Table 1.

Inference Results with Input Image(s) Only across all stages of repair.

		Cropped, oriented, resampled				Cropped, oriented, NOT resampled
		Single-Phase	Two-Phase	Four-Phase	CSP	Single-Phase	Two-Phase	Four–Phase	CSP
DSC	Anterior	0.71[0.63–0.75]	0.72[0.68–0.77]	0.73[0.68–0.78]	0.74[0.69–0.79]	0.72[0.66–0.76]	0.73[0.67–0.78]	0.74[0.68–0.77]	0.73[0.66–0.78]
	Posterior	0.63[0.58–0.73]	0.66[0.61–0.73]	0.66[0.58–0.72]	0.69[0.65–0.76]	0.66[0.55–0.71]	0.67[0.57–0.72]	0.65[0.6–0.71]	0.64[0.57–0.71]
	Septal	0.65[0.55–0.69]	0.67[0.57–0.71]	0.64[0.55–0.73]	0.69[0.58–0.75]	0.64[0.54–0.7]	0.67[0.58–0.71]	0.65[0.53–0.72]	0.68[0.53–0.72]
	Merged	0.75[0.7–0.78]	0.77[0.73–0.8]	0.76[0.73–0.8]	0.77[0.72–0.81]	0.74[0.7–0.79]	0.77[0.73–0.81]	0.76[0.71–0.81]	0.76[0.71–0.8]
	Average	0.64[0.61–0.7]	0.68[0.64–0.72]	0.67[0.63–0.72]	0.7[0.67–0.74]	0.65[0.61–0.7]	0.67[0.64–0.75]	0.68[0.63–0.73]	0.67[0.61–0.72]
MBD	Anterior	1.03[0.6–1.31]	0.92[0.55–1.36]	0.97[0.58–1.22]	0.85[0.49–1.15]	0.91[0.61–1.41]	0.95[0.55–1.49]	0.81[0.56–1.33]	0.96[0.53–1.26]
	Posterior	0.72[0.55–0.97]	0.73[0.53–1.2]	0.72[0.53–1.03]	0.74[0.55–1.04]	0.81[0.53–1]	0.77[0.54–1.18]	0.88[0.61–1.04]	0.66[0.56–0.99]
	Septal	0.79[0.64–1.01]	0.79[0.59–0.99]	0.8[0.63–0.99]	0.65[0.52–0.93]	0.88[0.66–1.28]	0.79[0.55–1.01]	0.75[0.57–0.98]	0.73[0.59–0.87]
	Merged	0.67[0.56–0.82]	0.6[0.46–0.69]	0.62[0.52–0.81]	0.59[0.47–0.79]	0.72[0.58–1.09]	0.66[0.49–0.88]	0.65[0.49–0.9]	0.61[0.5–0.79]
	Average	0.81[0.66–1.19]	0.84[0.64–1.14]	0.83[0.65–1.01]	0.75[0.61–1.14]	0.82[0.68–1.24]	0.81[0.56–1.27]	0.81[0.71–1.09]	0.78[0.6–1.12]

DSC and MBD measurements are presented for individual leaflets (anterior, posterior, septal), merged leaflets and average across individual leaflets. The columns represent different image frame inputs with and without resampling. The column of the best ranked FCN input configuration in bold. Metric values are displayed as median [IQR].