were not significant (P = 0.244). Volume CT dose index and size-specific dose estimate of SF-TBDE were lower than those of SECT (6.60 ± 1.56 vs 7.81 ± 3.02 mGy, P = 0.001; 9.25 ± 1.60 vs. 10.55 ± 3.54; P = 0.001). CONCLUSIONS: The SF-TBDE CT can provide similar image quality at a lower radiation dose compared with SECT.

Weighing features of lung and heart regions for thoracic disease classification.

BACKGROUND: Chest X-rays are the most commonly available and affordable radiological examination for screening thoracic diseases. According to the domain knowledge of screening chest X-rays, the pathological information usually lay on the lung and heart regions. However, it is costly to acquire region-level annotation in practice, and model training mainly relies on image-level class labels in a weakly supervised manner, which is highly challenging for computer-aided chest X-ray screening. To address this issue, some methods have been proposed recently to identify local regions containing pathological information, which is vital for thoracic disease classification. Inspired by this, we propose a novel deep learning framework to explore discriminative information from lung and heart regions. RESULT: We design a feature extractor equipped with a multi-scale attention module to learn global attention maps from global images. To exploit disease-specific cues effectively, we locate lung and heart regions containing pathological information by a well-trained pixel-wise segmentation model to generate binarization masks. By introducing element-wise logical AND operator on the learned global attention maps and the binarization masks, we obtain local attention maps in which pixels are are 1 for lung and heart region and 0 for other regions. By zeroing features of non-lung and heart regions in attention maps, we can effectively exploit their disease-specific cues in lung and heart regions. Compared to existing methods fusing global and local features, we adopt feature weighting to avoid weakening visual cues unique to lung and heart regions. Our method with pixel-wise segmentation can help overcome the deviation of locating local regions. Evaluated by the benchmark split on the publicly available chest X-ray14 dataset, the comprehensive experiments show that our method achieves superior performance compared to the state-of-the-art methods. CONCLUSION: We propose a novel deep framework for the multi-label classification of thoracic diseases in chest X-ray images. The proposed network aims to effectively exploit pathological regions containing the main cues for chest X-ray screening. Our proposed network has been used in clinic screening to assist the radiologists. Chest X-ray accounts for a significant proportion of radiological examinations. It is valuable to explore more methods for improving performance.

Contralaterally Enhanced Networks for Thoracic Disease Detection.

Identifying and locating diseases in chest X-rays are very challenging, due to the low visual contrast between normal and abnormal regions, and distortions caused by other overlapping tissues. An interesting phenomenon is that there exist many similar structures in the left and right parts of the chest, such as ribs, lung fields and bronchial tubes. This kind of similarities can be used to identify diseases in chest X-rays, according to the experience of broad-certificated radiologists. Aimed at improving the performance of existing detection methods, we propose a deep end-to-end module to exploit the contralateral context information for enhancing feature representations of disease proposals. First of all, under the guidance of the spine line, the spatial transformer network is employed to extract local contralateral patches, which can provide valuable context information for disease proposals. Then, we build up a specific module, based on both additive and subtractive operations, to fuse the features of the disease proposal and the contralateral patch. Our method can be integrated into both fully and weakly supervised disease detection frameworks. It achieves 33.17 AP50 on a carefully annotated private chest X-ray dataset which contains 31,000 images. Experiments on the NIH chest X-ray dataset indicate that our method achieves state-of-the-art performance in weakly-supervised disease localization.

A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation.

Instance level detection and segmentation of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images. Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN. The SAR-Net consists of three relation modules: 1. the anatomical structure relation module encoding spatial relations between diseases and anatomical parts. 2. the contextual relation module aggregating clues based on query-key pair of disease RoI and lung fields. 3. the disease relation module propagating co-occurrence and causal relations into disease proposals. Towards making a practical system, we also provide ChestX-Det, a chest X-Ray dataset with instance-level annotations (boxes and masks). ChestX-Det is a subset of the public dataset NIH ChestX-ray14. It contains ~3500 images of 13 common disease categories labeled by three board-certified radiologists. We evaluate our SAR-Net on it and another dataset DR-Private. Experimental results show that it can enhance the strong baseline of Mask R-CNN with significant improvements. The ChestX-Det is released at https://github.com/Deepwise-AILab/ChestX-Det-Dataset.

Canadian Society of Thoracic Radiology/Canadian Association of Radiologists Clinical Practice Guidance for Non-Vascular Thoracic MRI.

Historically thoracic MRI has been limited by the lower proton density of lung parenchyma, cardiac and respiratory motion artifacts and long acquisition times. Recent technological advancements in MR hardware systems and improvement in MR pulse sequences have helped overcome these limitations and expand clinical opportunities for non-vascular thoracic MRI. Non-vascular thoracic MRI has been established as a problem-solving imaging modality for characterization of thymic, mediastinal, pleural chest wall and superior sulcus tumors and for detection of endometriosis. It is increasingly recognized as a powerful imaging tool for detection and characterization of lung nodules and for assessment of lung cancer staging. The lack of ionizing radiation makes thoracic MRI an invaluable imaging modality for young patients, pregnancy and for frequent serial follow-up imaging. Lack of familiarity and exposure to non-vascular thoracic MRI and lack of consistency in existing MRI protocols have called for clinical practice guidance. The purpose of this guide, which was developed by the Canadian Society of Thoracic Radiology and endorsed by the Canadian Association of Radiologists, is to familiarize radiologists, other interested clinicians and MR technologists with common and less common clinical indications for non-vascular thoracic MRI, discuss the fundamental imaging findings and focus on basic and more advanced MRI sequences tailored to specific clinical questions.