Artificial intelligence (AI) is rapidly being applied to a wide range of fields, including medicine, and has been considered as an approach that may augment or substitute human professionals in primary healthcare. However, AI also raises several challenges and ethical concerns. In this article, the author investigates and discusses three aspects of AI in medicine and healthcare: the application and promises of AI, special ethical concerns pertaining to AI in some frontier fields, and suggestive ethical governance systems. Despite great potentials of frontier AI research and development in the field of medical care, the ethical challenges induced by its applications has put forward new requirements for governance. To ensure “trustworthy” AI applications in healthcare and medicine, the creation of an ethical global governance framework and system as well as special guidelines for frontier AI applications in medicine are suggested. The most important aspects include the roles of governments in ethical auditing and the responsibilities of stakeholders in the ethical governance system.

Medical imaging is now being reshaped by artificial intelligence (AI) and progressing rapidly toward future. In this article, we review the recent progress of AI-enabled medical imaging. Firstly, we briefly review the background about AI in its way of evolution. Then, we discuss the recent successes of AI in different medical imaging tasks, especially in image segmentation, registration, detection and recognition. Also, we illustrate several representative applications of AI-enabled medical imaging to show its advantage in real scenario, which includes lung nodule in chest CT, neuroimaging, mammography, and etc. Finally, we report the way of human-machine interaction. We believe that, in the future, AI will not only change the traditional way of medical imaging, but also improve the clinical routines of medical care and enable many aspects of the medical society.

With the continuous progress of virtual simulation technology, medical surgery visualization system has been developed from two-dimensional to three-dimensional, from digital to network and intelligentization. The visualization system with mixed reality technology will also be used in all stage of medical surgery, such as case discussion, surgical planning, intraoperative guidance, post-operative evaluation, rehabilitation, so as to further promote high intelligence, high precision of medical surgery, and consequently improve effectiveness of treatment and quality of medical service. This paper discusses the composition and technical characteristics of medical operation visualization system based on mixed reality technology, and introduces some typical applications of mixed reality technology in medical operation visualization, which provides a new perspective for the application of mixed technology in medical surgery.

In recent years, artificial intelligence (AI) has developed rapidly in the field of medical imaging. However, the collaborations among hospitals, research institutes and enterprises are insufficient at the present, and there are various issues in technological transformation and value landing of products in this area. To solve the core problems in the developmental path of medical imaging AI, the Chinese Innovative Alliance of Industry, Education, Research and Application of Artificial Intelligence for Medical Imaging compiled the White Paper on Medical Image AI in China. This article introduces the current status of collaboration, the clinical demands for medical imaging AI technique, and the key points in AI technology transformation: robustness, usability and security. We are facing challenges of lacking industry standards, data desensitization standard, assessment system, as well as corresponding regulations and policies to realize the application values of AI products in medical imaging. Further development of AI in medical imaging requires breakthroughs of the core algorithm, deep involvement of doctors, input from capitals, patience from societies, and most importantly, the resolutions from government for multiple difficulties in links of landing the technology.

Ovarian cancer is one of the three most common gynecological cancers in the world, and is regarded as a priority in terms of women’s cancer. In the past few years, many researchers have attempted to develop and apply artificial intelligence (AI) techniques to multiple clinical scenarios of ovarian cancer, especially in the field of medical imaging. AI-assisted imaging studies have involved computer tomography (CT), ultrasonography (US), and magnetic resonance imaging (MRI). In this review, we perform a literature search on the published studies that using AI techniques in the medical care of ovarian cancer, and bring up the advances in terms of four clinical aspects, including medical diagnosis, pathological classification, targeted biopsy guidance, and prognosis prediction. Meanwhile, current status and existing issues of the researches on AI application in ovarian cancer are discussed.

Objective We developed a universal lesion detector (ULDor) which showed good performance in in-lab experiments. The study aims to evaluate the performance and its ability to generalize in clinical setting via both external and internal validation.
Methods The ULDor system consists of a convolutional neural network (CNN) trained on around 80K lesion annotations from about 12K CT studies in the DeepLesion dataset and 5 other public organ-specific datasets. During the validation process, the test sets include two parts: the external validation dataset which was comprised of 164 sets of non-contrasted chest and upper abdomen CT scans from a comprehensive hospital, and the internal validation dataset which was comprised of 187 sets of low-dose helical CT scans from the National Lung Screening Trial (NLST). We ran the model on the two test sets to output lesion detection. Three board-certified radiologists read the CT scans and verified the detection results of ULDor. We used positive predictive value (PPV) and sensitivity to evaluate the performance of the model in detecting space-occupying lesions at all extra-pulmonary organs visualized on CT images, including liver, kidney, pancreas, adrenal, spleen, esophagus, thyroid, lymph nodes, body wall, thoracic spine, etc.
Results In the external validation, the lesion-level PPV and sensitivity of the model were 57.9% and 67.0%, respectively. On average, the model detected 2.1 findings per set, and among them, 0.9 were false positives. ULDor worked well for detecting liver lesions, with a PPV of 78.9% and a sensitivity of 92.7%, followed by kidney, with a PPV of 70.0% and a sensitivity of 58.3%. In internal validation with NLST test set, ULDor obtained a PPV of 75.3% and a sensitivity of 52.0% despite the relatively high noise level of soft tissue on images.
Conclusions The performance tests of ULDor with the external real-world data have shown its high effectiveness in multiple-purposed detection for lesions in certain organs. With further optimisation and iterative upgrades, ULDor may be well suited for extensive application to external data.

Hepatocellular carcinoma (HCC) is the sixth most common malignancy and the fourth leading cause of cancer related death worldwide. China covers over half of cases, leading HCC to be a vital threaten to public health. Despite advances in diagnosis and treatments, high recurrence rate remains a major obstacle in HCC management. Multi-omics currently facilitates surveillance, precise diagnosis, and personalized treatment decision making in clinical setting. Non-invasive radiomics utilizes preoperative radiological imaging to reflect subtle pixel-level pattern changes that correlate to specific clinical outcomes. Radiomics has been widely used in histopathological diagnosis prediction, treatment response evaluation, and prognosis prediction. High-throughput sequencing and gene expression profiling enabled genomics and proteomics to identify distinct transcriptomic subclasses and recurrent genetic alterations in HCC, which would reveal the complex multistep process of the pathophysiology. The accumulation of big medical data and the development of artificial intelligence techniques are providing new insights for our better understanding of the mechanism of HCC via multi-omics, and show potential to convert surgical/intervention treatment into an antitumorigenic one, which would greatly advance precision medicine in HCC management.

Regional healthcare platforms collect clinical data from hospitals in specific areas for the purpose of healthcare management. It is a common requirement to reuse the data for clinical research. However, we have to face challenges like the inconsistence of terminology in electronic health records (EHR) and the complexities in data quality and data formats in regional healthcare platform. In this paper, we propose methodology and process on constructing large scale cohorts which forms the basis of causality and comparative effectiveness relationship in epidemiology. We firstly constructed a Chinese terminology knowledge graph to deal with the diversity of vocabularies on regional platform. Secondly, we built special disease case repositories (i.e., heart failure repository) that utilize the graph to search the related patients and to normalize the data. Based on the requirements of the clinical research which aimed to explore the effectiveness of taking statin on 180-days readmission in patients with heart failure, we built a large-scale retrospective cohort with 29647 cases of heart failure patients from the heart failure repository. After the propensity score matching, the study group (n=6346) and the control group (n=6346) with parallel clinical characteristics were acquired. Logistic regression analysis showed that taking statins had a negative correlation with 180-days readmission in heart failure patients. This paper presents the workflow and application example of big data mining based on regional EHR data.

Objective To develope a deep learning algorithm for pathological classification of chronic gastritis and assess its performance using whole-slide images (WSIs).
Methods We retrospectively collected 1,250 gastric biopsy specimens (1,128 gastritis, 122 normal mucosa) from PLA General Hospital. The deep learning algorithm based on DeepLab v3 (ResNet-50) architecture was trained and validated using 1,008 WSIs and 100 WSIs, respectively. The diagnostic performance of the algorithm was tested on an independent test set of 142 WSIs, with the pathologists’ consensus diagnosis as the gold standard.
Results The receiver operating characteristic (ROC) curves were generated for chronic superficial gastritis (CSuG), chronic active gastritis (CAcG), and chronic atrophic gastritis (CAtG) in the test set, respectively.The areas under the ROC curves (AUCs) of the algorithm for CSuG, CAcG, and CAtG were 0.882, 0.905 and 0.910, respectively. The sensitivity and specificity of the deep learning algorithm for the classification of CSuG, CAcG, and CAtG were 0.790 and 1.000 (accuracy 0.880), 0.985 and 0.829 (accuracy 0.901), 0.952 and 0.992 (accuracy 0.986), respectively. The overall predicted accuracy for three different types of gastritis was 0.867. By flagging the suspicious regions identified by the algorithm in WSI, a more transparent and interpretable diagnosis can be generated.
Conclusion The deep learning algorithm achieved high accuracy for chronic gastritis classification using WSIs. By pre-highlighting the different gastritis regions, it might be used as an auxiliary diagnostic tool to improve the work efficiency of pathologists.

The recent spring up of the antineoplastic agents and the prolonged survival bring both challenge and chance to radiological practice. Radiological methods including CT, MRI and PET play an increasingly important role in evaluating the efficacy of these antineoplastic drugs. However, different antineoplastic agents potentially induce different radiological signs, making it a challenge for radiological response evaluation, which depends mainly on one-sided morphological response evaluation criteria in solid tumors (RECIST) in the status quo of clinical practice. This brings opportunities for the development of radiomics, which is promising to serve as a surrogate for response evaluations of anti-tumor treatments. In this article, we introduce the basic concepts of radiomics, review the state-of-art radiomics researches with highlights of radiomics application in predictions of molecular biomarkers, treatment response, and prognosis. We also provide in-depth analyses on major obstacles and future direction of this new technique in clinical investigations on new antineoplastic agents.

This special issue focuses on recent advances of medical AIs. It includes review articles for the key AI algorithms and technologies used in medicine, the current status of computer-aided diagnosis in several fields or diseases which are heavily studied, the examples of applications of AI in various forms, and the potential way that AI can cooperate and change the common practice of health system. We hope this issue can give experts and practitioners in medicine a comprehensive view of the status quo of medical AI and inspire more ideas for further development of this realm.