Artificial intelligence in diagnostic and interventional radiology: Where are we now?

Boeken, Tom; Feydy, Jean; Lecler, Augustin; Soyer, Philippe; Feydy, A.; Barat, Maxime; Duron, Loïc

doi:10.1016/j.diii.2022.11.004

Cited by 69 publications

(34 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence (AI) is increasingly used in the field of radiology although many limitations have been identified. 1,2 Large language models (LLMs) are deep learning models trained to understand and generate natural language. Generative pre-trained transformer (GPT) is a language generation model developed by OpenAI.…”

Section: Introductionmentioning

confidence: 99%

Appropriateness of Recommendations Provided by ChatGPT to Interventional Radiologists

2023

Self Cite

View full text Add to dashboard Cite

Purpose: The purpose of this study was to analyze the answers provided by ChatGPT to various questions in the field of interventional radiology (IR) and compare their correctness to a consensus of three interventional radiologists. Materials and Methods. Twenty questions were proposed to the online chat based ChatGPT about interventional radiology as indications for exams, complications and technical points. Answers were independently evaluated by 3 experts in interventional radiology with 10, 15 and 30 years or experiences and classified as correct, almost correct, or wrong. Results: Considering the consensus between the two IR, nine (9/20; 45%) were considered wrong, three (3/20; 15%) were considered almost correct and eight (8/20; 40%) were considered correct. Conclusion: ChatGPT can be useful in IR but the users must be aware of limitations such as too vague or inaccurate answers for the majority of questions.

show abstract

Section: Introductionmentioning

confidence: 99%

Appropriateness of Recommendations Provided by ChatGPT to Interventional Radiologists

2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, as a proof-of-concept study, here we demonstrate a pipeline for GPT 3.5 based model [25] fine-tuning and prediction with our recorded physiological signals (Figure 5d). For starter, our biosensor interface pipeline involves acquiring voltage or current signals using our ink printed electrochemical multimodal device.…”

Section: Chatgpt-bioelectronic Interfacementioning

confidence: 77%

Integrated Ink Printing Paper Based Self‐Powered Electrochemical Multimodal Biosensing (IFP^−Multi) with ChatGPT–Bioelectronic Interface for Personalized Healthcare Management

Xiong,

Dang,

Yang

et al. 2023

Advanced Science

View full text Add to dashboard Cite

Personalized healthcare management is an emerging field that requires the development of environment‐friendly, integrated, and electrochemical multimodal devices. In this study, the concept of integrated paper‐based biosensors (IFP−Multi) for personalized healthcare management is introduced. By leveraging ink printing technology and a ChatGPT–bioelectronic interface, these biosensors offer ultrahigh areal‐specific capacitance (74633 mF cm−2), excellent mechanical properties, and multifunctional sensing and humidity power generation capabilities. More importantly, the IFP−Multi devices have the potential to simulate deaf‐mute vocalization and can be integrated into wearable sensors to detect muscle contractions and bending motions. Moreover, they also enable monitoring of physiological signals from various body parts, such as the throat, nape, elbow, wrist, and knee, and successfully record sharp and repeatable signals generated by muscle contractions. In addition, the IFP−Multi devices demonstrate self‐powered handwriting sensing and moisture power generation for sweat‐sensing applications. As a proof‐of‐concept, a GPT 3.5 model‐based fine‐tuning and prediction pipeline that utilizes recorded physiological signals through IFP−Multi is showcased, enabling artificial intelligence with multimodal sensing capabilities for personalized healthcare management. This work presents a promising and ecofriendly approach to developing paper‐based electrochemical multimodal devices, paving the way for a new era of healthcare advancements.

show abstract

“…39 Missed GISTs were all less than 7 mm in size. 39 Although artificial intelligence (AI) has now multiple applications in abdominal imaging, 40,41 limited data in terms of tumour detection is currently available for GIST imaging and most studies refer to the detection of GIST with endoscopic ultrasound. 42 Currently, there is a limited data in the literature, so that GIST detection with imaging remains not fully elucidated.…”

Section: Lesion Detectionmentioning

confidence: 99%

CT and MRI of Gastrointestinal Stromal Tumours: New Trends and Perspectives

et al. 2023

Self Cite

View full text Add to dashboard Cite

Gastrointestinal stromal tumors (GISTs) are defined as mesenchymal tumors of the gastrointestinal tract that express positivity for CD117, which is a c- KIT proto-oncogene antigen. Expression of the c- KIT protein, a tyrosine kinase growth factor receptor, allows the distinction between GISTs and other mesenchymal tumors such as leiomyoma, leiomyosarcoma, schwannoma and neurofibroma. GISTs can develop anywhere in the gastrointestinal tract, as well as in the mesentery and omentum. Over the years, the management of GISTs has improved due to a better knowledge of their behaviors and risk or recurrence, the identification of specific mutations and the use of targeted therapies. This has resulted in a better prognosis for patients with GISTs. In parallel, imaging of GISTs has been revolutionized by tremendous progress in the field of detection, characterization, survival prediction and monitoring during therapy. Recently, a particular attention has been given to radiomics for the characterization of GISTs using analysis of quantitative imaging features. In addition, radiomics has currently many applications that are developed in conjunction with artificial intelligence with the aim of better characterizing GISTs and providing a more precise assessment of tumor burden. This article sums up recent advances in computed tomography and magnetic resonance imaging of GISTs in the field of image/data acquisition, tumor detection, tumor characterization, treatment response evaluation, and preoperative planning.

show abstract

Artificial intelligence in diagnostic and interventional radiology: Where are we now?

Cited by 69 publications

References 46 publications

Appropriateness of Recommendations Provided by ChatGPT to Interventional Radiologists

Appropriateness of Recommendations Provided by ChatGPT to Interventional Radiologists

Integrated Ink Printing Paper Based Self‐Powered Electrochemical Multimodal Biosensing (IFP^−Multi) with ChatGPT–Bioelectronic Interface for Personalized Healthcare Management

CT and MRI of Gastrointestinal Stromal Tumours: New Trends and Perspectives

Contact Info

Product

Resources

About

Artificial intelligence in diagnostic and interventional radiology: Where are we now?

Cited by 69 publications

References 46 publications

Appropriateness of Recommendations Provided by ChatGPT to Interventional Radiologists

Appropriateness of Recommendations Provided by ChatGPT to Interventional Radiologists

Integrated Ink Printing Paper Based Self‐Powered Electrochemical Multimodal Biosensing (IFP−Multi) with ChatGPT–Bioelectronic Interface for Personalized Healthcare Management

CT and MRI of Gastrointestinal Stromal Tumours: New Trends and Perspectives

Contact Info

Product

Resources

About

Integrated Ink Printing Paper Based Self‐Powered Electrochemical Multimodal Biosensing (IFP^−Multi) with ChatGPT–Bioelectronic Interface for Personalized Healthcare Management