Table 4.
AI model versus Reader A | AI model versus Reader B | Reader B versus Reader A | |
---|---|---|---|
True positive lesions | |||
Total | 214 | 210 | 246 |
Per patient (IQR) | 2 (0.0–12.0) | 1 (0.0–12.0) | 2.5 (1.0–14.5) |
False positive lesions | |||
Total | 45 | 41 | 25 |
Per patient (IQR) | 1 (0.0–2.3) | 1 (0.0–2.0) | 0.0 (0.0–1.3) |
False negative lesions | |||
Total | 53 | 59 | 21 |
Per patient (IQR) | 1 (0.0–2.0) | 1 (0.0–3.3) | 0.0 (0.0–1.0) |
Sensitivity (%) | 80 | 79 | 92 |
PPV (%) | 83 | 84 | 91 |
Number of lesions which are true positive, false positive and false negative for the AI model versus Reader A, the AI model versus Reader B and Reader B versus Reader A. Values are total number of lesions, median number of lesions per patient, median volume (ml) and median TLSREwb with interquartile range (IQR). Sensitivity and positive predictive value (PPV) are also presented for each comparison