Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

The value of S-Detect in improving the diagnostic performance of radiologists for the differential diagnosis of thyroid nodules.

In Medical ultrasonography

AIMS : To compare the diagnostic value of S-Detect (a computer aided diagnosis system using deep learning) in differentiating thyroid nodules in radiologists with different experience and to assess if S-Detect can improve the diagnostic performance of radiologists.

MATERIALS AND METHODS : Between February 2018 and October 2019, 204 thyroid nodules in 181 patients were included. An experienced radiologist performed ultrasound for thyroid nodules and obtained the result of S-Detect. Four radiologists with different experience on thyroid ultrasound (Radiologist 1, 2, 3, 4 with 1, 4, 9, 20 years, respectively) analyzed the conventional ultrasound images of each thyroid nodule and made a diagnosis of "benign" or "malignant" based on the TI-RADS category. After referring to S-Detect results, they re-evaluated the diagnoses. The diagnostic performance of radiologists was analyzed before and after referring to the results of S-Detect.

RESULTS : The accuracy, sensitivity, specificity, positive predictive value and negative predictive value of S-Detect were 77.0, 91.3, 65.2, 68.3 and 90.1%, respectively. In comparison with the less experienced radiologists (radiologist 1 and 2), S-Detect had a higher area under receiver operating characteristic curve (AUC), accuracy and specificity (p <0.05). In comparison with the most experienced radiologist, the diagnostic accuracy and AUC were lower (p<0.05). In the less experienced radiologists, the diagnostic accuracy, specificity and AUC were significantly improved when combined with S-Detect (p<0.05), but not for experienced radiologists (radiologist 3 and 4) (p>0.05).

CONCLUSIONS : S-Detect may become an additional diagnostic method for the diagnosis of thyroid nodules and improve the diagnostic performance of less experienced radiologists.

Wei Qi, Zeng Shu-E, Wang Li-Ping, Yan Yu-Jing, Wang Ting, Xu Jian-Wei, Zhang Meng-Yi, Lv Wen-Zhi, Cui Xin-Wu, Dietrich Christoph F

2020-Jul-06

General General

Deep learning for inferring transcription factor binding sites.

In Current opinion in systems biology

Deep learning is a powerful tool for predicting transcription factor binding sites from DNA sequence. Despite their high predictive accuracy, there are no guarantees that a high-performing deep learning model will learn causal sequence-function relationships. Thus a move beyond performance comparisons on benchmark datasets is needed. Interpreting model predictions is a powerful approach to identify which features drive performance gains and ideally provide insight into the underlying biological mechanisms. Here we highlight timely advances in deep learning for genomics, with a focus on inferring transcription factors binding sites. We describe recent applications, model architectures, and advances in local and global model interpretability methods, then conclude with a discussion on future research directions.

Koo Peter K, Ploenzke Matt

2020-Feb

Deep learning, interpretability, motifs, neural networks, transcription factor binding

Pathology Pathology

Integration of the ImageJ Ecosystem in the KNIME Analytics Platform.

In Frontiers in computer science

Open-source software tools are often used for analysis of scientific image data due to their flexibility and transparency in dealing with rapidly evolving imaging technologies. The complex nature of image analysis problems frequently requires many tools to be used in conjunction, including image processing and analysis, data processing, machine learning and deep learning, statistical analysis of the results, visualization, correlation to heterogeneous but related data, and more. However, the development, and therefore application, of these computational tools is impeded by a lack of integration across platforms. Integration of tools goes beyond convenience, as it is impractical for one tool to anticipate and accommodate the current and future needs of every user. This problem is emphasized in the field of bioimage analysis, where various rapidly emerging methods are quickly being adopted by researchers. ImageJ is a popular open-source image analysis platform, with contributions from a global community resulting in hundreds of specialized routines for a wide array of scientific tasks. ImageJ's strength lies in its accessibility and extensibility, allowing researchers to easily improve the software to solve their image analysis tasks. However, ImageJ is not designed for development of complex end-to-end image analysis workflows. Scientists are often forced to create highly specialized and hard-to-reproduce scripts to orchestrate individual software fragments and cover the entire life-cycle of an analysis of an image dataset. KNIME Analytics Platform, a user-friendly data integration, analysis, and exploration workflow system, was designed to handle huge amounts of heterogeneous data in a platform-agnostic, computing environment and has been successful in meeting complex end-to-end demands in several communities, such as cheminformatics and mass spectrometry. Similar needs within the bioimage analysis community led to the creation of the KNIME Image Processing extension which integrates ImageJ into KNIME Analytics Platform, enabling researchers to develop reproducible and scalable workflows, integrating a diverse range of analysis tools. Here we present how users and developers alike can leverage the ImageJ ecosystem via the KNIME Image Processing extension to provide robust and extensible image analysis within KNIME workflows. We illustrate the benefits of this integration with examples, as well as representative scientific use cases.

Dietz Christian, Rueden Curtis T, Helfrich Stefan, Dobson Ellen T A, Horn Martin, Eglinger Jan, Evans Edward L, McLean Dalton T, Novitskaya Tatiana, Ricke William A, Sherer Nathan M, Zijlstra Andries, Berthold Michael R, Eliceiri Kevin W

2020-Mar

Bioimaging, Fiji, ImageJ, KNIME, computational workflows, image analysis, interoperability, open-source

General General

Machine learning analysis of serum biomarkers for cardiovascular risk assessment in chronic kidney disease.

In Clinical kidney journal

Background : Chronic kidney disease (CKD) patients show an increased burden of atherosclerosis and high risk of cardiovascular events (CVEs). There are several biomarkers described as being associated with CVEs, but their combined effectiveness in cardiovascular risk stratification in CKD has not been tested. The objective of this work is to analyse the combined ability of 19 biomarkers associated with atheromatous disease in predicting CVEs after 4 years of follow-up in a subcohort of the NEFRONA study in individuals with different stages of CKD without previous CVEs.

Methods : Nineteen putative biomarkers were quantified in 1366 patients (73 CVEs) and their ability to predict CVEs was ranked by random survival forest (RSF) analysis. The factors associated with CVEs were tested in Fine and Gray (FG) regression models, with non-cardiovascular death and kidney transplant as competing events.

Results : RSF analysis detected several biomarkers as relevant for predicting CVEs. Inclusion of those biomarkers in an FG model showed that high levels of osteopontin, osteoprotegerin, matrix metalloproteinase-9 and vascular endothelial growth factor increased the risk for CVEs, but only marginally improved the discrimination obtained with classical clinical parameters: concordance index 0.744 (95% confidence interval 0.609-0.878) versus 0.723 (0.592-0.854), respectively. However, in individuals with diabetes treated with antihypertensives and lipid-lowering drugs, the determination of these biomarkers could help to improve cardiovascular risk estimates.

Conclusions : We conclude that the determination of four biomarkers in the serum of CKD patients could improve cardiovascular risk prediction in high-risk individuals.

Forné Carles, Cambray Serafi, Bermudez-Lopez Marcelino, Fernandez Elvira, Bozic Milica, Valdivielso Jose M

2020-Aug

biomarkers, cardiovascular risk, cohort study, competing risks, random forest

General General

Customer experiences in the age of artificial intelligence.

In Computers in human behavior ; h5-index 125.0

Artificial intelligence (AI) is revolutionising the way customers interact with brands. There is a lack of empirical research into AI-enabled customer experiences. Hence, this study aims to analyse how the integration of AI in shopping can lead to an improved AI-enabled customer experience. We propose a theoretical model drawing on the trust-commitment theory and service quality model. An online survey was distributed to customers who have used an AI- enabled service offered by a beauty brand. A total of 434 responses were analysed using partial least squares-structural equation modelling. The findings indicate the significant role of trust and perceived sacrifice as factors mediating the effects of perceived convenience, personalisation and AI-enabled service quality. The findings also reveal the significant effect of relationship commitment on AI-enabled customer experience. This study contributes to the existing literature by revealing the mediating effects of trust and perceived sacrifice and the direct effect of relationship commitment on AI-enabled customer experience. In addition, the study has practical implications for retailers deploying AI in services offered to their customers.

Ameen Nisreen, Tarhini Ali, Reppel Alexander, Anand Amitabh

2020-Sep-02

Artificial intelligence, Beauty brands, COVID 19, Customer experience, Trust-commitment theory, trust

Ophthalmology Ophthalmology

Artificial intelligence and deep learning in ophthalmology - present and future (Review).

In Experimental and therapeutic medicine

Since its introduction in 1959, artificial intelligence technology has evolved rapidly and helped benefit research, industries and medicine. Deep learning, as a process of artificial intelligence (AI) is used in ophthalmology for data analysis, segmentation, automated diagnosis and possible outcome predictions. The association of deep learning and optical coherence tomography (OCT) technologies has proven reliable for the detection of retinal diseases and improving the diagnostic performance of the eye's posterior segment diseases. This review explored the possibility of implementing and using AI in establishing the diagnosis of retinal disorders. The benefits and limitations of AI in the field of retinal disease medical management were investigated by analyzing the most recent literature data. Furthermore, the future trends of AI involvement in ophthalmology were analyzed, as AI will be part of the decision-making regarding the scientific investigation, diagnosis and therapeutic management.

Moraru Andreea Dana, Costin Danut, Moraru Radu Lucian, Branisteanu Daniel Constantin

2020-Oct

OCT, artificial intelligence, convolutional neural networks, deep learning, image analysis, image processing, machine learning, ophthalmology