Table 1 Characteristics of Data Sets
From: Deep learning for semi-automated unidirectional measurement of lung tumor size in CT
Parameter | NSCLC-Radiomics | CPTAC-LUAD | LCTSC | QIN LUNG CT | TCGA-LUSC | SPIE-AAPM Lung CT Challenge | LungCT-Diagnosis | RIDER Lung CT |
|---|---|---|---|---|---|---|---|---|
No. of Scans | 844 | 8 | 60 | 47 | 74 | 70 | 61 | 64 |
No. of Images | 52,072 | 1,676 | 9,593 | 3,954 | 36,518 | 22,489 | 4,682 | 15,419 |
No. of Annotated Images | 955 | 8 | 96 | 114 | 67 | 139 | 119 | 119 |
Training Set | 667 | 4 | 68 | 80 | 47 | 97 | 83 | 83 |
Age | 66.5 | 69.8 | 68.1 | 63.9 | 71.4 | 62.7 | NA | 61.6 |
Male | 446 (67) | 3 (75) | 30 (44) | 6 (8) | 33 (70) | 33 (34) | 0 (0) | 0 (0) |
Female | 221 (33) | 1 (25) | 38 (56) | 16 (20) | 14 (30) | 64 (66) | 0 (0) | 0 (0) |
Gender – Not Known | 0 (0) | 0 (0) | 0 (0) | 58 (72) | 0 (0) | 0 (0) | 83 (100) | 83 (100) |
Validation Set | 144 | 2 | 14 | 17 | 10 | 21 | 18 | 18 |
Age | 65.5 | 73 | 72.3 | 69.4 | 71.9 | 60.2 | NA | 66.1 |
Male | 101 (70) | 1 (50) | 5 (36) | 1 (6) | 6 (60) | 5 (24) | 0 (0) | 0 (0) |
Female | 43 (30) | 1 (50) | 9 (64) | 7 (41) | 4 (40) | 16 (76) | 0 (0) | 0 (0) |
Gender – Not Known | 0 (0) | 0 (0) | 0 (0) | 9 (53) | 0 (0) | 0 (0) | 18 (100) | 18 (100) |
Test Set | 144 | 2 | 14 | 17 | 10 | 21 | 18 | 18 |
Age | 68.6 | 73 | 71.2 | 65.6 | 72.3 | 55.7 | NA | 63.2 |
Male | 106 (74) | 1 (50) | 7 (50) | 6 (35) | 5 (50) | 12 (57) | 0 (0) | 0 (0) |
Female | 38 (26) | 1 (50) | 7 (50) | 0 (0) | 5 (50) | 9 (43) | 0 (0) | 0 (0) |
Gender – Not Known | 0 (0) | 0 (0) | 0 (0) | 11 (65) | 0 (0) | 0 (0) | 18 (100) | 18 (100) |
Characteristic | ||||||||
Slice thickness (mm) | 3.0 | 1.3—3.0 | 1.3—3.0 | 2.5—6.0 | 1.0—5.0 | 1.0 | 2.5—6.0 | 1.3 |
Increment (mm) | 3.0 | 0.6—3.0 | 1.3—3.0 | 2.0—5.0 | 0.6—5.0 | 1.0 | 2.5—5.0 | 1.3 |
In-plane Resolution (mm) | 0.97 | 0.56—1.37 | 0.98—1.37 | 0.59—0.95 | 0.55—0.98 | 0.55—0.90 | 0.59—0.95 | 0.51—0.90 |
Dataset Version | Version 2: Updated 2016/05/31 | Version 4: Updated 2018/10/24 | Version 1: Updated 2017/05/17 | Version 2: Updated 2017/07/31 | Version 3: Updated 2017/01/30 | Version 2: Updated 2016/09/23 | Version 1: Updated 2014/12/30 | Version 2: Updated 2014/11/14 |