A multi-level similarity measure for the retrieval of the common CT imaging signs of lung diseases

Micro-computed tomography (micro-CT) is a promising novel medical imaging modality that allows for non-destructive volumetric imaging of surgical tissue specimens at high spatial resolution. The aim of this study is to provide a comprehensive assessment of the clinical applications of micro-CT for the tissue-based diagnosis of lung diseases. This scoping review was conducted in accordance with the PRISMA Extension for Scoping Reviews, aiming to include every clinical study reporting on micro-CT imaging of human lung tissues. A literature search yielded 570 candidate articles, out of which 37 were finally included in the review. Of the selected studies, 9 studies explored via micro-CT imaging the morphology and anatomy of normal human lung tissue; 21 studies investigated microanatomic pulmonary alterations due to obstructive or restrictive lung diseases, such as chronic obstructive pulmonary disease, idiopathic pulmonary fibrosis, and cystic fibrosis; and 7 studies examined the utility of micro-CT imaging in assessing lung cancer lesions (n = 4) or in transplantation-related pulmonary alterations (n = 3). The selected studies reported that micro-CT could successfully detect several lung diseases providing three-dimensional images of greater detail and resolution than routine optical slide microscopy, and could additionally provide valuable volumetric insight in both restrictive and obstructive lung diseases. In conclusion, micro-CT-based volumetric measurements and qualitative evaluations of pulmonary tissue structures can be utilized for the clinical management of a variety of lung diseases. With micro-CT devices becoming more accessible, the technology has the potential to establish itself as a core diagnostic imaging modality in pathology and to enable integrated histopathologic and radiologic assessment of lung cancer and other lung diseases.

Download Full-text

AN INTELLIGENT CBMIR SYSTEM FOR DETECTION AND LOCALIZATION OF LUNG DISEASES

International Journal of Advanced Research ◽

10.21474/ijar01/13311 ◽

2021 ◽

Vol 9 (08) ◽

pp. 651-660

Author(s):

Nora I. Yahia ◽

◽

Ayman I. Al-Dosouki ◽

Sahar A. Mokhtar ◽

Hany M. Harb ◽

...

Keyword(s):

Medical Image ◽

Lung Diseases ◽

Medical Instrument ◽

Detection Accuracy ◽

Retrieval Process ◽

Recognition Efficiency ◽

Imaging Signs ◽

Detection And Localization ◽

Aided Diagnosis ◽

Detector Model

The diagnosis of lung diseases is a complicated and time-consuming task for radiologists. Often radiologists struggle with accurately diagnosing lung diseases, They use Commonly CT imaging signs (CISs) which common appear in CT lung nodules in the diagnosis of lung diseases. Computer-aided diagnosis systems (CAD) can automatically diagnose and detect these signs by analyzing CT scans, which will reduce radiologists workload. The diagnosis and recognition efficiency and accuracy can be improved by using content-based medical image retrieval (CBMIR). This paper proposes a new intelligent CBMIR method to retrieve CISs helping in diagnosing and recognize lung diseases by using deep Convolutional Neural Network (CNN). Fine-tuned YOLOv4 (You Only Look Once) object detector model are proposed to fast detect and efficiently localize signs in real-time. The proposed CBMIR system can be applied as a useful and accurate medical instrument for diagnostics. The experimental results show an average detection accuracy of CT signs lung diseases as high as 92% and a mean average precision (MAP) of 0.92 is achieved using the proposed technique. Also, it takes only 0.1 milliseconds for the retrieval process. The proposed system presents high improvement as compared to the other system. It achieved better precision of retrieval results and the fastest run of the retrieval time.

Download Full-text

Differential diagnoses of fibrosing lung diseases

BJR|Open ◽

10.1259/bjro.20190009 ◽

2019 ◽

Vol 1 (1) ◽

pp. 20190009

Author(s):

Carolyn Horst ◽

Bahareh Gholipour ◽

Arjun Nair ◽

Joseph Jacob

Keyword(s):

Lung Diseases ◽

Hypersensitivity Pneumonitis ◽

Individual Case ◽

Ct Imaging ◽

Diagnostic Process ◽

Imaging Features ◽

Future Directions ◽

Essential Information ◽

Scientific Databases ◽

Current State

Objectives: To describe the challenges inherent in diagnosing fibrosing lung diseases (FLD) on CT imaging and methodologies by which the diagnostic process may be simplified. Methods: Extensive searches in online scientific databases were performed to provide relevant and contemporary evidence that describe the current state of knowledge related to FLD diagnosis. This includes descriptions of the utility of a working diagnosis for an individual case discussed in a multidisciplinary team (MDT) setting and challenges associated with the lack of consensus guidelines for diagnosing chronic hypersensitivity pneumonitis. Results: As well as describing imaging features that indicate the presence of a fibrosing lung disease, those CT characteristics that nuance a diagnosis of the various FLDs are considered. The review also explains the essential information that a radiologist needs to convey to an MDT when reading a CT scan. Lastly, we provide some insights as to the future directions the field make take in the upcoming years. Conclusions: This review outlines the current state of FLD diagnosis and emphasizes areas where knowledge is limited, and more evidence is required. Fundamentally, however, it provides a guide for radiologists when tackling CT imaging in a patient with FLD. Advances in knowledge: This review encompasses advice from recent guideline statements and evidence from the latest studies in FLD to provide an up-to-date manual for radiologists to aid the diagnosis of FLD on CT imaging in an MDT setting.

Download Full-text

Multi-Level Multi-Modality Fusion Radiomics: Application to PET and CT Imaging for Prognostication of Head and Neck Cancer

IEEE Journal of Biomedical and Health Informatics ◽

10.1109/jbhi.2019.2956354 ◽

2020 ◽

Vol 24 (8) ◽

pp. 2268-2277 ◽

Cited By ~ 1

Author(s):

Wenbing Lv ◽

Saeed Ashrafinia ◽

Jianhua Ma ◽

Lijun Lu ◽

Arman Rahmim

Keyword(s):

Head And Neck Cancer ◽

Head And Neck ◽

Neck Cancer ◽

Ct Imaging ◽

Multi Level

Download Full-text

Information Model Governance for Diverse Disciplines

10.5194/egusphere-egu2020-10600 ◽

2020 ◽

Author(s):

John S. Hughes ◽

Daniel J. Crichton

Keyword(s):

Reference Model ◽

Configuration Management ◽

Information Model ◽

Data Representation ◽

Planetary Science ◽

Complex Data ◽

Data Types ◽

The Common ◽

Multi Level ◽

Science Disciplines

The PDS4 Information Model (IM) Version 1.13.0.0 was released for use in December 2019. The ontology-based IM remains true to its foundational principles found in the Open Archive Information System (OAIS) Reference Model (ISO 14721) and the Metadata Registry (MDR) standard (ISO/IEC 11179). The standards generated from the IM have become the de-facto data archiving standards for the international planetary science community and have successfully scaled to meet the requirements of the diverse and evolving planetary science disciplines.A key foundational principle is the use of a multi-level governance scheme that partitions the IM into semi-independent dictionaries. The governance scheme first partitions the IM vertically into three levels, the common, discipline, and project/mission levels. The IM is then partitioned horizontally across both discipline and project/mission levels into individual Local Data Dictionaries (LDDs).The Common dictionary defines the classes used across the science disciplines such as product, collection, bundle, data formats, data types, and units of measurement. The dictionary resulted from a large collaborative effort involving domain experts across the community. An ontology modeling tool was used to enforce a modeling discipline, for configuration management, to ensure consistency and extensibility, and to enable interoperability. The Common dictionary encompasses the information categories defined in the OAIS RM, specifically data representation, provenance, fixity, identification, reference, and context. Over the last few years, the Common dictionary has remained relatively stable in spite of requirements levied by new missions, instruments, and more complex data types.Since the release of the Common dictionary, the creation of a significant number of LDDs has proved the effectiveness of multi-level, steward-based governance. This scheme is allowing the IM to scale to meet the archival and interoperability demands of the evolving disciplines. In fact, an LDD development &#8220;cottage industry&#8221; has emerged that required improvements to the development processes and configuration management.&#160; An LDD development tool now allows dictionary stewards to quickly produce specialized LDDs that are consistent with the Common dictionary.The PDS4 Information Model is a world-class knowledge-base that governs the Planetary Science community's trusted digital repositories. This presentation will provide an overview of the model and additional information about its multi-level governance scheme including the topics of stewardship, configuration management, processes, and oversight.

Download Full-text