1
|
Frosolini A, Franz L, Caragli V, Genovese E, de Filippis C, Marioni G. Artificial Intelligence in Audiology: A Scoping Review of Current Applications and Future Directions. SENSORS (BASEL, SWITZERLAND) 2024; 24:7126. [PMID: 39598904 PMCID: PMC11598364 DOI: 10.3390/s24227126] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/14/2024] [Revised: 10/31/2024] [Accepted: 11/04/2024] [Indexed: 11/29/2024]
Abstract
The integration of artificial intelligence (AI) into medical disciplines is rapidly transforming healthcare delivery, with audiology being no exception. By synthesizing the existing literature, this review seeks to inform clinicians, researchers, and policymakers about the potential and challenges of integrating AI into audiological practice. The PubMed, Cochrane, and Google Scholar databases were searched for articles published in English from 1990 to 2024 with the following query: "(audiology) AND ("artificial intelligence" OR "machine learning" OR "deep learning")". The PRISMA extension for scoping reviews (PRISMA-ScR) was followed. The database research yielded 1359 results, and the selection process led to the inclusion of 104 manuscripts. The integration of AI in audiology has evolved significantly over the succeeding decades, with 87.5% of manuscripts published in the last 4 years. Most types of AI were consistently used for specific purposes, such as logistic regression and other statistical machine learning tools (e.g., support vector machine, multilayer perceptron, random forest, deep belief network, decision tree, k-nearest neighbor, or LASSO) for automated audiometry and clinical predictions; convolutional neural networks for radiological image analysis; and large language models for automatic generation of diagnostic reports. Despite the advances in AI technologies, different ethical and professional challenges are still present, underscoring the need for larger, more diverse data collection and bioethics studies in the field of audiology.
Collapse
Affiliation(s)
- Andrea Frosolini
- Maxillofacial Surgery Unit, Department of Medical Biotechnology, S. Maria alle Scotte University Hospital of Siena, 53100 Siena, Italy;
| | - Leonardo Franz
- Phoniatris and Audiology Unit, Department of Neuroscience DNS, University of Padova, 33100 Treviso, Italy; (L.F.); (C.d.F.); (G.M.)
| | - Valeria Caragli
- Audiology Program, Otorhinolaryngology Unit, Department of Medical and Surgical Sciences for Children and Adults, University of Modena and Reggio Emilia, 41124 Modena, Italy;
| | - Elisabetta Genovese
- Audiology Program, Otorhinolaryngology Unit, Department of Medical and Surgical Sciences for Children and Adults, University of Modena and Reggio Emilia, 41124 Modena, Italy;
- Audiology Program, Department of Maternal, Child and Adult Medical and Surgical Sciences, University of Modena and Reggio Emilia, 41124 Modena, Italy
| | - Cosimo de Filippis
- Phoniatris and Audiology Unit, Department of Neuroscience DNS, University of Padova, 33100 Treviso, Italy; (L.F.); (C.d.F.); (G.M.)
| | - Gino Marioni
- Phoniatris and Audiology Unit, Department of Neuroscience DNS, University of Padova, 33100 Treviso, Italy; (L.F.); (C.d.F.); (G.M.)
| |
Collapse
|
2
|
Spinos D, Martinos A, Petsiou DP, Mistry N, Garas G. Artificial Intelligence in Temporal Bone Imaging: A Systematic Review. Laryngoscope 2024. [PMID: 39352072 DOI: 10.1002/lary.31809] [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: 05/08/2024] [Revised: 08/03/2024] [Accepted: 09/17/2024] [Indexed: 10/03/2024]
Abstract
OBJECTIVE The human temporal bone comprises more than 30 identifiable anatomical components. With the demand for precise image interpretation in this complex region, the utilization of artificial intelligence (AI) applications is steadily increasing. This systematic review aims to highlight the current role of AI in temporal bone imaging. DATA SOURCES A Systematic Review of English Publications searching MEDLINE (PubMed), COCHRANE Library, and EMBASE. REVIEW METHODS The search algorithm employed consisted of key items such as 'artificial intelligence,' 'machine learning,' 'deep learning,' 'neural network,' 'temporal bone,' and 'vestibular schwannoma.' Additionally, manual retrieval was conducted to capture any studies potentially missed in our initial search. All abstracts and full texts were screened based on our inclusion and exclusion criteria. RESULTS A total of 72 studies were included. 95.8% were retrospective and 88.9% were based on internal databases. Approximately two-thirds involved an AI-to-human comparison. Computed tomography (CT) was the imaging modality in 54.2% of the studies, with vestibular schwannoma (VS) being the most frequent study item (37.5%). Fifty-eight out of 72 articles employed neural networks, with 72.2% using various types of convolutional neural network models. Quality assessment of the included publications yielded a mean score of 13.6 ± 2.5 on a 20-point scale based on the CONSORT-AI extension. CONCLUSION Current research data highlight AI's potential in enhancing diagnostic accuracy with faster results and decreased performance errors compared to those of clinicians, thus improving patient care. However, the shortcomings of the existing research, often marked by heterogeneity and variable quality, underscore the need for more standardized methodological approaches to ensure the consistency and reliability of future data. LEVEL OF EVIDENCE NA Laryngoscope, 2024.
Collapse
Affiliation(s)
- Dimitrios Spinos
- South Warwickshire NHS Foundation Trust, Warwick, UK
- University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - Anastasios Martinos
- National and Kapodistrian University of Athens School of Medicine, Athens, Greece
| | | | - Nina Mistry
- Gloucestershire Hospitals NHS Foundation Trust, ENT, Head and Neck Surgery, Gloucester, UK
| | - George Garas
- Surgical Innovation Centre, Department of Surgery and Cancer, Imperial College London, St. Mary's Hospital, London, UK
- Athens Medical Center, Marousi & Psychiko Clinic, Athens, Greece
| |
Collapse
|
3
|
Heman-Ackah SM, Blue R, Quimby AE, Abdallah H, Sweeney EM, Chauhan D, Hwa T, Brant J, Ruckenstein MJ, Bigelow DC, Jackson C, Zenonos G, Gardner P, Briggs SE, Cohen Y, Lee JYK. A multi-institutional machine learning algorithm for prognosticating facial nerve injury following microsurgical resection of vestibular schwannoma. Sci Rep 2024; 14:12963. [PMID: 38839778 PMCID: PMC11153496 DOI: 10.1038/s41598-024-63161-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2023] [Accepted: 05/26/2024] [Indexed: 06/07/2024] Open
Abstract
Vestibular schwannomas (VS) are the most common tumor of the skull base with available treatment options that carry a risk of iatrogenic injury to the facial nerve, which can significantly impact patients' quality of life. As facial nerve outcomes remain challenging to prognosticate, we endeavored to utilize machine learning to decipher predictive factors relevant to facial nerve outcomes following microsurgical resection of VS. A database of patient-, tumor- and surgery-specific features was constructed via retrospective chart review of 242 consecutive patients who underwent microsurgical resection of VS over a 7-year study period. This database was then used to train non-linear supervised machine learning classifiers to predict facial nerve preservation, defined as House-Brackmann (HB) I vs. facial nerve injury, defined as HB II-VI, as determined at 6-month outpatient follow-up. A random forest algorithm demonstrated 90.5% accuracy, 90% sensitivity and 90% specificity in facial nerve injury prognostication. A random variable (rv) was generated by randomly sampling a Gaussian distribution and used as a benchmark to compare the predictiveness of other features. This analysis revealed age, body mass index (BMI), case length and the tumor dimension representing tumor growth towards the brainstem as prognosticators of facial nerve injury. When validated via prospective assessment of facial nerve injury risk, this model demonstrated 84% accuracy. Here, we describe the development of a machine learning algorithm to predict the likelihood of facial nerve injury following microsurgical resection of VS. In addition to serving as a clinically applicable tool, this highlights the potential of machine learning to reveal non-linear relationships between variables which may have clinical value in prognostication of outcomes for high-risk surgical procedures.
Collapse
Affiliation(s)
- Sabrina M Heman-Ackah
- Department of Neurosurgery, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, 15th Floor, Philadelphia, PA, 19104, USA.
- Department of Bioengineering, University of Pennsylvania, Philadelphia, PA, USA.
| | - Rachel Blue
- Department of Neurosurgery, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, 15th Floor, Philadelphia, PA, 19104, USA
| | - Alexandra E Quimby
- Department of Otorhinolaryngology, University of Pennsylvania, Philadelphia, PA, USA
- Department of Otolaryngology and Communication Sciences, SUNY Upstate Medical University Hospital, Syracuse, NY, USA
| | - Hussein Abdallah
- School of Medicine, University of Pittsburgh, Pittsburgh, PA, USA
| | - Elizabeth M Sweeney
- Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, PA, USA
| | - Daksh Chauhan
- University of Pennsylvania, Perelman School of Medicine, Philadelphia, PA, USA
| | - Tiffany Hwa
- Department of Otorhinolaryngology, University of Pennsylvania, Philadelphia, PA, USA
| | - Jason Brant
- Department of Otorhinolaryngology, University of Pennsylvania, Philadelphia, PA, USA
- Corporal Michael J. Crescenz VAMC, Philadelphia, PA, USA
| | - Michael J Ruckenstein
- Department of Otorhinolaryngology, University of Pennsylvania, Philadelphia, PA, USA
| | - Douglas C Bigelow
- Department of Otorhinolaryngology, University of Pennsylvania, Philadelphia, PA, USA
| | - Christina Jackson
- Department of Neurosurgery, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, 15th Floor, Philadelphia, PA, 19104, USA
| | - Georgios Zenonos
- Center for Cranial Base Surgery, University of Pittsburgh, Pittsburgh, PA, USA
| | - Paul Gardner
- Center for Cranial Base Surgery, University of Pittsburgh, Pittsburgh, PA, USA
| | - Selena E Briggs
- Department of Otolaryngology, MedStar Washington Hospital Center, Washington, DC, USA
- Department of Otolaryngology, Georgetown University, Washington, DC, USA
| | - Yale Cohen
- Department of Bioengineering, University of Pennsylvania, Philadelphia, PA, USA
- Department of Otorhinolaryngology, University of Pennsylvania, Philadelphia, PA, USA
- University of Pennsylvania, Perelman School of Medicine, Philadelphia, PA, USA
| | - John Y K Lee
- Department of Neurosurgery, Perelman Center for Advanced Medicine, University of Pennsylvania, 3400 Civic Center Boulevard, 15th Floor, Philadelphia, PA, 19104, USA
- Department of Otorhinolaryngology, University of Pennsylvania, Philadelphia, PA, USA
| |
Collapse
|
4
|
Wang D, Liu J, Lin Q, Yu H. A decision-making system based on case-based reasoning for predicting stroke rehabilitation demands in heterogeneous information environment. Appl Soft Comput 2024; 154:111358. [DOI: 10.1016/j.asoc.2024.111358] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/03/2025]
|
5
|
Koechli C, Zwahlen DR, Schucht P, Windisch P. Radiomics and machine learning for predicting the consistency of benign tumors of the central nervous system: A systematic review. Eur J Radiol 2023; 164:110866. [PMID: 37207398 DOI: 10.1016/j.ejrad.2023.110866] [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: 03/14/2023] [Revised: 04/28/2023] [Accepted: 05/03/2023] [Indexed: 05/21/2023]
Abstract
PURPOSE Predicting the consistency of benign central nervous system (CNS) tumors prior to surgery helps to improve surgical outcomes. This review summarizes and analyzes the literature on using radiomics and/or machine learning (ML) for consistency prediction. METHOD The Medical Literature Analysis and Retrieval System Online (MEDLINE) database was screened for studies published in English from January 1st 2000. Data was extracted according to the PRISMA guidelines and quality of the studies was assessed in compliance with the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). RESULTS Eight publications were included focusing on pituitary macroadenomas (n = 5), pituitary adenomas (n = 1), and meningiomas (n = 2) using a retrospective (n = 6), prospective (n = 1), and unknown (n = 1) study design with a total of 763 patients for the consistency prediction. The studies reported an area under the curve (AUC) of 0.71-0.99 for their respective best performing model regarding the consistency prediction. Of all studies, four articles validated their models internally whereas none validated their models externally. Two articles stated making data available on request with the remaining publications lacking information with regard to data availability. CONCLUSIONS The research on consistency prediction of CNS tumors is still at an early stage regarding the use of radiomics and different ML techniques. Best-practice procedures regarding radiomics and ML need to be followed more rigorously to facilitate the comparison between publications and, accordingly, the possible implementation into clinical practice in the future.
Collapse
Affiliation(s)
- Carole Koechli
- Department of Radiation Oncology, Kantonsspital Winterthur, 8401 Winterthur, Switzerland; Universitätsklinik für Neurochirurgie, Bern University Hospital, 3010 Bern, Switzerland.
| | - Daniel R Zwahlen
- Department of Radiation Oncology, Kantonsspital Winterthur, 8401 Winterthur, Switzerland
| | - Philippe Schucht
- Universitätsklinik für Neurochirurgie, Bern University Hospital, 3010 Bern, Switzerland
| | - Paul Windisch
- Department of Radiation Oncology, Kantonsspital Winterthur, 8401 Winterthur, Switzerland
| |
Collapse
|
6
|
Gheorghe L, Negru D, Cobzeanu MD, Palade OD, Botnariu EG, Cobzeanu BM, Cobzeanu ML. The Diagnostic Accuracy of Pure-Tone Audiometry Screening Protocols for Vestibular Schwannoma in Patients with Asymmetrical Hearing Loss-A Systematic Review and Meta-Analysis. Diagnostics (Basel) 2022; 12:diagnostics12112776. [PMID: 36428836 PMCID: PMC9689241 DOI: 10.3390/diagnostics12112776] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Revised: 11/01/2022] [Accepted: 11/07/2022] [Indexed: 11/16/2022] Open
Abstract
(1) Background: Magnetic resonance imaging (MRI) is the gold standard investigation for all patients who present with asymmetrical hearing loss (AHL) and a high index of suspicion for vestibular schwannoma (VS). However, pure-tone audiometry (PTA) is an investigation that can be used for the screening of these patients in order to reduce the costs. The aim of this systematic review and meta-analysis was to evaluate the diagnostic accuracy of different PTA protocols for VS in patients with ASHL, when compared with MRI; (2) Methods: Medline, Embase, and Cochrane databases were used to find relevant studies. All prospective and retrospective observational studies that evaluated the accuracy of PTA protocols for the screening of VS were assessed, according to the international guidelines; (3) Results: We analyzed seven studies (4369 patients) of poor-to-moderate quality. Their pooled sensitivity was good (0.73-0.93), but their specificity was low (0.31-0.60). All protocols were located in the right lower quadrant on the likelihood scattergram, and the post-test probabilities for positive and negative diagnosis of these protocols were extremely low; (4) Conclusions: PTA protocols cannot be used for a proper screening or diagnosis of vestibular schwannoma despite their good sensibility, and MRI remains the gold standard for this purpose.
Collapse
Affiliation(s)
- Liliana Gheorghe
- Surgical Department, Faculty of Medicine, University of Medicine and Pharmacy “Grigore T. Popa”, 700115 Iasi, Romania
- Emergency Clinical Hospital “Sfântul Spiridon” Iasi, 700111 Iasi, Romania
| | - Dragos Negru
- Surgical Department, Faculty of Medicine, University of Medicine and Pharmacy “Grigore T. Popa”, 700115 Iasi, Romania
- Emergency Clinical Hospital “Sfântul Spiridon” Iasi, 700111 Iasi, Romania
| | - Mihail Dan Cobzeanu
- Surgical Department, Faculty of Medicine, University of Medicine and Pharmacy “Grigore T. Popa”, 700115 Iasi, Romania
- Emergency Clinical Hospital “Sfântul Spiridon” Iasi, 700111 Iasi, Romania
| | - Octavian Dragos Palade
- Surgical Department, Faculty of Medicine, University of Medicine and Pharmacy “Grigore T. Popa”, 700115 Iasi, Romania
- Emergency Clinical Hospital “Sfântul Spiridon” Iasi, 700111 Iasi, Romania
- Correspondence: (O.D.P.); (E.G.B.)
| | - Eosefina Gina Botnariu
- Emergency Clinical Hospital “Sfântul Spiridon” Iasi, 700111 Iasi, Romania
- Internal Medicine Department, Faculty of Medicine, University of Medicine and Pharmacy “Grigore T. Popa”, 700115 Iasi, Romania
- Correspondence: (O.D.P.); (E.G.B.)
| | - Bogdan Mihail Cobzeanu
- Surgical Department, Faculty of Medicine, University of Medicine and Pharmacy “Grigore T. Popa”, 700115 Iasi, Romania
- Clinical Rehabilitation Hospital, 700661 Iasi, Romania
| | - Maria-Luiza Cobzeanu
- Surgical Department, Faculty of Medicine, University of Medicine and Pharmacy “Grigore T. Popa”, 700115 Iasi, Romania
- Emergency Clinical Hospital “Sfântul Spiridon” Iasi, 700111 Iasi, Romania
| |
Collapse
|
7
|
Convolutional Neural Networks to Detect Vestibular Schwannomas on Single MRI Slices: A Feasibility Study. Cancers (Basel) 2022; 14:cancers14092069. [PMID: 35565199 PMCID: PMC9104481 DOI: 10.3390/cancers14092069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/10/2022] [Revised: 03/30/2022] [Accepted: 04/19/2022] [Indexed: 02/04/2023] Open
Abstract
Simple Summary Due to the fact that they take inter-slice information into account, 3D- and 2.5D-convolutional neural networks (CNNs) potentially perform better in tumor detection tasks than 2D-CNNs. However, this potential benefit is at the expense of increased computational power and the need for segmentations as an input. Therefore, in this study we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. We retrained (539 patients) and internally validated (94 patients) a pretrained CNN using contrast-enhanced MRI slices from one institution. Furthermore, we externally validated the CNN using contrast-enhanced MRI slices from another institution. This resulted in an accuracy of 0.949 (95% CI 0.935–0.963) and 0.912 (95% CI 0.866–0.958) for the internal and external validation, respectively. Our findings indicate that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased requirement for computational power and the fact that there is no need for segmentations. Abstract In this study. we aimed to detect vestibular schwannomas (VSs) in individual magnetic resonance imaging (MRI) slices by using a 2D-CNN. A pretrained CNN (ResNet-34) was retrained and internally validated using contrast-enhanced T1-weighted (T1c) MRI slices from one institution. In a second step, the model was externally validated using T1c- and T1-weighted (T1) slices from a different institution. As a substitute, bisected slices were used with and without tumors originating from whole transversal slices that contained part of the unilateral VS. The model predictions were assessed based on the categorical accuracy and confusion matrices. A total of 539, 94, and 74 patients were included for training, internal validation, and external T1c validation, respectively. This resulted in an accuracy of 0.949 (95% CI 0.935–0.963) for the internal validation and 0.912 (95% CI 0.866–0.958) for the external T1c validation. We suggest that 2D-CNNs might be a promising alternative to 2.5-/3D-CNNs for certain tasks thanks to the decreased demand for computational power and the fact that there is no need for segmentations. However, further research is needed on the difference between 2D-CNNs and more complex architectures.
Collapse
|
8
|
Gadot R, Anand A, Lovin BD, Sweeney AD, Patel AJ. Predicting surgical decision-making in vestibular schwannoma using tree-based machine learning. Neurosurg Focus 2022; 52:E8. [DOI: 10.3171/2022.1.focus21708] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2021] [Accepted: 01/19/2022] [Indexed: 11/06/2022]
Abstract
OBJECTIVE
Vestibular schwannomas (VSs) are the most common neoplasm of the cerebellopontine angle in adults. Though these lesions are generally slow growing, their growth patterns and associated symptoms can be unpredictable, which may complicate the decision to pursue conservative management versus active intervention. Additionally, surgical decision-making can be controversial because of limited high-quality evidence and multiple quality-of-life considerations. Machine learning (ML) is a powerful tool that utilizes data sets to essentialize multidimensional clinical processes. In this study, the authors trained multiple tree-based ML algorithms to predict the decision for active treatment versus MRI surveillance of VS in a single institutional cohort. In doing so, they sought to assess which preoperative variables carried the most weight in driving the decision for intervention and could be used to guide future surgical decision-making through an evidence-based approach.
METHODS
The authors reviewed the records of patients who had undergone evaluation by neurosurgery and otolaryngology with subsequent active treatment (resection or radiation) for unilateral VS in the period from 2009 to 2021, as well as those of patients who had been evaluated for VS and were managed conservatively throughout 2021. Clinical presentation, radiographic data, and management plans were abstracted from each patient record from the time of first evaluation until the last follow-up or surgery. Each encounter with the patient was treated as an instance involving a management decision that depended on demographics, symptoms, and tumor profile. Decision tree and random forest classifiers were trained and tested to predict the decision for treatment versus imaging surveillance on the basis of unseen data using an 80/20 pseudorandom split. Predictor variables were tuned to maximize performance based on lowest Gini impurity indices. Model performance was optimized using fivefold cross-validation.
RESULTS
One hundred twenty-four patients with 198 rendered decisions concerning management were included in the study. In the decision tree analysis, only a maximum tumor dimension threshold of 1.6 cm and progressive symptoms were required to predict the decision for treatment with 85% accuracy. Optimizing maximum dimension thresholds and including age at presentation boosted accuracy to 88%. Random forest analysis (n = 500 trees) predicted the decision for treatment with 80% accuracy. Factors with the highest variable importance based on multiple measures of importance, including mean minimal conditional depth and largest Gini impurity reduction, were maximum tumor dimension, age at presentation, Koos grade, and progressive symptoms at presentation.
CONCLUSIONS
Tree-based ML was used to predict which factors drive the decision for active treatment of VS with 80%–88% accuracy. The most important factors were maximum tumor dimension, age at presentation, Koos grade, and progressive symptoms. These results can assist in surgical decision-making and patient counseling. They also demonstrate the power of ML algorithms in extracting useful insights from limited data sets.
Collapse
Affiliation(s)
- Ron Gadot
- Department of Neurosurgery, Baylor College of Medicine
| | - Adrish Anand
- Department of Neurosurgery, Baylor College of Medicine
| | - Benjamin D. Lovin
- Department of Otolaryngology-Head and Neck Surgery, Baylor College of Medicine, Houston; and
| | - Alex D. Sweeney
- Department of Otolaryngology-Head and Neck Surgery, Baylor College of Medicine, Houston; and
| | - Akash J. Patel
- Department of Neurosurgery, Baylor College of Medicine
- Jan and Dan Duncan Neurological Research Institute, Texas Children’s Hospital, Houston, Texas
| |
Collapse
|