Table 4 Classification of segmented lesions
From: AI-based quantification of whole-body tumour burden on somatostatin receptor PET/CT
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 |