Breast Imaging in the Era of Big Data: Structured Reporting and Data Mining

Margolies, Laurie; Pandey, Gaurav; Horowitz, Eliot R.; Mendelson, David S.

doi:10.2214/ajr.15.15396

Cited by 53 publications

(26 citation statements)

References 59 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The introduction of BI-RADS in the late 1980 s laid the groundwork for this kind of structured reporting [15,16]. Breast lesions were allocated to categories ranging from benign to histologically proven malignancy.…”

Section: Discussionmentioning

confidence: 99%

Semi-automated De-identification of German Content Sensitive Reports for Big Data Analytics

Seuß

Dankerl

Ihle

et al. 2017

Fortschr Röntgenstr

View full text Add to dashboard Cite

ZUSAMMENFASSUNGZiel Projekte bei denen verschiedene Institutionen in Kooperation miteinander stehen, erfordern einen Schutz von Patientendaten durch selektive Deidentifizierung von Wörtern oder Ausdrücken. Eine automatisierte Deidentifikations-Software wurde entwickelt und anhand verschiedener medizinischer Berichte, zuerst ohne und anschließend nach Anpassung des Algorithmus an die Textstruktur, getestet. Ergebnisse Nativ wurden 61,3 % der direkten und 80,8 % der indirekten Kennungen nachgewiesen. Nach dem Training erhöhte sich die Leistung (P) auf 91,4 % (P25), 96,7 % (P50), 99,5 % (P100), 99,6 % (P250), 99,7 % (P500) und 100 % (P1000) für direkte Kennungen und 93,2 % (P25), 97,9 % (P50), 97,2 % (P100), 98,9 % (P250), 99,0 % (P500) und 99,3 % (P1000) für indirekte Kennungen. Im Durchschnitt wurden 5,3 % der medizinischen Begriffe als kritische Daten gekennzeichnet, nach dem Training waren es 4,0 % (P25), 3,6 % (P50), 4,0 % (P100), 3,7 % (P250), 4,3 % (P500), 3,1 % (P1000). Etwa 0,1 % der Füllwörter wurden gekennzeichnet. institutions require data security via selective de-identification of words or phrases. A semi-automated de-identification tool was developed and evaluated on different types of medical reports natively and after adapting the algorithm to the text structure. Material und MethodenMaterials and Methods A semi-automated de-identification tool was developed and evaluated for its sensitivity and specificity in detecting sensitive content in written reports. Data from 4671 pathology reports (4105 + 566 in two different formats), 2804 medical reports, 1008 operation reports, and 6223 radiology reports of 1167 patients suffering from breast cancer were de-identified. The content was itemized into four categories: direct identifiers (name, address), indirect identifiers (date of birth/operation, medical ID, etc.), medical terms, and filler words. The software was tested natively (without training) in order to establish a baseline. The reports were manually edited and the model re-trained for the next test set. After manually editing 25, 50, 100, 250, 500 and if applicable 1000 reports of each type re-training was applied.Results In the native test, 61.3 % of direct and 80.8 % of the indirect identifiers were detected. The performance (P) increased to 91.4 % (P25), 96.7 % (P50), 99.5 % (P100), 99.6 % (P250), 99.7 % (P500) and 100 % (P1000) for direct identifiers and to 93.2 % (P25), 97.9 % (P50), 97.2 % (P100), 98.9 % (P250), 99.0 % (P500) and 99.3 % (P1000) for indirect identifiers. Without training, 5.3 % of medical terms were falsely flagged as critical data. The performance increased, after training, to 4.0 % (P25), 3.6 % (P50), 4.0 % (P100), 3.7 % (P250), 4.3 % (P500), and 3.1 % (P1000). Roughly 0.1 % of filler words were falsely flagged.Conclusion Training of the developed de-identification tool continuously improved its performance. Training with roughly 100 edited reports enables reliable detection and labeling of sensitive data in different types of medical reports.

show abstract

Section: Discussionmentioning

confidence: 99%

Semi-automated De-identification of German Content Sensitive Reports for Big Data Analytics

Seuß

Dankerl

Ihle

et al. 2017

Fortschr Röntgenstr

View full text Add to dashboard Cite

show abstract

“…On the one side, there is a bottom-up, datadriven direction which we like to refer to as "imagebased modelling" or more broadly, "phenomenological modelling". Perhaps starting with the success of statistical shape modelling (Young and Frangi, 2009;Castro-Mateos et al, 2014), and successive developments leading to computational atlasing, computational anatomy (Miller et al, 2015) and disease state fingerprinting (Kumar et al, 2012;Mattila et al, 2011), these and other developments accelerated by machine learning emphasize learning and inference of knowledge directly from vast amounts of imaging data (Kansagra et al, 2016;Medrano-Gracia et al, 2015;Margolies et al, 2016). This confluence of image-based computational modelling with developments on population imaging (Volzke et al, 2012) will increasingly underpin computational models and phenotypes of health and disease.…”

Section: The Trend: From Data To Wisdom and Backmentioning

confidence: 99%

Precision Imaging: more descriptive, predictive and integrative imaging

Frangi

Taylor

Gooya

2016

Medical Image Analysis

View full text Add to dashboard Cite

Medical image analysis has grown into a matured field challenged by progress made across all medical imaging technologies and more recent breakthroughs in biological imaging. The cross-fertilisation between medical image analysis, biomedical imaging physics and technology, and domain knowledge from medicine and biology has spurred a truly interdisciplinary effort that stretched outside the original boundaries of the disciplines that gave birth to this field and created stimulating and enriching synergies. Consideration on how the field has evolved and the experience of the work carried out over the last 15 years in our centre, has led us to envision a future emphasis of medical imaging in Precision Imaging. Precision Imaging is not a new discipline but rather a distinct emphasis in medical imaging borne at the cross-roads between, and unifying the efforts behind mechanistic and phenomenological modelbased imaging. It captures three main directions in the effort to deal with the information deluge in imaging sciences, and thus achieve wisdom from data, information, and knowledge. Precision Imaging is finally characterised by being descriptive, predictive and integrative about the imaged object. This paper provides a brief and personal perspective on how the field has evolved, summarises and formalises our vision of Precision Imaging for Precision Medicine, and highlights some connections with past research and current trends in the field.

show abstract

“…Several times, the result of this exam is transmitted through report by a doctor who executes it for the requesting doctor [1]. The radiological report contains a lot of information that characterizes the medical condition of the patient and great percentage of this information is in an unstructured form, usually called free text, this methodology makes it hard and complex the processes of search, analysis and clinical research [2,3]. Figure 1 presents a fictitious report using a direct descriptive method without ontological structure.…”

Section: Introductionmentioning

confidence: 99%

“…Turning the extraction and solution of complex problems a simple task [3]. These advances allow radiological data to be stored in an ontologic classification, helping disease prevention and medical diagnosis, by structuring the information contained in the radiological report [2,3,6].…”

Section: Introductionmentioning

confidence: 99%

“…It is used to facilitate viewing the information's from the radiological report [4,5], at where each type of examination uses a singular structured system of radiological data. Thus, the study in question proposes a simple methodology for the structuring of reports of radiological examinations, opening the possibility for clinical and scientific research with the application of computational tools (artificial intelligence and intelligent systems), simplifying the preparation of the reports [3,5,6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Structuring the Radiological Report

Rocha¹,

Brasil²,

Lamas³

et al. 2018

Anais Do v Congresso Brasileiro De Eletromiografia E Cinesiologia E X Simpósio De Engenharia Biomédica

View full text Add to dashboard Cite

Data has become one the most precious asset of our modern society. Study of these data has been a most valuable source of information for understanding our daily events. Medical reports help us to understand the many diseases and how they affect us. However, when these reports are stored in an unstructured free text report, it makes their study expensive and complex. To facilitate the work of researchers and medicals, we propose structuring the radiological report. Using visual fields and the ontological information classification, it will be possible to create, classify and measure radiological reports information in an easier and more efficient way. We propose in this study use the Breast Ultrasonography report and elicitation of the domain's knowledge through an updated bibliographic survey on the specific radiological examination moving collected data to an ontological computational structure.

show abstract

Breast Imaging in the Era of Big Data: Structured Reporting and Data Mining

Cited by 53 publications

References 59 publications

Semi-automated De-identification of German Content Sensitive Reports for Big Data Analytics

Semi-automated De-identification of German Content Sensitive Reports for Big Data Analytics

Precision Imaging: more descriptive, predictive and integrative imaging

Structuring the Radiological Report

Contact Info

Product

Resources

About