Why imaging data alone is not enough: AI-based integration of imaging, omics, and clinical data

Labelling with dynamics: A data-efficient learning paradigm for medical image segmentation

The success of deep learning on image classification and recognition tasks has led to new applications in diverse contexts, including the field of medical imaging. However, two properties of deep neural networks (DNNs) may limit their future use in medical applications. The first is that DNNs require a large amount of labeled training data, and the second is that the deep learning-based models lack interpretability. In this paper, we propose and investigate a data-efficient framework for the task of general medical image segmentation. We address the two aforementioned challenges by introducing domain knowledge in the form of a strong prior into a deep learning framework. This prior is expressed by a customized dynamical system. We performed experiments on two different datasets, namely JSRT and ISIC2016 (heart and lungs segmentation on chest X-ray images and skin lesion segmentation on dermoscopy images). We have achieved competitive results using the same amount of training data compared to the state-of-the-art methods. More importantly, we demonstrate that our framework is extremely data-efficient, and it can achieve reliable results using extremely limited training data. Furthermore, the proposed method is rotationally invariant and insensitive to initialization.

Liquid biopsy for gastric cancer: Techniques, applications, and future directions

After the study of circulating tumor cells in blood through liquid biopsy (LB), this technique has evolved to encompass the analysis of multiple materials originating from the tumor, such as nucleic acids, extracellular vesicles, tumor-educated platelets, and other metabolites. Additionally, research has extended to include the examination of samples other than blood or plasma, such as saliva, gastric juice, urine, or stool. LB techniques are diverse, intricate, and variable. They must be highly sensitive, and pre-analytical, patient, and tumor-related factors significantly influence the detection threshold, diagnostic method selection, and potential results. Consequently, the implementation of LB in clinical practice still faces several challenges. The potential applications of LB range from early cancer detection to guiding targeted therapy or immunotherapy in both early and advanced cancer cases, monitoring treatment response, early identification of relapses, or assessing patient risk. On the other hand, gastric cancer (GC) is a disease often diagnosed at advanced stages. Despite recent advances in molecular understanding, the currently available treatment options have not substantially improved the prognosis for many of these patients. The application of LB in GC could be highly valuable as a non-invasive method for early diagnosis and for enhancing the management and outcomes of these patients. In this comprehensive review, from a pathologist's perspective, we provide an overview of the main options available in LB, delve into the fundamental principles of the most studied techniques, explore the potential utility of LB application in the context of GC, and address the obstacles that need to be overcome in the future to make this innovative technique a game-changer in cancer diagnosis and treatment within clinical practice.

Shedding light on ai in radiology: A systematic review and taxonomy of eye gaze-driven interpretability in deep learning

X-ray imaging plays a crucial role in diagnostic medicine. Yet, a significant portion of the global population lacks access to this essential technology due to a shortage of trained radiologists. Eye-tracking data and deep learning models can enhance X-ray analysis by mapping expert focus areas, guiding automated anomaly detection, optimizing workflow efficiency, and bolstering training methods for novice radiologists. However, the literature shows contradictory results regarding the usefulness of eye-tracking data in deep-learning architectures for abnormality detection. We argue that these discrepancies between studies in the literature are due to (a) the way eye-tracking data is (or is not) processed, (b) the types of deep learning architectures chosen, and (c) the type of application that these architectures will have. We conducted a systematic literature review using PRISMA to address these contradicting results. We analyzed 60 studies that incorporated eye-tracking data in a deep-learning approach for different application goals in radiology. We performed a comparative analysis to understand if eye gaze data contains feature maps that can be useful under a deep learning approach and whether they can promote more interpretable predictions. To the best of our knowledge, this is the first survey in the area that performs a thorough investigation of eye gaze data processing techniques and their impacts in different deep learning architectures for applications such as error detection, classification, object detection, expertise level analysis, fatigue estimation and human attention prediction in medical imaging data. Our analysis resulted in two main contributions: (1) taxonomy that first divides the literature by task, enabling us to analyze the value eye movement can bring for each case and build guidelines regarding architectures and gaze processing techniques adequate for each application, and (2) an overall analysis of how eye gaze data can promote explainability in radiology.

Predicting severe radiation-induced oral mucositis in head and neck cancer patients using integrated baseline CT radiomic, dosimetry, and clinical features: A machine learning approach

Purpose

To establish the early prediction models of radiation-induced oral mucositis (RIOM) based on baseline CT-based radiomic features (RFs), dosimetric data, and clinical features by machine learning models for head and neck cancer (HNC) patients.

Methods

In this single-center prospective study, 49 HNCs treated with curative intensity modulated radiotherapy (IMRT) were enrolled. Baseline CT images (i.e., CT simulation), dosimetric, and clinical features were collected. RIOM was assessed using CTCAE v.5.0. RFs were extracted from manually-contoured oral mucosa structures. Minimum-redundancy-maximum-relevance (mRMR) method was applied to select the most informative radiomics, dosimetric, and clinical features. Then, binary prediction models were constructed for predicting acute RIOM based on the top mRMR-ranked radiomics, dosimetric, and clinical features alone or in combination, using random forest classifier algorithm. The predictive performance of models was assessed using the area under the receiver operating curve (AUC), accuracy, weighted-average based sensitivity, precision, and F1-measure.

Results

Among extracted features, the top 10 RFs, the top 5 dose-volume features, and the top 5 clinical features were selected using mRMR method. The model exploiting the integrated features (10-radiomics + 5-dosimetric + 5-clinical) achieved the best prediction with AUC, accuracy, sensitivity, precision, and F1-measure values of 91.7 %, 90.0 %, 83.0 % 100.0 %, and 91.0 %, respectively. The model developed using baseline CT RFs alone provided the best performance compared to dose-volume features or clinical features alone, with an AUC of 87.0 %.

Conclusion

Our results suggest that the integration of baseline CT radiomic features with dosimetric and clinical features showed promising potential to improve the performance of machine learning models in early prediction of RIOM. The ultimate goal is to personalize radiotherapy for HNC patients.

Computational pathology-based weakly supervised prediction model for MGMT promoter methylation status in glioblastoma

Introduction

The methylation status of oxygen 6-methylguanine-DNA methyltransferase (MGMT) is closely related to the treatment and prognosis of glioblastoma. However, there are currently some challenges in detecting the methylation status of MGMT promoters. The hematoxylin and eosin (H&E)-stained histopathological slides have always been the gold standard for tumor diagnosis.

Methods

In this study, based on the TCGA database and H&E-stained Whole slide images (WSI) of Beijing Tiantan Hospital, we constructed a weakly supervised prediction model of MGMT promoter methylation status in glioblastoma by using two Transformer structure models.

Results

The accuracy scores of this model in the TCGA dataset and our independent dataset were 0.79 (AUC = 0.86) and 0.76 (AUC = 0.83), respectively.

Conclusion

The model demonstrates effective prediction of MGMT promoter methylation status in glioblastoma and exhibits some degree of generalization capability. At the same time, our study also shows that adding Patches automatic screening module to the computational pathology research framework of glioma can significantly improve the model effect.

National Cancer Institute Imaging Data Commons: Toward Transparency, Reproducibility, and Scalability in Imaging Artificial Intelligence

The remarkable advances of artificial intelligence (AI) technology are revolutionizing established approaches to the acquisition, interpretation, and analysis of biomedical imaging data. Development, validation, and continuous refinement of AI tools requires easy access to large high-quality annotated datasets, which are both representative and diverse. The National Cancer Institute (NCI) Imaging Data Commons (IDC) hosts large and diverse publicly available cancer image data collections. By harmonizing all data based on industry standards and colocalizing it with analysis and exploration resources, the IDC aims to facilitate the development, validation, and clinical translation of AI tools and address the well-documented challenges of establishing reproducible and transparent AI processing pipelines. Balanced use of established commercial products with open-source solutions, interconnected by standard interfaces, provides value and performance, while preserving sufficient agility to address the evolving needs of the research community. Emphasis on the development of tools, use cases to demonstrate the utility of uniform data representation, and cloud-based analysis aim to ease adoption and help define best practices. Integration with other data in the broader NCI Cancer Research Data Commons infrastructure opens opportunities for multiomics studies incorporating imaging data to further empower the research community to accelerate breakthroughs in cancer detection, diagnosis, and treatment. Published under a CC BY 4.0 license.

A systematic review exploring the association between the human gut microbiota and brain connectivity in health and disease

A body of pre-clinical evidence shows how the gut microbiota influence brain functioning, including brain connectivity. Linking measures of brain connectivity to the gut microbiota can provide important mechanistic insights into the bi-directional gut-brain communication. In this systematic review, we therefore synthesized the available literature assessing this association, evaluating the degree of consistency in microbiota-connectivity associations. Following the PRISMA guidelines, a PubMed search was conducted, including studies published up to September 1, 2022. We identified 16 studies that met the inclusion criteria. Several bacterial genera, including Prevotella, Bacteroides, Ruminococcus, Blautia, and Collinsella were most frequently reported in association with brain connectivity. Additionally, connectivity of the salience (specifically the insula and anterior cingulate cortex), default mode, and frontoparietal networks were most frequently associated with the gut microbiota, both in terms of microbial diversity and composition. There was no discernible pattern in the association between microbiota and brain connectivity. Altogether, based on our synthesis, there is evidence for an association between the gut microbiota and brain connectivity. However, many findings were poorly replicated across studies, and the specificity of the association is yet unclear. The current studies show substantial inter-study heterogeneity in methodology and reporting, limiting the robustness and reproducibility of the findings and emphasizing the need to harmonize methodological approaches. To enhance comparability and replicability, future research should focus on further standardizing processing pipelines and employing data-driven multivariate analysis strategies.

An Integrated Multi-Omics and Artificial Intelligence Framework for Advance Plant Phenotyping in Horticulture

This review discusses the transformative potential of integrating multi-omics data and artificial intelligence (AI) in advancing horticultural research, specifically plant phenotyping. The traditional methods of plant phenotyping, while valuable, are limited in their ability to capture the complexity of plant biology. The advent of (meta-)genomics, (meta-)transcriptomics, proteomics, and metabolomics has provided an opportunity for a more comprehensive analysis. AI and machine learning (ML) techniques can effectively handle the complexity and volume of multi-omics data, providing meaningful interpretations and predictions. Reflecting the multidisciplinary nature of this area of research, in this review, readers will find a collection of state-of-the-art solutions that are key to the integration of multi-omics data and AI for phenotyping experiments in horticulture, including experimental design considerations with several technical and non-technical challenges, which are discussed along with potential solutions. The future prospects of this integration include precision horticulture, predictive breeding, improved disease and stress response management, sustainable crop management, and exploration of plant biodiversity. The integration of multi-omics and AI holds immense promise for revolutionizing horticultural research and applications, heralding a new era in plant phenotyping.

Medical imaging and multimodal artificial intelligence models for streamlining and enhancing cancer care: opportunities and challenges

INTRODUCTION

Artificial intelligence (AI) has the potential to transform oncologic care. There have been significant developments in AI applications in medical imaging and increasing interest in multimodal models. These are likely to enable improved oncologic care through more precise diagnosis, increasingly in a more personalized and less invasive manner. In this review, we provide an overview of the current state and challenges that clinicians, administrative personnel and policy makers need to be aware of and mitigate for the technology to reach its full potential.

AREAS COVERED

The article provides a brief targeted overview of AI, a high-level review of the current state and future potential AI applications in diagnostic radiology and to a lesser extent digital pathology, focusing on oncologic applications. This is followed by a discussion of emerging approaches, including multimodal models. The article concludes with a discussion of technical, regulatory challenges and infrastructure needs for AI to realize its full potential.

EXPERT OPINION

There is a large volume of promising research, and steadily increasing commercially available tools using AI. For the most advanced and promising precision diagnostic applications of AI to be used clinically, robust and comprehensive quality monitoring systems and informatics platforms will likely be required.

An overview of meta-analyses on radiomics: more evidence is needed to support clinical translation

OBJECTIVE

To conduct an overview of meta-analyses of radiomics studies assessing their study quality and evidence level.

METHODS

A systematical search was updated via peer-reviewed electronic databases, preprint servers, and systematic review protocol registers until 15 November 2022. Systematic reviews with meta-analysis of primary radiomics studies were included. Their reporting transparency, methodological quality, and risk of bias were assessed by PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) 2020 checklist, AMSTAR-2 (A MeaSurement Tool to Assess systematic Reviews, version 2) tool, and ROBIS (Risk Of Bias In Systematic reviews) tool, respectively. The evidence level supporting the radiomics for clinical use was rated.

RESULTS

We identified 44 systematic reviews with meta-analyses on radiomics research. The mean ± standard deviation of PRISMA adherence rate was 65 ± 9%. The AMSTAR-2 tool rated 5 and 39 systematic reviews as low and critically low confidence, respectively. The ROBIS assessment resulted low, unclear and high risk in 5, 11, and 28 systematic reviews, respectively. We reperformed 53 meta-analyses in 38 included systematic reviews. There were 3, 7, and 43 meta-analyses rated as convincing, highly suggestive, and weak levels of evidence, respectively. The convincing level of evidence was rated in (1) T2-FLAIR radiomics for IDH-mutant vs IDH-wide type differentiation in low-grade glioma, (2) CT radiomics for COVID-19 vs other viral pneumonia differentiation, and (3) MRI radiomics for high-grade glioma vs brain metastasis differentiation.

CONCLUSIONS

The systematic reviews on radiomics were with suboptimal quality. A limited number of radiomics approaches were supported by convincing level of evidence.

CLINICAL RELEVANCE STATEMENT

The evidence supporting the clinical application of radiomics are insufficient, calling for researches translating radiomics from an academic tool to a practicable adjunct towards clinical deployment.

AI for life: Trends in artificial intelligence for biotechnology

Due to popular successes (e.g., ChatGPT) Artificial Intelligence (AI) is on everyone's lips today. When advances in biotechnology are combined with advances in AI unprecedented new potential solutions become available. This can help with many global problems and contribute to important Sustainability Development Goals. Current examples include Food Security, Health and Well-being, Clean Water, Clean Energy, Responsible Consumption and Production, Climate Action, Life below Water, or protect, restore and promote sustainable use of terrestrial ecosystems, sustainably manage forests, combat desertification, and halt and reverse land degradation and halt biodiversity loss. AI is ubiquitous in the life sciences today. Topics include a wide range from machine learning and Big Data analytics, knowledge discovery and data mining, biomedical ontologies, knowledge-based reasoning, natural language processing, decision support and reasoning under uncertainty, temporal and spatial representation and inference, and methodological aspects of explainable AI (XAI) with applications of biotechnology. In this pre-Editorial paper, we provide an overview of open research issues and challenges for each of the topics addressed in this special issue. Potential authors can directly use this as a guideline for developing their paper.

Rise of Deep Learning Clinical Applications and Challenges in Omics Data: A Systematic Review

This research aims to review and evaluate the most relevant scientific studies about deep learning (DL) models in the omics field. It also aims to realize the potential of DL techniques in omics data analysis fully by demonstrating this potential and identifying the key challenges that must be addressed. Numerous elements are essential for comprehending numerous studies by surveying the existing literature. For example, the clinical applications and datasets from the literature are essential elements. The published literature highlights the difficulties encountered by other researchers. In addition to looking for other studies, such as guidelines, comparative studies, and review papers, a systematic approach is used to search all relevant publications on omics and DL using different keyword variants. From 2018 to 2022, the search procedure was conducted on four Internet search engines: IEEE Xplore, Web of Science, ScienceDirect, and PubMed. These indexes were chosen because they offer enough coverage and linkages to numerous papers in the biological field. A total of 65 articles were added to the final list. The inclusion and exclusion criteria were specified. Of the 65 publications, 42 are clinical applications of DL in omics data. Furthermore, 16 out of 65 articles comprised the review publications based on single- and multi-omics data from the proposed taxonomy. Finally, only a small number of articles (7/65) were included in papers focusing on comparative analysis and guidelines. The use of DL in studying omics data presented several obstacles related to DL itself, preprocessing procedures, datasets, model validation, and testbed applications. Numerous relevant investigations were performed to address these issues. Unlike other review papers, our study distinctly reflects different observations on omics with DL model areas. We believe that the result of this study can be a useful guideline for practitioners who look for a comprehensive view of the role of DL in omics data analysis.

Missing data in multi-omics integration: Recent advances through artificial intelligence

Biological systems function through complex interactions between various 'omics (biomolecules), and a more complete understanding of these systems is only possible through an integrated, multi-omic perspective. This has presented the need for the development of integration approaches that are able to capture the complex, often non-linear, interactions that define these biological systems and are adapted to the challenges of combining the heterogenous data across 'omic views. A principal challenge to multi-omic integration is missing data because all biomolecules are not measured in all samples. Due to either cost, instrument sensitivity, or other experimental factors, data for a biological sample may be missing for one or more 'omic techologies. Recent methodological developments in artificial intelligence and statistical learning have greatly facilitated the analyses of multi-omics data, however many of these techniques assume access to completely observed data. A subset of these methods incorporate mechanisms for handling partially observed samples, and these methods are the focus of this review. We describe recently developed approaches, noting their primary use cases and highlighting each method's approach to handling missing data. We additionally provide an overview of the more traditional missing data workflows and their limitations; and we discuss potential avenues for further developments as well as how the missing data issue and its current solutions may generalize beyond the multi-omics context.

Utility of adding Radiomics to clinical features in predicting the outcomes of radiotherapy for head and neck cancer using machine learning

BACKGROUND

Radiomics involves the extraction of quantitative information from annotated Computed-Tomography (CT) images, and has been used to predict outcomes in Head and Neck Squamous Cell Carcinoma (HNSCC). Subjecting combined Radiomics and Clinical features to Machine Learning (ML) could offer better predictions of clinical outcomes. This study is a comparative performance analysis of ML models with Clinical, Radiomics, and Clinico-Radiomic datasets for predicting four outcomes of HNSCC treated with Curative Radiation Therapy (RT): Distant Metastases, Locoregional Recurrence, New Primary, and Residual Disease.

METHODOLOGY

The study used retrospective data of 311 HNSCC patients treated with radiotherapy between 2013-2018 at our centre. Binary prediction models were developed for the four outcomes with Clinical-only, Clinico-Radiomic, and Radiomics-only datasets, using three different ML classification algorithms namely, Random Forest (RF), Kernel Support Vector Machine (KSVM), and XGBoost. The best-performing ML algorithms of the three dataset groups was then compared.

RESULTS

The Clinico-Radiomic dataset using KSVM classifier provided the best prediction. Predicted mean testing accuracy for Distant Metastases, Locoregional Recurrence, New Primary, and Residual Disease was 97%, 72%, 99%, and 96%, respectively. The mean area under the receiver operating curve (AUC) was calculated and displayed for all the models using three dataset groups.

CONCLUSION

Clinico-Radiomic dataset improved the predictive ability of ML models over clinical features alone, while models built using Radiomics performed poorly. Radiomics data could therefore effectively supplement clinical data in predicting outcomes.

Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients

Composite MRI scales of central nervous system tissue destruction correlate stronger with clinical outcomes than their individual components in multiple sclerosis (MS) patients. Using machine learning (ML), we previously developed Combinatorial MRI scale (COMRISv1) solely from semi-quantitative (semi-qMRI) biomarkers. Here, we asked how much better COMRISv2 might become with the inclusion of quantitative (qMRI) volumetric features and employment of more powerful ML algorithm. The prospectively acquired MS patients, divided into training (n = 172) and validation (n = 83) cohorts underwent brain MRI imaging and clinical evaluation. Neurological examination was transcribed to NeurEx™ App that automatically computes disability scales. qMRI features were computed by lesion-TOADS algorithm. Modified random forest pipeline selected biomarkers for optimal model(s) in the training cohort. COMRISv2 models validated moderate correlation with cognitive disability [Spearman Rho = 0.674; Lin's concordance coefficient (CCC) = 0.458; p < 0.001] and strong correlations with physical disability (Spearman Rho = 0.830-0.852; CCC = 0.789-0.823; p < 0.001). The NeurEx led to the strongest COMRISv2 model. Addition of qMRI features enhanced performance only of cognitive disability model, likely because semi-qMRI biomarkers measure infratentorial injury with greater accuracy. COMRISv2 models predict most granular clinical scales in MS with remarkable criterion validity, expanding scientific utilization of cohorts with missing clinical data.

Artificial intelligence and machine learning in cancer imaging

An increasing array of tools is being developed using artificial intelligence (AI) and machine learning (ML) for cancer imaging. The development of an optimal tool requires multidisciplinary engagement to ensure that the appropriate use case is met, as well as to undertake robust development and testing prior to its adoption into healthcare systems. This multidisciplinary review highlights key developments in the field. We discuss the challenges and opportunities of AI and ML in cancer imaging; considerations for the development of algorithms into tools that can be widely used and disseminated; and the development of the ecosystem needed to promote growth of AI and ML in cancer imaging.

Turing test-inspired method for analysis of biases prevalent in artificial intelligence-based medical imaging

Due to the growing need to provide better global healthcare, computer-based and robotic healthcare equipment that depend on artificial intelligence has seen an increase in development. In order to evaluate artificial intelligence (AI) in computer technology, the Turing test was created. For evaluating the future generation of medical diagnostics and medical robots, it remains an essential qualitative instrument. We propose a novel methodology to assess AI-based healthcare technology that provided verifiable diagnostic accuracy and statistical robustness. In order to run our test, we used a state-of-the-art AI model and compared it to radiologists for checking how generalized the model is and if any biases are prevalent. We achieved results that can evaluate the performance of our chosen model for this study in a clinical setting and we also applied a quantifiable method for evaluating our modified Turing test results using a meta-analytical evaluation framework. His test provides a translational standard for upcoming AI modalities. Our modified Turing test is a notably strong standard to measure the actual performance of the AI model on a variety of edge cases and normal cases and also helps in detecting if the algorithm is biased towards any one type of case. This method extends the flexibility to detect any prevalent biases and also classify the type of bias.

Multi-omics disease module detection with an explainable Greedy Decision Forest

Machine learning methods can detect complex relationships between variables, but usually do not exploit domain knowledge. This is a limitation because in many scientific disciplines, such as systems biology, domain knowledge is available in the form of graphs or networks, and its use can improve model performance. We need network-based algorithms that are versatile and applicable in many research areas. In this work, we demonstrate subnetwork detection based on multi-modal node features using a novel Greedy Decision Forest (GDF) with inherent interpretability. The latter will be a crucial factor to retain experts and gain their trust in such algorithms. To demonstrate a concrete application example, we focus on bioinformatics, systems biology and particularly biomedicine, but the presented methodology is applicable in many other domains as well. Systems biology is a good example of a field in which statistical data-driven machine learning enables the analysis of large amounts of multi-modal biomedical data. This is important to reach the future goal of precision medicine, where the complexity of patients is modeled on a system level to best tailor medical decisions, health practices and therapies to the individual patient. Our proposed explainable approach can help to uncover disease-causing network modules from multi-omics data to better understand complex diseases such as cancer.

Early stage NSCLS patients' prognostic prediction with multi-information using transformer and graph neural network model

Background:

We proposed a population graph with Transformer-generated and clinical features for the purpose of predicting overall survival (OS) and recurrence-free survival (RFS) for patients with early stage non-small cell lung carcinomas and to compare this model with traditional models.

Methods:

The study included 1705 patients with lung cancer (stages I and II), and a public data set for external validation (n=127). We proposed a graph with edges representing non-imaging patient characteristics and nodes representing imaging tumour region characteristics generated by a pretrained Vision Transformer. The model was compared with a TNM model and a ResNet-Graph model. To evaluate the models' performance, the area under the receiver operator characteristic curve (ROC-AUC) was calculated for both OS and RFS prediction. The Kaplan–Meier method was used to generate prognostic and survival estimates for low- and high-risk groups, along with net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis. An additional subanalysis was conducted to examine the relationship between clinical data and imaging features associated with risk prediction.

Results:

Our model achieved AUC values of 0.785 (95% confidence interval [CI]: 0.716–0.855) and 0.695 (95% CI: 0.603–0.787) on the testing and external data sets for OS prediction, and 0.726 (95% CI: 0.653–0.800) and 0.700 (95% CI: 0.615–0.785) for RFS prediction. Additional survival analyses indicated that our model outperformed the present TNM and ResNet-Graph models in terms of net benefit for survival prediction.

Conclusions:

Our Transformer-Graph model was effective at predicting survival in patients with early stage lung cancer, which was constructed using both imaging and non-imaging clinical features. Some high-risk patients were distinguishable by using a similarity score function defined by non-imaging characteristics such as age, gender, histology type, and tumour location, while Transformer-generated features demonstrated additional benefits for patients whose non-imaging characteristics were non-discriminatory for survival outcomes.

Funding:

The study was supported by the National Natural Science Foundation of China (91959126, 8210071009), and Science and Technology Commission of Shanghai Municipality (20XD1403000, 21YF1438200).

Integrating Biological and Radiological Data in a Structured Repository: a Data Model Applied to the COSMOS Case Study

Integrating the information coming from biological samples with digital data, such as medical images, has gained prominence with the advent of precision medicine. Research in this field faces an ever-increasing amount of data to manage and, as a consequence, the need to structure these data in a functional and standardized fashion to promote and facilitate cooperation among institutions. Inspired by the Minimum Information About BIobank data Sharing (MIABIS), we propose an extended data model which aims to standardize data collections where both biological and digital samples are involved. In the proposed model, strong emphasis is given to the cause-effect relationships among factors as these are frequently encountered in clinical workflows. To test the data model in a realistic context, we consider the Continuous Observation of SMOking Subjects (COSMOS) dataset as case study, consisting of 10 consecutive years of lung cancer screening and follow-up on more than 5000 subjects. The structure of the COSMOS database, implemented to facilitate the process of data retrieval, is therefore presented along with a description of data that we hope to share in a public repository for lung cancer screening research.

Construction of a Diagnostic Model for Lymph Node Metastasis of the Papillary Thyroid Carcinoma Using Preoperative Ultrasound Features and Imaging Omics

In this paper, we mainly adopted 337 patients who had undergone the surgery on lymph node metastasis of papillary thyroid carcinoma (PTC) as the sample population. In order to provide clinical reference for the intelligent decision-making in treatment plan and improvement of prognosis, we utilized ultrasound features and imaging features to construct five early diagnosis models for patients based on the ultrasound features, imaging features, and combined features. The model integrated with broad learning system (BLS) showed the best performance, with the area under the curve (AUC) of 0.857 (95% confidence interval (CI): 0.811–0.902)) and the accuracy of 0.805 (95% CI: 0.759–0.850). For demographic and clinical features, the prediction effect was also good, with the AUC more than 0.700.

How responsible is AI- identification of key public concerns using Sentiment Analysis and Topic Modeling

Many businesses around the World are adopting AI with the hope of increasing their top-line and bottom-line numbers. The COVID19 pandemic has further accelerated the journey. While AI technology promising to bring enormous benefits, the challenges come in similar proportions. In the current form, the requirements for transparency and trust are relatively low for AI systems. On the other hand, there is a lot of regulatory pressure for AI systems to be trustworthy and responsible. Challenges still exist both on the methods and theory side and how explanations are used in practice. The objective of this paper is to analyze Twitter data to extract sentiments and opinions in unstructured text. We attempted to use contextual text analytics to categorize the twitter data to understand the positive or negative sentiments and feelings for the AI Ethical challenges and highlight the key concerns. Text clustering has also been performed on positive and negative sentiments to understand the key themes behind people's concern.

MRI radiomic features-based machine learning approach to classify ischemic stroke onset time

PURPOSE

We aimed to investigate the ability of MRI radiomics features-based machine learning (ML) models to classify the time since stroke onset (TSS), which could aid in stroke assessment and treatment options.

METHODS

This study involved 84 patients with acute ischemic stroke due to anterior circulation artery occlusion (51 in the training cohort and 33 in the independent test cohort). Region of infarct segmentation was manually outlined by 3D-slicer software. Image processing including registration, normalization and radiomics features calculation were done in R (version 3.6.1). A total of 4312 radiomic features from each image sequence were captured and used in six ML models to estimate stroke onset time for binary classification (≤ 4.5 h). Receiver-operating characteristic curve (ROC) and other parameters were calculated to evaluate the performance of the models in both training and test cohorts.

RESULTS

Twelve radiomics and six clinic features were selected to construct the ML models for TSS classification. The deep learning model-based DWI/ADC radiomic features performed the best for binary TSS classification in the independent test cohort, with an AUC of 0.754, accuracy of 0.788, sensitivity of 0.952, specificity of 0.500, positive predictive value of 0.769, and negative predictive value of 0.857, respectively. Furthermore, adding clinical information did not improve the performance of the DWI/ADC-based deep learning model. The TSS prediction models can be visited at: http://123.57.65.199:3838/deeptss/ .

CONCLUSIONS

A unique deep learning model based on DWI/ADC radiomic features was constructed for TSS classification, which could aid in decision making for thrombolysis in patients with unknown stroke onset.

Computational approaches leveraging integrated connections of multi-omic data toward clinical applications

In line with the advances in high-throughput technologies, multiple omic datasets have accumulated to study biological systems and diseases coherently. No single omics data type is capable of fully representing cellular activity. The complexity of the biological processes arises from the interactions between omic entities such as genes, proteins, and metabolites. Therefore, multi-omic data integration is crucial but challenging. The impact of the molecular alterations in multi-omic data is not local in the neighborhood of the altered gene or protein; rather, the impact diffuses in the network and changes the functionality of multiple signaling pathways and regulation of the gene expression. Additionally, multi-omic data is high-dimensional and has background noise. Several integrative approaches have been developed to accurately interpret the multi-omic datasets, including machine learning, network-based methods, and their combination. In this review, we overview the most recent integrative approaches and tools with a focus on network-based methods. We then discuss these approaches according to their specific applications, from disease-network and biomarker identification to patient stratification, drug discovery, and repurposing.

Biomedical Ontologies to Guide AI Development in Radiology

The advent of deep learning has engendered renewed and rapidly growing interest in artificial intelligence (AI) in radiology to analyze images, manipulate textual reports, and plan interventions. Applications of deep learning and other AI approaches must be guided by sound medical knowledge to assure that they are developed successfully and that they address important problems in biomedical research or patient care. To date, AI has been applied to a limited number of real-world radiology applications. As AI systems become more pervasive and are applied more broadly, they will benefit from medical knowledge on a larger scale, such as that available through computer-based approaches. A key approach to represent computer-based knowledge in a particular domain is an ontology. As defined in informatics, an ontology defines a domain's terms through their relationships with other terms in the ontology. Those relationships, then, define the terms' semantics, or "meaning." Biomedical ontologies commonly define the relationships between terms and more general terms, and can express causal, part-whole, and anatomic relationships. Ontologies express knowledge in a form that is both human-readable and machine-computable. Some ontologies, such as RSNA's RadLex radiology lexicon, have been applied to applications in clinical practice and research, and may be familiar to many radiologists. This article describes how ontologies can support research and guide emerging applications of AI in radiology, including natural language processing, image-based machine learning, radiomics, and planning.

High-performance deep learning pipeline predicts individuals in mixtures of DNA using sequencing data

In this study, we proposed a deep learning (DL) model for classifying individuals from mixtures of DNA samples using 27 short tandem repeats and 94 single nucleotide polymorphisms obtained through massively parallel sequencing protocol. The model was trained/tested/validated with sequenced data from 6 individuals and then evaluated using mixtures from forensic DNA samples. The model successfully identified both the major and the minor contributors with 100% accuracy for 90 DNA mixtures, that were manually prepared by mixing sequence reads of 3 individuals at different ratios. Furthermore, the model identified 100% of the major contributors and 50-80% of the minor contributors in 20 two-sample external-mixed-samples at ratios of 1:39 and 1:9, respectively. To further demonstrate the versatility and applicability of the pipeline, we tested it on whole exome sequence data to classify subtypes of 20 breast cancer patients and achieved an area under curve of 0.85. Overall, we present, for the first time, a complete pipeline, including sequencing data processing steps and DL steps, that is applicable across different NGS platforms. We also introduced a sliding window approach, to overcome the sequence length variation problem of sequencing data, and demonstrate that it improves the model performance dramatically.

Artificial Intelligence and Radiomics in Head and Neck Cancer Care: Opportunities, Mechanics, and Challenges

The advent of large-scale high-performance computing has allowed the development of machine-learning techniques in oncologic applications. Among these, there has been substantial growth in radiomics (machine-learning texture analysis of images) and artificial intelligence (which uses deep-learning techniques for "learning algorithms"); however, clinical implementation has yet to be realized at scale. To improve implementation, opportunities, mechanics, and challenges, models of imaging-enabled artificial intelligence approaches need to be understood by clinicians who make the treatment decisions. This article aims to convey the basic conceptual premises of radiomics and artificial intelligence using head and neck cancer as a use case. This educational overview focuses on approaches for head and neck oncology imaging, detailing current research efforts and challenges to implementation.

Exploratory study on classification of diabetes mellitus through a combined Random Forest Classifier

BACKGROUND

Diabetes Mellitus (DM) has become the third chronic non-communicable disease that hits patients after tumors, cardiovascular and cerebrovascular diseases, and has become one of the major public health problems in the world. Therefore, it is of great importance to identify individuals at high risk for DM in order to establish prevention strategies for DM.

METHODS

Aiming at the problem of high-dimensional feature space and high feature redundancy of medical data, as well as the problem of data imbalance often faced. This study explored different supervised classifiers, combined with SVM-SMOTE and two feature dimensionality reduction methods (Logistic stepwise regression and LAASO) to classify the diabetes survey sample data with unbalanced categories and complex related factors. Analysis and discussion of the classification results of 4 supervised classifiers based on 4 data processing methods. Five indicators including Accuracy, Precision, Recall, F1-Score and AUC are selected as the key indicators to evaluate the performance of the classification model.

RESULTS

According to the result, Random Forest Classifier combining SVM-SMOTE resampling technology and LASSO feature screening method (Accuracy = 0.890, Precision = 0.869, Recall = 0.919, F1-Score = 0.893, AUC = 0.948) proved the best way to tell those at high risk of DM. Besides, the combined algorithm helps enhance the classification performance for prediction of high-risk people of DM. Also, age, region, heart rate, hypertension, hyperlipidemia and BMI are the top six most critical characteristic variables affecting diabetes.

CONCLUSIONS

The Random Forest Classifier combining with SVM-SMOTE and LASSO feature reduction method perform best in identifying high-risk people of DM from individuals. And the combined method proposed in the study would be a good tool for early screening of DM.

GENERATOR Breast DataMart-The Novel Breast Cancer Data Discovery System for Research and Monitoring: Preliminary Results and Future Perspectives

Background: Artificial Intelligence (AI) is increasingly used for process management in daily life. In the medical field AI is becoming part of computerized systems to manage information and encourage the generation of evidence. Here we present the development of the application of AI to IT systems present in the hospital, for the creation of a DataMart for the management of clinical and research processes in the field of breast cancer. Materials and methods: A multidisciplinary team of radiation oncologists, epidemiologists, medical oncologists, breast surgeons, data scientists, and data management experts worked together to identify relevant data and sources located inside the hospital system. Combinations of open-source data science packages and industry solutions were used to design the target framework. To validate the DataMart directly on real-life cases, the working team defined tumoral pathology and clinical purposes of proof of concepts (PoCs). Results: Data were classified into “Not organized, not ‘ontologized’ data”, “Organized, not ‘ontologized’ data”, and “Organized and ‘ontologized’ data”. Archives of real-world data (RWD) identified were platform based on ontology, hospital data warehouse, PDF documents, and electronic reports. Data extraction was performed by direct connection with structured data or text-mining technology. Two PoCs were performed, by which waiting time interval for radiotherapy and performance index of breast unit were tested and resulted available. Conclusions: GENERATOR Breast DataMart was created for supporting breast cancer pathways of care. An AI-based process automatically extracts data from different sources and uses them for generating trend studies and clinical evidence. Further studies and more proof of concepts are needed to exploit all the potentials of this system.

Explainable AI and Multi-Modal Causability in Medicine

Progress in statistical machine learning made AI in medicine successful, in certain classification tasks even beyond human level performance. Nevertheless, correlation is not causation and successful models are often complex “black-boxes”, which make it hard to understand why a result has been achieved. The explainable AI (xAI) community develops methods, e. g. to highlight which input parameters are relevant for a result; however, in the medical domain there is a need for causability: In the same way that usability encompasses measurements for the quality of use, causability encompasses measurements for the quality of explanations produced by xAI. The key for future human-AI interfaces is to map explainability with causability and to allow a domain expert to ask questions to understand why an AI came up with a result, and also to ask “what-if” questions (counterfactuals) to gain insight into the underlying independent explanatory factors of a result. A multi-modal causability is important in the medical domain because often different modalities contribute to a result.

From Hume to Wuhan: An Epistemological Journey on the Problem of Induction in COVID-19 Machine Learning Models and its Impact Upon Medical Research

Advances in computer science have transformed the way artificial intelligence is employed in academia, with Machine Learning (ML) methods easily available to researchers from diverse areas thanks to intuitive frameworks that yield extraordinary results. Notwithstanding, current trends in the mainstream ML community tend to emphasise wins over knowledge, putting the scientific method aside, and focusing on maximising metrics of interest. Methodological flaws lead to poor justification of method choice, which in turn leads to disregard the limitations of the methods employed, ultimately putting at risk the translation of solutions into real-world clinical settings. This work exemplifies the impact of the problem of induction in medical research, studying the methodological issues of recent solutions for computer-aided diagnosis of COVID-19 from chest X-Ray images.

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.

Artificial intelligence and hybrid imaging: the best match for personalized medicine in oncology

Artificial intelligence (AI) refers to a field of computer science aimed to perform tasks typically requiring human intelligence. Currently, AI is recognized in the broader technology radar within the five key technologies which emerge for their wide-ranging applications and impact in communities, companies, business, and value chain framework alike. However, AI in medical imaging is at an early phase of development, and there are still hurdles to take related to reliability, user confidence, and adoption. The present narrative review aimed to provide an overview on AI-based approaches (distributed learning, statistical learning, computer-aided diagnosis and detection systems, fully automated image analysis tool, natural language processing) in oncological hybrid medical imaging with respect to clinical tasks (detection, contouring and segmentation, prediction of histology and tumor stage, prediction of mutational status and molecular therapies targets, prediction of treatment response, and outcome). Particularly, AI-based approaches have been briefly described according to their purpose and, finally lung cancer-being one of the most extensively malignancy studied by hybrid medical imaging-has been used as illustrative scenario. Finally, we discussed clinical challenges and open issues including ethics, validation strategies, effective data-sharing methods, regulatory hurdles, educational resources, and strategy to facilitate the interaction among different stakeholders. Some of the major changes in medical imaging will come from the application of AI to workflow and protocols, eventually resulting in improved patient management and quality of life. Overall, several time-consuming tasks could be automatized. Machine learning algorithms and neural networks will permit sophisticated analysis resulting not only in major improvements in disease characterization through imaging, but also in the integration of multiple-omics data (i.e., derived from pathology, genomic, proteomics, and demographics) for multi-dimensional disease featuring. Nevertheless, to accelerate the transition of the theory to practice a sustainable development plan considering the multi-dimensional interactions between professionals, technology, industry, markets, policy, culture, and civil society directed by a mindset which will allow talents to thrive is necessary.

Plant Biosystems Design Research Roadmap 1.0

Human life intimately depends on plants for food, biomaterials, health, energy, and a sustainable environment. Various plants have been genetically improved mostly through breeding, along with limited modification via genetic engineering, yet they are still not able to meet the ever-increasing needs, in terms of both quantity and quality, resulting from the rapid increase in world population and expected standards of living. A step change that may address these challenges would be to expand the potential of plants using biosystems design approaches. This represents a shift in plant science research from relatively simple trial-and-error approaches to innovative strategies based on predictive models of biological systems. Plant biosystems design seeks to accelerate plant genetic improvement using genome editing and genetic circuit engineering or create novel plant systems through de novo synthesis of plant genomes. From this perspective, we present a comprehensive roadmap of plant biosystems design covering theories, principles, and technical methods, along with potential applications in basic and applied plant biology research. We highlight current challenges, future opportunities, and research priorities, along with a framework for international collaboration, towards rapid advancement of this emerging interdisciplinary area of research. Finally, we discuss the importance of social responsibility in utilizing plant biosystems design and suggest strategies for improving public perception, trust, and acceptance.

Towards effective machine learning in medical imaging analysis: A novel approach and expert evaluation of high-grade glioma 'ground truth' simulation on MRI

PURPOSE/OBJECTIVE(S)

Gliomas are uniformly fatal brain tumours with significant neurological and quality of life detriment to patients. Improvement in outcomes has remained largely unchanged in nearly 20 years. MRI (magnetic resonance imaging) is often used in diagnosis and management. Machine learning analyses of large-scale MRI data are pivotal in advancing the diagnosis, management and improve outcomes in neuro-oncology. A common challenge to robust machine learning approaches is the lack of large 'ground truth' datasets in supervised learning for building classification and prediction models. The creation of these datasets relies on human-expert input and is time-consuming and subjective error-prone, limiting effective machine learning applications. Simulation of mechanistic aspects such as geometry, location and physical properties of brain tumours can generate large-scale ground-truth datasets allowing for comparison of analysis techniques in clinical applications. We aimed to develop a transparent and convenient method for building 'ground truth' presentations of simulated glioma lesions on anatomical MRI.

MATERIALS/METHODS

The simulation workflow was created using the Feature Manipulation Engine (FME®), a data integration platform specializing in the spatial data processing. By compiling and integrating FME's functions to read, integrate, transform, validate, save, and display MRI data, and experimenting with ways to manipulate the parameters concerning location, size, shape, and signal intensity with the presentations of glioma, we were able to generate simulated appearances of high-grade gliomas on gadolinium-based high-resolution 3D T1-weighted MRI (1 mm³). Data of patients with canonical high-grade tumours were used as real-world tumours for validating the accuracy of the simulation. Twenty raters who are experienced with brain tumour interpretation on MRI independently completed a survey, designed to distinguish simulated and real-world brain tumours. Sensitivity and specificity were calculated for assessing the performance of the approach with the binary classification of simulated vs real-world tumours. Correlation and regression were used in run time analysis, assessing the software toolset's efficiency in producing different numbers of simulated lesions. Differences in the group means were examined using the non-parametric Kruskal-Wallis test.

RESULTS

The simulation method was developed as an interpretable and useful workflow for the easy creation of tumour simulations and incorporation into 3D MRI. A linear increase in the running time and memory usage was observed with an increasing number of generated lesions. The respondents' accuracy rate ranged between 33.3 and 83.3 %. The sensitivity and specificity were low for a human expert to differentiate simulated lesions from real gliomas (0.43 and 0.58) or vice versa (0.65 and 0.62). The mean scores ranking the real-world gliomas did not differ between the simulated and real tumours.

CONCLUSION

The reliable and user-friendly software method can allow for robust simulation of high-grade glioma on MRI. Ongoing research efforts include optimizing the workflow for generating glioma datasets as well as adapting it to simulating additional MRI brain changes.

Artificial Intelligence Tools for Refining Lung Cancer Screening

Nearly one-quarter of all cancer deaths worldwide are due to lung cancer, making this disease the leading cause of cancer death among both men and women. The most important determinant of survival in lung cancer is the disease stage at diagnosis, thus developing an effective screening method for early diagnosis has been a long-term goal in lung cancer care. In the last decade, and based on the results of large clinical trials, lung cancer screening programs using low-dose computer tomography (LDCT) in high-risk individuals have been implemented in some clinical settings, however, this method has various limitations, especially a high false-positive rate which eventually results in a number of unnecessary diagnostic and therapeutic interventions among the screened subjects. By using complex algorithms and software, artificial intelligence (AI) is capable to emulate human cognition in the analysis, interpretation, and comprehension of complicated data and currently, it is being successfully applied in various healthcare settings. Taking advantage of the ability of AI to quantify information from images, and its superior capability in recognizing complex patterns in images compared to humans, AI has the potential to aid clinicians in the interpretation of LDCT images obtained in the setting of lung cancer screening. In the last decade, several AI models aimed to improve lung cancer detection have been reported. Some algorithms performed equal or even outperformed experienced radiologists in distinguishing benign from malign lung nodules and some of those models improved diagnostic accuracy and decreased the false-positive rate. Here, we discuss recent publications in which AI algorithms are utilized to assess chest computer tomography (CT) scans imaging obtaining in the setting of lung cancer screening.

OpSeF: Open Source Python Framework for Collaborative Instance Segmentation of Bioimages

Various pre-trained deep learning models for the segmentation of bioimages have been made available as developer-to-end-user solutions. They are optimized for ease of use and usually require neither knowledge of machine learning nor coding skills. However, individually testing these tools is tedious and success is uncertain. Here, we present the Open Segmentation Framework (OpSeF), a Python framework for deep learning-based instance segmentation. OpSeF aims at facilitating the collaboration of biomedical users with experienced image analysts. It builds on the analysts' knowledge in Python, machine learning, and workflow design to solve complex analysis tasks at any scale in a reproducible, well-documented way. OpSeF defines standard inputs and outputs, thereby facilitating modular workflow design and interoperability with other software. Users play an important role in problem definition, quality control, and manual refinement of results. OpSeF semi-automates preprocessing, convolutional neural network (CNN)-based segmentation in 2D or 3D, and postprocessing. It facilitates benchmarking of multiple models in parallel. OpSeF streamlines the optimization of parameters for pre- and postprocessing such, that an available model may frequently be used without retraining. Even if sufficiently good results are not achievable with this approach, intermediate results can inform the analysts in the selection of the most promising CNN-architecture in which the biomedical user might invest the effort of manually labeling training data. We provide Jupyter notebooks that document sample workflows based on various image collections. Analysts may find these notebooks useful to illustrate common segmentation challenges, as they prepare the advanced user for gradually taking over some of their tasks and completing their projects independently. The notebooks may also be used to explore the analysis options available within OpSeF in an interactive way and to document and share final workflows. Currently, three mechanistically distinct CNN-based segmentation methods, the U-Net implementation used in Cellprofiler 3.0, StarDist, and Cellpose have been integrated within OpSeF. The addition of new networks requires little; the addition of new models requires no coding skills. Thus, OpSeF might soon become both an interactive model repository, in which pre-trained models might be shared, evaluated, and reused with ease.

Study Processes and Applications of Ultrasomics in Precision Medicine

Ultrasomics is the science of transforming digitally encrypted medical ultrasound images that hold information related to tumor pathophysiology into mineable high-dimensional data. Ultrasomics data have the potential to uncover disease characteristics that are not found with the naked eye. The task of ultrasomics is to quantify the state of diseases using distinctive imaging algorithms and thereby provide valuable information for personalized medicine. Ultrasomics is a powerful tool in oncology but can also be applied to other medical problems for which a disease is imaged. To date there is no comprehensive review focusing on ultrasomics. Here, we describe how ultrasomics works and its capability in diagnosing disease in different organs, including breast, liver, and thyroid. Its pitfalls, challenges and opportunities are also discussed.

The ethics of AI in health care: A mapping review

This article presents a mapping review of the literature concerning the ethics of artificial intelligence (AI) in health care. The goal of this review is to summarise current debates and identify open questions for future research. Five literature databases were searched to support the following research question: how can the primary ethical risks presented by AI-health be categorised, and what issues must policymakers, regulators and developers consider in order to be 'ethically mindful? A series of screening stages were carried out-for example, removing articles that focused on digital health in general (e.g. data sharing, data access, data privacy, surveillance/nudging, consent, ownership of health data, evidence of efficacy)-yielding a total of 156 papers that were included in the review. We find that ethical issues can be (a) epistemic, related to misguided, inconclusive or inscrutable evidence; (b) normative, related to unfair outcomes and transformative effectives; or (c) related to traceability. We further find that these ethical issues arise at six levels of abstraction: individual, interpersonal, group, institutional, and societal or sectoral. Finally, we outline a number of considerations for policymakers and regulators, mapping these to existing literature, and categorising each as epistemic, normative or traceability-related and at the relevant level of abstraction. Our goal is to inform policymakers, regulators and developers of what they must consider if they are to enable health and care systems to capitalise on the dual advantage of ethical AI; maximising the opportunities to cut costs, improve care, and improve the efficiency of health and care systems, whilst proactively avoiding the potential harms. We argue that if action is not swiftly taken in this regard, a new 'AI winter' could occur due to chilling effects related to a loss of public trust in the benefits of AI for health care.

Preoperative CT-based Deep Learning Model for Predicting Disease-Free Survival in Patients with Lung Adenocarcinomas

Background Deep learning models have the potential for lung cancer prognostication, but model output as an independent prognostic factor must be validated with clinical risk factors. Purpose To develop and validate a preoperative CT-based deep learning model for predicting disease-free survival in patients with lung adenocarcinoma. Materials and Methods In this retrospective study, a deep learning model was trained to extract prognostic information from preoperative CT examinations. Data set 1 for training, tuning, and internal validation consisted of patients with T1-4N0M0 adenocarcinoma resected between 2009 and 2015. Data set 2 for external validation included patients with clinical T1-2aN0M0 (stage I) adenocarcinomas resected in 2014. Discrimination was assessed by using Harrell C index and benchmarked against the clinical T category. The Greenwood-Nam-D'Agostino test was used for model calibration. The multivariable-adjusted hazard ratios (HRs) were analyzed with clinical prognostic factors by using the Cox regression. Results Evaluated were 800 patients (median age, 64 years; interquartile range, 56-70 years; 450 women) in data set 1 and 108 patients (median age, 63 years; interquartile range, 57-71 years; 60 women) in data set 2. The C indexes were 0.74-0.80 in the internal validation and 0.71-0.78 in the external validation, both comparable with the clinical T category (0.78 in the internal validation and 0.74 in the external validation; all P > .05). The model exhibited good calibration in all data sets (P > .05). Multivariable Cox regression revealed that model outputs were independent prognostic factors (hazard ratio [HR] of the categorical output, 2.5 [95% confidence interval {CI}: 1.03, 5.9; P = .04] in the internal validation and 3.6 [95% CI: 1.6, 8.5; P = .003] in the external validation). Other than the deep learning model, only smoking status (HR, 3.4; 95% CI: 1.4, 8.5; P = .007) contributed further to prediction of disease-free survival for patients after resection of clinical stage I adenocarcinomas. Conclusion A deep learning model for chest CT predicted disease-free survival for patients undergoing an operation for clinical stage I lung adenocarcinoma. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Shaffer in this issue.

Open Data for Differential Network Analysis in Glioma

The complexity of cancer diseases demands bioinformatic techniques and translational research based on big data and personalized medicine. Open data enables researchers to accelerate cancer studies, save resources and foster collaboration. Several tools and programming approaches are available for analyzing data, including annotation, clustering, comparison and extrapolation, merging, enrichment, functional association and statistics. We exploit openly available data via cancer gene expression analysis, we apply refinement as well as enrichment analysis via gene ontology and conclude with graph-based visualization of involved protein interaction networks as a basis for signaling. The different databases allowed for the construction of huge networks or specified ones consisting of high-confidence interactions only. Several genes associated to glioma were isolated via a network analysis from top hub nodes as well as from an outlier analysis. The latter approach highlights a mitogen-activated protein kinase next to a member of histondeacetylases and a protein phosphatase as genes uncommonly associated with glioma. Cluster analysis from top hub nodes lists several identified glioma-associated gene products to function within protein complexes, including epidermal growth factors as well as cell cycle proteins or RAS proto-oncogenes. By using selected exemplary tools and open-access resources for cancer research and differential network analysis, we highlight disturbed signaling components in brain cancer subtypes of glioma.