Computer-aided Diagnosis in Interstitial Lung Disease : Application of an Artificial Neural Network to Differential Diagnosis
| Project/Area Number |
12670886
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Radiation science
|
|---|
| Research Institution | NAGASAKI UNIVERSITY |
|---|
Principal Investigator |
ASHIZAWA Kazuto Nagasaki University Graduate School of Biomedical Sciences, Instructor, 大学院・医歯薬学総合研究科, 助手 (90274662)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
KATSURAGAWA Shigehiko Nippon Bunri University, Professor, NBU総合研究センター, 教授 (60021630)
HAYASHI Kuniaki Nagasaki University Graduate School of Biomedical Sciences, Professor, 大学院・医歯薬学総合研究科, 教授 (80039536)
|
|---|
| Project Period (FY) |
2000 – 2002
|
| Project Status |
Completed (Fiscal Year 2002)
|
| Budget Amount *help |
¥3,200,000 (Direct Cost: ¥3,200,000)
Fiscal Year 2002: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 2001: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 2000: ¥2,200,000 (Direct Cost: ¥2,200,000)
|
|---|
| Keywords | Interstitial lung disease / Computer-aided diagnosis / Artificial neural network / Chest radiography / High-resolution CT / コンピューター支援診断 / ニュウラルネットワーク |
|---|
| Research Abstract |
Purpose : We applied an artificial neural network (ANN) to differential diagnosis among certain diffuse lung diseases using high-resolution CT (HRCT) to evaluate the effect of the ANN output on radiologists' diagnostic performance.
Materials and Methods : We selected 130 clinical cases of diffuse lung disease. We used a single three-layer, feed-forward ANN with a back-propagation algorithm. The ANN was designed to differentiate among 11 diffuse lung diseases using 10 clinical parameters and 23 HRCT features. Therefore, the ANN consisted of 33 input units and 11 output units. Subjective ratings for 23 HRCT features were provided independently by eight radiologists. All clinical cases were used for training and testing of the ANN by using a round-robin technique. In the observer test, HRCT images were viewed by eight radiologists first without and then with ANN output. The radiologists' performance was evaluated with receiver operating characteristic (ROC) analysis with a continuous rating scale.
Results : The average A_z value for ANN performance obtained with all clinical parameters and HRCT features was 0.956. The diagnostic performance of all radiologists was significantly improved from 0.972 to 0.981 (p<0.005), when they used the ANN output based on their own feature ratings.
Conclusion : The ANN can provide a useful output as a "second opinion" to improve radiologists' diagnostic performance in the differential diagnosis of certain diffuse lung diseases using HRCT.
|
Report
(4 results)
Research Products
(12 results)
