基于机器学习的医学影像分析在药物研发和精准医疗方面的应用

MRI,PET,和CT等医学影像在新药研发和精准医疗中起着越来越重要的作用。影像技术可以被用来诊断疾病,评估药效,选择适应患者,或者确定用药剂量。 随着人工智能技术的发展,特别是机器学习以及深度学习技术在医学影像中的应用,使得我们可以用更短的时间,更少的放射剂量获取更高质量的影像。这些技术还可以帮助放射科医生缩短读片时间,提高诊断准确率。除此之外,机器学习技术还可以提高量化分析的可行性和精度,帮助建立影像与基因以及疾病的临床表现之间的关系。首先根据不同形态的医学影像,简单介绍他们在药物研发和精准医疗中的应用。并对机器学习在医学影像中的功能作一概括总结。最后讨论这个领域的挑战和机遇。     

Age-related macular degeneration: a target for nanotechnology derived medicines

Despite the fact that the retina is a fairly accessible portion of the central nervous system, there are virtually no treatments for early age-related macular degeneration (AMD). AMD is a degenerative retinal disease that causes progressive loss of central vision and is the leading cause of irreversible vision loss and legal blindness in individuals over the age of 50. Both environmental and genetic components play a role in its development. AMD is a multifactorial disease with characteristics that include drusen, hyperpigmentation and/or hypopigmentation of the retinal pigment epithelium (RPE), geographic atrophy and, in a subset of patients, late-stage choroidal neovascularization (CNV). Drugs that inhibit vascular endothelial growth factor (VEGF) have proven effective in treating late-stage CNV, but optimal means of drug delivery remains to be determined. Microscopic particles, whose size is on the nanometer scale, show considerable promise for drug delivery to the retina, for gene therapy, and for powering prosthetic "artificial retinas." This article summarizes the pathophysiology of AMD stressing potential applications from nanotechnology.     

Oxidative damage in age-related macular degeneration

Epidemiologic studies have suggested that elderly patients who consumed diets rich in antioxidants throughout their lives are less likely to be afflicted with age-related macular degeneration (AMD). This led to the Age-Related Eye Disease Study, which showed that supplements containing antioxidant vitamins and zinc reduce the risk of progression to severe stages of AMD. Despite these data that indirectly implicate oxidative damage in the pathogenesis of AMD, there has not been any direct demonstration of increased oxidative damage in the retinas of patients with AMD. In this study, we used biomarkers of oxidative damage in postmortem eyes from patients with AMD and comparably aged patients without AMD to directly assess for oxidative damage. Sections from 4 eyes with no pathologic features of AMD showed no immunofluorescent staining for markers of oxidative damage, while sections from 8 of 12 eyes with advanced geographic atrophy showed evidence of widespread oxidative damage in both posterior and anterior retina. Only 2 of 8 eyes with choroidal neovascularization and 2 of 16 eyes with diffuse drusen and no other signs of AMD showed evidence of oxidative damage. These data suggest that widespread oxidative damage occurs in the retina of some patients with AMD and is more likely to be seen in patients with advanced geographic atrophy. This does not rule out oxidative damage as a pathogenic mechanism in patients with CNV, but suggests that a subpopulation of patients with geographic atrophy may have a major deficiency in the oxidative defense system that puts the majority of cells in the retina at risk for oxidative damage.     

Clinical and Genetic Factors Associated with Progression of Geographic Atrophy Lesions in Age-Related Macular Degeneration

Worldwide, age-related macular degeneration (AMD) is a serious threat to vision loss in individuals over 50 years of age with a pooled prevalence of approximately 9%. For 2020, the number of people afflicted with this condition is estimated to reach 200 million. While AMD lesions presenting as geographic atrophy (GA) show high inter-individual variability, only little is known about prognostic factors. Here, we aimed to elucidate the contribution of clinical, demographic and genetic factors on GA progression. Analyzing the currently largest dataset on GA lesion growth (N = 388), our findings suggest a significant and independent contribution of three factors on GA lesion growth including at least two genetic factors (ARMS2_rs10490924 [P < 0.00088] and C3_rs2230199 [P < 0.00015]) as well as one clinical component (presence of GA in the fellow eye [P < 0.00023]). These correlations jointly explain up to 7.2% of the observed inter-individual variance in GA lesion progression and should be considered in strategy planning of interventional clinical trials aimed at evaluating novel treatment options in advanced GA due to AMD.     

Enrichment of Bruch's Membrane from Human Donor Eyes

Age-related macular degeneration (AMD) is a leading cause of visual impairment in the developed world. The disease manifests itself by the destruction of the center of the retina, called the macula, resulting in the loss of central vision. Early AMD is characterised by the presence of small, yellowish lesions called soft drusen that can progress onto late AMD such as geographic atrophy (dry AMD) or neovascularisation (wet AMD). Although the clinical changes are well described, and the understanding of genetic influences on conferring AMD risk are getting ever more detailed, one area lacking major progress is an understanding of the biochemical consequences of genetic risk. This is partly due to difficulties in understanding the biochemistry of Bruch’s membrane, a very thin extracellular matrix that acts as a biological filter of material from the blood supply and a scaffold on which the retinal pigment epithelial (RPE) cell monolayer resides. Drusen form within Bruch’s membrane and their presence disrupts nutrient flow to the RPE cells. Only by investigating the protein composition of Bruch’s membrane, and indeed how other proteins interact with it, can researchers hope to unravel the biochemical mechanisms underpinning drusen formation, development of AMD and subsequent vision loss. This paper details methodologies for enriching either whole Bruch’s membrane, or just from the macula region, so that it can be used for downstream biochemical analysis, and provide examples of how this is already changing the understanding of Bruch’s membrane biochemistry.     

基于深度学习的作物基因组学和遗传改良

随着世界人口的不断增长、食物需求量的不断增加,以及气候的不断变化,如何提高农作物产量已成为人类面临的一个巨大挑战。传统设计育种耗时长、效率低,已经不能满足新时代的育种需求。随着基因型和表型数据成本的不断降低,以及各种组学数据的爆炸式增长,人工智能技术作为能够在大数据中高效率挖掘信息的工具,在生物学领域受到了广泛关注。人工智能指导的设计育种将大大加快育种的效率,给育种带来革命性的变化。介绍了人工智能特别是深度学习在作物基因组学和遗传改良中的应用,并进行了总结与展望,以期为智能设计育种提供新的思路。     

组学时代下机器学习方法在临床决策支持中的应用

随着组学技术的不断发展,对于不同层次和类型的生物数据的获取方法日益成熟。在疾病诊治过程中会产生大量数据,通过机器学习等人工智能方法解析复杂、多维、多尺度的疾病大数据,构建临床决策支持工具,辅助医生寻找快速且有效的疾病诊疗方案是非常必要的。在此过程中,机器学习等人工智能方法的选择显得尤为重要。基于此,本文首先从类型和算法角度对临床决策支持领域中常用的机器学习等方法进行简要综述,分别介绍了支持向量机、逻辑回归、聚类算法、Bagging、随机森林和深度学习,对机器学习等方法在临床决策支持中的应用做了相应总结和分类,并对它们的优势和不足分别进行讨论和阐述,为临床决策支持中机器学习等人工智能方法的选择提供有效参考。     

Prostaglandin E1 infusion therapy in dry age-related macular degeneration

OBJECTIVE: The pilot study is intended to show whether prostaglandin E1 (PGE1) infusions are able to stop the gradual vision loss in dry age-related macular degeneration (AMD) and, further, to stabilize or improve visual acuity. METHODS: With PGE1 infusions 11 patients with different forms of dry AMD were treated and compared with a control group of 10 untreated patients with dry AMD. The target parameter was the visual acuity, as determined with the ETDRS logMAR charts. Other examinations performed during the study were tests of contrast vision, colour vision and central visual fields, as well as autofluorescence and fluorescein angiography and multifocal electroretinography. RESULTS: On termination of the infusions, six patients showed an increase in visual acuity by at least one line, an improvement that was seen in eight patients 2 months after the end of the infusion therapy. After 6 months, one patient exhibited an improvement of visual acuity by three lines and three patients an improvement by one line. Five patients were found to show no change of their baseline acuity values after 6 months, while two patients exhibited an impairment by one line. The visual acuity in the dry AMD control group without PGE1 treatment had decreased by 0.8 lines on the average after 6 months. Contrast vision, central visual fields and the multifocal electroretinogram showed improvements on the termination of infusions and up to 2 months later; no substantial change of these parameters, as compared with the baseline findings, was seen 6 months after the termination of infusions. SUMMARY: This pilot study suggests that PGE1 infusions have a stabilizing or improving effect on the visual acuity of patients with dry AMD. Owing to the limitations of a pilot study, these results should, however, be validated in a larger, randomized and blinded study.     

Application of radiomics and machine learning in head and neck cancers

With the continuous development of medical image informatics technology, more and more high-throughput quantitative data could be extracted from digital medical images, which has resulted in a new kind of omics-Radiomics. In recent years, in addition to genomics, proteomics and metabolomics, radiomic has attracted the interest of more and more researchers. Compared to other omics, radiomics can be perfectly integrated with clinical data, even with the pathology and molecular biomarker, so that the study can be closer to the clinical reality and more revealing of the tumor development. Mass data will also be generated in this process. Machine learning, due to its own characteristics, has a unique advantage in processing massive radiomic data. By analyzing mass amounts of data with strong clinical relevance, people can construct models that more accurately reflect tumor development and progression, thereby providing the possibility of personalized and sequential treatment of patients. As one of the cancer types whose treatment and diagnosis rely on imaging examination, radiomics has a very broad application prospect in head and neck cancers (HNC). Until now, there have been some notable results in HNC. In this review, we will introduce the concepts and workflow of radiomics and machine learning and their current applications in head and neck cancers, as well as the directions and applications of artificial intelligence in the treatment and diagnosis of HNC.     

Protein–DNA/RNA interactions: Machine intelligence tools and approaches in the era of artificial intelligence and big data

With the development of artificial intelligence (AI) technologies and the availability of large amounts of biological data, computational methods for proteomics have undergone a developmental process from traditional machine learning to deep learning. This review focuses on computational approaches and tools for the prediction of protein – DNA/RNA interactions using machine intelligence techniques. We provide an overview of the development progress of computational methods and summarize the advantages and shortcomings of these methods. We further compiled applications in tasks related to the protein – DNA/RNA interactions, and pointed out possible future application trends. Moreover, biological sequence-digitizing representation strategies used in different types of computational methods are also summarized and discussed.     

AI applications to medical images: From machine learning to deep learning

PurposeArtificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context.MethodsA narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections.ResultsWe first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way.ConclusionsBiomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.     

基于精神影像和人工智能的抑郁症客观生物学标志物研究进展

抑郁症是当今社会上造成首要危害且病因和病理机制最为复杂的精神疾病之一,寻找抑郁症的客观生物学标志物一直是精神医学研究和临床实践的重点和难点,而结合人工智能技术的磁共振影像(magnetic resonance imaging,MRI)技术被认为是目前抑郁症等精神疾病中最有可能率先取得突破进展的客观生物学标志物.然而,当前基于精神影像学的潜在抑郁症客观生物学标志物还未得到一致结论 .本文从精神影像学和以机器学习(machine learning,ML)与深度学习(deep learning, DL)等为代表的人工智能技术相结合的角度,首次从疾病诊断、预防和治疗等三大临床实践环节对抑郁症辅助诊疗的相关研究进行归纳分析,我们发现:a.具有诊断价值的脑区主要集中在楔前叶、扣带回、顶下缘角回、脑岛、丘脑以及海马等;b.具有预防价值的脑区主要集中在楔前叶、中央后回、背外侧前额叶、眶额叶、颞中回等;c.具有预测治疗反应价值的脑区主要集中在楔前叶、扣带回、顶下缘角回、额中回、枕中回、枕下回、舌回等.未来的研究可以通过多中心协作和数据变换提高样本量,同时将多元化的非影像学数据应用于数据挖掘,这将有利于提高人工智能模型的辅助分类能力,为探寻抑郁症的精神影像学客观生物学标志物及其临床应用提供科学证据和参考依据.     

Artificial intelligence and machine learning for medical imaging: A technology review

Artificial intelligence (AI) has recently become a very popular buzzword, as a consequence of disruptive technical advances and impressive experimental results, notably in the field of image analysis and processing. In medicine, specialties where images are central, like radiology, pathology or oncology, have seized the opportunity and considerable efforts in research and development have been deployed to transfer the potential of AI to clinical applications. With AI becoming a more mainstream tool for typical medical imaging analysis tasks, such as diagnosis, segmentation, or classification, the key for a safe and efficient use of clinical AI applications relies, in part, on informed practitioners. The aim of this review is to present the basic technological pillars of AI, together with the state-of-the-art machine learning methods and their application to medical imaging. In addition, we discuss the new trends and future research directions. This will help the reader to understand how AI methods are now becoming an ubiquitous tool in any medical image analysis workflow and pave the way for the clinical implementation of AI-based solutions.     

Sounding out the hidden data: A concise review of deep learning in photoacoustic imaging

The rapidly evolving field of photoacoustic tomography utilizes endogenous chromophores to extract both functional and structural information from deep within tissues. It is this power to perform precise quantitative measurements in vivo—with endogenous or exogenous contrast—that makes photoacoustic tomography highly promising for clinical translation in functional brain imaging, early cancer detection, real-time surgical guidance, and the visualization of dynamic drug responses. Considering photoacoustic tomography has benefited from numerous engineering innovations, it is of no surprise that many of photoacoustic tomography’s current cutting-edge developments incorporate advances from the equally novel field of artificial intelligence. More specifically, alongside the growth and prevalence of graphical processing unit capabilities within recent years has emerged an offshoot of artificial intelligence known as deep learning. Rooted in the solid foundation of signal processing, deep learning typically utilizes a method of optimization known as gradient descent to minimize a loss function and update model parameters. There are already a number of innovative efforts in photoacoustic tomography utilizing deep learning techniques for a variety of purposes, including resolution enhancement, reconstruction artifact removal, undersampling correction, and improved quantification. Most of these efforts have proven to be highly promising in addressing long-standing technical obstacles where traditional solutions either completely fail or make only incremental progress. This concise review focuses on the history of applied artificial intelligence in photoacoustic tomography, presents recent advances at this multifaceted intersection of fields, and outlines the most exciting advances that will likely propagate into promising future innovations.     

Prevalence and Genetic Characteristics of Geographic Atrophy among Elderly Japanese with Age-Related Macular Degeneration

Objective

To investigate the prevalence and genetic characteristics of geographic atrophy (GA) among elderly Japanese with advanced age-related macular degeneration (AMD) in a clinic-based study.

Methods

Two-hundred and ninety consecutive patients with advanced AMD were classified into typical neovascular AMD, polypoidal choroidal vasculopathy (PCV), retinal angiomatous proliferation (RAP) or geographic atrophy (GA). Genetic variants of ARMS2 A69S (rs10490924) and CFH I62V (rs800292) were genotyped using TaqMan Genotyping Assays. The clinical and genetic characteristics were compared between patients with and without GA.

Results

The number of patients diagnosed as having typical neovascular AMD, PCV, RAP and GA were 98 (33.8%), 151 (52.1%), 22 (7.5%) and 19 (6.6%), respectively. Of 19 patients with GA, 13 patients (68.4%) had unilateral GA with exudative AMD in the contralateral eye. Patients with GA were significantly older, with a higher prevalence of reticular pseudodrusen, bilateral involvement of advanced AMD and T-allele frequency of ARMS2 A69S compared with those with typical AMD and PCV; although there were no differences in the genetic and clinical characteristics among patients with GA and RAP.

Conclusions

The prevalence of GA was 6.6% among elderly Japanese with AMD. Patients with GA and RAP exhibited genetic and clinical similarities.     

Radiomics in radiooncology – Challenging the medical physicist

PurposeNoticing the fast growing translation of artificial intelligence (AI) technologies to medical image analysis this paper emphasizes the future role of the medical physicist in this evolving field. Specific challenges are addressed when implementing big data concepts with high-throughput image data processing like radiomics and machine learning in a radiooncology environment to support clinical decisions.MethodsBased on the experience of our interdisciplinary radiomics working group, techniques for processing minable data, extracting radiomics features and associating this information with clinical, physical and biological data for the development of prediction models are described. A special emphasis was placed on the potential clinical significance of such an approach.ResultsClinical studies demonstrate the role of radiomics analysis as an additional independent source of information with the potential to influence the radiooncology practice, i.e. to predict patient prognosis, treatment response and underlying genetic changes. Extending the radiomics approach to integrate imaging, clinical, genetic and dosimetric data (‘panomics’) challenges the medical physicist as member of the radiooncology team.ConclusionsThe new field of big data processing in radiooncology offers opportunities to support clinical decisions, to improve predicting treatment outcome and to stimulate fundamental research on radiation response both of tumor and normal tissue. The integration of physical data (e.g. treatment planning, dosimetric, image guidance data) demands an involvement of the medical physicist in the radiomics approach of radiooncology. To cope with this challenge national and international organizations for medical physics should organize more training opportunities in artificial intelligence technologies in radiooncology.     

Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy

PurposeTo perform a systematic review on the research on the application of artificial intelligence (AI) to imaging published in Italy and identify its fields of application, methods and results.Materials and MethodsA Pubmed search was conducted using terms Artificial Intelligence, Machine Learning, Deep learning, imaging, and Italy as affiliation, excluding reviews and papers outside time interval 2015–2020. In a second phase, participants of the working group AI4MP on Artificial Intelligence of the Italian Association of Physics in Medicine (AIFM) searched for papers on AI in imaging.ResultsThe Pubmed search produced 794 results. 168 studies were selected, of which 122 were from Pubmed search and 46 from the working group. The most used imaging modality was MRI (44%) followed by CT(12%) ad radiography/mammography (11%). The most common clinical indication were neurological diseases (29%) and diagnosis of cancer (25%). Classification was the most common task for AI (57%) followed by segmentation (16%). 65% of studies used machine learning and 35% used deep learning. We observed a rapid increase of research in Italy on artificial intelligence in the last 5 years, peaking at 155% from 2018 to 2019.ConclusionsWe are witnessing an unprecedented interest in AI applied to imaging in Italy, in a diversity of fields and imaging techniques. Further initiatives are needed to build common frameworks and databases, collaborations among different types of institutions, and guidelines for research on AI.     

The LOC387715 gene, smoking, body mass index, environmental associations with advanced age-related macular degeneration

BACKGROUND AND AIMS: Age-related macular degeneration (AMD) is the leading cause of blindness in the Western World. It is now evident that both genetic and environmental factors contribute to disease susceptibility. We tested the hypotheses that (a) a common coding SNP in the LOC387715 gene is associated with advanced AMD (geographic atrophy or choroidal neovascularization), and (b) that modifiable environmental exposures alter AMD susceptibility associated with this SNP. METHODS: A case-control association analysis was performed on participants (530 advanced AMD cases and 280 controls) ascertained as part of the multi-center Age-Related Eye Disease Study. AMD status was determined by the reading center from fundus photographs using the AREDS AMD grading categorization. Environmental risk factor exposure data was collected from participants whose DNA was also genotyped for the LOC387715 gene SNP rs10490924. Multivariate logistic regression analyses were performed. RESULTS AND CONCLUSIONS: The number of risk alleles at the LOC387715 SNP was associated with advanced AMD, with odds ratios (OR) = 3.0 (95% confidence interval (CI) 2.1-4.3) for the GT heterozygous genotype and OR = 12.1 (5.6-26.5) for the homozygous TT risk genotype, after controlling for demographic and behavioral risk factors. The LOC387715 SNP was associated with both forms of advanced AMD. Current cigarette smoking and body mass index were independently related to AMD, controlling for genotype. However, there was no statistical interaction between LOC387715 genotype and smoking with regard to advanced AMD development.     

Clinical applications of deep learning in breast MRI

Deep learning (DL) is one of the most powerful data-driven machine-learning techniques in artificial intelligence (AI). It can automatically learn from raw data without manual feature selection. DL models have led to remarkable advances in data extraction and analysis for medical imaging. Magnetic resonance imaging (MRI) has proven useful in delineating the characteristics and extent of breast lesions and tumors. This review summarizes the current state-of-the-art applications of DL models in breast MRI. Many recent DL models were examined in this field, along with several advanced learning approaches and methods for data normalization and breast and lesion segmentation. For clinical applications, DL-based breast MRI models were proven useful in five aspects: diagnosis of breast cancer, classification of molecular types, classification of histopathological types, prediction of neoadjuvant chemotherapy response, and prediction of lymph node metastasis. For subsequent studies, further improvement in data acquisition and preprocessing is necessary, additional DL techniques in breast MRI should be investigated, and wider clinical applications need to be explored.