Geoffrey Riley is a diagnostic radiologist specializing in musculoskeletal imaging at Stanford University Hospital. His focus is on orthopedic imaging including sports injuries, trauma, and musculoskeletal tumors. He has a special interest in innovative methods of teaching, business development and forensic radiology. As the Director of Radiology Continuing Medical Education, he oversees the Department of Radiology's educational course meetings.
Dr. Riley strives to develop teaching methods that go beyond the traditional lectures where trainees play a passive role. With his experience in serving as an expert witness in numerous civil cases, he has a special interest in educating trainees in medico-legal matters. He serves on the Medical Board of California as an expert reviewer, providing input on the standard of care for radiology.
As the radiology liason of Stanford Hospital's Sarcoma Tumor Board, he provides input on the care of patients with soft tissue, spine and bone tumors.
He is an active member of the Radiological Society of North America, the Society of Skeletal Radiology, and the American Roentgen Ray Society for which he serves on the Scientific Program and Educational Exhibit Subcommittees. Dr. Riley serves on the American Board of Radiology Diagnostic Radiology Core MSK Committee as a test question writer.
As a manuscript reviewer for The American Journal of Roentgenology, The Journal of Hip Preservation Surgery and Skeletal Radiology, he reviews submitted articles and advises the editors of these journal on which submitted papers should be accepted for publication.
Dr. Riley is board certified by the American National Board of Medical Examiners and by the American Board of Radiology.
- Diagnostic Radiology
- Musculoskeletal Diseases
- Orthopedic Radiology
- Spine imaging
- Sports Injuries
- Soft Tissue Tumors
- Magnetic Resonance Imaging MRI
- Bone Tumors
Clinical Professor, Radiology
Director of Radiology Continuing Medical Education, Stanford University, School of Medicine (2017 - Present)
Boards, Advisory Committees, Professional Organizations
CE/ACF Committee, Stanford University School of Medicine Department of Radiology (2014 - Present)
Physician Wellness Committee, Stanford University School of Medicine (2015 - Present)
Health Information Management System Committee, Stanford Health Care (2015 - Present)
Scientific Program Subcommittee, American Journal of Roentgenology (2014 - Present)
Educational Exhibit Subcommittee, American Journal of Roentgenology (2014 - Present)
Manuscript Reviewer, American Journal of Roentgenology (2014 - Present)
Manuscript Reviewer, Skeletal Radiology (2014 - Present)
Fellowship: UC Davis Dept of Radiology (1998) CA
Residency: UC Davis Radiology Residency (1997) CA
Internship: Creighton University Internal Medicine (1993) NE
Medical Education: Creighton University School of Medicine Registrar (1992) NE
Board Certification: Diagnostic Radiology, American Board of Radiology (1997)
Current Research and Scholarly Interests
Femoroacetabular impingement MRI, Hip MRI
- Erratum: Author Correction: Human-machine partnership with artificial intelligence for chest radiograph diagnosis. NPJ digital medicine 2019; 2: 129
Human-machine partnership with artificial intelligence for chest radiograph diagnosis.
NPJ digital medicine
2019; 2: 111
Human-in-the-loop (HITL) AI may enable an ideal symbiosis of human experts and AI models, harnessing the advantages of both while at the same time overcoming their respective limitations. The purpose of this study was to investigate a novel collective intelligence technology designed to amplify the diagnostic accuracy of networked human groups by forming real-time systems modeled on biological swarms. Using small groups of radiologists, the swarm-based technology was applied to the diagnosis of pneumonia on chest radiographs and compared against human experts alone, as well as two state-of-the-art deep learning AI models. Our work demonstrates that both the swarm-based technology and deep-learning technology achieved superior diagnostic accuracy than the human experts alone. Our work further demonstrates that when used in combination, the swarm-based technology and deep-learning technology outperformed either method alone. The superior diagnostic accuracy of the combined HITL AI solution compared to radiologists and AI alone has broad implications for the surging clinical AI deployment and implementation strategies in future practice.
View details for DOI 10.1038/s41746-019-0189-7
View details for PubMedID 31754637
View details for PubMedCentralID PMC6861262
The Cliff Sign: A New Radiographic Sign of Hip Instability
ORTHOPAEDIC JOURNAL OF SPORTS MEDICINE
2018; 6 (11): 2325967118807176
The preoperative diagnosis of hip microinstability is challenging. Although physical examination maneuvers and magnetic resonance imaging findings associated with microinstability have been described, there are limited reports of radiographic features. In patients with microinstability, we observed a high incidence of a steep drop-off on the lateral edge of the femoral head, which we have named the "cliff sign."(1) To determine the relationship of the cliff sign and associated measurements with intraoperative microinstability and (2) to determine the interobserver reliability of these measurements.Cohort study (diagnosis); Level of evidence, 2.A total of 115 consecutive patients who underwent hip arthroscopy were identified. Patients with prior hip surgery, Legg-Calve-Perthes disease, fractures, pigmented villonodular synovitis, or synovial chondromatosis were excluded, resulting in the inclusion of 96 patients in the study. A perfect circle around the femoral head was created on anteroposterior pelvis radiographs. If the lateral femoral head did not completely fill the perfect circle, it was considered a positive cliff sign. Five additional measurements relating to the cliff sign were calculated. The diagnosis of microinstability was made intraoperatively by the (1) amount of traction required to distract the hip, (2) lack of hip reduction after initial traction release following joint venting, or (3) intraoperative findings consistent with hip microinstability. Continuous variables were analyzed through use of unpaired t tests and discrete variables with Fisher exact tests. Interobserver reliability (n = 3) was determined for each measurement.Overall, 89% (39/44) of patients with microinstability had a cliff sign, compared with 27% of patients (14/52) without instability (P < .0001). Conversely, 74% of patients with a cliff sign had microinstability, while only 12% of patients without a cliff sign had instability (P < .0001). In women younger than 32 years with a cliff sign, 100% (20/20) were diagnosed with instability. No differences were found in any of the 5 additional measurements. Excellent interobserver reliability was found for the presence of a cliff sign and the cliff angle measurement.We have identified a radiographic finding, the cliff sign, that is associated with the intraoperative diagnosis of hip microinstability and has excellent interobserver reliability. Results showed that 100% of young women with a cliff sign had intraoperative microinstability. The cliff sign may be useful in the preoperative diagnosis of hip microinstability.
View details for PubMedID 30480017
- Extreme Sports Injuries to the Pelvis and Lower Extremity RADIOLOGIC CLINICS OF NORTH AMERICA 2018; 56 (6): 1013-+
- Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet PLOS MEDICINE 2018; 15 (11)
Extreme Sports Injuries to the Pelvis and Lower Extremity.
Radiologic clinics of North America
2018; 56 (6): 1013–33
Extreme sports are growing in popularity, and physicians are becoming increasingly aware of injuries related to these activities. Imaging plays a key role in diagnosing and determining clinical management of many of these injuries. This article describes general imaging techniques and findings in various injuries specific to multiple extreme sports.
View details for PubMedID 30322484
Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet.
2018; 15 (11): e1002699
BACKGROUND: Magnetic resonance imaging (MRI) of the knee is the preferred method for diagnosing knee injuries. However, interpretation of knee MRI is time-intensive and subject to diagnostic error and variability. An automated system for interpreting knee MRI could prioritize high-risk patients and assist clinicians in making diagnoses. Deep learning methods, in being able to automatically learn layers of features, are well suited for modeling the complex relationships between medical images and their interpretations. In this study we developed a deep learning model for detecting general abnormalities and specific diagnoses (anterior cruciate ligament [ACL] tears and meniscal tears) on knee MRI exams. We then measured the effect of providing the model's predictions to clinical experts during interpretation.METHODS AND FINDINGS: Our dataset consisted of 1,370 knee MRI exams performed at Stanford University Medical Center between January 1, 2001, and December 31, 2012 (mean age 38.0 years; 569 [41.5%] female patients). The majority vote of 3 musculoskeletal radiologists established reference standard labels on an internal validation set of 120 exams. We developed MRNet, a convolutional neural network for classifying MRI series and combined predictions from 3 series per exam using logistic regression. In detecting abnormalities, ACL tears, and meniscal tears, this model achieved area under the receiver operating characteristic curve (AUC) values of 0.937 (95% CI 0.895, 0.980), 0.965 (95% CI 0.938, 0.993), and 0.847 (95% CI 0.780, 0.914), respectively, on the internal validation set. We also obtained a public dataset of 917 exams with sagittal T1-weighted series and labels for ACL injury from Clinical Hospital Centre Rijeka, Croatia. On the external validation set of 183 exams, the MRNet trained on Stanford sagittal T2-weighted series achieved an AUC of 0.824 (95% CI 0.757, 0.892) in the detection of ACL injuries with no additional training, while an MRNet trained on the rest of the external data achieved an AUC of 0.911 (95% CI 0.864, 0.958). We additionally measured the specificity, sensitivity, and accuracy of 9 clinical experts (7 board-certified general radiologists and 2 orthopedic surgeons) on the internal validation set both with and without model assistance. Using a 2-sided Pearson's chi-squared test with adjustment for multiple comparisons, we found no significant differences between the performance of the model and that of unassisted general radiologists in detecting abnormalities. General radiologists achieved significantly higher sensitivity in detecting ACL tears (p-value = 0.002; q-value = 0.019) and significantly higher specificity in detecting meniscal tears (p-value = 0.003; q-value = 0.019). Using a 1-tailed t test on the change in performance metrics, we found that providing model predictions significantly increased clinical experts' specificity in identifying ACL tears (p-value < 0.001; q-value = 0.006). The primary limitations of our study include lack of surgical ground truth and the small size of the panel of clinical experts.CONCLUSIONS: Our deep learning model can rapidly generate accurate clinical pathology classifications of knee MRI exams from both internal and external datasets. Moreover, our results support the assertion that deep learning models can improve the performance of clinical experts during medical imaging interpretation. Further research is needed to validate the model prospectively and to determine its utility in the clinical setting.
View details for PubMedID 30481176
Extraskeletal osteosarcoma of the hand: the role of marginal excision and adjuvant radiation therapy.
Hand (New York, N.Y.)
2015; 10 (4): 602-606
Extraskeletal osteosarcoma of the hand is rare, and its optimal modality of local control is not currently known.A literature search was performed to identify studies that describe the treatment and outcomes of extraskeletal osteosarcoma. A second literature search was performed to identify studies that describe the treatment and outcomes of extraskeletal osteosarcoma of the hand specifically.The role of adjuvant radiation for extraskeletal osteosarcoma is not well defined. All cases in the literature describing treatment of extraskeletal osteosarcoma of the hand utilized amputation, and none of the patients described received radiation therapy. However, there are multiple reports showing excellent local control, minimal toxicity, and superior functional outcome with limb conservation and radiation rather than amputation of the hand in pediatric and adult soft tissue sarcoma.For extraskeletal osteosarcoma of the hand, we recommend a treatment approach with the goal of preservation of form and function using limb-sparing surgery and planned postoperative radiation.
View details for DOI 10.1007/s11552-015-9760-0
View details for PubMedID 26568711
Approach to MR Imaging of the Elbow and Wrist: Technical Aspects and Innovation.
Magnetic resonance imaging clinics of North America
2015; 23 (3): 355-366
Wrist and elbow MR imaging technology is advancing at a dramatic rate. Wrist and elbow MR imaging is performed at medium and higher field strengths with more specialized surface coils and more variable pulse sequences and postprocessing techniques. High field imaging and improved coils lead to an increased signal-to-noise ratio and increased variety of soft tissue contrast options. Three-dimensional imaging is improving in terms of usability and artifacts. Some of these advances have challenges in wrist and elbow imaging, such as postoperative patient imaging, cartilage mapping, and molecular imaging. This review considers technical advances in hardware and software and their clinical applications.
View details for DOI 10.1016/j.mric.2015.04.008
View details for PubMedID 26216768
- MRI of the Hip for the Evaluation of Femoroacetabular Impingement; Past, Present, and Future JOURNAL OF MAGNETIC RESONANCE IMAGING 2015; 41 (3): 558–72
MRI of the Hip for the evaluation of femoroacetabular impingement; past, present, and future.
Journal of magnetic resonance imaging : JMRI
2015; 41 (3): 558-572
The concept of femoroacetabular impingement (FAI) has, in a relatively short time, come to the forefront of orthopedic imaging. In just a few short years MRI findings that were in the past ascribed to degenerative change, normal variation, or other pathologies must now be described and included in radiology reports, as they have been shown, or are suspected to be related to, FAI. Crucial questions have come up in this time, including: what is the relationship of bony morphology to subsequent cartilage and labral damage, and most importantly, how is this morphology related to the development of osteoarthritis? In this review, we attempt to place a historical perspective on the controversy, provide guidelines for interpretation of MRI examinations of patients with suspected FAI, and offer a glimpse into the future of MRI of this complex condition. J. Magn. Reson. Imaging 2014. © 2014 Wiley Periodicals, Inc.
View details for DOI 10.1002/jmri.24725
View details for PubMedID 25155435
Foot and ankle injuries in sport: imaging correlation with arthroscopic and surgical findings.
Clinics in sports medicine
2013; 32 (3): 525-557
Foot and ankle injuries are common in sport. Although many available imaging techniques can be useful in identifying and classifying injuries, magnetic resonance imaging (MRI) provides high levels of sensitivity and specificity for articular and soft-tissue injuries. Arthroscopic and minimally invasive treatment techniques for foot and ankle injuries are rapidly evolving, minimizing morbidity and improving postoperative rehabilitation and return to play. Correlation between MRI and surgical findings can aid in both accessing and treating pathologic processes and structures.
View details for DOI 10.1016/j.csm.2013.03.007
View details for PubMedID 23773880
Hip-femoral acetabular impingement.
Clinics in sports medicine
2013; 32 (3): 409-425
Magnetic resonance imaging (MRI) has become a valuable technology for the diagnosis and treatment of femoroacetabular impingement (FAI). This article reviews the basic pathophysiology of FAI, as well as the techniques and indications for MRI and magnetic resonance arthrography. Normal MRI anatomy of the hip and pathologic MRI anatomy associated with FAI are also discussed. Several case examples are presented demonstrating the diagnosis and treatment of FAI.
View details for DOI 10.1016/j.csm.2013.03.010
View details for PubMedID 23773875
Magnetic Resonance Arthrography
RADIOLOGIC CLINICS OF NORTH AMERICA
2009; 47 (3): 471-?
Magnetic resonance arthrography is widely used throughout the world for joint imaging. It extends the capabilities of conventional MR imaging because contrast solution distends the joint capsule, outlines intraarticular structures, and extends into soft tissue tears and defects. MR arthrography exploits the natural advantages gained from a joint effusion and can be performed on any joint.
View details for DOI 10.1016/j.rcl.2009.02.001
View details for Web of Science ID 000265891400010
View details for PubMedID 19361671
Magnetic resonance imaging in the evaluation of sports injuries of the foot and ankle - A pictorial essay
JOURNAL OF THE AMERICAN PODIATRIC MEDICAL ASSOCIATION
2007; 97 (1): 59-67
Magnetic resonance imaging is playing an increasingly important role in evaluation of the injured athlete's foot and ankle. Magnetic resonance imaging allows accurate detection of bony abnormalities, such as stress fractures, and soft-tissue abnormalities, including ligament tears, tendon tears, and tendinopathy. The interpreter of magnetic resonance images should systematically review the images, noting normal structures and accounting for changes in soft-tissue and bony signal.
View details for Web of Science ID 000243774300007
View details for PubMedID 17218626
Magnetic resonance imaging of sports injuries of the elbow.
Topics in magnetic resonance imaging
2003; 14 (1): 69-86
Many abnormalities seen in the elbow result from trauma, often from sports such as baseball and tennis. Elbow problems are frequently related to the medial tension-lateral compression phenomenon, where repeated valgus stress produces flexor-pronator strain, ulnar collateral ligament sprain, ulnar traction spurring, and ulnar neuropathy. Lateral compression causes osteochondral lesions of the capitellum and radial head, degenerative arthritis, and loose bodies. Other elbow abnormalities seen on magnetic resonance imaging include radial collateral ligament injuries, biceps and triceps tendon injuries, other nerve entrapment syndromes, loose bodies, osseous and soft-tissue trauma, arthritis, and masses, including bursae.
View details for PubMedID 12606870
- Intraosseous lipoma of the calcaneus FOOT & ANKLE INTERNATIONAL 1997; 18 (1): 53-56
- Fibrous dysplasia of a parietal bone JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY 1997; 21 (1): 41-43