Combining deep learning and model-based segmentation for labeled spine CT segmentation

Buerger, Christian; Berg, Jens von; Franz, Astrid; Klinder, Tobias; Lorenz, Cristian; Lenga, Matthias

doi:10.1117/12.2549485

Cited by 12 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such an image may assist the radiologist in fracture assessment because the heat map typically does not contain information on the degree of fracture. Localization and labeling of vertebra [ 7 – 15 ] In addition to the fracture identification and localization the algorithm also assigns the vertebral label such as T8 or L4 to each fractured or all vertebrae visible in the images. Labeling is typically an initial step of fully automated fracture detection and classification algorithms.…”

Section: Vertebral Fracture Assessmentmentioning

confidence: 99%

“…Techniques like a support vector machine (SVM), random forest classification or CNNs are used for this task. Segmentation [ 7 , 12 – 19 ] AI-based automated vertebral fracture detection algorithms often require an automatic segmentation of the vertebrae or the vertebral bodies. Resulting segmentation masks facilitate the quantification of fracture.…”

Section: Vertebral Fracture Assessmentmentioning

confidence: 99%

See 1 more Smart Citation

Opportunistic Screening Techniques for Analysis of CT Scans

Engelke

Chaudry

Bartenschlager

2022

Curr Osteoporos Rep

View full text Add to dashboard Cite

Purpose of Review Opportunistic screening is a combination of techniques to identify subjects of high risk for osteoporotic fracture using routine clinical CT scans prescribed for diagnoses unrelated to osteoporosis. The two main components are automated detection of vertebral fractures and measurement of bone mineral density (BMD) in CT scans, in which a phantom for calibration of CT to BMD values is not used. This review describes the particular challenges of opportunistic screening and provides an overview and comparison of current techniques used for opportunistic screening. The review further outlines the performance of opportunistic screening. Recent Findings A wide range of technologies for the automatic detection of vertebral fractures have been developed and successfully validated. Most of them are based on artificial intelligence algorithms. The automated differentiation of osteoporotic from traumatic fractures and vertebral deformities unrelated to osteoporosis, the grading of vertebral fracture severity, and the detection of mild vertebral fractures is still problematic. The accuracy of automated fracture detection compared to classical radiological semi-quantitative Genant scoring is about 80%. Accuracy errors of alternative BMD calibration methods compared to simultaneous phantom-based calibration used in standard quantitative CT (QCT) range from below 5% to about 10%. The impact of contrast agents, frequently administered in clinical CT on the determination of BMD and on fracture risk determination is still controversial. Summary Opportunistic screening, the identification of vertebral fracture and the measurement of BMD using clinical routine CT scans, is feasible but corresponding techniques still need to be integrated into the clinical workflow and further validated with respect to the prediction of fracture risk.

show abstract

Section: Vertebral Fracture Assessmentmentioning

confidence: 99%

Section: Vertebral Fracture Assessmentmentioning

confidence: 99%

Opportunistic Screening Techniques for Analysis of CT Scans

Engelke

Chaudry

Bartenschlager

2022

Curr Osteoporos Rep

View full text Add to dashboard Cite

show abstract

“…Für die Identifikation von Wirbelkörperfrakturen wurde von uns ein Frakturdiagnostik-KI-Algorithmus entwickelt [12], der zunächst die Zentren der Wirbelkörper lokalisiert [13], um die dann Ausschnitte aus 3D Volumina der Größe 60 × 50 × 40 mm platziert werden, die den jeweiligen Wirbelkörper umschließen. Ein zweites neuronales Netz [14] wurde dann darauf trainiert, zu erkennen, ob der Ausschnitt einen Osteoporose-typisch frakturierten Wirbelkörper enthält oder nicht.…”

Section: Querverbindungen Von Osteologischen Zu Lungenerkrankungenunclassified

Radiologische Diagnostik und Prognostik von COVID-19: Einsatz von künstlicher Intelligenz und Zusammenhang mit muskulo-skelettaler Bildgebung

et al. 2022

View full text Add to dashboard Cite

ZusammenfassungDie COVID-19 Pandemie hat die Radiologie, wie viele andere Bereiche, vor völlig neue Herausforderungen gestellt. Radiologische Bildgebung spielt im Verbund mit Laboruntersuchungen und klinischen Daten eine wichtige Rolle bei der Diagnose von COVID-19. Anhand einer spezifischen Analyse der Lungenläsionen erlaubt sie auch Einschätzungen des Risikos schwerer Verläufe, wenngleich die Größenordnung des Informationsgewinns über biologisch klinische Daten hinaus im Einzelfall unterschiedlich und Gegenstand aktueller Forschung ist. Osteoporose-bedingte Frakturen stellen in diesem Zusammenhang möglicherweise einen unabhängigen Risikofaktor für schwere Verläufe dar. Die Pandemie hat aber auch neue Perspektiven eröffnet, insbesondere sind im Bereich der Bildgebung neue technologische Entwicklungen mit Nachdruck vorangetrieben worden. So arbeiten alle Universitätsradiologien am Projekt Radiological Cooperative Network (RACOON) zusammen, wobei auf der Basis strukturierter Befunde die Daten zusammengeführt und optional mit Methoden der künstlichen Intelligenz (KI) analysiert werden. Eine Zusammenführung mit KI-Methoden zur Frakturerkennungen bietet Perspektiven, Frakturinformationen automatisch zu gewinnen und in Risiko-Scores für schweren Verlauf mit einzubinden. Die neuen Strukturen und Methoden, die während der Pandemie entwickelt wurden, lassen sich auf andere Anwendungsbereiche wie die muskulo-skelettale Bildgebung übertragen und können so zu erheblichen technologischen Fortschritten in der radiologischen Diagnostik und Prognostik führen.

show abstract

“…Another interesting patient-level method was proposed in (Yilmaz et al, 2021). It follows a similar high-level scheme and employs a hierarchical convolutional network (Buerger et al, 2020) to localize vertebrae. Then a simple 4-layer CNN analyzes patches to estimate vertebrae deformity and fracture grades.…”

Section: Patient-level Fracture Classificationmentioning

confidence: 99%

Interpretable Vertebral Fracture Quantification via Anchor-Free Landmarks Localization

Zakharov¹,

Pisov²,

Alim³

et al. 2022

Preprint

View full text Add to dashboard Cite

Vertebral body compression fractures are early signs of osteoporosis. Though these fractures are visible on Computed Tomography (CT) images, they are frequently missed by radiologists in clinical settings. Prior research on automatic methods of vertebral fracture classification proves its reliable quality; however, existing methods provide hard-to-interpret outputs and sometimes fail to process cases with severe abnormalities such as highly pathological vertebrae or scoliosis. We propose a new two-step algorithm to localize the vertebral column in 3D CT images and then detect individual vertebrae and quantify fractures in 2D simultaneously. We train neural networks for both steps using a simple 6keypoints based annotation scheme, which corresponds precisely to the current clinical recommendation. Our algorithm has no exclusion criteria, processes 3D CT in 2 seconds on a single GPU, and provides an interpretable and verifiable output. The method approaches expert-level performance and demonstrates state-of-the-art results in vertebrae 3D localization (the average error is 1 mm), vertebrae 2D detection (precision and recall are 0.99), and fracture identification (ROC AUC at the patient level is up to 0.96). Our anchor-free vertebra detection network shows excellent generalizability on a new domain by achieving ROC AUC 0.95, sensitivity 0.85, specificity 0.9 on a challenging VerSe dataset with many unseen vertebra types .

show abstract

Combining deep learning and model-based segmentation for labeled spine CT segmentation

Cited by 12 publications

References 0 publications

Opportunistic Screening Techniques for Analysis of CT Scans

Opportunistic Screening Techniques for Analysis of CT Scans

Radiologische Diagnostik und Prognostik von COVID-19: Einsatz von künstlicher Intelligenz und Zusammenhang mit muskulo-skelettaler Bildgebung

Interpretable Vertebral Fracture Quantification via Anchor-Free Landmarks Localization

Contact Info

Product

Resources

About