A Sreekumari1, D Shanbhag1, D Yeo2, T Foo2, J Pilitsis3, J Polzin4, U Patil1, A Coblentz5, A Kapadia5, J Khinda5, A Boutet5, J Port6, I Hancu7. 1. From the GE Global Research Center (A.S., D.S., U.P.), Bangalore, India. 2. GE Global Research Center (D.Y., T.F., I.H.), Niskayuna, New York. 3. Albany Medical College (J.Pilitsis), Albany, New York. 4. GE Healthcare (J.Polzin), Milwaukee, Wisconsin. 5. University Hospital Network (A.C., A.K., J.K., A.B.), Toronto, Ontario, Canada. 6. Mayo Clinic (J.Port), Rochester, Minnesota. 7. GE Global Research Center (D.Y., T.F., I.H.), Niskayuna, New York ihancu1@gmail.com.
Abstract
BACKGROUND AND PURPOSE: MR imaging rescans and recalls can create large hospital revenue loss. The purpose of this study was to develop a fast, automated method for assessing rescan need in motion-corrupted brain series. MATERIALS AND METHODS: A deep learning-based approach was developed, outputting a probability for a series to be clinically useful. Comparison of this per-series probability with a threshold, which can depend on scan indication and reading radiologist, determines whether a series needs to be rescanned. The deep learning classification performance was compared with that of 4 technologists and 5 radiologists in 49 test series with low and moderate motion artifacts. These series were assumed to be scanned for 2 scan indications: screening for multiple sclerosis and stroke. RESULTS: The image-quality rating was found to be scan indication- and reading radiologist-dependent. Of the 49 test datasets, technologists created a mean ratio of rescans/recalls of (4.7 ± 5.1)/(9.5 ± 6.8) for MS and (8.6 ± 7.7)/(1.6 ± 1.9) for stroke. With thresholds adapted for scan indication and reading radiologist, deep learning created a rescan/recall ratio of (7.3 ± 2.2)/(3.2 ± 2.5) for MS, and (3.6 ± 1.5)/(2.8 ± 1.6) for stroke. Due to the large variability in the technologists' assessments, it was only the decrease in the recall rate for MS, for which the deep learning algorithm was trained, that was statistically significant (P = .03). CONCLUSIONS: Fast, automated deep learning-based image-quality rating can decrease rescan and recall rates, while rendering them technologist-independent. It was estimated that decreasing rescans and recalls from the technologists' values to the values of deep learning could save hospitals $24,000/scanner/year.
BACKGROUND AND PURPOSE: MR imaging rescans and recalls can create large hospital revenue loss. The purpose of this study was to develop a fast, automated method for assessing rescan need in motion-corrupted brain series. MATERIALS AND METHODS: A deep learning-based approach was developed, outputting a probability for a series to be clinically useful. Comparison of this per-series probability with a threshold, which can depend on scan indication and reading radiologist, determines whether a series needs to be rescanned. The deep learning classification performance was compared with that of 4 technologists and 5 radiologists in 49 test series with low and moderate motion artifacts. These series were assumed to be scanned for 2 scan indications: screening for multiple sclerosis and stroke. RESULTS: The image-quality rating was found to be scan indication- and reading radiologist-dependent. Of the 49 test datasets, technologists created a mean ratio of rescans/recalls of (4.7 ± 5.1)/(9.5 ± 6.8) for MS and (8.6 ± 7.7)/(1.6 ± 1.9) for stroke. With thresholds adapted for scan indication and reading radiologist, deep learning created a rescan/recall ratio of (7.3 ± 2.2)/(3.2 ± 2.5) for MS, and (3.6 ± 1.5)/(2.8 ± 1.6) for stroke. Due to the large variability in the technologists' assessments, it was only the decrease in the recall rate for MS, for which the deep learning algorithm was trained, that was statistically significant (P = .03). CONCLUSIONS: Fast, automated deep learning-based image-quality rating can decrease rescan and recall rates, while rendering them technologist-independent. It was estimated that decreasing rescans and recalls from the technologists' values to the values of deep learning could save hospitals $24,000/scanner/year.
Authors: Y W Lui; P D Chang; G Zaharchuk; D P Barboriak; A E Flanders; M Wintermark; C P Hess; C G Filippi Journal: AJNR Am J Neuroradiol Date: 2020-07-30 Impact factor: 3.825
Authors: Yasasvi Tadavarthi; Valeria Makeeva; William Wagstaff; Henry Zhan; Anna Podlasek; Neil Bhatia; Marta Heilbrun; Elizabeth Krupinski; Nabile Safdar; Imon Banerjee; Judy Gichoya; Hari Trivedi Journal: Radiol Artif Intell Date: 2022-02-02
Authors: Yoganand Balagurunathan; Andrew Beers; Michael Mcnitt-Gray; Lubomir Hadjiiski; Sandy Napel; Dmitry Goldgof; Gustavo Perez; Pablo Arbelaez; Alireza Mehrtash; Tina Kapur; Ehwa Yang; Jung Won Moon; Gabriel Bernardino Perez; Ricard Delgado-Gonzalo; M Mehdi Farhangi; Amir A Amini; Renkun Ni; Xue Feng; Aditya Bagari; Kiran Vaidhya; Benjamin Veasey; Wiem Safta; Hichem Frigui; Joseph Enguehard; Ali Gholipour; Laura Silvana Castillo; Laura Alexandra Daza; Paul Pinsky; Jayashree Kalpathy-Cramer; Keyvan Farahani Journal: IEEE Trans Med Imaging Date: 2021-11-30 Impact factor: 11.037
Authors: Hugo Vrenken; Mark Jenkinson; Dzung L Pham; Charles R G Guttmann; Deborah Pareto; Michel Paardekooper; Alexandra de Sitter; Maria A Rocca; Viktor Wottschel; M Jorge Cardoso; Frederik Barkhof Journal: Neurology Date: 2021-10-04 Impact factor: 9.910