Hilary L P Orlowski1, Matthew D Smyth2, Matthew S Parsons3, Sonika Dahiya4, Nima Sharifai5, Charles Hildebolt6, Aseem Sharma7. 1. Mallinckrodt Institute of Radiology, Washington University School of Medicine, 510 S. Kingshighway Boulevard, St. Louis, MO 63110, United States. Electronic address: Hilary.orlowski@wustl.edu. 2. Department of Neurological Surgery, Washington University School of Medicine, 660 South Euclid, Box 8057, St. Louis, MO 63110, United States. Electronic address: mdsmyth@wustl.edu. 3. Mallinckrodt Institute of Radiology, Washington University School of Medicine, 510 S. Kingshighway Boulevard, St. Louis, MO 63110, United States. Electronic address: parsonsms@wustl.edu. 4. Department of Pathology & Immunology, Washington University School of Medicine, 509 S. Euclid Ave, St. Louis, MO 63110, United States. Electronic address: sdahiya@wustl.edu. 5. Department of Pathology & Immunology, Washington University School of Medicine, 509 S. Euclid Ave, St. Louis, MO 63110, United States. Electronic address: nsharifai@wustl.edu. 6. Division of Biostatistics, Washington University School of Medicine, 660 S. Euclid Ave. St. Louis, MO 63110, United States. Electronic address: hildeboltc@wustl.edu. 7. Mallinckrodt Institute of Radiology, Washington University School of Medicine, 510 S. Kingshighway Boulevard, St. Louis, MO 63110, United States. Electronic address: aseemsharma@wustl.edu.
Abstract
OBJECTIVE: Detection of mesial temporal sclerosis (MTS) in children with epilepsy is important. We assessed whether an image-processing algorithm (Correlative Image Enhancement, CIE) could facilitate recognition of hippocampal signal abnormality in the presence of MTS by increasing contrast to noise ratio between affected hippocampus and normal gray matter. PATIENTS AND METHODS: Baseline coronal FLAIR images from brain MRIs of 27 children with epilepsy who underwent hippocampal resection were processed using CIE. These included 19 hippocampi with biopsy proven MTS and 8 biopsy proven normal hippocampi resected in conjunction with hemispherotomy. We assessed the effect of processing on contrast to noise ratio (CNR) between hippocampus and normal insular gray matter, and on assessment of hippocampal signal abnormality by two masked neuroradiologists. RESULTS: Processing resulted in a significant increase in mean CNR (from 3.9 ± 5.3 to 25.3 ± 25.8; P < 0.01) for hippocampi with MTS, with a substantial (>100%) increase from baseline seen in 15/19 (78.9%) cases. Baseline CNR of 1.7 ± 5.3 for normal hippocampi did not change significantly after processing (1.8 ± 5.3; P = 1.00). For one reader, baseline sensitivity (14/19; 73.6%) was unaffected but the specificity improved from 62.5% (5/8) to 100%. An increase in both sensitivity (from 73.6% to 78.9%) and specificity (from 62.5% to 75%) was seen for the second reader. CONCLUSION: By enhancing CNR for diseased hippocampi while leaving normal hippocampi relatively unaffected, CIE may improve the diagnostic accuracies of radiologists in detecting MTS-related signal alteration within the affected hippocampus.
OBJECTIVE: Detection of mesial temporal sclerosis (MTS) in children with epilepsy is important. We assessed whether an image-processing algorithm (Correlative Image Enhancement, CIE) could facilitate recognition of hippocampal signal abnormality in the presence of MTS by increasing contrast to noise ratio between affected hippocampus and normal gray matter. PATIENTS AND METHODS: Baseline coronal FLAIR images from brain MRIs of 27 children with epilepsy who underwent hippocampal resection were processed using CIE. These included 19 hippocampi with biopsy proven MTS and 8 biopsy proven normal hippocampi resected in conjunction with hemispherotomy. We assessed the effect of processing on contrast to noise ratio (CNR) between hippocampus and normal insular gray matter, and on assessment of hippocampal signal abnormality by two masked neuroradiologists. RESULTS: Processing resulted in a significant increase in mean CNR (from 3.9 ± 5.3 to 25.3 ± 25.8; P < 0.01) for hippocampi with MTS, with a substantial (>100%) increase from baseline seen in 15/19 (78.9%) cases. Baseline CNR of 1.7 ± 5.3 for normal hippocampi did not change significantly after processing (1.8 ± 5.3; P = 1.00). For one reader, baseline sensitivity (14/19; 73.6%) was unaffected but the specificity improved from 62.5% (5/8) to 100%. An increase in both sensitivity (from 73.6% to 78.9%) and specificity (from 62.5% to 75%) was seen for the second reader. CONCLUSION: By enhancing CNR for diseased hippocampi while leaving normal hippocampi relatively unaffected, CIE may improve the diagnostic accuracies of radiologists in detecting MTS-related signal alteration within the affected hippocampus.