Tumours and Tumour-Like Lesions of Bone

Kotnis, Nikhil; Davies, A. M.; James, Steven

doi:10.1007/174_2010_121

Cited by 2 publications

(1 citation statement)

References 201 publications

(281 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The clinical model was correctly able to predict hand and foot locations as negative predictors of malignancy and cranial and spinal locations as positive predictors of malignancy. The majority of tumors affecting the hand, cranium and spine are enchondromas; chordomas and chondrosarcomas; and bone metastases and multiple myeloma, respectively [30] , [31] , [32] , [33] . While the majority of bone tumors of the foot are benign, our clinical features model likely associated foot location with benign nature because the majority of foot-located lesions in our cohort were osteomyelitis, a bone tumor-mimicker that commonly affects the lower extremity.…”

Section: Discussionmentioning

confidence: 99%

Deep Learning for Classification of Bone Lesions on Routine MRI

Eweje

Bao

et al. 2021

EBioMedicine

View full text Add to dashboard Cite

Background Radiologists have difficulty distinguishing benign from malignant bone lesions because these lesions may have similar imaging appearances. The purpose of this study was to develop a deep learning algorithm that can differentiate benign and malignant bone lesions using routine magnetic resonance imaging (MRI) and patient demographics. Methods 1,060 histologically confirmed bone lesions with T1- and T2-weighted pre-operative MRI were retrospectively identified and included, with lesions from 4 institutions used for model development and internal validation, and data from a fifth institution used for external validation. Image-based models were generated using the EfficientNet-B0 architecture and a logistic regression model was trained using patient age, sex, and lesion location. A voting ensemble was created as the final model. The performance of the model was compared to classification performance by radiology experts. Findings The cohort had a mean age of 30±23 years and was 58.3% male, with 582 benign lesions and 478 malignant. Compared to a contrived expert committee result, the ensemble deep learning model achieved (ensemble vs. experts): similar accuracy (0·76 vs. 0·73, p=0·7), sensitivity (0·79 vs. 0·81, p=1·0) and specificity (0·75 vs. 0·66, p=0·48), with a ROC AUC of 0·82. On external testing, the model achieved ROC AUC of 0·79. Interpretation Deep learning can be used to distinguish benign and malignant bone lesions on par with experts. These findings could aid in the development of computer-aided diagnostic tools to reduce unnecessary referrals to specialized centers from community clinics and limit unnecessary biopsies. Funding This work was funded by a Radiological Society of North America Research Medical Student Grant (#RMS2013) and supported by the Amazon Web Services Diagnostic Development Initiative.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning for Classification of Bone Lesions on Routine MRI

Eweje

Bao

et al. 2021

EBioMedicine

View full text Add to dashboard Cite

show abstract

Recurrence of Cortical Venous Haemangioma in the Tibia: Interest of Sclerotherapy

Bouabdellah¹,

Mahfoudhi²,

Gorsane³

et al. 2015

IJCM

View full text Add to dashboard Cite

We report on a rare case of an intra-osseous haemangioma involving the medial portion of tibia in a 29-year-old man. The aim is to emphasize on diagnosis difficulties, possible recurrence and interest of sclerotherapy. In radiographs, the lesion was a well-defined osteolytic lesion having 3 mm of diameter with perimeter's sclerosis. The computed tomography images demonstrated an intra-medullar gap's image of the tibia with cortical participation. An osteoid osteoma was evocated but eliminated by the histhological examination. The osseous scintigraphy didn't find any anomaly. The outcome was marked by the recurrence of pain. T1-weighted Magnetic resonance imaging showed a hypointense lesion, while T2-weighted images revealed hyperintense areas, with internal, hypointense septa. Gadolinium-enhanced T1-weighted images showed lattice-like enhancement of the lesion. These images signed a recurrence of the intra-osseous venous haemangioma. The sclerotherapy improved the pain in three days and prevented another recurrence.

show abstract

Tumours and Tumour-Like Lesions of Bone

Cited by 2 publications

References 201 publications

Deep Learning for Classification of Bone Lesions on Routine MRI

Deep Learning for Classification of Bone Lesions on Routine MRI

Recurrence of Cortical Venous Haemangioma in the Tibia: Interest of Sclerotherapy

Contact Info

Product

Resources

About