Skip to main content

Table 1 Delineation metrics for GTVs on MRAC and sCTAC

From: Evaluating a radiotherapy deep learning synthetic CT algorithm for PET-MR attenuation correction in the pelvis

Metric

GTV

MRAC

sCTAC

DSC

Primary

\(0.990 \pm 0.002\)(0.978, 0.994)

\(0.992 \pm 0.002\)(0.983, 0.998)

\({\mathrm {DTA}}_{\rm mean}\)[mm]

Primary

\(0.06 \pm 0.01\)(0.02, 0.13)

\(0.06 \pm 0.01\)(0.01, 0.11)

\({\mathrm {DTA}}_{\max}\)[mm]

Primary

\(1.87 \pm 0.24\)(0.97 ,3.16)

\(1.76 \pm 0.13\)(1.23, 2.53)

Volume [\(\%\)]

Primary

\(0.7 \pm 0.5\)(\(-0.4\), 4.2)

\(0.7 \pm 0.5\)(\(-1.3\), 3.2)

DSC

Nodal

\(0.988 \pm 0.006\)(0.968, 1.000)

\(0.987 \pm 0.008\)(0.955, 1.000)

\({\mathrm {DTA}}_{mean}\)[mm]

Nodal

\(0.04 \pm 0.01\)(0.00, 0.07)

\(0.04 \pm 0.02\)(0.0, 0.11)

\({\mathrm {DTA}}_{\max}\)[mm]

Nodal

\(1.4 \pm 0.4\)(0.0, 2.34)

\(1.4 \pm 0.4\)(0.0, 2.0)

Volume [\(\%\)]

Nodal

\(0.8 \pm 0.3\)(0.0, 1.6)

\(1.1 \pm 0.6\)(\(-0.1\), 2.8)

  1. Volume indicates the volume difference between MRAC/sCTAC and CTAC, relative to the CTAC volume. All results given as mean ± standard error (minimum, maximum)