Content-Based Image Retrieval in Radiology: Current Status and Future Directions

By C. B. Akgül, Daniel L. Rubin, S. Napel, C. Beaulieu, Hayit Greenspan, B. Acar. Journal of digital imaging, 2010

402 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/bf2bac9006d0d1c292caf93f4281a57d4b83c9c4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Molecular Biology

Citations in the corpus

A fully automatic end-to-end method for content-based image retrieval of CT scans with similar liver lesion annotations (2017, background): “The goal of M-CBIR is to assist radiologists in the clinical decisionmaking process by finding clinical cases in large archives thatmost resemble a given case [10,11].”
Towards interactive Machine Learning (iML): Applying Ant Colony Algorithms to Solve the Traveling Salesman Problem with the Human-in-the-Loop Approach (2016, neutral): “in the instinctive, often almost instantaneous interpretation of complex patterns, for example, in diagnostic radiologic imaging: A promising technique to fill the semantic gap is to adopt an expert-in-the-loop approach, by integrating the physicians high-level expert knowledge into the retrieval pr”
Ontology-Guided Principal Component Analysis: Reaching the Limits of the Doctor-in-the-Loop (2016, background): “A good example is diagnostic radiologic imaging, where a promising approach is to fill the semantic gap by integrating the physicians high-level expert knowledge into the retrieval process by acquiring his/her relevance judgments regarding a set of initial retrieval results [1].”
Content-Based Medical Image Retrieval: A Survey of Applications to Multidimensional and Multimodality Data (2013, background): “A detailed discussion of various similarity measures can be found in [19].”
Toward Content Based Image Retrieval with Deep Convolutional Neural Networks (2015, background): “Although CBIR is not a new idea for the medical field, recent efforts have not been particularly effective [1-3].”
Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making (2019, methodology): “While a substantial body of work has focused on improving algorithmic capabilities [1, 22, 33, 34, 41], our work examines the user experience surrounding CBIR, an area that has been noted as deserving more attention [11, 34].”
eDoctor: machine learning and the future of medicine (2018, background): “Content-based image retrieval systems have also been proposed and designed, whereby a database of images can be searched based on the similarities between images [53, 54], empowered by text analysis of radiology reports [22].”
Endowing a Content-Based Medical Image Retrieval System with Perceptual Similarity Using Ensemble Strategy (2016, background): “Some modules of CBMIR architecture are also present in most of CAD definitions [27, 17].”
Interactive machine learning for health informatics: when do we need the human-in-the-loop? (2016, methodology): “…in diagnostic radiologic imaging: A promising technique to ﬁll the semantic gap is to adopt an expert-in-the-loop approach, to integrate the physicians high-level expert knowledge into the retrieval process by acquiring his/her relevance judgments regarding a set of initial retrieval results [22].”
A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop (2017, methodology): “…imaging: A promising technique to ﬁll the semantic gap is to adopt an expert-in-the-loop approach, by integrating the physicians high-level expert knowledge into the retrieval process and by acquiring his/her relevance judgments regarding a set of initial retrieval results (Akgl et al., 2011).”
Autoencoding the retrieval relevance of medical images (2015, background): “Thus, the hypothesis of this paper is that the relevance of image blocks is directly proportional to the error of an autoencoder when the hidden layer is smaller than the input/output layer assuming that images are widely free from noise.”
Collaborative Human-AI (CHAI): Evidence-Based Interpretable Melanoma Classification in Dermoscopic Images (2018, neutral): “Early approaches relied on low-level features and bag-ofvisual words, [9,10], but suffered from the “semantic gap”: feature similarity did not necessarily correlate to label similarity.”