RESUMEN
PURPOSE: The evaluation of all ribs on thin-slice CT images is time consuming and it can be difficult to accurately assess the location and type of rib fracture in an emergency. The aim of our study was to develop and validate a convolutional neural network (CNN) algorithm for the detection of acute rib fractures on thoracic CT images and to investigate the effect of the CNN algorithm on radiologists' performance. METHODS: The dataset for development of a CNN consisted of 539 thoracic CT scans with 4906 acute rib fractures. A three-dimensional faster region-based CNN was trained and evaluated by using tenfold cross-validation. For an observer performance study to investigate the effect of CNN outputs on radiologists' performance, 30 thoracic CT scans (28 scans with 90 acute rib fractures and 2 without rib fractures) which were not included in the development dataset were used. Observer performance study involved eight radiologists who evaluated CT images first without and second with CNN outputs. The diagnostic performance was assessed by using figure of merit (FOM) values obtained from the jackknife free-response receiver operating characteristic (JAFROC) analysis. RESULTS: When radiologists used the CNN output for detection of rib fractures, the mean FOM value significantly increased for all readers (0.759 to 0.819, P = 0.0004) and for displaced (0.925 to 0.995, P = 0.0028) and non-displaced fractures (0.678 to 0.732, P = 0.0116). At all rib levels except for the 1st and 12th ribs, the radiologists' true-positive fraction of the detection became significantly increased by using the CNN outputs. CONCLUSION: The CNN specialized for the detection of acute rib fractures on CT images can improve the radiologists' diagnostic performance regardless of the type of fractures and reader's experience. Further studies are needed to clarify the usefulness of the CNN for the detection of acute rib fractures on CT images in actual clinical practice.
Asunto(s)
Fracturas de las Costillas , Humanos , Redes Neurales de la Computación , Radiólogos , Fracturas de las Costillas/diagnóstico por imagen , Costillas , Tomografía Computarizada por Rayos X/métodosRESUMEN
OBJECTIVES: To compare "black ring-shaped burn" (BRSB) and charring using spectral computed tomography (CT). METHODS: Spectral CT was performed using chicken pectoralis minor muscle, processed in three ways and unprocessed as a control: a) BRSB generated by bringing the negative pole surface of a 3 V button battery (BB) into contact with the muscle; b) BRSB caused by a 1.5 V BB; c) charring caused by broiling; and d) control. Attenuation values were compared between BRSB and charring. Muscles were formalin-fixed and stained with Perls' Prussian blue. RESULTS: Attenuation values from polychromatic 120-kVp images were significantly higher for BRSBs than for charring. In the spectral Hounsfield unit curve, attenuation values for BRSBs were higher for lower energy. Histopathologically, BRSBs stained positively with Perls' Prussian blue. CONCLUSIONS: This study using spectral CT revealed that BRSB contains metal and confirmed the presence of Fe3+ histopathologically. BRSB differs from charring due to burns. ADVANCES IN KNOWLEDGE: The exact composition of BRSB remains unclear, but this report is the first to show that BRSB differs from charring using spectral CT. Clarification of the composition of BRSB is expected to facilitate the development of more effective BRSB removal therapy.