PURPOSE: To show that a deep learning (DL)-based, automated model for Lipiodol (Guerbet Pharmaceuticals, Paris, France) segmentation on cone-beam computed tomography (CT) after conventional transarterial chemoembolization performs closer to the "ground truth segmentation" than a conventional thresholding-based model. MATERIALS AND METHODS: This post hoc analysis included 36 patients with a diagnosis of hepatocellular carcinoma or other solid liver tumors who underwent conventional transarterial chemoembolization with an intraprocedural cone-beam CT. Semiautomatic segmentation of Lipiodol was obtained. Subsequently, a convolutional U-net model was used to output a binary mask that predicted Lipiodol deposition. A threshold value of signal intensity on cone-beam CT was used to obtain a Lipiodol mask for comparison. The dice similarity coefficient (DSC), mean squared error (MSE), center of mass (CM), and fractional volume ratios for both masks were obtained by comparing them to the ground truth (radiologist-segmented Lipiodol deposits) to obtain accuracy metrics for the 2 masks. These results were used to compare the model versus the threshold technique. RESULTS: For all metrics, the U-net outperformed the threshold technique: DSC (0.65 ± 0.17 vs 0.45 ± 0.22, P < .001) and MSE (125.53 ± 107.36 vs 185.98 ± 93.82, P = .005). The difference between the CM predicted and the actual CM was 15.31 mm ± 14.63 versus 31.34 mm ± 30.24 (P < .001), with lesser distance indicating higher accuracy. The fraction of volume present ([predicted Lipiodol volume]/[ground truth Lipiodol volume]) was 1.22 ± 0.84 versus 2.58 ± 3.52 (P = .048) for the current model's prediction and threshold technique, respectively. CONCLUSIONS: This study showed that a DL framework could detect Lipiodol in cone-beam CT imaging and was capable of outperforming the conventionally used thresholding technique over several metrics. Further optimization will allow for more accurate, quantitative predictions of Lipiodol depositions intraprocedurally.
PURPOSE: To show that a deep learning (DL)-based, automated model for Lipiodol (Guerbet Pharmaceuticals, Paris, France) segmentation on cone-beam computed tomography (CT) after conventional transarterial chemoembolization performs closer to the "ground truth segmentation" than a conventional thresholding-based model. MATERIALS AND METHODS: This post hoc analysis included 36 patients with a diagnosis of hepatocellular carcinoma or other solid liver tumors who underwent conventional transarterial chemoembolization with an intraprocedural cone-beam CT. Semiautomatic segmentation of Lipiodol was obtained. Subsequently, a convolutional U-net model was used to output a binary mask that predicted Lipiodol deposition. A threshold value of signal intensity on cone-beam CT was used to obtain a Lipiodol mask for comparison. The dice similarity coefficient (DSC), mean squared error (MSE), center of mass (CM), and fractional volume ratios for both masks were obtained by comparing them to the ground truth (radiologist-segmented Lipiodol deposits) to obtain accuracy metrics for the 2 masks. These results were used to compare the model versus the threshold technique. RESULTS: For all metrics, the U-net outperformed the threshold technique: DSC (0.65 ± 0.17 vs 0.45 ± 0.22, P < .001) and MSE (125.53 ± 107.36 vs 185.98 ± 93.82, P = .005). The difference between the CM predicted and the actual CM was 15.31 mm ± 14.63 versus 31.34 mm ± 30.24 (P < .001), with lesser distance indicating higher accuracy. The fraction of volume present ([predicted Lipiodol volume]/[ground truth Lipiodol volume]) was 1.22 ± 0.84 versus 2.58 ± 3.52 (P = .048) for the current model's prediction and threshold technique, respectively. CONCLUSIONS: This study showed that a DL framework could detect Lipiodol in cone-beam CT imaging and was capable of outperforming the conventionally used thresholding technique over several metrics. Further optimization will allow for more accurate, quantitative predictions of Lipiodol depositions intraprocedurally.
Authors: Ron C Gaba; Robert J Lewandowski; Ryan Hickey; Mark O Baerlocher; Emil I Cohen; Sean R Dariushnia; Bertrand Janne d'Othée; Siddharth A Padia; Riad Salem; David S Wang; Boris Nikolic; Daniel B Brown Journal: J Vasc Interv Radiol Date: 2016-02-02 Impact factor: 3.464
Authors: A Ganguly; A Fieselmann; M Marks; J Rosenberg; J Boese; Y Deuerling-Zheng; M Straka; G Zaharchuk; R Bammer; R Fahrig Journal: AJNR Am J Neuroradiol Date: 2011-07-14 Impact factor: 3.825
Authors: K Niu; P Yang; Y Wu; T Struffert; A Doerfler; S Schafer; K Royalty; C Strother; G-H Chen Journal: AJNR Am J Neuroradiol Date: 2016-02-18 Impact factor: 3.825
Authors: Milena A Miszczuk; Julius Chapiro; Jean-Francois H Geschwind; Vinayak Thakur; Nariman Nezami; Fabian Laage-Gaupp; Michal Kulon; Johanna M M van Breugel; Arash Fereydooni; MingDe Lin; Lynn Jeanette Savic; Bruno Tegel; Tamara Wahlin; Eliot Funai; Todd Schlachter Journal: Transl Oncol Date: 2020-02-22 Impact factor: 4.243