Joseph Benzakoun1, Sébastien Bommart2, Joël Coste3, Guillaume Chassagnon4, Mathieu Lederlin5, Samia Boussouar6, Marie-Pierre Revel7. 1. Hôpital Hôtel-Dieu, 1 parvis Notre-Dame, 75004 Paris, France; Université Paris Descartes, 12 rue de l'Ecole de Médecine, 75006 Paris, France. Electronic address: benzakoun.joseph@gmail.com. 2. CHU de Montpellier, 191 avenue du Doyen Gaston Giraud, 34000 Montpellier, France; INSERM U 1046, 371 avenue du Doyen G. Giraud, 34000 Montpellier, France. Electronic address: s-bommart@chu-montpellier.fr. 3. Hôpital Hôtel-Dieu, 1 parvis Notre-Dame, 75004 Paris, France; Université Paris Descartes, 12 rue de l'Ecole de Médecine, 75006 Paris, France. Electronic address: joel.coste@htd.aphp.fr. 4. Université Paris Descartes, 12 rue de l'Ecole de Médecine, 75006 Paris, France; Hôpital Cochin, Radiologie, 27 rue du Faubourg Saint Jacques, 75014 Paris, France. Electronic address: gchassagnon@gmail.com. 5. CHU de Rennes, Radiologie, 2 Rue Henri le Guilloux, 35000 Rennes, France; Université de Rennes 1, 9 Rue Jean Macé, 35000 Rennes, France. Electronic address: mathieu.lederlin@chu-rennes.fr. 6. Université Paris Descartes, 12 rue de l'Ecole de Médecine, 75006 Paris, France; Hôpital Européen Georges Pompidou, 20 Rue Leblanc, 75015 Paris, France. Electronic address: samiaboussouar@gmail.com. 7. Université Paris Descartes, 12 rue de l'Ecole de Médecine, 75006 Paris, France; Hôpital Cochin, Radiologie, 27 rue du Faubourg Saint Jacques, 75014 Paris, France. Electronic address: marie-pierre.revel@aphp.fr.
Abstract
OBJECTIVES: To evaluate the performance of a commercially available CAD system for automated detection and measurement of subsolid nodules. MATERIALS AND METHODS: The CAD system was tested on 50 pure ground-glass and 50 part-solid nodules (median diameter: 17mm) previously found on standard-dose CT scans in 100 different patients. True nodule detection and the total number of CAD marks were evaluated at different sensitivity settings. The influence of nodule and CT acquisition characteristics was analyzed with logistic regression. Software and manually measured diameters were compared with Spearman and Bland-Altman methods. RESULTS: With sensitivity adjusted for 3-mm nodule detection, 50/100 (50%) subsolid nodules were detected, at the average cost of 17 CAD marks per CT. These figures were respectively 26/100 (26%) and 2 at the 5-mm setting. At the highest sensitivity setting (2-mm nodule detection), the average number of CAD marks per CT was 41 but the nodule detection rate only increased to 54%. Part-solid nodules were better detected than pure ground glass nodules: 36/50 (72%) versus 14/50 (28%) at the 3-mm setting (p<0.0001), with no influence of the solid component size. Except for the type (i.e. part solid or pure ground glass), no other nodule characteristic influenced the detection rate. High-quality segmentation was obtained for 79 nodules, which for automated measurements correlated well with manual measurements (rho=0.90[0.84-0.93]). All part-solid nodules had software-measured attenuation values above -671Hounsfield units (HU). CONCLUSION: The detection rate of subsolid nodules by this CAD system was insufficient, but high-quality segmentation was obtained in 79% of cases, allowing automated measurement of size and attenuation.
OBJECTIVES: To evaluate the performance of a commercially available CAD system for automated detection and measurement of subsolid nodules. MATERIALS AND METHODS: The CAD system was tested on 50 pure ground-glass and 50 part-solid nodules (median diameter: 17mm) previously found on standard-dose CT scans in 100 different patients. True nodule detection and the total number of CAD marks were evaluated at different sensitivity settings. The influence of nodule and CT acquisition characteristics was analyzed with logistic regression. Software and manually measured diameters were compared with Spearman and Bland-Altman methods. RESULTS: With sensitivity adjusted for 3-mm nodule detection, 50/100 (50%) subsolid nodules were detected, at the average cost of 17 CAD marks per CT. These figures were respectively 26/100 (26%) and 2 at the 5-mm setting. At the highest sensitivity setting (2-mm nodule detection), the average number of CAD marks per CT was 41 but the nodule detection rate only increased to 54%. Part-solid nodules were better detected than pure ground glass nodules: 36/50 (72%) versus 14/50 (28%) at the 3-mm setting (p<0.0001), with no influence of the solid component size. Except for the type (i.e. part solid or pure ground glass), no other nodule characteristic influenced the detection rate. High-quality segmentation was obtained for 79 nodules, which for automated measurements correlated well with manual measurements (rho=0.90[0.84-0.93]). All part-solid nodules had software-measured attenuation values above -671Hounsfield units (HU). CONCLUSION: The detection rate of subsolid nodules by this CAD system was insufficient, but high-quality segmentation was obtained in 79% of cases, allowing automated measurement of size and attenuation.
Authors: Ramandeep Singh; Mannudeep K Kalra; Fatemeh Homayounieh; Chayanin Nitiwarangkul; Shaunagh McDermott; Brent P Little; Inga T Lennes; Jo-Anne O Shepard; Subba R Digumarthy Journal: Quant Imaging Med Surg Date: 2021-04
Authors: John T Murchison; Gillian Ritchie; David Senyszak; Jeroen H Nijwening; Gerben van Veenendaal; Joris Wakkie; Edwin J R van Beek Journal: PLoS One Date: 2022-05-05 Impact factor: 3.752