Musculoskeletal and Emergency Imaging| Volume 81, P24-32, January 2022

Download started.


Precise anatomical localization and classification of rib fractures on CT using a convolutional neural network

Published:September 21, 2021DOI:


      • A novel CNN model can automatically detect and output the precise anatomical localization and classification of rib fractures.
      • The sensitivity of localization reached 94.87% and 97.11% in the right and left ribs, respectively.
      • The CNN model had a certain robustness verified by the external test, and it matched or surpassed the detection and classification performance of experienced radiologists.



      To develop a convolutional neural network (CNN) model for the detection, precise anatomical localization (right 1-12th and left 1-12th) and classification (fresh, healing and old fractures) of rib fractures automatically, and to compare the performance with the experienced radiologists.

      Materials and methods

      A total of 640 rib fracture patients with 340,501 annotations were retrospectively collected from three hospitals. They consisted of a classification training dataset (n = 482), a localization training dataset (n = 30), an internal testing dataset (n = 90) and an external testing dataset (n = 38). RetinaNet with rib localization postprocessing and the result merging technique were employed to structure the CNN model. ROC curve, free-response ROC curve, AUC, precision, recall, and F1-score were calculated to choose the better option between model I (training classification and localization data together) and model II (adding an additional classification model to model I).


      The detection and classification performance of rib fractures was better in model II than in model I. The sensitivity of localization reached 97.11% and 94.87% on the right and left ribs, respectively. In the external dataset with different CT scanner and slice thickness, model II showed better diagnostic performance. Moreover, the CNN model was superior in diagnosing fresh and healing fractures to 5 radiologists and consumed shorter diagnosis time.


      Our CNN model was capable of detection, precise anatomical localization, and classification of rib fractures automatically.


      CNN (convolutional neural network), DL (deep learning), ROC (receiver operating characteristic), fROC (free-response receiver operating characteristic), AUC (area under the curve), RPN (region proposal network), GT (ground truth)


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to Clinical Imaging
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Lin F.C.
        • Li R.Y.
        • Tung Y.W.
        • Jeng K.C.
        • Tsai S.C.
        Morbidity, mortality, associated injuries, and management of traumatic rib fractures.
        J Chin Med Assoc. 2016; 79: 329-334
        • Cho S.H.
        • Sung Y.M.
        • Kim M.S.
        Missed rib fractures on evaluation of initial chest CT for trauma patients: pattern analysis and diagnostic value of coronal multiplanar reconstruction images with multidetector row CT.
        Br J Radiol. 2012; 85: e845-e850
        • Senekjian L.
        • Nirula R.
        Rib fracture fixation: indications and outcomes.
        Crit Care Clin. 2017; 33: 153-165
        • Zhang B.
        • Jia C.
        • Wu R.
        • Lv B.
        • Li B.
        • Li F.
        • et al.
        Improving rib fracture detection accuracy and reading efficiency with deep learning-based detection software: a clinical evaluation.
        Br J Radiol. 2020; 9420200870
        • Talbot B.S.
        • Gange Jr., C.P.
        • Chaturvedi A.
        • Klionsky N.
        • Hobbs S.K.
        • Chaturvedi A.
        Traumatic rib injury: patterns, imaging pitfalls, complications, and treatment.
        Radiographics. 2017; 37: 628-651
        • Wang D.
        • Li L.
        • Li N.
        • He J.
        MDCT evaluation of costal bone lesions.
        Medicine. 2015; 94
        • Murphy C.E.T.
        • Raja A.S.
        • Baumann B.M.
        • Medak A.J.
        • Langdorf M.I.
        • Nishijima D.K.
        • et al.
        Rib fracture diagnosis in the Panscan Era.
        Ann Emerg Med. 2017; 70: 904-909
        • Kim J.
        • Kim S.
        • Kim Y.J.
        • Kim K.G.
        • Park J.
        Quantitative measurement method for possible rib fractures in chest radiographs.
        Healthc Inform Res. 2013; 19: 196-204
        • Zhou Q.Q.
        • Wang J.
        • Tang W.
        • Hu Z.C.
        • Xia Z.Y.
        • Li X.S.
        • et al.
        Automatic detection and classification of rib fractures on thoracic CT using convolutional neural network: accuracy and feasibility.
        Korean J Radiol. 2020; 21: 869-879
        • Krupinski E.A.
        • Berbaum K.S.
        • Caldwell R.T.
        • Schartz K.M.
        • Kim J.
        Long radiology workdays reduce detection and accommodation accuracy.
        J Am Coll Radiol. 2010; 7: 698-704
        • Urbaneja A.
        • De Verbizier J.
        • Formery A.S.
        • Tobon-Gomez C.
        • Nace L.
        • Blum A.
        • et al.
        Automatic rib cage unfolding with CT cylindrical projection reformat in polytraumatized patients for rib fracture detection and characterization: feasibility and clinical application.
        Eur J Radiol. 2019; 110: 121-127
        • Ringl H.
        • Lazar M.
        • Topker M.
        • Woitek R.
        • Prosch H.
        • Asenbaum U.
        • et al.
        The ribs unfolded - a CT visualization algorithm for fast detection of rib fractures: effect on sensitivity and specificity in trauma patients.
        Eur Radiol. 2015; 25: 1865-1874
        • Dankerl P.
        • Seuss H.
        • Ellmann S.
        • Cavallaro A.
        • Uder M.
        • Hammon M.
        Evaluation of rib fractures on a single-in-plane image reformation of the rib cage in CT examinations.
        Acad Radiol. 2017; 24: 153-159
        • Glemser P.A.
        • Pfleiderer M.
        • Heger A.
        • Tremper J.
        • Krauskopf A.
        • Schlemmer H.P.
        • et al.
        New bone post-processing tools in forensic imaging: a multi-reader feasibility study to evaluate detection time and diagnostic accuracy in rib fracture assessment.
        Int J Leg Med. 2017; 131: 489-496
        • Weikert T.
        • Noordtzij L.A.
        • Bremerich J.
        • Stieltjes B.
        • Parmar V.
        • Cyriac J.
        • et al.
        Assessment of a deep learning algorithm for the detection of rib fractures on whole-body trauma computed tomography.
        Korean J Radiol. 2020; 21: 891-899
        • Jin L.
        • Yang J.
        • Kuang K.
        • Ni B.
        • Gao Y.
        • Sun Y.
        Deep-learning-assisted detection and segmentation of rib fractures from CT scans: development and validation of FracNet.
        EBioMedicine. 2020; : 62
        • Zhou Q.-Q.
        • Tang W.
        • Wang J.
        • Hu Z.-C.
        • Xia Z.-Y.
        • Zhang R.
        • et al.
        Automatic detection and classification of rib fractures based on patients' CT images and clinical information via convolutional neural network.
        Eur Radiol. 2020; 31: 3815-3825
        • Iqbal I.
        • Younus M.
        • Walayat K.
        • Kakar M.U.
        • Ma J.
        Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images.
        Comput Med Imaging Graph. 2021; 88101843
        • Dunnmon J.A.
        • Yi D.
        • Langlotz C.P.
        • Re C.
        • Rubin D.L.
        • Lungren M.P.
        Assessment of convolutional neural networks for automated classification of chest radiographs.
        Radiology. 2019; 290: 537-544
        • Thian Y.L.
        • Li Y.
        • Jagmohan P.
        • Sia D.
        • Chan V.E.Y.
        • Tan R.T.
        Convolutional neural networks for automated fracture detection and localization on wrist radiographs.
        Radiology. 2019; 1
        • Candemir S.
        • White R.D.
        • Demirer M.
        • Gupta V.
        • Bigelow M.T.
        • Prevedello L.M.
        • et al.
        Automated coronary artery atherosclerosis detection and weakly supervised localization on coronary CT angiography with a deep 3-dimensional convolutional neural network.
        Comput Med Imaging Graph. 2020; 83101721
        • Zura R.
        • Xu Z.J.
        • Della Rocca G.J.
        • Mehta S.
        • Steen R.G.
        When is a fracture not “Fresh”? Aligning reimbursement with patient outcome after treatment with low-intensity pulsed ultrasound.
        J Orthop Trauma. 2017; 31: 248-251
        • Wootton-Gorges S.L.
        • Stein-Wexler R.
        • Walton J.W.
        • Rosas A.J.
        • Coulter K.P.
        • Rogers K.K.
        Comparison of computed tomography and chest radiography in the detection of rib fractures in abused infants.
        Child Abuse Negl. 2008; 32: 659-663
        • Arredondo-Gomez E.
        Treatment of traumatic clavicular pseudoarthrosis with the hunec colchero nail.
        Acta Ortop Mex. 2007; 21: 63-68
        • Lin T.Y.
        • Goyal P.
        • Girshick R.
        • He K.
        • Dollar P.
        Focal loss for dense object detection.
        IEEE Trans Pattern Anal Mach Intell. 2020; 42: 318-327
        • Shan F.
        • Gao Y.
        • Wang J.
        • Gao W.
        Lung infection quantification of COVID-19 in CT images with deep learning.
        • Hu J.
        • Zheng Z.F.
        • Wang S.H.
        • Si D.L.
        • Yuan Y.Q.
        • Gao B.L.
        Missed rib fractures on initial chest CT in trauma patients: time patterns, clinical and forensic significance.
        Eur Radiol. 2020; 31: 2332-2339
        • Sun F.
        • Kong T.
        • Huang W.
        • Tan C.
        • Fang B.
        • Liu H.
        Feature pyramid reconfiguration with consistent loss for object detection.
        IEEE Trans Image Process. 2019;
        • Li Q.
        • Yu Z.
        • Qi T.
        • Zheng L.
        • Qi S.
        • He Z.
        • et al.
        Inspection of visible components in urine based on deep learning.
        Med Phys. 2020; 47: 2937-2949