On the interplay of machine learning and background knowledge in image interpretation by Bayesian networks

Velikova, Marina; Lucas, Peter; Samulski, Maurice; Karssemeijer, Nico

doi:10.1016/j.artmed.2012.12.004

Cited by 41 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, several studies described an appropriate reference standard that included histopathology with either clinical follow-up or cancer registry matching to ascertain outcomes [9,14,16,18,21,28,31]. Studies proposed to develop and/or evaluate AI models or techniques for breast cancer detection [9,11,18,21,22,27,28,26], or for diagnosis (classification) or interpretation of mammographic examinations [13,14,15,16,20,[23][24][25]30], or dealt with advancing computer-aided detection (CAD) systems through new AI models [10,12,17,19,29]; and one study investigated AI for discrimination between benign and cancerous lesions jointly with cancer risk prediction [31]. Rodriguez-Ruiz et al [9] reported a multi-reader study comparing an AI system with radiologists' interpretation of various datasets of screening and clinical mammographic examinations.…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence (AI) for the early detection of breast cancer: a scoping review to assess AI’s potential in breast screening practice

Houssami

Kirkpatrick-Jones

Noguchi

et al. 2019

Expert Review of Medical Devices

134

View full text Add to dashboard Cite

Introduction: Various factors are driving interest in the application of artificial intelligence (AI) for breast cancer (BC) detection, but it is unclear whether the evidence warrants large-scale use in population-based screening. Areas covered: We performed a scoping review, a structured evidence synthesis describing a broad research field, to summarize knowledge on AI evaluated for BC detection and to assess AI's readiness for adoption in BC screening. Studies were predominantly small retrospective studies based on highly selected image datasets that contained a high proportion of cancers (median BC proportion in datasets 26.5%), and used heterogeneous techniques to develop AI models; the range of estimated AUC (area under ROC curve) for AI models was 69.2-97.8% (median AUC 88.2%). We identified various methodologic limitations including use of non-representative imaging data for model training, limited validation in external datasets, potential bias in training data, and few comparative data for AI versus radiologists' interpretation of mammography screening. Expert opinion: Although contemporary AI models have reported generally good accuracy for BC detection, methodological concerns, and evidence gaps exist that limit translation into clinical BC screening settings. These should be addressed in parallel to advancing AI techniques to render AI transferable to large-scale population-based screening.

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence (AI) for the early detection of breast cancer: a scoping review to assess AI’s potential in breast screening practice

Houssami

Kirkpatrick-Jones

Noguchi

et al. 2019

Expert Review of Medical Devices

134

View full text Add to dashboard Cite

show abstract

“…Bayesian network constructs can combine expert knowledge and data-driven modeling (Seixas et al 2014;Velikova et al 2013). Using an intermediate feature selection step before constructing and applying the BN model provides insight into the dataset under investigation and guides model development.…”

Section: Discussionmentioning

confidence: 99%

Application of Bayesian networks in determining nanoparticle-induced cellular outcomes using transcriptomics

et al. 2019

View full text Add to dashboard Cite

Inroads have been made in our understanding of the risks posed to human health and the environment by nanoparticles (NPs) but this area requires continuous research and monitoring. Machine learning techniques have been applied to nanotoxicology with very encouraging results. This study deals with bridging physicochemical properties of NPs, experimental exposure conditions and in vitro characteristics with biological effects of NPs on a molecular cellular level from transcriptomics studies. The bridging is done by developing and implementing Bayesian Networks (BNs) with or without data preprocessing. The BN structures are derived either automatically or methodologically and compared. Early stage nanotoxicity measurements represent a challenge, not least when attempting to predict adverse outcomes and modeling is critical to understanding the biological effects of exposure to NPs. The preprocessed data-driven BN showed improved performance over automatically structured BN and the BN with unprocessed datasets. The prestructured BN captures inter relationships between NP properties, exposure condition and in vitro characteristics and links those with cellular effects based on statistic correlation findings. Information gain analysis showed that exposure dose, NP and cell line variables were the most influential attributes in predicting the biological effects. The BN methodology proposed in this study successfully predicts a number of toxicologically relevant cellular disrupted biological processes such as cell cycle and proliferation pathways, cell adhesion and extracellular matrix responses, DNA damage and repair mechanisms etc., with a success rate >80%. The model validation from independent data shows a robust and promising methodology for incorporating transcriptomics outcomes in a hazard and, by extension, risk assessment modeling framework by predicting affected cellular functions from experimental conditions.

show abstract

“…Historically the naïve Bayesian classifier, back-propagation neural networks, and symbolic learning were used in several biomedical applications, but recently improved algorithms are being encouraged that can handle missing and noisy data, also give insight and transparency of the diagnostic knowledge, and performs well even with small set of data points (Kononenko 2001). Machine learning pervaded several interesting applications in biomedical engineering for example non-invasive estimation of blood glucose level and blood pressure (Monte-Moreno 2011), kernel based classification approaches of epilepsy diagnosis from EEG (Lima and Coelho 2011), classifier ensemble to tackle missing features (Nanni et al 2012), ECG analysis from statistical, geometric and nonlinear features (Jovic and Bogunovic 2011;Maglaveras et al 1998), application of Bayesian network in bi-level multi-classifier (Sierra et al 2001) and image interpretation (Velikova et al 2013), machine learning approaches for Dementia scoring (Mani et al 1999) etc. Regarding histo-pathological image analyses, several biomedical applications of machine learning techniques like object level, spatially related and multi-scale feature extraction, graph based modeling, feature selection, dimensionality reduction and manifold-learning are reviewed in (Gurcan et al 2009).…”

Section: Constraints For Applying Traditional Machine Learning Technimentioning

confidence: 99%

Machine Learning Techniques for Remote Healthcare

Das¹,

Maharatna²

2013

Systems Design for Remote Healthcare

View full text Add to dashboard Cite

In this chapter, popular machine learning techniques are discussed in the context of remote healthcare. In this domain the main challenges are low computational complexity and hardware implementation, and not just conventional way of mathematical analysis of machine learning algorithms. Statistical view-point of different machine learning techniques, standard parametric and nonparametric algorithms for classification and clustering are briefly discussed. A practical 12-lead Electrocardiogram (ECG) signal based myocardial scar classification example has also been shown as a representative example. Complexity of few classification algorithms, online implementation issues for statistical feature extraction and some open research problems have also been introduced briefly.

show abstract

On the interplay of machine learning and background knowledge in image interpretation by Bayesian networks

Cited by 41 publications

References 27 publications

Artificial Intelligence (AI) for the early detection of breast cancer: a scoping review to assess AI’s potential in breast screening practice

Artificial Intelligence (AI) for the early detection of breast cancer: a scoping review to assess AI’s potential in breast screening practice

Application of Bayesian networks in determining nanoparticle-induced cellular outcomes using transcriptomics

Machine Learning Techniques for Remote Healthcare

Contact Info

Product

Resources

About