Automated Rib Fracture Detection of Postmortem Computed Tomography Images Using Machine Learning Techniques

Imaging techniques is widely used for medical diagnostics. This leads in some cases to a real bottleneck when there is a lack of medical practitioners and the images have to be manually processed. In such a situation there is a need to reduce the amount of manual work by automating part of the analysis. In this article, we investigate the potential of a machine learning algorithm for medical image processing by computing a topological invariant classifier. First, we select retrospectively from our database of postmortem computed tomography images of rib fractures. The images are prepared by applying a rib unfolding tool that flattens the rib cage to form a two-dimensional projection. We compare the results of our analysis with two independent convolutional neural network models. In the case of the neural network model, we obtain an $F_1$ Score of 0.73. To access the performance of our classifier, we compute the relative proportion of images that were not shared between the two classes. We obtain a precision of 0.60 for the images with rib fractures.

[1]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[2]  A Di Giancamillo,et al.  Sensitivity of autopsy and radiological examination in detecting bone fractures in an animal model: implications for the assessment of fatal child physical abuse. , 2006, Forensic science international.

[3]  Gary Hatch,et al.  CT based volume measurement and estimation in cases of pericardial effusion. , 2012, Journal of forensic and legal medicine.

[4]  John D. Hunter,et al.  Matplotlib: A 2D Graphics Environment , 2007, Computing in Science & Engineering.

[5]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[6]  Fernando Collado-Mesa,et al.  The Role of Artificial Intelligence in Diagnostic Radiology: A Survey at a Single Radiology Residency Training Program. , 2018, Journal of the American College of Radiology : JACR.

[7]  Peter Dankerl,et al.  Evaluation of Rib Fractures on a Single-in-plane Image Reformation of the Rib Cage in CT Examinations. , 2017, Academic radiology.

[8]  Grzegorz Soza,et al.  The ribs unfolded - a CT visualization algorithm for fast detection of rib fractures: effect on sensitivity and specificity in trauma patients , 2015, European Radiology.

[9]  Akinobu Shimizu,et al.  An Automated Segmentation Algorithm for CT Volumes of Livers with Atypical Shapes and Large Pathological Lesions , 2014, IEICE Trans. Inf. Syst..

[10]  J. Weeks,et al.  The first 1,701,936 knots , 1998 .

[11]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[12]  Heinz-Peter Schlemmer,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 , 2016, International Journal of Legal Medicine.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  V. Jones.  A polynomial invariant for knots via von Neumann algebras , 1985 .

[15]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[16]  Kenneth C. Millett,et al.  A new polynomial invariant of knots and links , 1985 .

[17]  S. Grabherr,et al.  Development and validation of a postmortem radiological alteration index: the RA-Index , 2012, International Journal of Legal Medicine.

[18]  Yann LeCun,et al.  Une procedure d'apprentissage pour reseau a seuil asymmetrique (A learning scheme for asymmetric threshold networks) , 1985 .

[19]  J. W. Alexander,et al.  On Types of Knotted Curves , 1926 .

[20]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[21]  Bilwaj Gaonkar,et al.  Automated tumor volumetry using computer-aided image segmentation. , 2015, Academic radiology.

[22]  Kieran Campbell,et al.  Supplementary Materials for , 2016 .

[23]  Feng Liu,et al.  Deep Learning and Its Applications in Biomedicine , 2018, Genom. Proteom. Bioinform..

[24]  Katherine P Andriole,et al.  Optimizing analysis, visualization, and navigation of large image data sets: one 5000-section CT scan can ruin your whole day. , 2011, Radiology.

[25]  J. W. Alexander.  Topological invariants of knots and links , 1928 .

[26]  C. O’Donnell,et al.  "Buckle" rib fracture: an artifact following cardio-pulmonary resuscitation detected on postmortem CT. , 2011, Legal medicine.

[27]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[28]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[29]  Michel Boileau,et al.  Progress in knot theory and related topics , 1997 .

[30]  Wolf Schweitzer,et al.  Rib fractures at postmortem computed tomography (PMCT) validated against the autopsy. , 2013, Forensic science international.