Table 2 Contingency table for assessment of the deep-learning algorithm across 11 diagnostic classes on the validation set (N = 3,962)

From: Development and validation of a smartphone-based deep-learning-enabled system to detect middle-ear conditions in otoscopic images

 

“Ground truth” label

Deep-learning prediction

Normal

Wax plug

Eardrum perforation

OME

CCR

Otitis externa

Tympanosclerosis

AOM

Osteoma

Foreign body

Tympanic graft

TOTAL

Normal

525

0

0

1

0

0

0

0

0

0

0

526

Wax plug

1

529

1

0

1

0

0

0

0

0

0

532

Eardrum perforation

0

0

516

0

0

0

0

0

0

0

0

516

OME

2

0

0

488

0

0

0

0

0

0

0

490

CCR

0

0

0

0

530

0

0

0

0

0

1

531

Otitis externa

0

0

9

0

0

280

0

0

0

0

0

289

Tympanosclerosis

2

0

0

0

0

0

267

0

0

0

0

269

AOM

0

0

0

0

0

0

0

258

0

0

0

258

Osteoma

0

0

0

0

0

0

0

0

202

0

0

202

Foreign body

0

0

0

0

0

0

0

0

0

176

0

176

Tympanic graft

0

0

0

0

0

0

0

0

0

0

173

173

TOTAL

530

529

526

489

531

280

267

258

202

176

174

3962

  1. AOM acute otitis media, CCR cavity after cholesteatoma removal, OME otitis media with effusion.