Computerized Bone Age Estimation Using Deep Learning Based Program : Evaluation of the Accuracy and Efficiency
OBJECTIVE: The purpose of this study is to evaluate the accuracy and efficiency of a new automatic software system for bone age assessment and to validate its feasibility in clinical practice.
MATERIALS AND METHODS: A Greulich-Pyle method-based deep-learning technique was used to develop the automatic software system for bone age determination. Using this software, bone age was estimated from left-hand radiographs of 200 patients (3-17 years old) using first-rank bone age (software only), computer-assisted bone age (two radiologists with software assistance), and Greulich-Pyle atlas-assisted bone age (two radiologists with Greulich-Pyle atlas assistance only). The reference bone age was determined by the consensus of two experienced radiologists.
RESULTS: First-rank bone ages determined by the automatic software system showed a 69.5% concordance rate and significant correlations with the reference bone age (r = 0.992; p < 0.001). Concordance rates increased with the use of the automatic software system for both reviewer 1 (63.0% for Greulich-Pyle atlas-assisted bone age vs 72.5% for computer-assisted bone age) and reviewer 2 (49.5% for Greulich-Pyle atlas-assisted bone age vs 57.5% for computer-assisted bone age). Reading times were reduced by 18.0% and 40.0% for reviewers 1 and 2, respectively.
CONCLUSION: Automatic software system showed reliably accurate bone age estimations and appeared to enhance efficiency by reducing reading times without compromising the diagnostic accuracy.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2017 |
---|---|
Erschienen: |
2017 |
Enthalten in: |
Zur Gesamtaufnahme - volume:209 |
---|---|
Enthalten in: |
AJR. American journal of roentgenology - 209(2017), 6 vom: 17. Dez., Seite 1374-1380 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Kim, Jeong Rye [VerfasserIn] |
---|
Links: |
---|
Themen: |
Bone age |
---|
Anmerkungen: |
Date Completed 05.12.2017 Date Revised 10.12.2019 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.2214/AJR.17.18224 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM275690911 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM275690911 | ||
003 | DE-627 | ||
005 | 20231225010243.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2017 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.2214/AJR.17.18224 |2 doi | |
028 | 5 | 2 | |a pubmed24n0918.xml |
035 | |a (DE-627)NLM275690911 | ||
035 | |a (NLM)28898126 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Kim, Jeong Rye |e verfasserin |4 aut | |
245 | 1 | 0 | |a Computerized Bone Age Estimation Using Deep Learning Based Program |b Evaluation of the Accuracy and Efficiency |
264 | 1 | |c 2017 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 05.12.2017 | ||
500 | |a Date Revised 10.12.2019 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a OBJECTIVE: The purpose of this study is to evaluate the accuracy and efficiency of a new automatic software system for bone age assessment and to validate its feasibility in clinical practice | ||
520 | |a MATERIALS AND METHODS: A Greulich-Pyle method-based deep-learning technique was used to develop the automatic software system for bone age determination. Using this software, bone age was estimated from left-hand radiographs of 200 patients (3-17 years old) using first-rank bone age (software only), computer-assisted bone age (two radiologists with software assistance), and Greulich-Pyle atlas-assisted bone age (two radiologists with Greulich-Pyle atlas assistance only). The reference bone age was determined by the consensus of two experienced radiologists | ||
520 | |a RESULTS: First-rank bone ages determined by the automatic software system showed a 69.5% concordance rate and significant correlations with the reference bone age (r = 0.992; p < 0.001). Concordance rates increased with the use of the automatic software system for both reviewer 1 (63.0% for Greulich-Pyle atlas-assisted bone age vs 72.5% for computer-assisted bone age) and reviewer 2 (49.5% for Greulich-Pyle atlas-assisted bone age vs 57.5% for computer-assisted bone age). Reading times were reduced by 18.0% and 40.0% for reviewers 1 and 2, respectively | ||
520 | |a CONCLUSION: Automatic software system showed reliably accurate bone age estimations and appeared to enhance efficiency by reducing reading times without compromising the diagnostic accuracy | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a bone age | |
650 | 4 | |a children | |
650 | 4 | |a deep learning | |
650 | 4 | |a neural network model | |
700 | 1 | |a Shim, Woo Hyun |e verfasserin |4 aut | |
700 | 1 | |a Yoon, Hee Mang |e verfasserin |4 aut | |
700 | 1 | |a Hong, Sang Hyup |e verfasserin |4 aut | |
700 | 1 | |a Lee, Jin Seong |e verfasserin |4 aut | |
700 | 1 | |a Cho, Young Ah |e verfasserin |4 aut | |
700 | 1 | |a Kim, Sangki |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t AJR. American journal of roentgenology |d 1981 |g 209(2017), 6 vom: 17. Dez., Seite 1374-1380 |w (DE-627)NLM000037109 |x 1546-3141 |7 nnns |
773 | 1 | 8 | |g volume:209 |g year:2017 |g number:6 |g day:17 |g month:12 |g pages:1374-1380 |
856 | 4 | 0 | |u http://dx.doi.org/10.2214/AJR.17.18224 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 209 |j 2017 |e 6 |b 17 |c 12 |h 1374-1380 |