Juhun Lee1, Robert M Nishikawa1, Ingrid Reiser2, John M Boone3. 1. Department of Radiology, University of Pittsburgh, Pittsburgh, PA, USA. 2. Department of Radiology, The University of Chicago, Chicago, IL, USA. 3. Department of Radiology, University of California Davis Medical Center, Sacramento, CA, USA.
Abstract
PURPOSE: Many computer aided diagnosis (CADx) tools for breast cancer begin by fully or semiautomatically segmenting a given breast lesion and then classifying the lesion's likelihood of malignancy using quantitative features extracted from the image. It is often assumed that better segmentation will result in better classification. However, this has not been thoroughly evaluated. The purpose of this study is to evaluate the relationship between computer segmentation performance and computer classification performance. METHOD: We used 85 breast lesions (32 benign, 56 malignant) from breast computed tomography (CT) cases of 82 women. We prepared one smooth and one sharp iterative image reconstructions (IIR) and a clinical reconstruction for each of the 82 breast CT scans. For each reconstruction, we created 15 segmentation outcomes by applying 15 different segmentation algorithms. Specifically, we simulated 15 segmentation algorithms by changing parameters in a single segmentation algorithm. We then created 15 classification outcomes by conducting quantitative image feature analysis on the segmented image results. Using a 10-fold cross-validation, we evaluated the relationship between segmentation and classification performances. RESULT: We found a low positive correlation between segmentation and classification performances for the smooth IIR (median Pearson's rho = 0.18), while a moderate positive correlation (median Pearson's rho = 0.4-0.43) was found between the two performances for the sharp IIR and clinical reconstruction. However, we found large variations in both segmentation and classification performances for the sharp IIR and clinical reconstruction. There were cases where segmentation algorithms resulted in similar segmentation performances, but the corresponding classification performances were different. These results indicate that an improvement in segmentation performance does not guarantee an improvement in the corresponding classification performance. CONCLUSION: Computer segmentation is an indirect variable affecting the computer classification. As better segmentation does not guarantee better classification, we should report both segmentation and classification performances when comparing segmentation algorithms.
PURPOSE: Many computer aided diagnosis (CADx) tools for breast cancer begin by fully or semiautomatically segmenting a given breast lesion and then classifying the lesion's likelihood of malignancy using quantitative features extracted from the image. It is often assumed that better segmentation will result in better classification. However, this has not been thoroughly evaluated. The purpose of this study is to evaluate the relationship between computer segmentation performance and computer classification performance. METHOD: We used 85 breast lesions (32 benign, 56 malignant) from breast computed tomography (CT) cases of 82 women. We prepared one smooth and one sharp iterative image reconstructions (IIR) and a clinical reconstruction for each of the 82 breast CT scans. For each reconstruction, we created 15 segmentation outcomes by applying 15 different segmentation algorithms. Specifically, we simulated 15 segmentation algorithms by changing parameters in a single segmentation algorithm. We then created 15 classification outcomes by conducting quantitative image feature analysis on the segmented image results. Using a 10-fold cross-validation, we evaluated the relationship between segmentation and classification performances. RESULT: We found a low positive correlation between segmentation and classification performances for the smooth IIR (median Pearson's rho = 0.18), while a moderate positive correlation (median Pearson's rho = 0.4-0.43) was found between the two performances for the sharp IIR and clinical reconstruction. However, we found large variations in both segmentation and classification performances for the sharp IIR and clinical reconstruction. There were cases where segmentation algorithms resulted in similar segmentation performances, but the corresponding classification performances were different. These results indicate that an improvement in segmentation performance does not guarantee an improvement in the corresponding classification performance. CONCLUSION: Computer segmentation is an indirect variable affecting the computer classification. As better segmentation does not guarantee better classification, we should report both segmentation and classification performances when comparing segmentation algorithms.