1
|
Faghani S, Moassefi M, Madhavan AA, Mark IT, Verdoorn JT, Erickson BJ, Benson JC. Identifying Patients with CSF-Venous Fistula Using Brain MRI: A Deep Learning Approach. AJNR Am J Neuroradiol 2024; 45:439-443. [PMID: 38423747 DOI: 10.3174/ajnr.a8173] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Accepted: 12/12/2023] [Indexed: 03/02/2024]
Abstract
BACKGROUND AND PURPOSE Spontaneous intracranial hypotension is an increasingly recognized condition. Spontaneous intracranial hypotension is caused by a CSF leak, which is commonly related to a CSF-venous fistula. In patients with spontaneous intracranial hypotension, multiple intracranial abnormalities can be observed on brain MR imaging, including dural enhancement, "brain sag," and pituitary engorgement. This study seeks to create a deep learning model for the accurate diagnosis of CSF-venous fistulas via brain MR imaging. MATERIALS AND METHODS A review of patients with clinically suspected spontaneous intracranial hypotension who underwent digital subtraction myelogram imaging preceded by brain MR imaging was performed. The patients were categorized as having a definite CSF-venous fistula, no fistula, or indeterminate findings on a digital subtraction myelogram. The data set was split into 5 folds at the patient level and stratified by label. A 5-fold cross-validation was then used to evaluate the reliability of the model. The predictive value of the model to identify patients with a CSF leak was assessed by using the area under the receiver operating characteristic curve for each validation fold. RESULTS There were 129 patients were included in this study. The median age was 54 years, and 66 (51.2%) had a CSF-venous fistula. In discriminating between positive and negative cases for CSF-venous fistulas, the classifier demonstrated an average area under the receiver operating characteristic curve of 0.8668 with a standard deviation of 0.0254 across the folds. CONCLUSIONS This study developed a deep learning model that can predict the presence of a spinal CSF-venous fistula based on brain MR imaging in patients with suspected spontaneous intracranial hypotension. However, further model refinement and external validation are necessary before clinical adoption. This research highlights the substantial potential of deep learning in diagnosing CSF-venous fistulas by using brain MR imaging.
Collapse
Affiliation(s)
- Shahriar Faghani
- From the Radiology Informatics Lab, Department of Radiology, Mayo Clinic, Rochester, Minnesota
| | - Mana Moassefi
- From the Radiology Informatics Lab, Department of Radiology, Mayo Clinic, Rochester, Minnesota
| | | | - Ian T Mark
- Department of Radiology, Mayo Clinic, Rochester, Minnesota
| | | | - Bradley J Erickson
- From the Radiology Informatics Lab, Department of Radiology, Mayo Clinic, Rochester, Minnesota
| | - John C Benson
- Department of Radiology, Mayo Clinic, Rochester, Minnesota
| |
Collapse
|
2
|
Faghani S, Patel S, Rhodes NG, Powell GM, Baffour FI, Moassefi M, Glazebrook KN, Erickson BJ, Tiegs-Heiden CA. Deep-learning for automated detection of MSU deposits on DECT: evaluating impact on efficiency and reader confidence. FRONTIERS IN RADIOLOGY 2024; 4:1330399. [PMID: 38440382 PMCID: PMC10909828 DOI: 10.3389/fradi.2024.1330399] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Accepted: 01/31/2024] [Indexed: 03/06/2024]
Abstract
Introduction Dual-energy CT (DECT) is a non-invasive way to determine the presence of monosodium urate (MSU) crystals in the workup of gout. Color-coding distinguishes MSU from calcium following material decomposition and post-processing. Manually identifying these foci (most commonly labeled green) is tedious, and an automated detection system could streamline the process. This study aims to evaluate the impact of a deep-learning (DL) algorithm developed for detecting green pixelations on DECT on reader time, accuracy, and confidence. Methods We collected a sample of positive and negative DECTs, reviewed twice-once with and once without the DL tool-with a 2-week washout period. An attending musculoskeletal radiologist and a fellow separately reviewed the cases, simulating clinical workflow. Metrics such as time taken, confidence in diagnosis, and the tool's helpfulness were recorded and statistically analyzed. Results We included thirty DECTs from different patients. The DL tool significantly reduced the reading time for the trainee radiologist (p = 0.02), but not for the attending radiologist (p = 0.15). Diagnostic confidence remained unchanged for both (p = 0.45). However, the DL model identified tiny MSU deposits that led to a change in diagnosis in two cases for the in-training radiologist and one case for the attending radiologist. In 3/3 of these cases, the diagnosis was correct when using DL. Conclusions The implementation of the developed DL model slightly reduced reading time for our less experienced reader and led to improved diagnostic accuracy. There was no statistically significant difference in diagnostic confidence when studies were interpreted without and with the DL model.
Collapse
Affiliation(s)
- Shahriar Faghani
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, Rochester, MN, United States
| | - Soham Patel
- Department of Radiology, Mayo Clinic, Rochester, MN, United States
| | | | - Garret M. Powell
- Department of Radiology, Mayo Clinic, Rochester, MN, United States
| | | | - Mana Moassefi
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, Rochester, MN, United States
| | | | - Bradley J. Erickson
- Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic, Rochester, MN, United States
| | | |
Collapse
|
3
|
Tano ZE, Cumpanas AD, Gorgen ARH, Rojhani A, Altamirano-Villarroel J, Landman J. Surgical Artificial Intelligence: Endourology. Urol Clin North Am 2024; 51:77-89. [PMID: 37945104 DOI: 10.1016/j.ucl.2023.06.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2023]
Abstract
Endourology is ripe with information that includes patient factors, laboratory tests, outcomes, and visual data, which is becoming increasingly complex to assess. Artificial intelligence (AI) has the potential to explore and define these relationships; however, humans might not be involved in the input, analysis, or even determining the methods of analysis. Herein, the authors present the current state of AI in endourology and highlight the need for urologists to share their proposed AI solutions for reproducibility outside of their institutions and prepare themselves to properly critique this new technology.
Collapse
Affiliation(s)
- Zachary E Tano
- Department of Urology, University of California, Irvine, 3800 West Chapman Avenue, Suite 7200, Orange, CA 92868, USA.
| | - Andrei D Cumpanas
- Department of Urology, University of California, Irvine, 3800 West Chapman Avenue, Suite 7200, Orange, CA 92868, USA
| | - Antonio R H Gorgen
- Department of Urology, University of California, Irvine, 3800 West Chapman Avenue, Suite 7200, Orange, CA 92868, USA
| | - Allen Rojhani
- Department of Urology, University of California, Irvine, 3800 West Chapman Avenue, Suite 7200, Orange, CA 92868, USA
| | - Jaime Altamirano-Villarroel
- Department of Urology, University of California, Irvine, 3800 West Chapman Avenue, Suite 7200, Orange, CA 92868, USA
| | - Jaime Landman
- Department of Urology, University of California, Irvine, 3800 West Chapman Avenue, Suite 7200, Orange, CA 92868, USA
| |
Collapse
|
4
|
Padovan M, Cosci B, Petillo A, Nerli G, Porciatti F, Scarinci S, Carlucci F, Dell’Amico L, Meliani N, Necciari G, Lucisano VC, Marino R, Foddis R, Palla A. ChatGPT in Occupational Medicine: A Comparative Study with Human Experts. Bioengineering (Basel) 2024; 11:57. [PMID: 38247934 PMCID: PMC10813435 DOI: 10.3390/bioengineering11010057] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2023] [Revised: 01/01/2024] [Accepted: 01/04/2024] [Indexed: 01/23/2024] Open
Abstract
The objective of this study is to evaluate ChatGPT's accuracy and reliability in answering complex medical questions related to occupational health and explore the implications and limitations of AI in occupational health medicine. The study also provides recommendations for future research in this area and informs decision-makers about AI's impact on healthcare. A group of physicians was enlisted to create a dataset of questions and answers on Italian occupational medicine legislation. The physicians were divided into two teams, and each team member was assigned a different subject area. ChatGPT was used to generate answers for each question, with/without legislative context. The two teams then evaluated human and AI-generated answers blind, with each group reviewing the other group's work. Occupational physicians outperformed ChatGPT in generating accurate questions on a 5-point Likert score, while the answers provided by ChatGPT with access to legislative texts were comparable to those of professional doctors. Still, we found that users tend to prefer answers generated by humans, indicating that while ChatGPT is useful, users still value the opinions of occupational medicine professionals.
Collapse
Affiliation(s)
- Martina Padovan
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Bianca Cosci
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Armando Petillo
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Gianluca Nerli
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Francesco Porciatti
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Sergio Scarinci
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Francesco Carlucci
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Letizia Dell’Amico
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Niccolò Meliani
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Gabriele Necciari
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Vincenzo Carmelo Lucisano
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Riccardo Marino
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | - Rudy Foddis
- Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (B.C.); (A.P.); (G.N.); (F.P.); (S.S.); (F.C.); (L.D.); (N.M.); (G.N.); (R.M.)
| | | |
Collapse
|