PURPOSE: The goal is to automatically detect anomalous vascular cross-sections to attract the radiologist's attention to possible lesions and thus reduce the time spent to analyze the image volume. MATERIALS AND METHODS: We assume that both lesions and calcifications can be considered as local outliers compared to a normal cross-section. Our approach uses an intensity metric within a machine learning scheme to differentiate normal and abnormal cross-sections. It is formulated as a Density Level Detection problem and solved using a Support Vector Machine (DLD-SVM). The method has been evaluated on 42 synthetic phantoms and on 9 coronary CT data sets annotated by 2 experts. RESULTS: The specificity of the method was 97.57% on synthetic data, and 86.01% on real data, while its sensitivity was 82.19 and 81.23%, respectively. The agreement with the observers, measured by the kappa coefficient, was substantial (κ = 0.72). After the learning stage, which is performed off-line, the average processing time was within 10 s per artery. CONCLUSIONS: To our knowledge, this is the first attempt to use the DLD-SVM approach to detect vascular abnormalities. Good specificity, sensitivity and agreement with experts, as well as a short processing time, show that our method can facilitate medical diagnosis and reduce evaluation time by attracting the reader's attention to suspect regions.
PURPOSE: The goal is to automatically detect anomalous vascular cross-sections to attract the radiologist's attention to possible lesions and thus reduce the time spent to analyze the image volume. MATERIALS AND METHODS: We assume that both lesions and calcifications can be considered as local outliers compared to a normal cross-section. Our approach uses an intensity metric within a machine learning scheme to differentiate normal and abnormal cross-sections. It is formulated as a Density Level Detection problem and solved using a Support Vector Machine (DLD-SVM). The method has been evaluated on 42 synthetic phantoms and on 9 coronary CT data sets annotated by 2 experts. RESULTS: The specificity of the method was 97.57% on synthetic data, and 86.01% on real data, while its sensitivity was 82.19 and 81.23%, respectively. The agreement with the observers, measured by the kappa coefficient, was substantial (κ = 0.72). After the learning stage, which is performed off-line, the average processing time was within 10 s per artery. CONCLUSIONS: To our knowledge, this is the first attempt to use the DLD-SVM approach to detect vascular abnormalities. Good specificity, sensitivity and agreement with experts, as well as a short processing time, show that our method can facilitate medical diagnosis and reduce evaluation time by attracting the reader's attention to suspect regions.
Authors: Fei Zhao; Honghai Zhang; Andreas Wahle; Matthew T Thomas; Alan H Stolpen; Thomas D Scholz; Milan Sonka Journal: Med Image Anal Date: 2009-02-21 Impact factor: 8.545
Authors: Kevin M Cherry; Brandon Peplinski; Lauren Kim; Shijun Wang; Le Lu; Weidong Zhang; Jianfei Liu; Zhuoshi Wei; Ronald M Summers Journal: Med Image Anal Date: 2014-10-13 Impact factor: 8.545
Authors: Maria A Zuluaga; Ninon Burgos; Alex F Mendelson; Andrew M Taylor; Sébastien Ourselin Journal: Med Image Anal Date: 2015-09-16 Impact factor: 8.545
Authors: Ahmed M Ghanem; Ahmed H Hamimi; Jatin R Matta; Aaron Carass; Reham M Elgarf; Ahmed M Gharib; Khaled Z Abd-Elmoniem Journal: Sci Rep Date: 2019-01-10 Impact factor: 4.379
Authors: Carlos A Peña-Solórzano; David W Albrecht; Richard B Bassed; Michael D Burke; Matthew R Dimmock Journal: Forensic Sci Int Date: 2020-10-18 Impact factor: 2.395