JP4280334B2 - Irradiation squeezing presence / absence determination device, method, and computer-readable storage medium - Google Patents

Irradiation squeezing presence / absence determination device, method, and computer-readable storage medium Download PDF

Info

Publication number
JP4280334B2
JP4280334B2 JP23910298A JP23910298A JP4280334B2 JP 4280334 B2 JP4280334 B2 JP 4280334B2 JP 23910298 A JP23910298 A JP 23910298A JP 23910298 A JP23910298 A JP 23910298A JP 4280334 B2 JP4280334 B2 JP 4280334B2
Authority
JP
Japan
Prior art keywords
squeezing
absence
determination
irradiation
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
JP23910298A
Other languages
Japanese (ja)
Other versions
JP2000060842A (en
Inventor
弘之 新畠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Canon Inc
Original Assignee
Canon Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Canon Inc filed Critical Canon Inc
Priority to JP23910298A priority Critical patent/JP4280334B2/en
Publication of JP2000060842A publication Critical patent/JP2000060842A/en
Application granted granted Critical
Publication of JP4280334B2 publication Critical patent/JP4280334B2/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Landscapes

  • Analysing Materials By The Use Of Radiation (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Processing (AREA)
  • Transforming Light Signals Into Electric Signals (AREA)
  • Image Analysis (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Description

【0001】
【発明の属する技術分野】
本発明は、放射線の照射しぼり付きの撮像装置で撮影された画像から、照射しぼりの有無を判定する照射しぼり有無判定装置、方法及びこの装置で用いられるコンピュータ読み取り可能な記憶媒体に関し、特に画像全体から得られる特性値から決まる濃度値の端領域における出現頻度から照射しぼりの有無を判定する場合に用いて好適なものである。
【0002】
【従来の技術】
近年のデジタル技術の進歩により放射線画像をデジタル画像信号に変換し、このデジタル画像信号に画像処理を行い、CRT等に表示、あるいはプリント出力することが行われている。ところで、放射線画像の撮影においては、人道上の理由より、また、不要領域からの散乱を防ぎコントラスの低下を防止するために、放射線を必要領域のみにしか照射しない照射しぼりが行われるのが一般的である。また、画像処理を行うにあたり、濃度値の分布から処理パラメータを決定し、決定されたパラメータに基づき画像処理を行うのが普通である。しかしながら、照射領域が限定されない場合には、関心領域外のいわば不要情報を画像処理パラメータの決定に使用することになり、適切な画像処理が行えないという問題が生じる。
【0003】
従って、照射領域を抽出し、関心領域のみの情報から画像処理パラメータを決定する必要がある。照射領域を抽出する方法としては、例えば画像濃度値を微分しその値から照射端を判定するものや、特公平6−90412号公報に示されるように照射領域外のすそ野の領域を想定し、このすそ野を1次近似式で近似し、実濃度値と1次近似式の値との差異から照射端を判定する方法等が知られている。
【0004】
しかし、上記各照射端抽出方法は、照射しぼりがあることを前提として成り立つ方法であり、各照射端抽出方法を用いるためには、前処理として照射しぼりの有る無しを判定する必要がある。
【0005】
照射しぼりの有る無しを判定する方法としては、従来よりUSP5091970号公報に示されるように、画像中心部の濃度平均、中間値等と画像端部の濃度平均値とを比較し、画像端部の濃度値が一定値以下なら照射しぼりありとする方法がある。
【0006】
【発明が解決しようとする課題】
しかしながら上記USP5091970号公報の方法では、照射しぼりが行われない時に画像端部に撮影部位がかかった場合に、この画像端部にかかった撮影部位の面積と放射線の透過率とにより画像端部の平均濃度が変動する。そのため照射しぼりが行われていないのに照射しぼり有りと誤判定するという問題があった。
また、照射線量が小さい場合に、画像中心部と画像端部との濃度差がなくなり、照射しぼりがないのに照射しぼり有りと誤判定するという問題があった。
【0007】
本発明は上記のような問題を解決するためになされたもので、照射しぼりの有無を正確に判定できるようにすることを目的とする。
【0008】
【課題を解決するための手段】
本発明の照射しぼり有無判定装置は、放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段と、上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり有りと判定した場合は絞り有りと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定手段と、を備えることを特徴とする。
また、本発明の照射しぼり有無判定装置の他の特徴とするところは、放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段と、上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり無しと判定した場合は絞り無しと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定手段と、を備えることを特徴とする。
【0009】
本発明の照射しぼり有無判定方法は、放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段によってしぼりの有無を判定するしぼり有無判定ステップと、上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり有りと判定した場合は絞り有りと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定ステップと、を備えることを特徴とする。
また、本発明の照射しぼり有無判定方法の他の特徴とするところは、放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段によってしぼりの有無を判定するしぼり有無判定ステップと、上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり無しと判定した場合は絞り無しと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定ステップと、を備えることを特徴とする。
【0010】
本発明の記憶媒体は、放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段によってしぼりの有無を判定するしぼり有無判定ステップと、上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり有りと判定した場合は絞り有りと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定ステップと、をコンピュータに実行させるためのプログラムを記憶したことを特徴とする。
また、本発明の記憶媒体の他の特徴とするところは、放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段によってしぼりの有無を判定するしぼり有無判定ステップと、上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり無しと判定した場合は絞り無しと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定ステップと、をコンピュータに実行させるためのプログラムを記憶したことを特徴とする。
【0011】
【発明の実施の形態】
以下、本発明の実施の形態を図面と共に説明する。
図1は、本発明の第1の実施の形態による照射しぼり有無判定装置の構成を示すブロックである。
図1において、101は第1のしぼり有無判定部、102は第2のしぼり有無判定部、103は第3のしぼり有無判定部を示し、104は第1〜第3のしぼり有無判定部101〜103の判定結果から統合的にしぼりの有無を判定する判定部を示す。
【0012】
次に各しぼり有無判定部101〜104について順次説明する。
図2は照射しぼりなしで撮影された手のX線画像を示す。
図3は照射しぼり有りで撮影されたX線画像を示し、領域Aが横幅dx、縦幅dyの画像端部を示す。
【0013】
図4は第1のしぼり有無判定部101の構成を示すブロック図であり、図において、401は画像全体から第1の特性値を計算する第2の特性値算出手段、402は第1の特性値計算手段401で算出された特性値に基づいて決定された濃度値が上記画像端部Aに出現する頻度を計算する第1の出現頻度計算手段、403は第1の出現頻度計算手段402で計算された値から照射しぼりの有無を判定する第1の判定手段である。
【0014】
次に第1のしぼり有無判定部101の動作について図5のフローチャートを用いて説明する。ここでは例えば左端部で照射しぼりがあるかないかを判定する場合について説明する。
第1の特性値算出手段401で画像全体のMAX値を算出する。ここでのMAX値は画像全体の累積ヒストグラムの上位部、例えば5%点としてもよいし、画像濃度値をソートし上位部としてもよい(ステップS501)。
【0015】
次に第1の出現頻度計算手段402は、第1の特性値算出手段401で算出されたMAX値の一定割合、例えば90%以上の濃度値の画像端部Aでの出現頻度を計算する(ステップS502)。
【0016】
次に第1の判定手段403は、第1の出現頻度計算手段402で計算された出現頻度が一定値Th1より大きいならば、完全に照射しぼり無しとし、flg11=1、flg1=1とする(ステップS503)。また上記出現頻度がTh1以下でTh2より大きければ、しぼり無しの可能性大とし、flg11=2,flg1=1とする(ステップS504)。そしてTh2以下でTh3より大きければしぼり有りの可能性大とし、flg11=3,flg=2とする(S505)。Th3以下ならば完全にしぼり無しとする。ここで例えばTh1=0.3、Th2=0.1、Th3=0.05とする。
【0017】
以上のように、第1のしぼり有無判定部101によれば、画像全体のMAX値から決められる画像端部の濃度の出現頻度を判定基準として用い、照射しぼりの有無を判定するので、照射端部に撮影対象がかかっても安定した判定が行える効果がある。また、放射線量の強弱の影響を受けず、放射線量が少ない場合や、画像端部全体を撮影対象が覆う場合にも安定して判定が行える効果がある。
【0018】
次に第2の判定部102について説明する。
図6は照射しぼり有りでX線撮影された画像を示し、Xa,Xbは照射端の水平軸に対する位置を示す。領域A,B,C,Dが画像端部を示し、A,Bが照射しぽりがある領域を示し、C,Dは照射しぼりがない領域を示す。
【0019】
図7は第2の判定部102の構成を示すブロック図である。
図7において、701は照射端を抽出する座標を指示する座標指示手段、702は座標指示手段701で指示された座標の1次元データから、照射端点を決めるために用いる特性値を計算する第2の特性値抽出手段、703は第2の特性値抽出手段702で計算された特性値から照射端点を抽出する端点抽出手段、704は端点抽出手段703で抽出された照射端点の座標を記憶する記憶手段、705は記憶手段704で記憶された照射端点の座標の値から照射しぼりの有無を判定する第2の判定手段である。
【0020】
次に第2の判定部102動作について図8のフローチャートを用いて説明する。ここでは例えば下端部で照射しぼりが有るか無いかを判定する場合について説明する。
座標指示手段701は図6に示すXa,Xb間の複数のX軸場の座標を示す。例えば、本実施の形態ではXa,Xb間を均等に10等分した座標(i=1〜10)を用いる(ステップS801)。
【0021】
次に第2の特性値抽出手段702では、座標指示手段701の指示する座標の1次元データから(1)式で示される計算式に従い2次差分値SSi(y)を計算する(ステップS802)。ここでiは座標指示手段801が示す座標の番号である。またfi(y)はXa,Xb間で垂直に横切る1次元データ列を示し、yはその座標を示す。dは差分距離を示す定数である。
SSi(y)=fi(y−d)一2×fi(y)十fi(y+d)───(1)
【0022】
端点抽出手段803は(2)式に従い照射端yiを抽出する(ステップS803)。
SS(yi)=min{SS(yi) 0≦y≦Length}───(2)
【0023】
そして、記憶手段704は照射端の座標yiを記憶する(ステップS804)。
以上のステップS801〜S804の処理をl=1〜10まで繰り返す。ただし、Lengthは画像データの横軸の長さを示す。
【0024】
次に第2の判定手段705は、記憶手段704に記憶される照射端点の座標の平均値を計算し(ステツプS805)、照射端点の分散値Bvを計算する(ステップS806)。そして、分散値Bvが一定数Th4以上ならば照射しぼり無し、それ以外なら照射しぼり有りとする(ステップS807)。
【0025】
ここで図8には説明していないが、分散値がTh4より大きければ、flg21=1、flg2=1として完全にしぼり無しと判定し、Th4以下でTh5より大きければ、しぼり無しの可能性大と判定し、flg21=2、flg2=1とする。またTh5以下でTh6より大きければ、しぼり有りの可能性大と判定し、flg21=3、f1g2=2とする。最後にTh6以下の場合、flg21=4、flg2=2として完全にしぼり有りと判定する。
【0026】
尚、Th4,Th5,Th6は実験的に決まる定教であり、Th4>Th5>Th6の関係がある。複数列で照射端を求めており、照射しぼり(下部)があれば、複数の端点はほぼ同一横軸上に並ぶので分散Bvは小さくなり、照射しぼりが無ければ照射端点の座標はばらけるため分散値Bvは大きくなる。
【0027】
上記の説明では2次差分を用いたが、照射端の濃度が急峻に変化する場合には1次差分あるいは高次差分を用いてもよい。その場合には、画像端部から値を検索し、一定閾値以上の値が最初に現れたた点を照射端候補とする。
また、判定手段で判定指標として分散値を用いているが、標準偏差等、その他度数の離散度を示す指標を用いても同様な効果が得られる。
【0028】
以上のように、第2のしぼり有無判定部102によれば、判定基準として複数の照射端点の座標値の分散を用いるため、その値を基準として照射しぼりの有無をうまく抽出できる効果がある。また2次差分値を用いているため、X線の透過率の悪い物体に対しても、X線の直接照射される領域とそうでない領域との境界点を精度よく判定することができる。そのため、画像端部に腹部等のX線透過率の低い部位がかぶさっていても、照射しぼりの有無を精度よく抽出することができる。
【0029】
次に第3のしぼり判定部103について説明する。
図9は第3のしぼり判定部103の構成を示すブロック図である。
図9において、901は1次元画像データの2次差分値を計算する2次差分値計算手段、902は2次差分値計算手段901で計算された2次差分値に基づいて照射領域の左端点を抽出する左端点抽出手段、903は2次差分値計算手段901で計算された2次差分値に基づいて照射領域の右端点を抽出する右端点抽出手段、904は左端点抽出手段902で抽出された左端点と右端点抽出手段903で抽出された右端点と、予め求められている照射領域の左右端点との近似度を判定し、近似度が高ければ照射しぼり無しと判定し、近似度が低ければ照射しぼり有りと判定する第3の判定手段である。
【0030】
次に第3のしぼり有無判定部103の動作について図10フローチャートを用いて説明する。ここでは例えば下端部(図6C部)で照射しぼりが有るか無いかを判定する場合について説明する。
2次差分値計算手段901は(3)式で示される計算式に従い2次差分値SS(x)を計算する(ステップS1001)。ここでf(x)は領域C内を水平方向に横切る1次元データ列を示し、xはその座標を示す。dは差分距離を示す定数である。
SS(d)=f(x−d)一2×f(x)十f(x+d)───(3)
【0031】
左端点抽出手段902は(4)式に従い左照射端x1を抽出する(ステップS1002)。ここでバーxは左右照射端内の水平軸上の座標とする(図6のXaからXbの間の座標)。
【0032】
【数1】

Figure 0004280334
【0033】
次に右端点抽出手段903は(5)式に従い右照射端x2を抽出する(ステップS103)。
【0034】
【数2】
Figure 0004280334
【0035】
ただし、Lengthは画像データの横軸の長さを示す。
【0036】
次に第3の判定手段904は予め求められた照射端と式(4)、(5)で求められた照射端とを比較し、|x1−xa|≦Th8かつ|x2−xb|≦Th8ならば照射しぼり無しと判定し、flg3=1とする。それ以外の場合は照射しぼり有りと判定し、flg3=2とする(ステップS304)。
【0037】
また、図10では説明していないが、|x1−xa|<Th7かつ|x2−xb|<Th7ならば完全にしぼり無しとし、flg31=1、flg3=1とする。さらにTh7≦|x1−xa|<Th8かつTH7≦|x2−xb|<Th8ならば、しぼり無しの可能性大としてflg31=2、flg3=1とする。また、Th8≦|x1−xa|<Th9かつTH8≦|x2−xb|<Th9ならば、しぼり有りの可能性大としてflg31=3、flg3=4とする。そして最後に、Th9≦|x1−xa|かつTh9≦|x2−xb|ならば、完全にしぼり有りとしてflg31=4、flg3=2とする。
【0038】
尚、Th7,Th8,Th9は近似幅を示す定数で、Th7<Th8<Th9なる関係がある。A、B、C端についても同様に判定する。
また照射端を抽出する場合にさらに条件を付加して、2次差分値が一定閾値以下となる条件を置いてもよい。さらに、照射端での濃度変化が急峻な場合には、照射端として1次微分、2次微分、さらなる高次微分の値を2次差分の代わりに用いてよい。この場合、各値の絶対値が一定閾値以上の箇所を照射端候補とする。
【0039】
以上のようにこのしぼり有無判定部103によれば、判定基準として2次差分値を用いているため、X線の透過率の悪い物体に対しても、X線の直接照射される領域とそうでない領域との境界点を精度よく抽出することができる。そのため、画像端部に腹部などのX線透過率の低い部位が覆いかぷさっていても、照射しぼりの有無を精度よく抽出することができる効果がある。
【0040】
次に判定部104による各しぼり有無判定部101〜103の判定結果の統合方法について説明する。
本実施の形態の統合法則は、判定部104により各しぼり有無判定部101〜103の判定結果のうち多数の判定結果を採用するものである。具体的に図11のフローチャートに従い説明する。
まず第1のしぼり有無判定部101の判定がしぼり有り無しか判定し(S1101)、しぼり無しならば第2のしぼり有無判定部102の判定結果を参照し、しぼり無しなら判定部104の判定結果をしぼり無しとして処理を終了する。
【0041】
第2のしぼり有無判定部102の判定結果がしぼり有りなら第3のしぼり有無判定部103の判定結果を参照し、しぼり無しなら判定部104の判定結果をしぼり無しとし、しぼり有りなら判定結果をしぼり有りとして処理を終了する。
【0042】
また第1のしぼり有無判定部101の判定がしぼり有りならば第2のしぼり有無判定部102の判定結果を参照し、しぼり有りなら判定部104の判定結果をしぼり有りとして処理を終了する。第2のしぼり有無判定部102の判定結果がしぼりなしなら第3のしぼり有無判定部103の判定結果を参照し、しぼり無しなら判定部104の判定結果をしぼり無しとし、しぼり有りなら判定結果をしぼり有りとして処理を終了する。
【0043】
本実施の形態では、しぼり有無判定部を3種しか用いてないが、それ以上の数に拡張してもよい。また、本実施の形態で用いた以外の照射しぼりの有無を判定するアルゴリズムを用いてもよい。
【0044】
以上のように本実施の形態では、複数のしぼり有無判定部の結果を統合するので、判定精度が上がる効果がある。さらに、複数のしぼり有無の判定結果のうち多数の判定に従って最終判定をするので、しぼり有無判定部を一つしか使わない場合より精度が上がる効果がある。
【0045】
次に第2の実施の形態による各しぼり有無判定部101〜103の結果の統合方法について図12のフローチャートを用いて説明する。
本実施の形態では、第1のしぼり有無判定部101の結果が完全にしぼり無しならぱ判定部104の判定結果をしぼり無しとして処理を終了する。
【0046】
また、第1のしぼり有無判定部101の結果が完全にしぼり無し以外ならステップ1202の判定に進む(S1201)。次にステップS1202では、第1のしぼり有無判定蔀101の結果が完全にしぼり有りならば、判定部104の判定結果をしぼり有りとして処理を終了し、それ以外ならばステップS1203に進む。ステップS1203では、第1のしぼり有無判定部101の結果がしぼり無しの可能性大がどうか判定し、しぼり無しの可能性大ならばステップS1204に進み、それ以外の場合はステップS1206に進む。
【0047】
そして、第2のしぼり有無判定部102の判定結果がしぼり無しならば判定部104の判定結果をしぼり無しとして処理を終了し、それ以外の場合はステップS1205に進む(S1204) 。そして、S1205では第3のしぼり有無判定部103の結果がしぼり無しならば判定部104の結果をしぼり無しとし、しぼり有りならば判定部104の結果をしぼり有りとして処理を終了する。
尚、各しぼり有無の判定部101〜103のアルゴリズムを順列的に入れ替えて図12と同一の処理を行ってもよい。
【0048】
本実施の形態によれば、各しぼり有無判定部の結果にしぼり有無の判定に対し確実性の高い判定が出る場合は、その判定結果を採用することでより判定精度が上がる効果がある。
また、各しぼり有無判定部の判定の確実性が低い場合には、各しぼり有無判定部の判定結果のうち多数を占める判定結果を採用するためより判定精度が上がる効果がある。
【0049】
次に第3の実施による各しぼり有無判定部101〜103の結果の統合方法について図13を用いて説明する。
本実施の形態では、各しぼり有無判定部のうちの一つの判定部の判定結果が完全にしぼり有りと判定した場合、判定部104の判定結果をしぼり有りとして処理を終了する。
各しぼり有無判定部の判定結果がいずれも完全にしぼり有りでなかった場合は、図11に示す第1の実施の形態と同様の処理を行う。
【0050】
本実施の形態によれば、各しぼり有無の判定結果のうち、確実な判定結果があればその結果を採用するので、判定精度が上がる効果がある。さらに、各しぼり有無の判定結果のうち、確実な判定結果が無い場合には、第1の実施の形態と同様の処理を行うことにより判定精度が上がる効果がある。
【0051】
次に第4の実施の形態による各しぼり有無判定部101〜103の結果の統合方法について図14を用いて説明する。
本実施の形態では、各しぼり有無判定部のうち一つの判定部の判定結果が完全にしぼり無しと判定した場合、判定部104の判定結果をしぼり無しとして処理を終了する。
各しぼり有無の判定部の判定結果がいずれも完全にしぼり無しでなかった場合は、図11に示す第1の実施の形態と同様の処理を行う。
【0052】
本実施の形態によれば、各しぼり有無の判定結果のうち、確実な判定結果があればその結果を採用するので、判定精度が上がる効果がある。さらに、各しぼり有無の判定結果のうち、確実な判定結果が無い場合には、第1の実施の形態と同様の処理を行うことにより判定精度が上がる効果がある。
【0053】
次に第5の実施の形態を説明する。
本実施の形態では、各しぼり有無判定部の結果を数値化し、その結果の合計値からしぼりの有無を判定する。例えばflg11が1ならば判定値h1=2、flg11が2ならば判定値h1=1、flg11が3ならば判定値h1=−1、flg11が4ならば判定値h1=−2とする。同様に、flg21が1ならば判定値h2=2、flg21が2ならば判定値h2=1、flg21が3ならば判定値h2=−1、flg21が4ならば判定値h2=−2とする。
【0054】
同様に、flg31が1ならば判定値h3=2、flg31が2ならば判定値h3=1、flg31が3ならば判定値h3=−1、flg31が4ならば判定値h3=−2とする。そしてh1+h2+h3の合計値から判定部104がしぼりの有無を判定する。例えば合計値が0以上の場合にしぼり無し、0より下の場合にしぼり有りと判定する。
尚、本実施の形態においては、しぼり有無判定部の数を増やしてもよい。また、判定の数値化を変更してもよい。
【0055】
本実施の形態によれば、各しぼり有無の判定部の結果を数値化して総合的に判定できるため、判定精度が上がる効果がある。
【0056】
次に第6の実施の形態を説明する。
第1のしぼり有無判定部101の出現頻度計算手段402で計算された出現頻度、第2のしぼり有無判定部102の第2の判定手段705で計算された照射端点の分散値、第3のしぼり有無判定部103の第3の判定手段904で計算される|x1−xa|、|x2−x1|の合計値を説明変数とし、しぼりの有無を目的変数として重回帰分析を行い線形式を作成する。例えば目的変数をしぼりが有れば1、無ければ0とする。そして未知な画像が入力されたならば、上記説明変数を計算し、上記線形式の値を求め、例えば線形式の値が0.5以上ならしぼり有り、O.5よリ下ならばしぼり無しとする。
【0057】
尚、ここでは線形回帰式を用いたが、ニューラルネット、エージェント等を用いてもよい。
またしぼり有無判定部は3つに限るものではない。
【0058】
本実施の形態によれば、各しぼり有無判定部位の結果を統計的に判定結果に反映することが可能であり、より判定精度が上がる効果がある。また関数の作成にニューラルネットを用いた場合には、非線型な統計分布を反映することが可能でより判定精度が上がる効果がある。
【0059】
次に本発明による記憶媒体について説明する。
図1、図4、図7、図9の各ブロックから成るシステムを、CPU、ROM等のメモリを含むコンピュータシステムで構成する場合、上記メモリは本発明による記憶媒体を構成する。この記憶媒体には、図5、図6、図8、図10、図11等のフローチャートについて前述した動作を制御するための処理手順を実行するためのプログラムが記憶される。
【0060】
また、この記憶媒体としては、ROM、RAM等の半導体メモリ、光ディスク、光磁気ディスク、磁気媒体等を用いてよく、これらをCD−ROM、フロッピィディスク、磁気媒体、磁気カード、不揮発性メモリカード等に構成して用いてよい。
【0061】
従って、この記憶媒体を上記各図に示したシステムや装置以外の他のシステムや装置で用い、そのシステムあるいはコンピュータがこの記憶媒体に格納されたプログラムコードを読み出し、実行することによっても、前述した各実施の形態と同等の機能を実現できると共に、同等の効果を得ることができ、本発明の目的を達成することができる。
【0062】
また、コンピュータ上で稼働しているOS等が処理の一部又は全部を行う場合、あるいは、記憶媒体から読み出されたプログラムコードが、コンピュータに挿入された拡張機能ボードやコンピュータに接続された拡張機能ユニットに備わるメモリに書き込まれた後、そのプログラムコードの指示に基づいて、上記拡張機能ボードや拡張機能ユニットに備わるCPU等が処理の一部又は全部を行う場合にも、各実施の形態と同等の機能を実現できると共に、同等の効果を得ることができ、本発明の目的を達成することができる。
【0063】
【発明の効果】
以上説明したように、本発明によれば、各判定結果のうち、確実な判定結果があればその結果を採用するので、判定精度が上がる効果がある。さらに、各判定結果のうち、確実な判定結果が無い場合には、複数のしぼり有無の判定結果のうち多数の判定に従って最終判定をするので、しぼり有無判定基準を一つしか使わない場合より精度が上がる効果がある。
【0068】
さらに、本発明の他の特徴によれば、判定基準として画像全体のMAX値から決められる濃度の出現頻度を用いることにより、照射端部に撮影対象がかかっても安定した判定が行える効果がる。また、放射線量の強弱の影響を受けず、放射線量が少ない場合や、画像端部全体を撮影対象が覆う場合にも安定して判定が行える効果がある。
【0069】
また、判定基準として、複数の照射端点の座標値の分散を用いることにより、その値を基準として照射しぼりの有無をうまく抽出できる効果がある。さらに、2次差分値を用いることにより、X線の透過率の悪い物体に対しても、X線の直接照射される領域とそうでない領域との境界点を精度よく判定することができる。そのため、画像端部に腹部等のX線透過率の低い部位がかぶさっていても、照射しぼりの有無を精度よく抽出することができる。
【図面の簡単な説明】
【図1】本発明の第1の実施の形態を示すブロック図である。
【図2】照射しぼり無しで撮影した手のX線画像を示す構成図である。
【図3】照射しぼり有りで撮影した手のX線画像と照射端部Aを示す構成図である。
【図4】第1のしぼり有無判定部の構成を示すブロック図である。
【図5】第1のしぼり有無判定部の処理の流れを示すフローチャートである。
【図6】第2のしぼり有無判定部の判定領域を示す構成図である。
【図7】第2のしぼり有無判定部の構成を示すブロック図である。
【図8】第2のしぼり有無判定部の処理の流れを示すフローチャートである。
【図9】第3のしぼり有無判定部の構成を示すブロック図である。
【図10】第3のしぼり有無判定部の処理の流れを示すフローチャートである。
【図11】第1の実施の形態の処理の流れを示すフローチャートである。
【図12】第2の実施の形態の処理の流れを示すフローチャートである。
【図13】第3の実施の形態の処理の流れを示すフローチャートである。
【図14】第4の実施の形態の処理の流れを示すフローチャートである。
【符号の説明】
101 第1のしぼり有無判定部
102 第2のしぼり有無判定部
103 第3のしぼり有無判定部
104 判定部
401 第1の特性値算出手段
402 第1の出現頻度計算手段
403 第1の判定手段
701 座標指示手段
702 特性値抽出手段
703 端点抽出手段
704 記憶手段
705 第2の判定手段
901 2次差分値計算手段
902 左端点抽出手段
903 右端点抽出手段
904 第3の判定手段[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an irradiation-threshold presence / absence determination device and method for determining the presence / absence of irradiation-threshold from an image taken by an imaging device with radiation-threshold-down, and a computer-readable storage medium used in this device, in particular. This is suitable for use in determining the presence or absence of irradiation from the appearance frequency in the end region of the density value determined from the characteristic value obtained from the above.
[0002]
[Prior art]
With recent advances in digital technology, a radiation image is converted into a digital image signal, image processing is performed on the digital image signal, and the image is displayed on a CRT or printed out. By the way, in radiographic image capturing, for humanitarian reasons, in order to prevent scattering from unnecessary areas and to prevent reduction of contrast, it is common to perform irradiation squeezing that irradiates only the necessary areas. Is. In performing image processing, it is common to determine processing parameters from the distribution of density values and perform image processing based on the determined parameters. However, when the irradiation area is not limited, so-called unnecessary information outside the region of interest is used for determination of the image processing parameter, which causes a problem that appropriate image processing cannot be performed.
[0003]
Therefore, it is necessary to extract an irradiation region and determine an image processing parameter from information on only the region of interest. As a method for extracting the irradiation region, for example, a method of differentiating the image density value and determining the irradiation end from the value, or a region of the base field outside the irradiation region as shown in Japanese Patent Publication No. 6-90412, A method is known in which this bottom field is approximated by a first-order approximation expression, and the irradiation end is determined from the difference between the actual density value and the value of the first-order approximation expression.
[0004]
However, each of the above-mentioned irradiation end extraction methods is a method that is based on the assumption that there is an irradiation squeeze, and in order to use each irradiance end extraction method, it is necessary to determine whether or not there is an irradiation squeeze as preprocessing.
[0005]
As a method for determining the presence or absence of irradiation squeezing, as shown in US Pat. No. 5,091,970, the density average, intermediate value, etc. at the center of the image are compared with the density average value at the edge of the image. If the density value is below a certain value, there is a method of squeezing.
[0006]
[Problems to be solved by the invention]
However, in the method of US Pat. No. 5,091,970, when an imaging region is applied to the edge of the image when the irradiation is not performed, the area of the imaging region is affected by the area of the imaging region applied to the image edge and the transmittance of radiation. Average concentration varies. For this reason, there has been a problem of erroneously determining that there is irradiation even though irradiation is not performed.
In addition, when the irradiation dose is small, there is a problem that there is no difference in density between the center of the image and the edge of the image, and there is a problem of erroneous determination that there is irradiation even though there is no irradiation.
[0007]
The present invention has been made to solve the above-described problems, and an object of the present invention is to make it possible to accurately determine the presence or absence of irradiation.
[0008]
[Means for Solving the Problems]
The irradiation squeezing presence / absence determination device according to the present invention includes at least two squeezing presence / absence determination units having different criteria for determining the presence / absence of irradiation squeezing with respect to a radiographic image, and the first squeezing determination unit among the plurality of squeezing presence / absence determination units. If the presence / absence determining means determines that there is a restriction, it is determined that there is a restriction. Otherwise, the presence / absence of the restriction is determined based on the determination result of the restriction presence / absence determination means that is different from the first restriction presence / absence determination means. And an integrated determination unit.
In addition, another feature of the irradiation squeezing presence / absence determination device according to the present invention is that at least two squeezing presence / absence determination means having different criteria for determining the presence / absence of irradiation squeezing with respect to a radiographic image, Of the determining means, when the first squeezing presence / absence determining means determines that there is no squeezing, it is determined that there is no aperture, and in other cases, the determination result of the squeezing presence / absence determining means that is different from the first squeezing presence / absence determining means. And integrated determination means for determining the presence or absence of an aperture based on the above.
[0009]
The irradiation squeezing presence / absence determination method of the present invention includes a squeezing presence / absence determination step in which the presence / absence of squeezing is determined by at least two squeezing presence / absence determination means different from each other in the determination criterion of the presence or absence of radiation squeezing with respect to a radiographic image, Of the squeezing presence / absence determining means, if the first squeezing presence / absence determining means determines that there is a squeezing, it is determined that there is a squeezing, and otherwise, the squeezing presence / absence determining means is different from the first squeezing presence / absence determining means. An integrated determination step of determining the presence or absence of an aperture based on the determination result.
Another feature of the present invention is a method for determining the presence / absence of squeezing by means of at least two squeezing / non-squeezing determining means for determining the presence / absence of radiation squeezing for radiographic images. Of the plurality of squeezing presence / absence determination means, when the first squeezing presence / absence determination unit determines that there is no squeezing, it is determined that there is no squeezing, and in other cases, the first squeezing presence / absence determination unit is determined. And an integrated determination step of determining the presence or absence of an aperture based on a determination result of a squeezing presence / absence determination unit different from the determination unit.
[0010]
The storage medium according to the present invention includes a squeezing presence / absence determination step for determining the presence / absence of squeezing by at least two squeezing / non-squeezing determination means having different criteria for determining the presence / absence of irradiation irradiation with respect to a radiographic image, and the plurality of squeezing / non-squeezing determinations Among the means, when the first squeezing presence / absence determining means determines that there is squeezing, it is determined that there is a squeezing, and in other cases, the determination result of the squeezing presence / absence determining means different from the first squeezing presence / absence determining means is used. A program for causing a computer to execute an integrated determination step for determining whether or not there is an aperture based on the program is stored.
Another feature of the storage medium according to the present invention is that the presence / absence of the squeezing is determined by at least two squeezing / non-squeezing determining means having different criteria for determining the presence / absence of the irradiation squeezing for the radiographic image. Of the plurality of squeezing presence / absence determining means, if the first squeezing presence / absence determining means determines that there is no squeezing, it is determined that there is no aperture, and otherwise, the first squeezing presence / absence determining means A program for causing a computer to execute an integrated determination step of determining the presence or absence of a diaphragm based on the determination results of different squeezing presence / absence determination means is characterized.
[0011]
DETAILED DESCRIPTION OF THE INVENTION
Embodiments of the present invention will be described below with reference to the drawings.
FIG. 1 is a block diagram showing a configuration of an irradiation-thinning presence / absence determination device according to the first embodiment of the present invention.
In FIG. 1, reference numeral 101 denotes a first squeezing presence / absence determination unit, 102 denotes a second squeezing presence / absence determination unit, 103 denotes a third squeezing presence / absence determination unit, and 104 denotes first to third squeezing presence / absence determination units 101 to 101. The determination part which determines the presence or absence of squeezing integratedly from the determination result of 103 is shown.
[0012]
Next, each of the squeezing presence / absence determining units 101 to 104 will be described sequentially.
FIG. 2 shows an X-ray image of a hand taken without irradiation.
FIG. 3 shows an X-ray image taken with irradiation, and a region A shows an image end portion having a horizontal width dx and a vertical width dy.
[0013]
FIG. 4 is a block diagram showing the configuration of the first squeezing presence / absence determination unit 101. In FIG. 4, 401 is a second characteristic value calculation means for calculating a first characteristic value from the entire image, and 402 is a first characteristic. First appearance frequency calculation means for calculating the frequency at which the density value determined based on the characteristic value calculated by the value calculation means 401 appears at the image edge A, and 403 is the first appearance frequency calculation means 402. It is the 1st determination means which determines the presence or absence of irradiation squeezing from the calculated value.
[0014]
Next, the operation of the first squeezing presence / absence determining unit 101 will be described with reference to the flowchart of FIG. Here, for example, a case will be described in which it is determined whether or not there is irradiation at the left end.
The first characteristic value calculation unit 401 calculates the MAX value of the entire image. The MAX value here may be the upper part of the cumulative histogram of the entire image, for example, the 5% point, or the image density values may be sorted and used as the upper part (step S501).
[0015]
Next, the first appearance frequency calculation unit 402 calculates the appearance frequency at the image end A of a certain ratio of the MAX value calculated by the first characteristic value calculation unit 401, for example, a density value of 90% or more ( Step S502).
[0016]
Next, if the appearance frequency calculated by the first appearance frequency calculation means 402 is larger than a certain value Th1, the first determination means 403 determines that there is no irradiation completely and sets flg11 = 1 and flg1 = 1 ( Step S503). If the appearance frequency is equal to or less than Th1 and greater than Th2, the possibility of no squeezing is assumed to be large, and flg11 = 2 and flg1 = 1 are set (step S504). If it is equal to or less than Th2 and greater than Th3, the possibility of squeezing is set, and flg11 = 3 and flg = 2 are set (S505). If it is less than Th3, no squeeze is made. Here, for example, Th1 = 0.3, Th2 = 0.1, and Th3 = 0.05.
[0017]
As described above, according to the first reduction presence / absence determination unit 101, the presence / absence of irradiation reduction is determined using the appearance frequency of the density at the image edge determined from the MAX value of the entire image as a determination criterion. There is an effect that a stable determination can be made even if an object to be photographed is applied to the part. In addition, there is an effect that the determination can be performed stably even when the radiation dose is small or when the imaging target covers the entire image edge without being affected by the intensity of the radiation dose.
[0018]
Next, the second determination unit 102 will be described.
FIG. 6 shows an X-ray image taken with irradiation squeezed, and Xa and Xb show the positions of the irradiation end with respect to the horizontal axis. Regions A, B, C, and D indicate the edge of the image, A and B indicate regions that are irradiated, and C and D indicate regions that are not irradiated.
[0019]
FIG. 7 is a block diagram illustrating a configuration of the second determination unit 102.
In FIG. 7, reference numeral 701 denotes a coordinate instruction means for instructing coordinates for extracting an irradiation end, and reference numeral 702 denotes a second characteristic value used for determining the irradiation end point from the one-dimensional data of the coordinates instructed by the coordinate instruction means 701. Characteristic value extraction means 703, an end point extraction means for extracting an irradiation end point from the characteristic value calculated by the second characteristic value extraction means 702, and a storage for storing the coordinates of the irradiation end point extracted by the end point extraction means 703. A means 705 is a second determination means for determining the presence or absence of irradiation from the value of the coordinates of the irradiation end point stored in the storage means 704.
[0020]
Next, operation | movement of the 2nd determination part 102 is demonstrated using the flowchart of FIG. Here, for example, a case where it is determined whether or not there is irradiation at the lower end will be described.
A coordinate instruction unit 701 indicates the coordinates of a plurality of X-axis fields between Xa and Xb shown in FIG. For example, in the present embodiment, coordinates (i = 1 to 10) obtained by equally dividing Xa and Xb into 10 parts are used (step S801).
[0021]
Next, the second characteristic value extracting unit 702 calculates the secondary difference value SSi (y) from the one-dimensional data of the coordinates indicated by the coordinate indicating unit 701 according to the calculation formula shown by the formula (1) (step S802). . Here, i is a coordinate number indicated by the coordinate instruction means 801. Further, fi (y) indicates a one-dimensional data string that crosses vertically between Xa and Xb, and y indicates the coordinates thereof. d is a constant indicating the difference distance.
SSi (y) = fi (y−d) 1-2 × fi (y) + fi (y + d) (1)
[0022]
The end point extraction unit 803 extracts the irradiation end yi according to the equation (2) (step S803).
SS (yi) = min {SS (yi) 0 ≦ y ≦ Length} (2)
[0023]
And the memory | storage means 704 memorize | stores the coordinate yi of an irradiation end (step S804).
The above steps S801 to S804 are repeated from 1 = 1 to 10. Here, Length indicates the length of the horizontal axis of the image data.
[0024]
Next, the second determination unit 705 calculates the average value of the coordinates of the irradiation end point stored in the storage unit 704 (step S805), and calculates the dispersion value Bv of the irradiation end point (step S806). If the dispersion value Bv is equal to or greater than a certain number Th4, no irradiation is performed, and otherwise, irradiation is performed (step S807).
[0025]
Although not described in FIG. 8, if the variance value is greater than Th4, it is determined that flg21 = 1 and flg2 = 1 are complete, and if it is less than Th4 and greater than Th5, there is a large possibility of no squeeze. And flg21 = 2 and flg2 = 1. If it is equal to or less than Th5 and greater than Th6, it is determined that there is a large possibility of squeezing, and flg21 = 3 and f1g2 = 2. Finally, if it is less than Th6, it is determined that flg21 = 4 and flg2 = 2 and that there is complete squeezing.
[0026]
Th4, Th5, and Th6 are experimentally determined teachings, and have a relationship of Th4>Th5> Th6. If the irradiation end is obtained in a plurality of rows and there is an irradiation squeeze (lower part), the plurality of end points are arranged on substantially the same horizontal axis, so the variance Bv becomes small. If there is no irradiation squeezing, the coordinates of the irradiation end point vary. The variance value Bv increases.
[0027]
In the above description, the secondary difference is used. However, when the density at the irradiation end changes sharply, a primary difference or a high-order difference may be used. In that case, a value is searched from the edge of the image, and a point where a value equal to or greater than a certain threshold value first appears is set as an irradiation end candidate.
Further, although the variance value is used as the determination index by the determination means, the same effect can be obtained by using an index indicating the discrete degree of other frequencies such as standard deviation.
[0028]
As described above, according to the second squeezed presence / absence determination unit 102, since the variance of the coordinate values of a plurality of irradiation end points is used as a determination criterion, there is an effect that the presence / absence of squeezing can be well extracted based on that value. In addition, since the secondary difference value is used, the boundary point between the area directly irradiated with X-rays and the area not irradiated can be accurately determined even for an object with low X-ray transmittance. Therefore, even if a portion having a low X-ray transmittance, such as the abdomen, covers the edge of the image, it is possible to accurately extract the presence of irradiation.
[0029]
Next, the third squeezing determination unit 103 will be described.
FIG. 9 is a block diagram illustrating a configuration of the third squeezing determination unit 103.
In FIG. 9, reference numeral 901 denotes a secondary difference value calculation means for calculating the secondary difference value of the one-dimensional image data, and 902 denotes a left end point of the irradiation area based on the secondary difference value calculated by the secondary difference value calculation means 901. 903 is a right end point extracting means for extracting the right end point of the irradiation area based on the secondary difference value calculated by the secondary difference value calculating means 901, and 904 is extracted by the left end point extracting means 902 The degree of approximation between the left end point and the right end point extracted by the right end point extracting means 903 and the left and right end points of the irradiation area obtained in advance is determined. If the degree of approximation is high, it is determined that there is no irradiation, and the degree of approximation Is a third determination means for determining that there is irradiation squeezing.
[0030]
Next, the operation of the third squeezing presence / absence determining unit 103 will be described with reference to the flowchart of FIG. Here, for example, a case will be described in which it is determined whether or not there is irradiation at the lower end (portion in FIG. 6C).
The secondary difference value calculation means 901 calculates the secondary difference value SS (x) according to the calculation formula shown by the formula (3) (step S1001). Here, f (x) indicates a one-dimensional data string traversing the region C in the horizontal direction, and x indicates the coordinates. d is a constant indicating the difference distance.
SS (d) = f (x−d) 1 × 2 × f (x) + f (x + d) (3)
[0031]
The left end point extraction means 902 extracts the left irradiation end x1 according to the equation (4) (step S1002). Here, the bar x is a coordinate on the horizontal axis in the left and right irradiation ends (coordinate between Xa and Xb in FIG. 6).
[0032]
[Expression 1]
Figure 0004280334
[0033]
Next, the right end point extracting means 903 extracts the right irradiation end x2 according to the equation (5) (step S103).
[0034]
[Expression 2]
Figure 0004280334
[0035]
Here, Length indicates the length of the horizontal axis of the image data.
[0036]
Next, the third determination unit 904 compares the irradiation end obtained in advance with the irradiation end obtained by the equations (4) and (5), and | x1-xa | ≦ Th8 and | x2-xb | ≦ Th8. Then, it is determined that there is no irradiation squeeze, and flg3 = 1. In other cases, it is determined that there is irradiation and flg3 = 2 is set (step S304).
[0037]
Although not described in FIG. 10, if | x1-xa | <Th7 and | x2-xb | <Th7, it is assumed that there is no squeeze and flg31 = 1 and flg3 = 1. Further, if Th7 ≦ | x1−xa | <Th8 and TH7 ≦ | x2−xb | <Th8, it is assumed that flg31 = 2 and flg3 = 1 as the possibility of no squeezing. Further, if Th8 ≦ | x1−xa | <Th9 and TH8 ≦ | x2−xb | <Th9, it is assumed that flg31 = 3 and flg3 = 4 as the possibility that there is a reduction. Finally, if Th9 ≦ | x1−xa | and Th9 ≦ | x2−xb |, it is assumed that there is a complete reduction, and flg31 = 4 and flg3 = 2.
[0038]
Th7, Th8, and Th9 are constants indicating approximate widths, and have a relationship of Th7 <Th8 <Th9. The same determination is made for the A, B, and C ends.
In addition, when extracting the irradiation end, a condition may be added so that the secondary difference value is equal to or less than a certain threshold value. Further, when the density change at the irradiation end is steep, the values of the first derivative, the second derivative, and the further higher derivative may be used as the irradiation end instead of the secondary difference. In this case, a point where the absolute value of each value is equal to or greater than a certain threshold is set as an irradiation end candidate.
[0039]
As described above, according to the squeezing presence / absence determination unit 103, since the secondary difference value is used as a determination criterion, even an object with low X-ray transmittance is considered to be an area directly irradiated with X-rays. It is possible to accurately extract boundary points with non-regions. Therefore, there is an effect that the presence / absence of irradiation squeezing can be accurately extracted even when the image end portion is covered with a portion having a low X-ray transmittance such as the abdomen.
[0040]
Next, a method for integrating the determination results of each of the reduced presence / absence determination units 101 to 103 by the determination unit 104 will be described.
The integration rule of the present embodiment employs a large number of determination results among the determination results of the respective presence / absence determination units 101 to 103 by the determination unit 104. This will be specifically described with reference to the flowchart of FIG.
First, it is determined whether or not the first squeezing presence / absence determining unit 101 determines whether or not there is a squeezing (S1101). If there is no squeezing, the determination result of the second squeezing presence / absence determining unit 102 is referred to. The process ends with no squeezing.
[0041]
If the determination result of the second squeezing presence / absence determination unit 102 is squeezed, the determination result of the third squeezing / non-squeezing determination unit 103 is referred to. If there is no squeezing, the determination result of the determination unit 104 is determined to be no squeezing. The process is terminated as there is a squeeze.
[0042]
Also, if the first squeezing presence / absence determining unit 101 determines that there is a squeezing, the determination result of the second squeezing / non-squeezing determining unit 102 is referred to. If there is a squeezing, the determination result of the determining unit 104 is determined to be squeezing and the processing is terminated. If the determination result of the second squeezing presence / absence determining unit 102 is not squeezed, the determination result of the third squeezing / non-squeezing determining unit 103 is referred to. If there is no squeezing, the determination result of the deciding unit 104 is determined to be no squeezing. The process is terminated as there is a squeeze.
[0043]
In the present embodiment, only three types of squeezing presence / absence determination units are used, but the number may be expanded to a larger number. In addition, an algorithm for determining the presence or absence of irradiation reduction other than that used in the present embodiment may be used.
[0044]
As described above, in the present embodiment, the results of a plurality of the presence / absence determination units are integrated, which has the effect of improving the determination accuracy. Further, since the final determination is made according to a large number of determinations among a plurality of determination results on the presence / absence of squeezing, there is an effect that accuracy is improved as compared with the case where only one squeezing / non-squeezing determination unit is used.
[0045]
Next, a method for integrating the results of the respective presence / absence determining units 101 to 103 according to the second embodiment will be described with reference to the flowchart of FIG.
In the present embodiment, if the result of the first squeezing / non-squeezing determining unit 101 is completely non-squeezed, the determination result of the squeezing determining unit 104 is determined to be non-squeezed and the process is terminated.
[0046]
On the other hand, if the result of the first squeezing presence / absence determining unit 101 is not completely squeezed, the process proceeds to step 1202 (S1201). Next, in step S1202, if the result of the first squeezing presence / absence determination bar 101 is completely reduced, the determination result of the determination unit 104 is determined to be squeezed, and the process ends. Otherwise, the process proceeds to step S1203. In step S1203, it is determined whether or not the result of the first squeezing presence / absence determination unit 101 is high in the possibility of no squeezing. If the possibility of no squeezing is high, the process proceeds to step S1204. Otherwise, the process proceeds to step S1206.
[0047]
If the determination result of the second squeezing presence / absence determining unit 102 is that there is no squeezing, the determination result of the deciding unit 104 is determined to be squeezed, and otherwise, the process ends (S1204). In step S1205, if the result of the third squeezing presence / absence determination unit 103 indicates that there is no squeezing, the result of the determination unit 104 is determined to be squeezed, and if there is a squeeze, the result of the determination unit 104 is determined to be squeezed and the processing is terminated.
Note that the same processing as that in FIG. 12 may be performed by permutating the algorithms of the determination units 101 to 103 for the presence or absence of squeezing.
[0048]
According to the present embodiment, when a highly reliable determination is made with respect to the determination of the presence / absence of squeezing as a result of each squeezing / non-presence determining unit, there is an effect that the determination accuracy is further improved by adopting the determination result.
In addition, when the certainty of determination by each of the presence / absence determination units is low, the determination result occupying a large number of the determination results of the respective determination / non-existence determination units is adopted, so that the determination accuracy is further improved.
[0049]
Next, a method of integrating the results of the respective presence / absence determining units 101 to 103 according to the third embodiment will be described with reference to FIG.
In the present embodiment, when the determination result of one determination unit among the respective reduction presence / absence determination units determines that there is a complete reduction, the determination result of the determination unit 104 is determined to be the reduction, and the process is terminated.
If none of the determination results of each of the squeezed presence / absence determining units is completely squeezed, the same processing as in the first embodiment shown in FIG. 11 is performed.
[0050]
According to the present embodiment, if there is a certain determination result among the determination results of the presence or absence of the squeezing, the determination result is adopted, so that the determination accuracy is improved. Furthermore, when there is no reliable determination result among the determination results of the presence or absence of each squeezing, there is an effect that the determination accuracy is improved by performing the same processing as in the first embodiment.
[0051]
Next, a method of integrating the results of the respective presence / absence determining units 101 to 103 according to the fourth embodiment will be described with reference to FIG.
In the present embodiment, when the determination result of one determination unit of each of the presence / absence determination units determines that there is no squeeze, the determination result of the determination unit 104 is determined to be no squeeze, and the process ends.
If none of the determination results of the determination units for the presence / absence of squeezing is completely squeezed, processing similar to that in the first embodiment shown in FIG. 11 is performed.
[0052]
According to the present embodiment, if there is a certain determination result among the determination results of the presence or absence of the squeezing, the determination result is adopted, so that the determination accuracy is improved. Furthermore, when there is no reliable determination result among the determination results of the presence or absence of each squeezing, there is an effect that the determination accuracy is improved by performing the same processing as in the first embodiment.
[0053]
Next, a fifth embodiment will be described.
In the present embodiment, the result of each of the presence / absence determination units is digitized, and the presence / absence of the reduction is determined from the total value of the results. For example, if flg11 is 1, the determination value h1 = 2, if flg11 is 2, the determination value h1 = 1, if flg11 is 3, the determination value h1 = -1, and if flg11 is 4, the determination value h1 = -2. Similarly, if flg21 is 1, decision value h2 = 2, if flg21 is 2, decision value h2 = 1, if flg21 is 3, decision value h2 = -1, and if flg21 is 4, decision value h2 = -2. .
[0054]
Similarly, if flg31 is 1, decision value h3 = 2, if flg31 is 2, decision value h3 = 1, if flg31 is 3, decision value h3 = -1 and if flg31 is 4, decision value h3 = -2. . And the determination part 104 determines the presence or absence of squeezing from the total value of h1 + h2 + h3. For example, when the total value is 0 or more, it is determined that there is no squeezing, and when it is lower than 0, it is determined that there is squeezing.
In the present embodiment, the number of squeezing presence / absence determining units may be increased. Further, the digitization of the determination may be changed.
[0055]
According to the present embodiment, the result of the determination unit for the presence or absence of each squeezing can be digitized and comprehensively determined, so that the determination accuracy is improved.
[0056]
Next, a sixth embodiment will be described.
Appearance frequency calculated by the appearance frequency calculation unit 402 of the first squeezing presence / absence determination unit 101, dispersion value of the irradiation end point calculated by the second determination unit 705 of the second squeezing presence / absence determination unit 102, and third squeezing The total value of | x1−xa | and | x2−x1 | calculated by the third determination means 904 of the presence / absence determination unit 103 is used as an explanatory variable, and multiple regression analysis is performed using the presence / absence of squeezing as a target variable to create a line format To do. For example, the objective variable is 1 if there is a threshold, and 0 if there is no objective variable. If an unknown image is input, the explanatory variable is calculated to obtain the value of the line format. For example, if the value of the line format is 0.5 or more, there is a reduction. If it is less than 5 mm, there is no squeezing.
[0057]
Although a linear regression equation is used here, a neural network, an agent, or the like may be used.
Further, the squeezing presence / absence determining unit is not limited to three.
[0058]
According to the present embodiment, it is possible to statistically reflect the result of each of the squeezing presence / absence determination portions in the determination result, and there is an effect that the determination accuracy is further improved. In addition, when a neural network is used to create a function, it is possible to reflect a non-linear statistical distribution, which has the effect of increasing the determination accuracy.
[0059]
Next, the storage medium according to the present invention will be described.
When the system composed of the blocks shown in FIGS. 1, 4, 7, and 9 is constituted by a computer system including a memory such as a CPU and a ROM, the memory constitutes a storage medium according to the present invention. This storage medium stores a program for executing the processing procedure for controlling the operation described above with reference to the flowcharts of FIGS. 5, 6, 8, 10, and 11.
[0060]
As the storage medium, a semiconductor memory such as ROM or RAM, an optical disk, a magneto-optical disk, a magnetic medium, or the like may be used. These may be a CD-ROM, a floppy disk, a magnetic medium, a magnetic card, a nonvolatile memory card, or the like. It may be configured and used.
[0061]
Therefore, the storage medium is used in other systems and apparatuses other than the systems and apparatuses shown in the above drawings, and the system or computer reads out and executes the program code stored in the storage medium as described above. Functions equivalent to those in each embodiment can be realized, and equivalent effects can be obtained, and the object of the present invention can be achieved.
[0062]
Also, when the OS running on the computer performs part or all of the processing, or the program code read from the storage medium is an extension function board inserted in the computer or an extension connected to the computer Even when the CPU or the like provided in the extended function board or the extended function unit performs part or all of the processing based on the instruction of the program code after being written in the memory provided in the functional unit, While equivalent functions can be realized, equivalent effects can be obtained, and the object of the present invention can be achieved.
[0063]
【The invention's effect】
As described above, according to the present invention, if there is a certain determination result among the determination results, the determination result is adopted, so that the determination accuracy is improved. In addition, if there is no reliable judgment result among the judgment results, the final judgment is made according to many judgments among the judgment results for the presence or absence of the squeezing, so the accuracy is higher than when only one squeezing judgment criterion is used. Is effective.
[0068]
Further, according to another feature of the present invention, by using the appearance frequency of the density determined from the MAX value of the entire image as a determination criterion, there is an effect that a stable determination can be performed even when an imaging target is applied to the irradiation end. . In addition, there is an effect that the determination can be performed stably even when the radiation dose is small or when the imaging target covers the entire image edge without being affected by the intensity of the radiation dose.
[0069]
In addition, by using the variance of the coordinate values of a plurality of irradiation end points as a determination criterion, there is an effect that the presence / absence of irradiation squeezing can be well extracted based on that value. Further, by using the secondary difference value, it is possible to accurately determine a boundary point between an area directly irradiated with X-rays and an area not irradiated with X-rays even for an object with low X-ray transmittance. Therefore, even if a portion having a low X-ray transmittance, such as the abdomen, covers the edge of the image, it is possible to accurately extract the presence of irradiation.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a first embodiment of the present invention.
FIG. 2 is a configuration diagram showing an X-ray image of a hand imaged without squeezing irradiation;
FIG. 3 is a configuration diagram showing an X-ray image of a hand and an irradiation end A taken with irradiation squeezing.
FIG. 4 is a block diagram illustrating a configuration of a first squeezing presence / absence determining unit.
FIG. 5 is a flowchart showing a flow of processing of a first squeezing presence / absence determining unit.
FIG. 6 is a configuration diagram showing a determination area of a second squeezing presence / absence determination unit;
FIG. 7 is a block diagram showing a configuration of a second squeezing presence / absence determining unit.
FIG. 8 is a flowchart showing a flow of processing of a second squeezing presence / absence determining unit.
FIG. 9 is a block diagram showing a configuration of a third squeezing presence / absence determining unit.
FIG. 10 is a flowchart showing a flow of processing of a third squeezing presence / absence determining unit.
FIG. 11 is a flowchart illustrating a processing flow according to the first embodiment;
FIG. 12 is a flowchart illustrating a processing flow according to the second embodiment;
FIG. 13 is a flowchart illustrating a processing flow according to the third embodiment;
FIG. 14 is a flowchart illustrating a process flow according to the fourth embodiment;
[Explanation of symbols]
101 First squeezing presence / absence determination unit
102 Second squeezing presence / absence determination unit
103 Third squeezing presence / absence determination unit
104 judgment part
401 First characteristic value calculation means
402 First appearance frequency calculation means
403 first determination means
701 Coordinate instruction means
702 Characteristic value extraction means
703 Endpoint extraction means
704 Memory means
705 Second determination means
901 Secondary difference value calculation means
902 Left end point extraction means
903 Right end point extraction means
904 Third determination means

Claims (7)

放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段と、
上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり有りと判定した場合は絞り有りと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定手段と、
を備えることを特徴とする照射しぼり有無判定装置。
At least two squeezed presence / absence judging means each having different judgment criteria for the presence or absence of radiation squeezing with respect to the radiographic image;
Of the plurality of squeezing presence / absence determining means, when the first squeezing presence / absence determining means determines that there is a squeezing, it is determined that there is an aperture, and in other cases, the squeezing presence / absence different from the first squeezing presence / absence determining means Integrated determination means for determining the presence or absence of an aperture based on the determination result of the determination means;
An irradiation squeezing presence / absence judging device comprising:
放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段と、
上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり無しと判定した場合は絞り無しと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定手段と、
を備えることを特徴とする照射しぼり有無判定装置。
At least two squeezed presence / absence judging means each having different judgment criteria for the presence or absence of radiation squeezing with respect to the radiographic image;
Of the plurality of squeezing presence / absence determining means, when the first squeezing presence / absence determining means determines that there is no squeezing, it is determined that there is no squeezing, and in other cases, the squeezing presence / absence different from the first squeezing presence / absence determining means. Integrated determination means for determining the presence or absence of an aperture based on the determination result of the determination means;
An irradiation squeezing presence / absence judging device comprising:
上記各しぼり有無判定手段の上記判定基準は、画像全体の濃度のMAX値から決められる濃度の出現頻度、複数の照射端点の座標値の分散、2次差分値の少なくとも一つを用いることを特徴とする請求項1又は2に記載の照射しぼり有無判定装置。  The determination criterion of each of the squeezing presence / absence determining means uses at least one of a density appearance frequency determined from a MAX value of the density of the entire image, a variance of coordinate values of a plurality of irradiation end points, and a secondary difference value. The irradiation squeezing presence / absence judging device according to claim 1 or 2. 放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段によってしぼりの有無を判定するしぼり有無判定ステップと、
上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり有りと判定した場合は絞り有りと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定ステップと、
を備えることを特徴とする照射しぼり有無判定方法。
A squeezing presence / absence determination step of determining the presence / absence of squeezing by at least two squeezing / non-squeezing determination means different from each other in the determination criteria of the presence / absence of irradiation irradiation with respect to the radiographic image;
Of the plurality of squeezing presence / absence determining means, when the first squeezing presence / absence determining means determines that there is a squeezing, it is determined that there is an aperture, and in other cases, the squeezing presence / absence different from the first squeezing presence / absence determining means An integrated determination step of determining the presence or absence of an aperture based on the determination result of the determination means;
A method for determining the presence or absence of irradiation squeezing.
放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段によってしぼりの有無を判定するしぼり有無判定ステップと、
上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり無しと判定した場合は絞り無しと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定ステップと、
を備えることを特徴とする照射しぼり有無判定方法。
A squeezing presence / absence determination step of determining the presence / absence of squeezing by at least two squeezing / non-squeezing determination means different from each other in the determination criteria of the presence / absence of irradiation irradiation with respect to the radiographic image;
Of the plurality of squeezing presence / absence determining means, when the first squeezing presence / absence determining means determines that there is no squeezing, it is determined that there is no squeezing, and in other cases, the squeezing presence / absence different from the first squeezing presence / absence determining means. An integrated determination step of determining the presence or absence of an aperture based on the determination result of the determination means;
A method for determining the presence or absence of irradiation squeezing.
放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段によってしぼりの有無を判定するしぼり有無判定ステップと、
上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり有りと判定した場合は絞り有りと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定ステップと、
をコンピュータに実行させるためのプログラムを記憶したことを特徴とするコンピュータ読み取り可能な記憶媒体。
A squeezing presence / absence determination step of determining the presence / absence of squeezing by at least two squeezing / non-squeezing determination means different from each other in the determination criteria of the presence / absence of irradiation irradiation with respect to the radiographic image;
Of the plurality of squeezing presence / absence determining means, when the first squeezing presence / absence determining means determines that there is a squeezing, it is determined that there is an aperture, and in other cases, the squeezing presence / absence different from the first squeezing presence / absence determining means An integrated determination step of determining the presence or absence of an aperture based on the determination result of the determination means;
A computer-readable storage medium storing a program for causing a computer to execute the program.
放射線撮影画像に対して放射線照射しぼりの有無の判定基準がそれぞれ異なる少なくとも二つのしぼり有無判定手段によってしぼりの有無を判定するしぼり有無判定ステップと、
上記複数のしぼり有無判定手段のうち、第1のしぼり有無判定手段がしぼり無しと判定した場合は絞り無しと判定し、それ以外の場合には、上記第1のしぼり有無判定手段と異なるしぼり有無判定手段の判定結果に基づいて絞りの有無を判定する統合判定ステップと、
をコンピュータに実行させるためのプログラムを記憶したことを特徴とするコンピュータ読み取り可能な記憶媒体。
A squeezing presence / absence determination step of determining the presence / absence of squeezing by at least two squeezing / non-squeezing determination means different from each other in the determination criteria of the presence / absence of irradiation irradiation with respect to the radiographic image;
Of the plurality of squeezing presence / absence determining means, when the first squeezing presence / absence determining means determines that there is no squeezing, it is determined that there is no squeezing, and in other cases, the squeezing presence / absence different from the first squeezing presence / absence determining means. An integrated determination step of determining the presence or absence of an aperture based on the determination result of the determination means;
A computer-readable storage medium storing a program for causing a computer to execute the program.
JP23910298A 1998-08-25 1998-08-25 Irradiation squeezing presence / absence determination device, method, and computer-readable storage medium Expired - Fee Related JP4280334B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP23910298A JP4280334B2 (en) 1998-08-25 1998-08-25 Irradiation squeezing presence / absence determination device, method, and computer-readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP23910298A JP4280334B2 (en) 1998-08-25 1998-08-25 Irradiation squeezing presence / absence determination device, method, and computer-readable storage medium

Publications (2)

Publication Number Publication Date
JP2000060842A JP2000060842A (en) 2000-02-29
JP4280334B2 true JP4280334B2 (en) 2009-06-17

Family

ID=17039846

Family Applications (1)

Application Number Title Priority Date Filing Date
JP23910298A Expired - Fee Related JP4280334B2 (en) 1998-08-25 1998-08-25 Irradiation squeezing presence / absence determination device, method, and computer-readable storage medium

Country Status (1)

Country Link
JP (1) JP4280334B2 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4708712B2 (en) * 2004-02-04 2011-06-22 キヤノン株式会社 Image processing apparatus, control method therefor, and program
JP7370933B2 (en) 2020-06-05 2023-10-30 富士フイルム株式会社 Control device, radiation imaging system, control processing method, and control processing program
JP7316976B2 (en) * 2020-06-05 2023-07-28 富士フイルム株式会社 Image processing device, radiation imaging system, image processing method, and image processing program

Also Published As

Publication number Publication date
JP2000060842A (en) 2000-02-29

Similar Documents

Publication Publication Date Title
JP4999163B2 (en) Image processing method, apparatus, and program
JP2002504727A (en) Pulmonary nodule detection using edge gradient histogram
Piórkowski A statistical dominance algorithm for edge detection and segmentation of medical images
KR100432491B1 (en) Method of extracting fingerprint features using ridge direction model
JPH10500321A (en) Automated method and system for detecting lesions in medical computed tomography scans
KR100780957B1 (en) Apparatus and method for selecting image
JPH11149559A (en) Automatic human eye detecting method in digital picture
JP2005296605A (en) Method of segmenting a radiographic image into diagnostically relevant and diagnostically irrelevant regions
JP2009502232A (en) Detection of lung nodules on chest radiographs
US9014447B2 (en) System and method for detection of lesions in three-dimensional digital medical image
EP2500864B1 (en) Irradiation field recognition
CN113379739B (en) Ultrasonic image identification method, device, equipment and storage medium
Taheri et al. Enhanced breast cancer classification with automatic thresholding using SVM and Harris corner detection
JP4280334B2 (en) Irradiation squeezing presence / absence determination device, method, and computer-readable storage medium
KR101162605B1 (en) Texture feature extraction method in ct images
Abdelaziz et al. K-means algorithm with level set for brain tumor segmentation
Khudhur et al. Edge detection and features extraction for dental X-ray
Khalid et al. Fusion of fuzzy heuristic and particle swarm optimization as an edge detector
Dey et al. Chest X-ray analysis to detect mass tissue in lung
Taheri et al. Automated single and multi-breast tumor segmentation using improved watershed technique in 2D MRI images
Kohad et al. Diagnosis of lung cancer using support vector machine with ant colony optimization technique
JP2003079606A (en) Abnormal shadow-detecting system
KR101294255B1 (en) Apparatus and method for determining region of interest
JP3397652B2 (en) Image determining method, image determining apparatus, and storage medium
Gordon et al. An agglomerative segmentation framework for non-convex regions within uterine cervix images

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20050811

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20081030

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20081202

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20090202

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20090303

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20090316

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20120319

Year of fee payment: 3

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20130319

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20140319

Year of fee payment: 5

LAPS Cancellation because of no payment of annual fees