Samjhana Thapaliya1, Samuel L Brady1,2, Elanchezhian Somasundaram1,2, Christopher G Anton1,2, Brian D Coley1,2,3, Alexander J Towbin1,2,3, Bin Zhang3,4, Jonathan R Dillman1,2, Andrew T Trout5,6,7. 1. Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Avenue, MLC 5031, Cincinnati, OH, 45229, USA. 2. Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA. 3. Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, USA. 4. Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. 5. Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Avenue, MLC 5031, Cincinnati, OH, 45229, USA. andrew.trout@cchmc.org. 6. Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA. andrew.trout@cchmc.org. 7. Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, USA. andrew.trout@cchmc.org.
Abstract
BACKGROUND: Deep learning Computed Tomography (CT) reconstruction (DLR) algorithms promise to improve image quality but the impact on clinical diagnostic performance remains to be demonstrated. We aimed to compare DLR to standard iterative reconstruction for detection of urolithiasis by unenhanced CT in children and young adults. METHODS: This was an IRB approved retrospective study involving post-hoc reconstruction of clinically acquired unenhanced abdomen/pelvis CT scans. Images were reconstructed with six different manufacturer-standard DLR algorithms and reformatted in 3 planes (axial, sagittal, and coronal) at 3 mm intervals. De-identified reconstructions were loaded as independent examinations for review by 3 blinded radiologists (R1, R2, R3) tasked with identifying and measuring all stones. Results were compared to the clinical iterative reconstruction images as a reference standard. IntraClass correlation coefficients and kappa (k) statistics were used to quantify agreement. RESULTS: CT data for 14 patients (mean age: 17.3 ± 3.4 years, 5 males and 9 females, weight class: 31-70 kg (n = 6), 71-100 kg (n = 7), > 100 kg (n = 1)) were reconstructed into 84 total exams. 7 patients had urinary tract calculi. Interobserver agreement on the presence of any urinary tract calculus was substantial to almost perfect (k = 0.71-1) for all DLR algorithms. Agreement with the reference standard on number of calculi was excellent (ICC = 0.78-0.96) and agreement on the size of the largest calculus was fair to excellent (ICC = 0.51-0.97) depending on reviewer and DLR algorithm. CONCLUSION: Deep learning reconstruction of unenhanced CT images allows similar renal stone detectability compared to iterative reconstruction.
BACKGROUND: Deep learning Computed Tomography (CT) reconstruction (DLR) algorithms promise to improve image quality but the impact on clinical diagnostic performance remains to be demonstrated. We aimed to compare DLR to standard iterative reconstruction for detection of urolithiasis by unenhanced CT in children and young adults. METHODS: This was an IRB approved retrospective study involving post-hoc reconstruction of clinically acquired unenhanced abdomen/pelvis CT scans. Images were reconstructed with six different manufacturer-standard DLR algorithms and reformatted in 3 planes (axial, sagittal, and coronal) at 3 mm intervals. De-identified reconstructions were loaded as independent examinations for review by 3 blinded radiologists (R1, R2, R3) tasked with identifying and measuring all stones. Results were compared to the clinical iterative reconstruction images as a reference standard. IntraClass correlation coefficients and kappa (k) statistics were used to quantify agreement. RESULTS: CT data for 14 patients (mean age: 17.3 ± 3.4 years, 5 males and 9 females, weight class: 31-70 kg (n = 6), 71-100 kg (n = 7), > 100 kg (n = 1)) were reconstructed into 84 total exams. 7 patients had urinary tract calculi. Interobserver agreement on the presence of any urinary tract calculus was substantial to almost perfect (k = 0.71-1) for all DLR algorithms. Agreement with the reference standard on number of calculi was excellent (ICC = 0.78-0.96) and agreement on the size of the largest calculus was fair to excellent (ICC = 0.51-0.97) depending on reviewer and DLR algorithm. CONCLUSION: Deep learning reconstruction of unenhanced CT images allows similar renal stone detectability compared to iterative reconstruction.
Authors: Samuel L Brady; Andrew T Trout; Elanchezhian Somasundaram; Christopher G Anton; Yinan Li; Jonathan R Dillman Journal: Radiology Date: 2020-11-17 Impact factor: 11.105
Authors: Courtney A Coursey; David D Casalino; Erick M Remer; Ronald S Arellano; Jay T Bishoff; Manjiri Dighe; Pat Fulgham; Stanley Goldfarb; Gary M Israel; Elizabeth Lazarus; John R Leyendecker; Massoud Majd; Paul Nikolaidis; Nicholas Papanicolaou; Srinivasa Prasad; Parvati Ramchandani; Sheila Sheth; Raghunandan Vikram Journal: Ultrasound Q Date: 2012-09 Impact factor: 1.657
Authors: Andrea Steuwe; Birte Valentin; Oliver T Bethge; Alexandra Ljimani; Günter Niegisch; Gerald Antoch; Joel Aissa Journal: Diagnostics (Basel) Date: 2022-07-05