Text Mining in Radiology Reports

Gong, Tianxia; Tan, Chew Lim; Leong, Tze-Yun; Lee, Cheng Kiang; Pang, Boon Chuan; Lim, Charles; Tian, Qi; Tang, Suisheng; Zhang, Zhuo

doi:10.1109/icdm.2008.150

Cited by 21 publications

(18 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MetaMap identifies phrases with medical terms and map the terms to Unified Medical Language System (UMLS) Metathesaurus, which contains terms from the various controlled vocabularies. We use the method described in [10] to find the relations between the pathology and anatomy terms extracted so that we know where the pathology occurs. For example, after term mapping and parsing, the syntactic relations of the words and terms in the example report from Section 1 are shown in Figure 5.…”

Section: Pathology and Anatomy Term Extraction From Radiology Reportmentioning

confidence: 99%

Automatic labeling and classification of brain CT images

Gong

Wang

et al. 2011

2011 18th IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

Automatic medical image classification is difficult because of the lacking of training data. As manual labeling is too costly, we provide an automatic labeling solution to this problem by making use of the radiology report associated with the medical images. We first segment and reconstruct the 3D regions of interest (ROIs) from the medical images, and extract pathology and anatomy information from the associated report. We use an anatomical atlas to map the ROIs to the anatomy part(s) and match the pathology information of the same anatomy part(s) from the text. In this way, the ROIs are automatically labeled with pathology types which can be served as class labels, and a training data set of a large number of training instances is generated automatically. We extract the volume, color, location, and shape features of the ROIs, and classify the types of ROIs using these features. The overall evaluation result is promising to doctors and medical professionals. Our experiment is conducted using traumatic brain injury CT images; however, our framework of automatically labeling and classifying medical cases can be extended to medical images in other modality or of other anatomical part.

show abstract

Section: Pathology and Anatomy Term Extraction From Radiology Reportmentioning

confidence: 99%

Automatic labeling and classification of brain CT images

Gong

Wang

et al. 2011

2011 18th IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, previously there are techniques [1], [2] proposed to mining free-text medical reports. However, lots semantically similar terms exist in these reports.…”

Section: Introductionmentioning

confidence: 99%

Semantic Similarity Measures in the Biomedical Domain by Leveraging a Web Search Engine

Hsieh

Chang

Chen

et al. 2013

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Various researches in web related semantic similarity measures have been deployed. However, measuring semantic similarity between two terms remains a challenging task. The traditional ontology-based methodologies have a limitation that both concepts must be resided in the same ontology tree(s). Unfortunately, in practice, the assumption is not always applicable. On the other hand, if the corpus is sufficiently adequate, the corpus-based methodologies can overcome the limitation. Now, the web is a continuous and enormous growth corpus. Therefore, a method of estimating semantic similarity is proposed via exploiting the page counts of two biomedical concepts returned by Google AJAX web search engine. The features are extracted as the co-occurrence patterns of two given terms P and Q, by querying P, Q, as well as P AND Q, and the web search hit counts of the defined lexico-syntactic patterns. These similarity scores of different patterns are evaluated, by adapting support vector machines for classification, to leverage the robustness of semantic similarity measures. Experimental results validating against two datasets: dataset 1 provided by A. Hliaoutakis; dataset 2 provided by T. Pedersen, are presented and discussed. In dataset 1, the proposed approach achieves the best correlation coefficient (0.802) under SNOMED-CT. In dataset 2, the proposed method obtains the best correlation coefficient (SNOMED-CT: 0.705; MeSH: 0.723) with physician scores comparing with measures of other methods. However, the correlation coefficients (SNOMED-CT: 0.496; MeSH: 0.539) with coder scores received opposite outcomes. In conclusion, the semantic similarity findings of the proposed method are close to those of physicians' ratings. Furthermore, the study provides a cornerstone investigation for extracting fully relevant information from digitizing, free-text medical records in the National Taiwan University Hospital database.

show abstract

“…They used brain CT radiology reports as domain for testing of system. The System includes feature extraction and retrieval of reports [1]. The Friedman encode radiology reports using semantic approach.…”

Section: Related Workmentioning

confidence: 99%

“…In medical technology due to wider adoption of electronic medical record systems, many reports and large medical text data are generated in hospitals and other health institutions daily [1]. The medical report include the patient's medical condition in detail like medical history; prescription and results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Text Mining in Radiology Reports by SVM Classifier

Bodile¹,

Kshirsagar²

2015

IJCA

View full text Add to dashboard Cite

Medical text mining has gained increasing popularity in recent years. Now a days, large amount of medical text data are daily generated in health institutions, but never refer again as it is very time consuming task. In Radiology research area, most of the reports are in free text format and usually unprocessed, hence it is difficult to access the valuable information for medical professional unless proper text mining is not applied. There are some systems for radiology report information retrieval like MedLEE, NeuRadIR, CBIR but very few of them make use of text associated with image This paper proposes a text mining system to deals with this problem by using statistical machine translation approach. The radiology report is given to the system as input and system will return the similar report match with the entered report from the database.The SVM classifier is use in SMT approach to find the match report. Precision and Recall accuracy measures are used for evaluation purpose.

show abstract

Text Mining in Radiology Reports

Cited by 21 publications

References 10 publications

Automatic labeling and classification of brain CT images

Automatic labeling and classification of brain CT images

Semantic Similarity Measures in the Biomedical Domain by Leveraging a Web Search Engine

Text Mining in Radiology Reports by SVM Classifier

Contact Info

Product

Resources

About