Adaptive Generation of Structured Medical Report Using NER Regarding Deep Learning

Wu, Cheng-Tse; Chang, Hsiao-Ko; Liu, Ji-Han; Jang, Jyh-Shing Roger

doi:10.1109/taai.2018.00012

Cited by 3 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tatiya Padang Tunggal, The Design of X-Ray Film Reader with Film Presence Detector abnormal problems on chest X-rays was investigated by Kieu [25]. The Adaptive Generation of Structured Medical Reports Using NER Regarding Deep Learning was investigated by Wu [26]. Information entropy measurements and clustering improve edge detection in medical X-ray images studied by Hrzic [27].…”

Section: Comparison Of Image Enhancement Methods For Lumbarmentioning

confidence: 99%

The Design of X-Ray Film Reader with Film Presence Detector

Tunggal

Arrosyid

Silva

et al. 2021

jrc

View full text Add to dashboard Cite

X-Ray viewer is a tool for observing the results of X-Ray films using ray lighting. It aims to get clearer readings of X-Ray films by radiographers and doctors. X-Ray viewers in hospitals generally cannot be carried anywhere because they use fluorescent lamps as a source of radiation and use 220 Volt AC voltage directly. So that its use is less effective and efficient because it must be connected directly to a 220 Volt AC power source and requires large power. In this regard the author wants to design an X-Ray viewer tool that can be used to read the results of X-Ray films clearly and is portable so that the device can be used anywhere because it uses a battery as a voltage source and is equipped with a presence detection sensor film in order to save energy so that the use of tools is more effective and efficient.

show abstract

Section: Comparison Of Image Enhancement Methods For Lumbarmentioning

confidence: 99%

The Design of X-Ray Film Reader with Film Presence Detector

Tunggal

Arrosyid

Silva

et al. 2021

jrc

View full text Add to dashboard Cite

show abstract

“…We ruled out 5 works with these exclusion criteria, leaving a total of 40 papers. The amount of papers found in each step is detailed in Table 45 Discarded with exclusion criteria [5,55,91,137,139] 5 Total articles [7, 15, 35, 37, 39, 43, 46-48, 50, 60, 65, 66, 74, 83-85, 87, 90, 92, 93, 95, 114, 114, 117, 120, 122, 125, 126, 136, 140, 142, 143, 145-150, 150, 154, 155, 155] 40 Table 1. Papers found for each query and database, and included or discarded with different criteria.…”

Section: Survey Methodology: Search and Selection Of Papersmentioning

confidence: 99%

A Survey on Deep Learning and Explainability for Automatic Report Generation from Medical Images

Messina¹,

Pino²,

Parra³

et al. 2020

Preprint

View full text Add to dashboard Cite

Every year physicians face an increasing demand of image-based diagnosis from patients, a problem that can be addressed with recent artificial intelligence methods. In this context, we survey works in the area of automatic report generation from medical images, with emphasis on methods using deep neural networks, with respect to: (1) Datasets, (2) Architecture Design, (3) Explainability and (4) Evaluation Metrics. Our survey identifies interesting developments, but also remaining challenges. Among them, the current evaluation of generated reports is especially weak, since it mostly relies on traditional Natural Language Processing (NLP) metrics, which do not accurately capture medical correctness.

show abstract