Title |
Automatic classification of histopathological diagnoses for building a large scale tissue catalogue
|
---|---|
Published in |
Health and Technology, December 2016
|
DOI | 10.1007/s12553-016-0169-8 |
Pubmed ID | |
Authors |
Robert Reihs, Heimo Müller, Stefan Sauer, Kurt Zatloukal |
Abstract |
In this paper an automatic classification system for pathological findings is presented. The starting point in our undertaking was a pathologic tissue collection with about 1.4 million tissue samples described by free text records over 23 years. Exploring knowledge out of this "big data" pool is a challenging task, especially when dealing with unstructured data spanning over many years. The classification is based on an ontology-based term extraction and decision tree build with a manually curated classification system. The information extracting system is based on regular expressions and a text substitution system. We describe the generation of the decision trees by medical experts using a visual editor. Also the evaluation of the classification process with a reference data set is described. We achieved an F-Score of 89,7% for ICD-10 and an F-Score of 94,7% for ICD-O classification. For the information extraction of the tumor staging and receptors we achieved am F-Score ranging from 81,8 to 96,8%. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 20 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Bachelor | 3 | 15% |
Researcher | 3 | 15% |
Student > Master | 3 | 15% |
Student > Doctoral Student | 2 | 10% |
Student > Ph. D. Student | 1 | 5% |
Other | 2 | 10% |
Unknown | 6 | 30% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 5 | 25% |
Medicine and Dentistry | 5 | 25% |
Nursing and Health Professions | 2 | 10% |
Agricultural and Biological Sciences | 1 | 5% |
Decision Sciences | 1 | 5% |
Other | 1 | 5% |
Unknown | 5 | 25% |