A semi-automatic technique to quantify complex tuberculous lung lesions on 18F-fluorodeoxyglucose positron emission tomography/computerised tomography images.
Stephanus T MalherbePatrick DupontIlse KantPetri AhlersMagdalena KrielAndré G LoxtonRay Y ChenLaura E ViaFriedrich ThienemannRobert J WilkinsonClifton E BarryStephanie Griffith-RichardsAnnare EllmanKatharina RonacherJill WinterGerhard WalzlJames M Warwicknull nullPublished in: EJNMMI research (2018)
Our technique is promising to segment and quantify the lung scans of pulmonary tuberculosis patients in a semi-automatic manner, appropriate for measuring treatment response. Further validation is required in larger cohorts.
Keyphrases
- positron emission tomography
- computed tomography
- pulmonary tuberculosis
- deep learning
- end stage renal disease
- pet ct
- ejection fraction
- machine learning
- pet imaging
- mycobacterium tuberculosis
- newly diagnosed
- chronic kidney disease
- prognostic factors
- peritoneal dialysis
- magnetic resonance imaging
- patient reported outcomes
- patient reported
- neural network
- clinical decision support
- dual energy