2022
DOI: 10.1148/ryai.210092
|View full text |Cite
|
Sign up to set email alerts
|

Automated Identification and Measurement Extraction of Pancreatic Cystic Lesions from Free-Text Radiology Reports Using Natural Language Processing

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 14 publications
(7 citation statements)
references
References 19 publications
0
7
0
Order By: Relevance
“…Inter-observer agreement was almost perfect after image reconstruction, with a weighted Kappa statistic between 0.97 and 0.98 (p < 0.0001). Yamashita et al (2021) took a unique approach to AI-guided diagnosis by using natural language processing (NLP) to identify patients with PCLs and extract lesion measurements from CT and MRI radiologist reports [60]. The true positive rate was 98.2% with a false positive rate of 3.0% when the model was compared against the consensus of two radiologists' annotations.…”
Section: Cross-sectional Imaging In Pclsmentioning
confidence: 99%
“…Inter-observer agreement was almost perfect after image reconstruction, with a weighted Kappa statistic between 0.97 and 0.98 (p < 0.0001). Yamashita et al (2021) took a unique approach to AI-guided diagnosis by using natural language processing (NLP) to identify patients with PCLs and extract lesion measurements from CT and MRI radiologist reports [60]. The true positive rate was 98.2% with a false positive rate of 3.0% when the model was compared against the consensus of two radiologists' annotations.…”
Section: Cross-sectional Imaging In Pclsmentioning
confidence: 99%
“…4 As such, there is growing interest in using artificial intelligence-based language models to automatically extract structured information from freetext medical reports. [5][6][7][8][9][10] Large language models have shown promising results in various natural language processing tasks, including text summarization, translation and question-answering, not to mention the processing of radiology reports. [5][6][7][8]11 These models possess distinct capabilities such as zero-shot and few-shot learning, which enable them to understand and perform tasks without prior training by leveraging prompt learning from provided examples.…”
Section: Introductionmentioning
confidence: 99%
“…[5][6][7][8][9][10] Large language models have shown promising results in various natural language processing tasks, including text summarization, translation and question-answering, not to mention the processing of radiology reports. [5][6][7][8]11 These models possess distinct capabilities such as zero-shot and few-shot learning, which enable them to understand and perform tasks without prior training by leveraging prompt learning from provided examples. 7,[12][13][14] Recently, there has been a rapid increase in original articles experimenting with Generative Pre-trained Transformer (GPT)-4 by OpenAI (San Francisco, CA), the most powerful large language model to date, in the field of radiology.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Artificial intelligence (AI) has been widely used in various medical scenarios such as prevention, diagnosis, and treatment, such as diagnosing heart disease ( Feshki and Shijani, 2016 ), providing medical advice ( Nov et al, 2020 ), detecting skin cancer ( Takiddin et al, 2021 ), identifying layout lesions ( Yamashita et al, 2021 ), and reading CT image of suspected COVID-19 cases ( Mei et al, 2020 ), etc.…”
Section: Introductionmentioning
confidence: 99%