MedNexus
2021年 · 第01卷第02期
MedNexus
暂无数据 暂无数据 暂无数据 暂无数据In recent years, the incidence of myopia has increased at an alarming rate among children and adolescents in China. The exploration of an effective prevention and control method for myopia is in urgent need. With the development of information technology in the past decade, artificial intelligence with the Internet of Things technology (AIoT) is characterized by strong computing power, advanced algorithm, continuous monitoring, and accurate prediction of long-term progression. Therefore, big data and artificial intelligence technology have the potential to be applied to data mining of myopia etiology and prediction of myopia occurrence and development. More recently, there has been a growing recognition that myopia study involving AIoT needs to undergo a rigorous evaluation to demonstrate robust results.
After more than 60 years of development, artificial intelligence (AI) has been widely used in various fields. Especially in recent years, with the development of deep learning, AI has made many remarkable achievements in the medical field. Dermatology, as a clinical discipline with morphology as its main feature, is particularly suitable for the development of AI. The rapid development of skin imaging technology has helped dermatologists to assist in the diagnosis of diseases and has greatly improved the accuracy of diagnosis. Skin imaging data have natural big data attributes, which is important for AI research. The establishment of the Chinese Skin Image Database (CSID) has solved many problems such as isolated data islands and inconsistent data quality. Based on the CSID, many pioneering achievements have been made in the research and development of AI-assisted decision-making software, the establishment of expert organizations, personnel training, scientific research, and so on. At present, there are still many problems with AI in the field of dermatology, such as clinical validation, medical device licensing, interdisciplinary, and standard formulation, which urgently need to be solved by joint efforts of all parties.
Complete and transparent reporting is of critical importance for randomized controlled trials (RCTs). The present study aimed to determine the reporting quality and methodological quality of RCTs for interventions involving artificial intelligence (AI) and their protocols.
We searched MEDLINE (via PubMed), Embase, Web of Science, CBMdisc, Wanfang Data, and CNKI from January 1, 2016, to November 11, 2020, to collect RCTs involving AI. We also extracted the protocol of each included RCT if it could be obtained. CONSORT-AI (Consolidated Standards of Reporting Trials-Artificial Intelligence) statement and Cochrane Collaboration’s tool for assessing risk of bias (ROB) were used to evaluate the reporting quality and methodological quality, respectively, and SPIRIT-AI (The Standard Protocol Items: Recommendations for Interventional Trials-Artificial Intelligence) statement was used to evaluate the reporting quality of the protocols. The associations of the reporting rate of CONSORT-AI with the publication year, journal’s impact factor (IF), number of authors, sample size, and first author’s country were analyzed univariately using Pearson’s chi-squared test, or Fisher’s exact test if the expected values in any of the cells were below 5. The compliance of the retrieved protocols to SPIRIT-AI was presented descriptively.
Overall, 29 RCTs and three protocols were considered eligible. The CONSORT-AI items "title and abstract" and "interpretation of results" were reported by all RCTs, with the items with the lowest reporting rates being "funding" (0), "implementation" (3.5%), and "harms" (3.5%). The risk of bias was high in 13 (44.8%) RCTs and not clear in 15 (51.7%) RCTs. Only one RCT (3.5%) had a low risk of bias. The compliance was not significantly different in terms of the publication year, journal’s IF, number of authors, sample size, or first author’s country. Ten of the 35 SPIRIT-AI items (funding, participant timeline, allocation concealment mechanism, implementation, data management, auditing, declaration of interests, access to data, informed consent materials and biological specimens) were not reported by any of the three protocols.
The reporting and methodological quality of RCTs involving AI need to be improved. Because of the limited availability of protocols, their quality could not be fully judged. Following the CONSORT-AI and SPIRIT-AI statements and with appropriate guidance on the risk of bias when designing and reporting AI-related RCTs can promote standardization and transparency.
The prevalence of thyroid cancer is growing rapidly. Early and precise diagnosis is critical in thyroid cancer caring. An automatic thyroid cancer diagnostic tool can be valuable to achieve early detection and diagnostic consistency. Only the follicular areas in the sample contain useful information to the thyroid cancer diagnosis based on fine needle aspiration (FNA). This study aimed to develop a highly efficient accurate method for follicular cell areas segmentation (FCAS) of thyroid cytopathological whole slide images (WSIs).
A total of 96 cell samples from July 2017 to July 2018 were collected in one hospital in Beijing, China. Forty-three WSIs were selected and manually labeled, including 17 cases of papillary thyroid carcinoma sample and 26 cases of benign sample. Six thousand and nine hundred cropped typical image patches (available on https://github.com/bupt-ai-cz/Hybrid-Model-Enabling-Highly-Efficient-Follicular-Segmentation) of 1024 × 1024 pixels from 13 large WSIs were used for patch-level model training and testing and all of the 13 large WSIs were papillary thyroid carcinoma samples. Thirty testing WSIs with an average size 36,217 × 29,400 (from 10,240 × 10,240 to 81,920 × 61,440) were used to test the effectiveness of the hybrid model. Based on the traditional semantic segmentation model deeplabv3, we constructed a hybrid segmentation architecture by adding a classification branch into the segmentation scheme to improve efficiency. Accuracy was used to measure the performance of the classification model; pixel accuracy (pAcc), mean accuracy (mAcc), mean intersection over union (mIoU), and frequency weighted intersection over union (fwIoU) were used to measure the performance of the segmentation model, respectively.
Using this method, up to 93% WSI segmentation time was reduced by skipping the colloidal areas and the blank background areas. The average processing time of 30 WSI was 49.49 s. On the patch dataset, this hybrid model might reach pAcc=98.65%, mAcc=85.60%, mIoU=79.61%, and fwIoU=97.54%. On the WSI dataset, this model might reach pAcc=99.30%, mAcc=68.94%, mIoU=58.21%, and fwIoU=99.50%.
The proposed hybrid method might significantly improve previous solutions and achieve the superior performance of efficiency and accuracy.
Medical artificial intelligence (AI) is an important technical asset to support medical supply-side reforms and national development in the big data era. Clinical data from multiple disciplines represent building blocks for the development and application of AI-aided diagnostic and treatment systems based on medical big data. However, the inconsistent quality of these data resources in AI research leads to waste and inefficiencies. Therefore, it is crucial that the field formulates the requirements and content related to data processing as part of the development of intelligent medicine. To promote medical AI research worldwide, the "Belt and Road" International Ophthalmic Artificial Intelligence Research and Development Alliance will establish a series of expert recommendations for data quality in intelligent medicine.
本文规定了眼底彩色照片注释的术语和定义、基本要求、注释要求和质量控制。
本期目次
