OBJECTIVE: We present herein a novel algorithm for architectural distortion detection that utilizes the point convergence index with the likelihood of lines (e.g., spiculations) relating to architectural distortion. MATERIALS AND METHODS: Validation was performed using 25 computed radiography (CR) mammograms, each of which has an architectural distortion with radiating spiculations. The proposed method comprises five steps. First, the lines were extracted on mammograms, such as spiculations of architectural distortion as well as lines in the mammary gland. Second, the likelihood of spiculation for each extracted line was calculated. In the third step, point convergence index weighted by this likelihood was evaluated at each pixel to enhance distortion only. Fourth, local maxima of the index were extracted as candidates for the distortion, then classified based on nine features in the last step. RESULTS: Point convergence index without the proposed likelihood generated 84.48/image false-positives (FPs) on average. Conversely, the proposed index succeeded in decreasing this number to 12.48/image on average when sensitivity was 100%. After the classification step, number of FPs was reduced to 0.80/image with 80.0% sensitivity. CONCLUSION: Combination of the likelihood of lines with point convergence index is effective in extracting architectural distortion with radiating spiculations.
OBJECTIVE: We present herein a novel algorithm for architectural distortion detection that utilizes the point convergence index with the likelihood of lines (e.g., spiculations) relating to architectural distortion. MATERIALS AND METHODS: Validation was performed using 25 computed radiography (CR) mammograms, each of which has an architectural distortion with radiating spiculations. The proposed method comprises five steps. First, the lines were extracted on mammograms, such as spiculations of architectural distortion as well as lines in the mammary gland. Second, the likelihood of spiculation for each extracted line was calculated. In the third step, point convergence index weighted by this likelihood was evaluated at each pixel to enhance distortion only. Fourth, local maxima of the index were extracted as candidates for the distortion, then classified based on nine features in the last step. RESULTS: Point convergence index without the proposed likelihood generated 84.48/image false-positives (FPs) on average. Conversely, the proposed index succeeded in decreasing this number to 12.48/image on average when sensitivity was 100%. After the classification step, number of FPs was reduced to 0.80/image with 80.0% sensitivity. CONCLUSION: Combination of the likelihood of lines with point convergence index is effective in extracting architectural distortion with radiating spiculations.
Authors: Jay A Baker; Eric L Rosen; Joseph Y Lo; Edgardo I Gimenez; Ruth Walsh; Mary Scott Soo Journal: AJR Am J Roentgenol Date: 2003-10 Impact factor: 3.959
Authors: Andrew J Evans; Sarah E Pinder; Jonathan J James; Ian O Ellis; Eleanor Cornford Journal: AJR Am J Roentgenol Date: 2006-11 Impact factor: 3.959
Authors: H C Burrell; D M Sibbering; A R Wilson; S E Pinder; A J Evans; L J Yeoman; C W Elston; I O Ellis; R W Blamey; J F Robertson Journal: Radiology Date: 1996-06 Impact factor: 11.105
Authors: Balaji Ganeshan; Olga Strukowska; Karoline Skogen; Rupert Young; Chris Chatwin; Ken Miles Journal: Front Oncol Date: 2011-10-17 Impact factor: 6.244