Comparative Analysis of Computer-Aided Diagnosis and Computer-Assisted Subjective Assessment in Thyroid Ultrasound
The value of computer-aided diagnosis (CAD) and computer-assisted techniques equipped with different TIRADS remains ambiguous. Parallel diagnosis performances of computer-assisted subjective assessments and CAD were compared based on AACE, ATA, EU, and KSThR TIRADS. CAD software computed the diagnos...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/842dc9b312bf41cc8cb0678114fe4f24 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | The value of computer-aided diagnosis (CAD) and computer-assisted techniques equipped with different TIRADS remains ambiguous. Parallel diagnosis performances of computer-assisted subjective assessments and CAD were compared based on AACE, ATA, EU, and KSThR TIRADS. CAD software computed the diagnosis of 162 thyroid nodule sonograms. Two raters (R<sub>1</sub> and R<sub>2</sub>) independently rated the sonographic features of the nodules using an online risk calculator while blinded to pathology results. Diagnostic efficiency measures were calculated based on the final pathology results. R<sub>1</sub> had higher diagnostic performance outcomes than CAD with similarities between KSThR (SEN: 90.3% vs. 83.9%, <i>p</i> = 0.57; SPEC: 46% vs. 51%, <i>p</i> = 0.21; AUROC: 0.76 vs. 0.67, <i>p</i> = 0.02), and EU (SEN: 85.5% vs. 79%, <i>p</i> = 0.82; SPEC: 62% vs. 55%, <i>p</i> = 0.27; AUROC: 0.74 vs. 0.67, <i>p</i> = 0.06). Similarly, R<sub>2</sub> had higher AUROC and specificity but lower sensitivity than CAD (KSThR-AUROC: 0.74 vs. 0.67, <i>p</i> = 0.13; SPEC: 61% vs. 46%, <i>p</i> = 0.02 and SEN: 75.8% vs. 83.9%, <i>p</i> = 0.31, and EU-AUROC: 0.69 vs. 0.67, <i>p</i> = 0.57, SPEC: 64% vs. 55%, <i>p</i> = 0.19, and SEN: 71% vs. 79%, <i>p</i> = 0.51, respectively). CAD had higher sensitivity but lower specificity than both R<sub>1</sub> and R<sub>2</sub> with AACE for 114 specified nodules (SEN: 92.5% vs. 88.7%, <i>p</i> = 0.50; 92.5% vs. 79.3%, <i>p</i> = 0.02, and SPEC: 26.2% vs. 54.1%, <i>p</i> = 0.001; 26.2% vs. 62.3%, <i>p</i> < 0.001, respectively). All diagnostic performance outcomes were comparable for ATA with 96 specified nodules. Computer-assisted subjective interpretation using KSThR is more ideal for ruling out papillary thyroid carcinomas than CAD. Future larger multi-center and multi-rater prospective studies with a diverse representation of thyroid cancers are necessary to validate these findings. |
|---|