Computer-aided Diagnosis on Chest Radiograph : Clinical Usefulness of Temporal Subtraction for detection of Interval Changes
| Project/Area Number |
15591285
|
|---|
| 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, Hospital of Medicine of Dentistry, Assistant Professor, 医学部・歯学部付属病院, 講師 (90274662)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
林 邦昭 長崎大学, 大学院・医歯薬学総合研究科, 教授 (80039536)
|
|---|
| Project Period (FY) |
2003 – 2005
|
| Project Status |
Completed (Fiscal Year 2005)
|
| Budget Amount *help |
¥3,100,000 (Direct Cost: ¥3,100,000)
Fiscal Year 2005: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 2004: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 2003: ¥1,500,000 (Direct Cost: ¥1,500,000)
|
|---|
| Keywords | Computer-aided diagnosis / Temporal subtraction for detection of interval change / Chest radiography |
|---|
| Research Abstract |
Temporal subtraction scheme, which is one of the computer-aided diagnosis, is the technique by which a previous chest radiograph is subtracted from a current radiograph in order to enhance interval changes. The purpose of this study is to evaluate the usefulness of this scheme on digital chest radiographs for the detection of interval changes in various lesions seen in daily clinical practice.
We performed the observer test as a retrospective study. Forty pairs of digital chest radiographs in 20 cases with interval changes including nodular opacity, localized consolidation, diffuse lung opacity and so on, and 20 cases without interval changes were used. Temporal subtraction images were obtained from a commercially available computer-aided diagnosis (CAD) system (Truedia/XR ; Mitsubishi Space Software, Japan). Eight observers provided their confidence levels for the presence or absence of interval changes without and with temporal subtraction. Their confidence levels were represented on
… More
a 5-point rating scale (5 : definitely absent, 4 : probably absent, 3 : possibly present, 2 : probably present, 1 : definitely present). The diagnostic performance of observers was improved with use of temporal subtraction in less experienced radiologists.
We used this scheme in daily clinical work, and evaluated its usefulness prospectively. Radiologists provided their confidence levels for the presence or absence of interval changes without subtraction on a 5-point rating scale. After that they changed their confidence levels with subtraction in needed. Although the majority of the cases in daily clinical practice were normal or showed no interval change, there were not a few cases in which subtraction images alerted radiologists to locations of missed lesions, or suggested that their interpretations were false positive.
In conclusion, the temporal subtraction scheme is useful in the detection of interval changes for various lesions seen in daily work, especially for less experienced radiologists. Less
|
Report
(4 results)
Research Products
(12 results)
