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

Yamashita, Rikiya; Bird, Kristen N; Cheung, P.; Decker, Johannes Hugo; Flory, Marta; Goff, Daniel; Morimoto, Linda Nayeli; Shon, Andy; Wentland, Andrew L.; Rubin, Daniel L.; Desser, Terry S.

doi:10.1148/ryai.210092

Cited by 14 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

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%

Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma

Jiang

Chao

Culp

et al. 2023

Cancers

View full text Add to dashboard Cite

Pancreatic cancer is projected to become the second leading cause of cancer-related mortality in the United States by 2030. This is in part due to the paucity of reliable screening and diagnostic options for early detection. Amongst known pre-malignant pancreatic lesions, pancreatic intraepithelial neoplasia (PanIN) and intraductal papillary mucinous neoplasms (IPMNs) are the most prevalent. The current standard of care for the diagnosis and classification of pancreatic cystic lesions (PCLs) involves cross-sectional imaging studies and endoscopic ultrasound (EUS) and, when indicated, EUS-guided fine needle aspiration and cyst fluid analysis. However, this is suboptimal for the identification and risk stratification of PCLs, with accuracy of only 65–75% for detecting mucinous PCLs. Artificial intelligence (AI) is a promising tool that has been applied to improve accuracy in screening for solid tumors, including breast, lung, cervical, and colon cancer. More recently, it has shown promise in diagnosing pancreatic cancer by identifying high-risk populations, risk-stratifying premalignant lesions, and predicting the progression of IPMNs to adenocarcinoma. This review summarizes the available literature on artificial intelligence in the screening and prognostication of precancerous lesions in the pancreas, and streamlining the diagnosis of pancreatic cancer.

show abstract

Section: Cross-sectional Imaging In Pclsmentioning

confidence: 99%

Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma

Jiang

Chao

Culp

et al. 2023

Cancers

View full text Add to dashboard Cite

show abstract

“…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

Using GPT‐4 for LI‐RADS feature extraction and categorization with multilingual free‐text reports

Gu,

Lee,

Shin

et al. 2024

Liver International

View full text Add to dashboard Cite

Background and AimsThe Liver Imaging Reporting and Data System (LI‐RADS) offers a standardized approach for imaging hepatocellular carcinoma. However, the diverse styles and structures of radiology reports complicate automatic data extraction. Large language models hold the potential for structured data extraction from free‐text reports. Our objective was to evaluate the performance of Generative Pre‐trained Transformer (GPT)‐4 in extracting LI‐RADS features and categories from free‐text liver magnetic resonance imaging (MRI) reports.MethodsThree radiologists generated 160 fictitious free‐text liver MRI reports written in Korean and English, simulating real‐world practice. Of these, 20 were used for prompt engineering, and 140 formed the internal test cohort. Seventy‐two genuine reports, authored by 17 radiologists were collected and de‐identified for the external test cohort. LI‐RADS features were extracted using GPT‐4, with a Python script calculating categories. Accuracies in each test cohort were compared.ResultsOn the external test, the accuracy for the extraction of major LI‐RADS features, which encompass size, nonrim arterial phase hyperenhancement, nonperipheral ‘washout’, enhancing ‘capsule’ and threshold growth, ranged from .92 to .99. For the rest of the LI‐RADS features, the accuracy ranged from .86 to .97. For the LI‐RADS category, the model showed an accuracy of .85 (95% CI: .76, .93).ConclusionsGPT‐4 shows promise in extracting LI‐RADS features, yet further refinement of its prompting strategy and advancements in its neural network architecture are crucial for reliable use in processing complex real‐world MRI reports.

show abstract

“…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%

Did Artificial Intelligence Invade Humans? The Study on the Mechanism of Patients’ Willingness to Accept Artificial Intelligence Medical Care: From the Perspective of Intergroup Threat Theory

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence (AI) has become one of the core driving forces for the future development of the medical industry, but patients are skeptical about the use of AI in medical care. Based on the intergroup threat theory (ITT), this study verified that patients would regard AI as an external group, triggering the perceived threat of the external group, which results in avoidance behaviors in the treatment (experiment 1: n = 446) and diagnosis (experiment 2: n = 330) scenarios. The results show that despite AI can provide expert-level accuracy in medical care, patients are still more likely to rely on human doctors and experience more negative emotions as AI is more involved in medical care (experiment 1). Furthermore, patients pay more attention to threats at the individual level related to themselves, such as realistic threats related to privacy issues and symbolic threats related to the neglect of personal characteristics. In contrast, realistic threats and symbolic threats at the group level had less effect on patients in the medical scenario (experiment 2).

show abstract

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

Cited by 14 publications

References 19 publications

Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma

Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma

Using GPT‐4 for LI‐RADS feature extraction and categorization with multilingual free‐text reports

Did Artificial Intelligence Invade Humans? The Study on the Mechanism of Patients’ Willingness to Accept Artificial Intelligence Medical Care: From the Perspective of Intergroup Threat Theory

Contact Info

Product

Resources

About