A Review Paper about Deep Learning for Medical Image Analysis.

Medical imaging refers to the process of obtaining images of internal organs for therapeutic purposes such as discovering or studying diseases. The primary objective of medical image analysis is to improve the efficacy of clinical research and treatment options. Deep learning has revamped medical image analysis, yielding excellent results in image processing tasks such as registration, segmentation, feature extraction, and classification. The prime motivations for this are the availability of computational resources and the resurgence of deep convolutional neural networks. Deep learning techniques are good at observing hidden patterns in images and supporting clinicians in achieving diagnostic perfection. It has proven to be the most effective method for organ segmentation, cancer detection, disease categorization, and computer-assisted diagnosis. Many deep learning approaches have been published to analyze medical images for various diagnostic purposes. In this paper, we review the work exploiting current state-of-the-art deep learning approaches in medical image processing. We begin the survey by providing a synopsis of research works in medical imaging based on convolutional neural networks. Second, we discuss popular pretrained models and general adversarial networks that aid in improving convolutional networks' performance. Finally, to ease direct evaluation, we compile the performance metrics of deep learning models focusing on COVID-19 detection and child bone age prediction.

Level Set Image Feature Detection and Application in COVID-19 Image Feature Knowledge Detection.

Artificial intelligence (AI) scholars and mediciners have reported AI systems that accurately detect medical imaging and COVID-19 in chest images. However, the robustness of these models remains unclear for the segmentation of images with nonuniform density distribution or the multiphase target. The most representative one is the Chan-Vese (CV) image segmentation model. In this paper, we demonstrate that the recent level set (LV) model has excellent performance on the detection of target characteristics from medical imaging relying on the filtering variational method based on the global medical pathology facture. We observe that the capability of the filtering variational method to obtain image feature quality is better than other LV models. This research reveals a far-reaching problem in medical-imaging AI knowledge detection. In addition, from the analysis of experimental results, the algorithm proposed in this paper has a good effect on detecting the lung region feature information of COVID-19 images and also proves that the algorithm has good adaptability in processing different images. These findings demonstrate that the proposed LV method should be seen as an effective clinically adjunctive method using machine-learning healthcare models.

Vascular Spectrum of Imaging Findings in COVID-19: Ischemic, Hemorrhagic, and Thromboembolic Complications

Abstract Ischemic strokes secondary to occlusion of large vessels have been described in patients with COVID-19. Also, venous thrombosis and pulmonary thromboembolism have been related to the disease. Vascular occlusion may be associated with a prothrombotic state due to COVID-19-related coagulopathy and endotheliopathy. Intracranial hemorrhagic lesions can additionally be seen in these patients. The causative mechanism of hemorrhage could be associated with anticoagulant therapy or factors such as coagulopathy and endotheliopathy. We report on cases of ischemic, thrombotic, and hemorrhagic complications in six patients diagnosed with SARS-CoV-2 infection. Chest computed tomography (CT) showed typical SARS-CoV-2 pneumonia findings in all the cases, which were all confirmed by either serology or reverse transcription polymerase chain reaction (RT-PCR) tests.

AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging.

Rapid advances in artificial intelligence (AI) and machine learning, and specifically in deep learning (DL) techniques, have enabled broad application of these methods in health care. The promise of the DL approach has spurred further interest in computer-aided diagnosis (CAD) development and applications using both "traditional" machine learning methods and newer DL-based methods. We use the term CAD-AI to refer to this expanded clinical decision support environment that uses traditional and DL-based AI methods. Numerous studies have been published to date on the development of machine learning tools for computer-aided, or AI-assisted, clinical tasks. However, most of these machine learning models are not ready for clinical deployment. It is of paramount importance to ensure that a clinical decision support tool undergoes proper training and rigorous validation of its generalizability and robustness before adoption for patient care in the clinic. To address these important issues, the American Association of Physicists in Medicine (AAPM) Computer-Aided Image Analysis Subcommittee (CADSC) is charged, in part, to develop recommendations on practices and standards for the development and performance assessment of computer-aided decision support systems. The committee has previously published two opinion papers on the evaluation of CAD systems and issues associated with user training and quality assurance of these systems in the clinic. With machine learning techniques continuing to evolve and CAD applications expanding to new stages of the patient care process, the current task group report considers the broader issues common to the development of most, if not all, CAD-AI applications and their translation from the bench to the clinic. The goal is to bring attention to the proper training and validation of machine learning algorithms that may improve their generalizability and reliability and accelerate the adoption of CAD-AI systems for clinical decision support.

Infection prevention and control in medical imaging surveys: The need to map to guidelines to address systemic issues?

BACKGROUND: Infection prevention and control (IPC) in the medical imaging (MI) setting is recognised as an important factor in providing high-quality patient care and safe working conditions. Surveys are commonly used and have advantages for IPC research. The aim of this study was to identify the core concepts in surveys published in the literature that examined IPC in MI environments. METHODS: A literature review was conducted to identify studies that employed a survey relating to IPC in the MI setting. For each included study, descriptive study information and survey information were extracted. For IPC-specific survey items, directed content analysis was undertaken, using eleven pre-determined codes based on the 'Australian Guidelines for the Prevention and Control of Infection in Healthcare'. Content that related to 'Knowledge', 'Attitudes' and 'Practice' were also identified. RESULTS: A total of 23 studies and 21 unique surveys were included in this review. IPC-specific survey items assessed diverse dimensions of IPC, most commonly relating to 'transmission-based precautions' and 'applying standard and transmission-based precautions during procedures'. 'Practice' and 'Knowledge' related survey items were most frequent, compared to 'Attitudes'. CONCLUSION: MI research using survey methods have focused on the 'entry' points of IPC, rather than systemic IPC matters around policy, education, and stewardship. The concepts of 'Knowledge', 'Attitudes' and 'Practice' are integrated in IPC surveys in the MI context, with a greater focus evident on staff knowledge and practice. Existing topics within IPC surveys in MI are tailored to individual studies and locales, with lack of consistency to national frameworks.

New Biosensor for Determination of Neuropilin-1 with Detection by Surface Plasmon Resonance Imaging.

Neuropilin-1 is transmembrane protein with soluble isoforms. It plays a pivotal role in both physiological and pathological processes. NRP-1 is involved in the immune response, formation of neuronal circuits, angiogenesis, survival and migration of cells. The specific SPRI biosensor for the determination of neuropilin-1 was constructed using mouse monoclonal antibody that captures unbound NRP-1 form body fluids. The biosensor exhibits linearity of the analytical signal between 0.01 and 2.5 ng/mL, average precision value 4.7% and recovery between 97% and 104%. The detection limit is 0.011 ng/mL, and the limit of quantification is 0.038 ng/mL. The biosensor was validated by parallel determination of NRP-1 in serum and saliva samples using the ELISA test, with good agreement of the results.

COVID-19 imaging, where do we go from here? Bibliometric analysis of medical imaging in COVID-19.

OBJECTIVES: We conducted a systematic and comprehensive bibliometric analysis of COVID-19-related medical imaging to determine the current status and indicate possible future directions. METHODS: This research provides an analysis of Web of Science Core Collection (WoSCC) indexed articles on COVID-19 and medical imaging published between 1 January 2020 and 30 June 2022, using the search terms "COVID-19" and medical imaging terms (such as "X-ray" or "CT"). Publications based solely on COVID-19 themes or medical image themes were excluded. CiteSpace was used to identify the predominant topics and generate a visual map of countries, institutions, authors, and keyword networks. RESULTS: The search included 4444 publications. The journal with the most publications was European Radiology, and the most co-cited journal was Radiology. China was the most frequently cited country in terms of co-authorship, with the Huazhong University of Science and Technology being the institution contributing with the highest number of relevant co-authorships. Research trends and leading topics included: assessment of initial COVID-19-related clinical imaging features, differential diagnosis using artificial intelligence (AI) technology and model interpretability, diagnosis systems construction, COVID-19 vaccination, complications, and predicting prognosis. CONCLUSIONS: This bibliometric analysis of COVID-19-related medical imaging helps clarify the current research situation and developmental trends. Subsequent trends in COVID-19 imaging are likely to shift from lung structure to function, from lung tissue to other related organs, and from COVID-19 to the impact of COVID-19 on the diagnosis and treatment of other diseases. Key Points • We conducted a systematic and comprehensive bibliometric analysis of COVID-19-related medical imaging from 1 January 2020 to 30 June 2022. • Research trends and leading topics included assessment of initial COVID-19-related clinical imaging features, differential diagnosis using AI technology and model interpretability, diagnosis systems construction, COVID-19 vaccination, complications, and predicting prognosis. • Future trends in COVID-19-related imaging are likely to involve a shift from lung structure to function, from lung tissue to other related organs, and from COVID-19 to the impact of COVID-19 on the diagnosis and treatment of other diseases.

Management of patients with advanced prostate cancer-metastatic and/or castration-resistant prostate cancer: Report of the Advanced Prostate Cancer Consensus Conference (APCCC) 2022.

BACKGROUND: Innovations in imaging and molecular characterisation together with novel treatment options have improved outcomes in advanced prostate cancer. However, we still lack high-level evidence in many areas relevant to making management decisions in daily clinical practise. The 2022 Advanced Prostate Cancer Consensus Conference (APCCC 2022) addressed some questions in these areas to supplement guidelines that mostly are based on level 1 evidence. OBJECTIVE: To present the voting results of the APCCC 2022. DESIGN, SETTING, AND PARTICIPANTS: The experts voted on controversial questions where high-level evidence is mostly lacking: locally advanced prostate cancer; biochemical recurrence after local treatment; metastatic hormone-sensitive, non-metastatic, and metastatic castration-resistant prostate cancer; oligometastatic prostate cancer; and managing side effects of hormonal therapy. A panel of 105 international prostate cancer experts voted on the consensus questions. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The panel voted on 198 pre-defined questions, which were developed by 117 voting and non-voting panel members prior to the conference following a modified Delphi process. A total of 116 questions on metastatic and/or castration-resistant prostate cancer are discussed in this manuscript. In 2022, the voting was done by a web-based survey because of COVID-19 restrictions. RESULTS AND LIMITATIONS: The voting reflects the expert opinion of these panellists and did not incorporate a standard literature review or formal meta-analysis. The answer options for the consensus questions received varying degrees of support from panellists, as reflected in this article and the detailed voting results are reported in the supplementary material. We report here on topics in metastatic, hormone-sensitive prostate cancer (mHSPC), non-metastatic, castration-resistant prostate cancer (nmCRPC), metastatic castration-resistant prostate cancer (mCRPC), and oligometastatic and oligoprogressive prostate cancer. CONCLUSIONS: These voting results in four specific areas from a panel of experts in advanced prostate cancer can help clinicians and patients navigate controversial areas of management for which high-level evidence is scant or conflicting and can help research funders and policy makers identify information gaps and consider what areas to explore further. However, diagnostic and treatment decisions always have to be individualised based on patient characteristics, including the extent and location of disease, prior treatment(s), co-morbidities, patient preferences, and treatment recommendations and should also incorporate current and emerging clinical evidence and logistic and economic factors. Enrolment in clinical trials is strongly encouraged. Importantly, APCCC 2022 once again identified important gaps where there is non-consensus and that merit evaluation in specifically designed trials. PATIENT SUMMARY: The Advanced Prostate Cancer Consensus Conference (APCCC) provides a forum to discuss and debate current diagnostic and treatment options for patients with advanced prostate cancer. The conference aims to share the knowledge of international experts in prostate cancer with healthcare providers worldwide. At each APCCC, an expert panel votes on pre-defined questions that target the most clinically relevant areas of advanced prostate cancer treatment for which there are gaps in knowledge. The results of the voting provide a practical guide to help clinicians discuss therapeutic options with patients and their relatives as part of shared and multidisciplinary decision-making. This report focuses on the advanced setting, covering metastatic hormone-sensitive prostate cancer and both non-metastatic and metastatic castration-resistant prostate cancer. TWITTER SUMMARY: Report of the results of APCCC 2022 for the following topics: mHSPC, nmCRPC, mCRPC, and oligometastatic prostate cancer. TAKE-HOME MESSAGE: At APCCC 2022, clinically important questions in the management of advanced prostate cancer management were identified and discussed, and experts voted on pre-defined consensus questions. The report of the results for metastatic and/or castration-resistant prostate cancer is summarised here.