JPH06123B2 - Chest X-ray examination support device - Google Patents
Chest X-ray examination support deviceInfo
- Publication number
- JPH06123B2 JPH06123B2 JP60166265A JP16626585A JPH06123B2 JP H06123 B2 JPH06123 B2 JP H06123B2 JP 60166265 A JP60166265 A JP 60166265A JP 16626585 A JP16626585 A JP 16626585A JP H06123 B2 JPH06123 B2 JP H06123B2
- Authority
- JP
- Japan
- Prior art keywords
- boundary line
- diaphragm
- value
- abnormality
- image
- 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 - Lifetime
Links
- 210000004072 lung Anatomy 0.000 claims description 35
- 230000005856 abnormality Effects 0.000 claims description 26
- 238000005259 measurement Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 230000002159 abnormal effect Effects 0.000 description 8
- 238000000034 method Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 5
- 206010020880 Hypertrophy Diseases 0.000 description 3
- 210000000709 aorta Anatomy 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000011976 chest X-ray Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000002253 acid Substances 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Analysing Materials By The Use Of Radiation (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Description
【発明の詳細な説明】 ［産業上の利用分野］ 本発明は、Ｘ線画像情報に基づき自動的に胸部Ｘ線画像
（被検体）の異常の有無を調べ、Ｘ線検診を支援する胸
部Ｘ線検診支援装置に関する。DETAILED DESCRIPTION OF THE INVENTION [Industrial field of application] The present invention automatically checks for abnormalities in a chest X-ray image (subject) based on X-ray image information, and assists X-ray examination. The present invention relates to a line examination support device.
［従来の技術］ 学校，会社等の団体では、年一回程度のＸ線間接撮影に
よる胸部の検診が義務付けられており、それらのＸ線写
真は専門医によって一つ一つ読影され、異常の有無をチ
ェックされる。[Prior Art] Schools, companies, and other organizations are obliged to perform chest X-ray examinations about once a year, and these X-rays are read one by one by a specialist to determine whether there is any abnormality. Is checked.
このような作業は従来全て手作業で行われており、その
手助けをするものとして、ロール状のフィルムを自動的
に搬送し、次々に別の写真を拡大表示するビュアー等が
開発されているに過ぎない。Conventionally, all of this work is done manually, and as a means of helping this, viewers and the like have been developed that automatically convey roll-shaped film and enlarge and display different photographs one after another. Not too much.
［発明が解決しようとする問題点］ Ｘ線間接撮影は、検診の対象となっている者全てについ
て行われるため、これらのＸ線写真の数は膨大なものと
なり、医師が全てを読影するためには、多くの時間を要
する。例えば、学生数１万人の大学では、医師２名によ
って約２か月の期間を要すると言われている。[Problems to be Solved by the Invention] Since indirect X-ray photography is performed for all persons who are the targets of examination, the number of these X-ray photographs becomes enormous, and the doctor interprets all of them. Takes a lot of time. For example, a university with 10,000 students is said to require about two months by two doctors.
又、短かい間に高度な判定を行うことを繰り返すため、
長時間この作業を行うと精神的及び肉体的疲労が大き
く、注意力の低下から疾病を見逃す恐れがある。In addition, in order to repeat advanced judgment in a short time,
If this work is performed for a long time, mental and physical fatigue is great, and there is a risk of overlooking the illness due to a decrease in attention.
更に被検体の個人差による写真の出来上がりも大きくば
らつくことが多く、中には濃度が高くなり過ぎ肉眼では
読影が困難になる場合がある。In addition, the quality of the photograph often varies greatly depending on the individual difference of the subject, and in some cases the density becomes too high and interpretation may be difficult with the naked eye.
本発明は上記問題点に鑑みてなされたもので、その目的
は、Ｘ線写真検診における医師の読影作業を支援し、検
診の効率と正確さを向上させることにある。The present invention has been made in view of the above problems, and an object thereof is to support a doctor's image interpretation work in an X-ray examination and improve the efficiency and accuracy of the examination.
本発明の代表的なものの特徴は、以下のとおりである。 The features of the representative one of the present invention are as follows.
すなわち、Ｘ線画像情報を記憶する装置と、該装置に記
憶されたＸ線画像情報を順次読み出し、肺野領域と横隔
膜との境界線を抽出する装置と、抽出された前記肺野領
域と横隔膜との境界線の形状に関し、横隔膜の形がな
めらかな円弧状であるかどうか、右の横隔膜が左のも
のより高い位置にあるかどうかという、検診項目に相応
した所定の計測・演酸を行う装置と、該計測・演算を行
う装置により得られたデータについて、下記〜の判
定基準を適用し、その基準の少なくとも一つに合致する
場合に、被検体に異常があると判定する、正常／異常の
判定を行う装置と、該正常／異常の判定を行う装置によ
る判定結果を知らせる装置とからなることを特徴とする
ものである。That is, a device for storing X-ray image information, a device for sequentially reading the X-ray image information stored in the device, and extracting a boundary line between the lung field region and the diaphragm, and the extracted lung field region and diaphragm. Regarding the shape of the boundary line between and, perform the prescribed measurement and acid deduction corresponding to the examination items, whether the shape of the diaphragm is a smooth arc or whether the right diaphragm is higher than the left one. For the data obtained by the device and the device that performs the measurement / calculation, the following criteria (1) to (4) are applied, and if at least one of the criteria is met, it is determined that the subject has an abnormality. It is characterized in that it comprises an apparatus for making an abnormality determination and an apparatus for notifying the result of the determination made by the apparatus for making a normal / abnormal determination.
（判断基準） 該境界線の両端を結ぶ直線の傾きの値が基準範囲以外
の場合 該境界線の両端を結ぶ直線と実際の境界線とのずれの
量が基準値を越えた場合 該境界線を２次曲線で近似し、近似した２次曲線の係
数の値が基準範囲以外の場合 該境界線を２次曲線で近似し、近似した２次曲線と実
際の境界線とのずれの量が基準値を越えた場合 該境界線の両端の距離の値が基準範囲以外の場合 左横隔膜の境界線が右横隔膜の境界線の位置よりも低
い位置にない場合 〔作用〕 本発明のＸ線写真検診支援装置では、陰影判断ではな
く、部位の境界線に的を絞つた処理を行う。したがつ
て、本発明の装置は、高度な階調処理が不要であり、ま
た、基本的には２値化データ処理のみでよく、処理が簡
単であり、低コスト化にも資するものである。(Judgment Criteria) When the slope value of the straight line connecting both ends of the boundary line is outside the reference range When the amount of deviation between the straight line connecting both ends of the boundary line and the actual boundary line exceeds the reference value The boundary line Is approximated by a quadratic curve, and the coefficient value of the approximated quadratic curve is outside the reference range. The boundary line is approximated by a quadratic curve, and the amount of deviation between the approximated quadratic curve and the actual boundary line is When the value exceeds the reference value and when the value of the distance between both ends of the boundary line is outside the reference range When the boundary line of the left diaphragm is not lower than the position of the boundary line of the right diaphragm [Operation] X-ray photograph of the present invention The medical examination support device performs a process focusing on the boundary line of the region, not the shadow judgment. Therefore, the apparatus of the present invention does not require high-level gradation processing, and basically only requires binarized data processing, and the processing is simple and contributes to cost reduction. .
また、本装置を用いれば、医師は、特に、横隔膜の境界
線形状の判断が不要となり、その他の判断に集中できる
ことになり、診断効率の向上に資するものである。In addition, the use of this device makes it unnecessary for the doctor to judge the boundary line shape of the diaphragm, and allows the doctor to concentrate on other judgments, which contributes to improvement in diagnosis efficiency.
［実施例］ 以下、図面を用いて本発明の実施例を詳細に説明する。Embodiments Embodiments of the present invention will be described in detail below with reference to the drawings.
第１図は本発明の一実施例の要部構成を示すブロック図
で、この図は、Ｘ線写真を読取る画像入力装置も備えた
実施例を示している。図において、１はＸ線写真を読取
る画像入力装置で、例えばポリゴンミラー等を用いて光
スポットを胸部Ｘ線写真上で掃引して、その透過光をフ
ォトセンサに導き、得られた電気信号を順次Ａ／Ｄ変換
（アナログ／ディジタル変換）し、ディジタル画像デー
タとして出力するものである。この画像入力装置として
は、光ビームを偏向する構成ではなく、ＣＣＤ等の団体
撮像素子や撮像管を用いて電子的に走査する構成のもの
を使用してもよい。FIG. 1 is a block diagram showing a main configuration of an embodiment of the present invention, and this figure shows an embodiment including an image input device for reading an X-ray photograph. In the figure, 1 is an image input device for reading an X-ray photograph, for example, a light spot is swept on a chest X-ray photograph using a polygon mirror or the like, the transmitted light is guided to a photosensor, and the obtained electric signal is A / D conversion (analog / digital conversion) is sequentially performed, and output as digital image data. As the image input device, a device for electronically scanning using a collective image pickup device such as CCD or an image pickup tube may be used instead of a device for deflecting a light beam.
２は画像入力装置１から送られてきた画像データ等を記
憶する画像記憶装置で、処理の高速性から通常はＲＡＭ
等の半導体メモリが用いられる。しかし、磁気ディス
ク，フロッピーディスク，光ディスク等のディスクメモ
リ、或いは磁気テープ，磁気バブル等を用いることも可
能である。An image storage device 2 stores image data and the like sent from the image input device 1, and is usually a RAM because of high processing speed.
Etc. semiconductor memory is used. However, it is also possible to use a disk memory such as a magnetic disk, a floppy disk, an optical disk, a magnetic tape, a magnetic bubble or the like.
３は画像記憶装置２より画像データを順次読出し、肺野
に相当する部分と周辺の部分との境界線（輪郭線）を示
すデータを求める画像処理装置である。境界線の抽出方
法には、１次又は２次微分オペレータを入力画像に作用
させその後に２値化を行って境界を抽出する方法がある
が、本実施例では、後述の如く、まず入力画像データを
２値化し、３×３や２×２等の小画素領域からなるマス
クを用い、このマスクを移動しながら境界線を求める方
法を採用している。この２値化の闘値としては、例え
ば、各行の画像データの平均値をその行の闘値として用
いる。この闘値を用いれば、実質的に濃度変換を行つた
ことになり、濃度ヒストグラム等に基づき入力画像デー
タを濃度変換し、固定闘値を用いて２値化する場合に比
べて、処理が楽である。又、この画像処理装置３にて、
ノイズの除去が行われる。Reference numeral 3 denotes an image processing device which sequentially reads image data from the image storage device 2 and obtains data indicating a boundary line (contour line) between a portion corresponding to the lung field and a peripheral portion. As a method of extracting the boundary line, there is a method of applying a first-order or second-order differential operator to the input image and then performing binarization to extract the boundary. In this embodiment, as described later, first, the input image is first extracted. A method of binarizing the data and using a mask made up of small pixel areas such as 3 × 3 and 2 × 2 and determining the boundary line while moving the mask is adopted. As the threshold value for this binarization, for example, the average value of the image data of each row is used as the threshold value for that row. If this threshold value is used, it means that the density conversion is substantially performed, and the processing is easier than the case where the input image data is density converted based on the density histogram and binarized using the fixed threshold value. Is. In addition, in this image processing device 3,
Noise is removed.
４は抽出された境界線の形状に関し検診項目に相応した
計測・演算を行う画像計測装置で、画像処理装置３にて
求められ画像記憶装置２に格納された境界線データの中
から、必要なデータを読出して、後述の計測・演算を行
うもの、５は該画像計測装置４の出力から検診項目に関
する判定を行う判定装置である。判定装置５にて画像計
測装置の出力が正常の値を越えていると判定した場合に
は、異常であることが医師にわかるように表示装置６に
表示される構成になっている。Reference numeral 4 denotes an image measuring device that performs measurement / calculation on the shape of the extracted boundary line according to the examination item, and is necessary from the boundary line data obtained by the image processing device 3 and stored in the image storage device 2. Reference numeral 5 denotes a determination device for reading out data and performing later-described measurement / calculation. The determination device 5 determines the inspection item from the output of the image measurement device 4. When the determination device 5 determines that the output of the image measurement device exceeds a normal value, the display device 6 is configured to display the abnormality so that the doctor can know.
次に、上記実施例の動作を第２図乃至第９図を用いて具
体的に説明する。Next, the operation of the above embodiment will be specifically described with reference to FIGS.
（Ｘ線写真の入力） Ｘ線写真は、画像入力装置１によって約２００μｍのサ
ンプリングピッチで読取られ、濃度範囲０〜３を２５６
階調に量子化される。このときＸ線写真は正立して入力
され、第２図に示すように、写真の左上が（１，１）、
右下が（Ｋ，Ｌ）としたＫ行Ｌ列の行列として表現さ
れ、画像記憶装置２に格納される。尚、サンプリングピ
ッチは、２００μｍに固定されたものではなく、場合に
応じて２５μｍから１０００μｍ程度まで変化させるこ
とができる。又、読取り濃度範囲や、量子化レベルも変
化させてもよい。(Input of X-ray photograph) The X-ray photograph is read by the image input device 1 at a sampling pitch of about 200 μm, and the density range of 0 to 3 is 256.
Quantized into gradation. At this time, the X-ray photograph is input upright, and as shown in FIG. 2, the upper left corner of the photograph is (1, 1),
The lower right part is represented as a matrix of K rows and L columns with (K, L) stored in the image storage device 2. The sampling pitch is not fixed to 200 μm, but can be changed from 25 μm to about 1000 μm depending on the case. Also, the read density range and the quantization level may be changed.
（境界線の抽出） 肺野領域の境界の抽出は、画像処理装置３によって、２
値化、境界線追跡、の２段階によって行われる。(Extraction of Boundary Line) The extraction of the boundary of the lung field region is performed by the image processing device 3 in 2
It is carried out in two steps: quantification and boundary tracking.
２値化は、適当な闘値を用いその値を越えた画素を１、
その値以下の画素を０とする処理により、肺野領域とそ
の周辺とを明確に分離するために行う。このようにして
２値画像に変換された画像データについて、１と０との
境界を追跡することにより、肺野領域の境界線を抽出す
る。Binarization uses an appropriate threshold value to set the number of pixels exceeding that value to 1,
A process of setting pixels equal to or less than that value to 0 is performed to clearly separate the lung field region and its periphery. The boundary line of the lung field region is extracted by tracing the boundary between 1 and 0 in the image data thus converted into the binary image.
抽出された境界線データは、第３図に示すように、後の
計測に都合のよいように左右それぞれの肺野について、
（Ａ）肺野外側の境界線ＲＯＢ及びＬＯＢ、（Ｂ）肺野
内側の境界線ＲＩＢ及びＬＩＢ、（Ｃ）横隔膜の境界線
ＲＤＢ及びＬＤＢの左右それぞれ３つのデータとして求
める。これらの境界線データ、（Ａ），（Ｂ）は各行に
おける境界線の存在する列の値の配列として、（Ｃ）は
各列における境界線の存在する行の値の配列として与え
られる。尚、ＲＯＢ，ＲＩＢ，ＲＤＢの先頭文字「Ｒ」
は右肺を意味し、ＬＯＢ，ＬＩＢ，ＬＤＢの先頭文字
「Ｌ」は左肺を意味する。The extracted boundary line data is, as shown in FIG. 3, for each of the left and right lung fields for convenience of later measurement.
Three pieces of data are respectively obtained on the left and right sides of (A) outer boundary lines ROB and LOB, (B) inner lung field boundaries RIB and LIB, and (C) diaphragm boundary lines RDB and LDB. These boundary line data (A) and (B) are given as an array of the values of the column where the boundary line exists in each row, and (C) is given as an array of the values of the row where the boundary line exists in each column. The first character "R" of ROB, RIB, RDB
Means the right lung, and the first letter “L” of LOB, LIB, LDB means the left lung.
（異常の判定方法） 入力されたＸ線画像に疾病等がの異常があるかどうかを
判定するための項目と、判定処理について述べる。(Abnormality Judging Method) Items for judging whether or not there is an abnormality such as a disease in the input X-ray image and the judgment processing will be described.
判定項目は次の６点である。The judgment items are the following 6 points.
（Ｉ）左右の肺が対称であるかどうか （II）横隔膜の形がなめらかな円弧状であるかどうか （III）右の横隔が左のものより高い位置にあるかどう
か （IV）脊椎が真直ぐかどうか （Ｖ）心陰影に肥大が見られないかどうか （VI）大動脈に突出が見られないかどうか これらの判定項目についての画像計測装置４によって求
められた計測値が、判定装置５によって、別に定めた基
準値と比較され、異常の有無が判定される。(I) Whether the left and right lungs are symmetrical (II) Whether the shape of the diaphragm is a smooth arc (III) Whether the right diaphragm is higher than the left one (IV) The spine Whether it is straight (V) Whether hypertrophy is not seen in the heart shadow (VI) Whether protrusion is not seen in the aorta The measurement values obtained by the image measuring device 4 for these determination items are determined by the determining device 5. , And the presence or absence of abnormality is determined by comparison with a separately set reference value.
この基準値は、同様の計測を正常例について多数計測
し、その結果の値の平均値及び標準偏差を用いて決定す
ればよい。This reference value may be determined by measuring a large number of similar measurements for normal cases and using the average value and standard deviation of the results.
次に、各項目を列挙し、その判定処理について述べる。Next, each item is listed and the determination process is described.
（Ｉ）左右の肺が対称であるかどうか これは、右肺と左肺との幅の差の二乗平均を求め、それ
が基準値以下かどうかによって判定を行うものである。
幅の差の二乗の二乗平均をＳＦとすると、 を求めればよい。ここで、第４図に示すようにＮ（≠
ｎ）は右肺の上端部Ｉ０から下端部Ｉｎまでの画素数で
あり、ＲＬＷ（Ｉ）及びＬＬＷ（Ｉ）は、行番号Ｉにお
ける右肺の幅と左肺の幅を示すものである。(I) Whether the left and right lungs are symmetrical In this, the root mean square of the difference between the widths of the right lung and the left lung is obtained, and the determination is made based on whether or not it is below a reference value.
If SF is the root mean square of the width difference, You should ask. Here, as shown in FIG. 4, N (≠
n) is the number of pixels from the upper end I 0 to the lower end In of the right lung, and RLW (I) and LLW (I) indicate the width of the right lung and the width of the left lung at line number I. .
このＳＦが、基準値よりも大きければ左右の肺の対称性
が悪いと判断し、何らかの異常があると判定する。If this SF is larger than the reference value, it is determined that the left and right lungs have poor symmetry, and it is determined that there is some abnormality.
それぞれの肺の幅ＲＬＷ，ＬＬＷは、画像処理装置３に
よって求められた肺野内側の境界線と肺野外側の境界線
との差の絶対値を用いればよい。As the widths RLW and LLW of the respective lungs, the absolute value of the difference between the boundary line inside the lung field and the boundary line outside the lung field determined by the image processing device 3 may be used.
即ち、 ＲＬＷ（Ｉ）＝ＲＩＢ（Ｉ）−ＲＯＢ（Ｉ） ＬＬＷ（Ｉ）＝ＬＯＢ（Ｉ）−ＬＩＢ（Ｉ） で求められる。That is, RLW (I) = RIB (I) -ROB (I) LLW (I) = LOB (I) -LIB (I).
又、境界線同士の差を用いる他に、境界線を抽出するた
めの２値画像を用い左右それぞれの肺野領域を含む矩形
領域においての行方向の投影（Ｐrojection）を用いて
もよい。In addition to using the difference between the boundary lines, a binary image for extracting the boundary lines may be used and projection in the row direction in a rectangular area including the left and right lung field areas may be used.
（II）横隔膜の形がなめらかな円弧状であるかどうか 横隔膜の異常の判定には、なめらかな円弧状であるかど
うか、適当な傾きがあるかどうか等の観点より、左右そ
れぞれの横隔膜の境界線について、５項目の計測値を求
め、それらが基準範囲内にあるかどうかで行う。(II) Whether the shape of the diaphragm is a smooth arc shape To determine whether the diaphragm is abnormal, whether it is a smooth arc shape or whether there is an appropriate inclination, etc. For the line, the measurement values of 5 items are obtained, and it is determined whether or not they are within the reference range.
５項目の計測値とは、境界線の両端を結ぶ直線につい
て、 その直線の傾き その直線の実際の境界線とのずれの総和境界線を２次
曲線で近似し、 近似した２次曲線の係数の値 近似した２次曲線と実際の境界線とのずれの総和 及び、 境界線の両端の距離 である。The measured values of the five items are the straight line connecting both ends of the boundary line, the slope of the straight line, the total deviation of the straight line from the actual boundary line, approximated by a quadratic curve, and the coefficient of the approximated quadratic curve The value is the sum of the deviation between the approximated quadratic curve and the actual boundary line, and the distance between both ends of the boundary line.
以下、それぞれの計測値の求め方について、第５図を用
いて詳しく述べる。左右それぞれの横隔膜について同様
の計測を行うので、ここでは右の横隔膜についてだけ説
明を行う。Hereinafter, how to obtain each measured value will be described in detail with reference to FIG. Since the same measurement is performed for each of the left and right diaphragms, only the right diaphragm will be described here.
境界線の両端を結ぶ直線の傾き 横隔膜境界線ＲＤＢの両端をＲ１，Ｐ２とし、画像行列
上の位置がそれぞれ（Ｉ１，Ｊ１）、（Ｉ２，Ｊ２）で
あるとすると、両端を結ぶ直線Ｆ（Ｊ）は、 Ｆ（Ｊ）＝ａ・Ｊ＋ｂ で表わされ、係数ａは、 ａ＝（Ｉ２−Ｉ１）／（Ｊ２−Ｉ１） となる。Slope of a straight line connecting both ends of the boundary line If both ends of the diaphragm boundary line RDB are R 1 and P 2, and positions on the image matrix are (I 1 , J 1 ), (I 2 , J 2 ), respectively, The straight line F (J) connecting both ends is expressed by F (J) = a · J + b, and the coefficient a is a = (I 2 −I 1 ) / (J 2 −I 1 ).
ここで、この係数ａの値が基準範囲以外の場合に、異常
と判定する。Here, if the value of the coefficient a is outside the reference range, it is determined to be abnormal.
境界線の両端を結ぶ直線と実際の境界線とのずれの総
和 で求めた直線Ｆ（Ｊ）を用い、次の式により、横隔膜
の円弧の曲がり具合を示す係数ＤＦ１を求める。Using the straight line F (J) obtained by the sum of the deviation between the straight line connecting both ends of the boundary line and the actual boundary line, the coefficient DF1 indicating the degree of curvature of the diaphragm arc is calculated by the following formula.
このＤＦ１の値が、基準値を越えた場合に、異常と判定
する。 When the value of DF1 exceeds the reference value, it is determined to be abnormal.
境界線を近似した２次曲線の係数の値 境界線ＲＤＢを２次曲線で近似し、その曲線Ｇ（Ｊ）の
式を Ｇ（Ｊ）＝ｃ・Ｊ２＋ｄ・Ｊ＋ｅ とする。The value of the coefficient of the quadratic curve that approximates the boundary line The boundary line RDB is approximated by a quadratic curve, and the equation of the curve G (J) is G (J) = c · J 2 + d · J + e.
ここで、係数ｃ，ｄの値が基準範囲以外の場合に、異常
と判定する。Here, when the values of the coefficients c and d are out of the reference range, it is determined as abnormal.
境界線を近似した２次曲線と実際の境界線とのずれの
総和 で求めた２次曲線Ｇ（Ｊ）を用い、実際の境界線ＲＤ
Ｂとのずれの総和ＤＦ２を次式により求める。The actual boundary line RD is calculated by using the quadratic curve G (J) obtained by the sum of the deviations between the quadratic curve approximating the boundary line and the actual boundary line.
The sum DF2 of the deviation from B is calculated by the following formula.
このずれの量（二乗）の総和ＤＦ２の値が、基準値を越
えた場合に、異常と判定する。 When the value of the total sum DF2 of the amounts (squares) of this deviation exceeds the reference value, it is determined to be abnormal.
境界線の両端の距離 境界線の両端の距離ＤＦ３は、両端の点Ｐ１，Ｐ２の画
像行列上の位置（Ｉ１，Ｊ１）、（Ｉ２，Ｊ２）より、
次式により求められる。The distance DF3 at both ends of the boundary line The distance DF3 at both ends of the boundary line is calculated from the positions (I 1 , J 1 ) and (I 2 , J 2 ) of the points P 1 , P 2 at both ends on the image matrix,
It is calculated by the following formula.
この境界線の両端の距離ＤＦ３の値が基準範囲以外の場
合に、異常と判定する。 When the value of the distance DF3 at both ends of this boundary line is outside the reference range, it is determined to be abnormal.
（III）右の横隔膜が左のものより高い位置にあるかど
うか 左右それぞれの横隔膜境界線ＲＤＢ及びＬＤＢは、画像
行列上の各列における境界線の存在する行の値を示して
おり、それぞれ値の最も小さいところが横隔膜の一番高
い位置である。従つて、第６図に示すように、境界線デ
ータＲＤＢ，ＬＤＢのそれぞれの最小値を求めそれらを
比較し、ＲＤＢの最小値がＬＤＢのそれより大きい場合
に、異常があると判定すればよい。(III) Whether the right diaphragm is higher than the left diaphragm left and right diaphragm boundary lines RDB and LDB indicate the values of the row in which the boundary line exists in each column on the image matrix. The smallest point is the highest position in the diaphragm. Therefore, as shown in FIG. 6, the minimum values of the boundary line data RDB and LDB are obtained and compared, and when the minimum value of RDB is larger than that of LDB, it may be determined that there is an abnormality. .
横隔膜に不規則な形状がある場合には、単なる最小値で
は不確実になる可能性があるが、このようなことを避け
るためには、実際の境界線データではなく、（II）で求
めた２次近似曲線を用いるのがよい。又、それぞれの境
界線データの平均値を求めその値を比較することによっ
て判定をしてもよい。If the diaphragm has an irregular shape, the mere minimum value may be uncertain, but in order to avoid such a thing, it was calculated using (II) instead of the actual boundary line data. It is better to use a quadratic approximation curve. Alternatively, the determination may be made by obtaining an average value of the respective boundary line data and comparing the average values.
（IV）脊椎が真直ぐかどうか 左右両肺野内側境界線の存在する列の左右各点の間の中
点を各行についてそれぞれ求め、それらの中点を結んだ
曲線Ｆ（Ｉ）を求める。ここで、Ｆ（Ｉ）は、第７図に
示すようにＲＩＢ及びＬＩＢから、次式により求められ
る。Ｉは各行の番号である。(IV) Whether or not the spine is straight The midpoint between the left and right points of the column in which the left and right medial borders of the lungs are present is determined for each row, and the curve F (I) connecting these midpoints is determined. Here, F (I) is obtained from RIB and LIB as shown in FIG. I is the number of each line.
Ｆ（Ｉ）＝｛ＬＩＢ（Ｉ）＋ＲＩＢ（Ｉ）｝／２ このＦ（Ｉ）について、隣接する行毎の差分を求め、肺
野の上半分の部分における差分の平均ＶＦを求める。Ｖ
Ｆは次式により求められる。F (I) = {LIB (I) + RIB (I)} / 2 With respect to this F (I), the difference between adjacent rows is calculated, and the average VF of the differences in the upper half of the lung field is calculated. V
F is calculated by the following equation.
このＶＦの値が基準値の範囲を越えた場合に、異常があ
ると判定する。 When the value of this VF exceeds the range of the reference value, it is determined that there is an abnormality.
（Ｖ）心陰影に肥大が見られないかどうか 第８図の如く、左右各肺の内側の境界線ＲＩＢ，ＬＩＢ
と、肺野の中央の行及び内側境界線の下端の行で囲まれ
る部分の面積が基準範囲以外の場合に、異常があると判
定する。(V) Whether hypertrophy is not seen in the heart shadow. As shown in Fig. 8, the inner boundary lines RIB and LIB of the left and right lungs.
If the area of the part surrounded by the central line of the lung field and the lower line of the inner boundary line is outside the reference range, it is determined that there is an abnormality.
肺野の中央の行をＩｍ、境界線の下端の行をＩｎとする
と面積ＨＦは、 で求められる。If the central line of the lung field is Im and the lower line of the boundary line is In, the area HF is Required by.
このＨＦの値が基準値の範囲を越えた場合に、異常があ
ると判定する。When the HF value exceeds the reference value range, it is determined that there is an abnormality.
（VI）大動脈に突出が見られないかどうか左肺の内側の
境界線ＬＩＢに注目し、その境界線をいくつかの小区間
に分割し、境界線を近似する垂直な直線とのずれが基準
値以上の小区間がある場合に、被検体に異常があると判
定する。判定に用いるＬＩＢの区間は、上端から肺野の
中央までである。(VI) Pay attention to the inner boundary line LIB of the left lung to see if the aorta has no protrusion, divide the boundary line into some small sections, and use the deviation from a vertical straight line that approximates the boundary line as a reference. When there is a small section equal to or larger than the value, it is determined that the subject has an abnormality. The LIB section used for the determination is from the upper end to the center of the lung field.
ＬＩＢの上端の行Ｉ０、肺野の中央の行をＩｎとする
と、境界線を近似する垂直な直線の列の値Ｍは、 で求められる。ここで、Ｎは肺野の上端Ｉ０から中央Ｉ
ｎまでの行数である。更に、この区間をｎ個の小区間に
分解しそれぞれの小区間のＬＩＢとＭとの差の総和を求
める。小区間ｎの総和ＭＦｍは、 で求められる。Assuming that the uppermost row I 0 of the LIB and the central row of the lung field are In, the value M of the vertical straight line column that approximates the boundary line is Required by. Here, N is from the upper end I 0 of the lung field to the central I
The number of rows up to n. Further, this section is decomposed into n subsections, and the total sum of the differences between LIB and M of each subsection is obtained. The sum MFm of the small sections n is Required by.
全ての小区間ｍについてＭＦｍを求め、これらの何れか
が基準値を越えた場合に、異常があると判定する。MFm is calculated for all the small sections m, and if any of these exceeds a reference value, it is determined that there is an abnormality.
（判定結果の表示） 以上のようにして求めた各項目についての判定結果は、
この支援装置を用いている医師等にわかる形で表示され
る。ここでは、操作を指示するためのＣＲＴ端末に、異
常があつた場合に、その写真の番号、被検者のデータ及
び異常のあつた項目と計測した値とを表示する。ここ
で、表示の形式としては、印字式の端末を用いてもよい
し、表示項目を変更しても構わない。又、計測の対象と
なつた画像データを画像表示端末に表示し、異常と判定
された部分に色を付けた輝度を増す等の表示を行うこと
も可能である。更に、視覚的な表示だけでなく、異常の
際に警告の音を出すことも等も考えられる。又、Ｘ線写
真フィルムを自動的に搬送する機構を持つ装置では、異
常の見られたフィルムのみを正常のフィルムとは別の搬
出口から排出することにより異常を知らせてもよい。(Display of judgment result) The judgment result for each item obtained as described above is
It is displayed in a form understandable by a doctor or the like using this support device. Here, when there is an abnormality in the CRT terminal for instructing the operation, the number of the photograph, the data of the subject, the item indicating the abnormality, and the measured value are displayed. Here, as a display format, a print-type terminal may be used, or display items may be changed. It is also possible to display the image data that is the object of measurement on the image display terminal, and display such that the brightness that is colored in the area determined to be abnormal is increased. Further, not only a visual display but also a sound of a warning when an abnormality occurs may be considered. Further, in an apparatus having a mechanism for automatically transporting an X-ray photographic film, it is possible to notify the abnormality by ejecting only the film in which the abnormality is found from a carry-out port different from the normal film.
尚、上記説明ではＸ線写真を読取つて判定を行う場合を
述べたが、Ｘ線ＴＶ等のように撮影時に直接電気信号に
変換される装置を用いる場合には、この信号を直線Ａ／
Ｄ変換して画像記憶装置２に格納してもよい。又、Ｘ線
写真（Ｘ線透過画像）に限らず、ＣＴ等の断層写真や、
ＭＲＩ等の他のモダリティの画像を用いることも可能で
ある。In the above description, the case where the X-ray photograph is read to make the determination has been described. However, when using a device such as an X-ray TV which is directly converted into an electric signal at the time of photographing, this signal is converted into a straight line A /
It may be D-converted and stored in the image storage device 2. Not only X-ray photographs (X-ray transmission images), but also tomographic photographs such as CT,
Images of other modalities such as MRI can also be used.
［発明の効果］ 以上説明したように、本発明によれば、Ｘ線写真画像上
に異常があるかどうかが、医師が読影する前に表示され
る。従つて、異常の疑いのある写真についてはその部位
について細かく観察し、疑いのない写真については確認
のみを行うということができる。従つて、従来は全ての
Ｘ線写真を１枚１枚丁寧に観察することにより行つてい
たＸ線写真検診の効率を向上させることができる。[Effect of the Invention] As described above, according to the present invention, whether or not there is an abnormality on the X-ray image is displayed before the doctor interprets the image. Therefore, it can be said that the site of a photograph suspected of abnormality is observed in detail and only the confirmation is conducted for a photograph without any doubt. Therefore, it is possible to improve the efficiency of X-ray examination, which has been conventionally performed by carefully observing all X-rays one by one.
又、被検体や撮影の条件による写真の仕上がり濃度のば
らつきも、画像処理により一定の条件での計測が可能に
なるため、肉眼では読影が困難な写真であっても異常の
有無を判定でき、疾病の見落しを減少させることができ
る。Also, variations in the finished density of the photograph due to the subject and photographing conditions can be measured under a certain condition by image processing, so it is possible to determine the presence or absence of abnormality even for photographs that are difficult to interpret with the naked eye. Disease oversight can be reduced.
第１図は本発明の一実施例を示すブロック図、第２図は
画像データの行列による表現の説明図、第３図は肺野と
その周辺との境界線の説明図、第４図は左右の肺が対称
であるかどうかを判定するための説明図、第５図は横隔
膜の形がなめらかな円弧状であるかどうかを判定するた
めの説明図、第６図は右の横隔膜が左のものより高い位
置にあるかどうかを判定するための説明図、第７図は脊
椎が真直ぐかどうかを判定するための説明図、第８図は
心陰影に肥大が見られないかどうかを判定するための説
明図、第９図は大動脈に突出が見られないかどうかを判
定するための説明図である。 １…画像入力装置 ２…画像記憶装置 ３…画像処理装置 ４…画像計測装置 ５…判定装置 ６…表示装置FIG. 1 is a block diagram showing an embodiment of the present invention, FIG. 2 is an explanatory diagram of a matrix representation of image data, FIG. 3 is an explanatory diagram of a boundary line between a lung field and its periphery, and FIG. FIG. 5 is an explanatory diagram for determining whether the left and right lungs are symmetrical, FIG. 5 is an explanatory diagram for determining whether the shape of the diaphragm is a smooth arc, and FIG. 6 is a right diaphragm for the left. Fig. 7 is an explanatory diagram for determining whether it is in a higher position than that of Fig. 7, Fig. 7 is an explanatory diagram for determining whether the spine is straight, and Fig. 8 is determined whether there is no hypertrophy in the cardiac shadow FIG. 9 is an explanatory diagram for doing so, and FIG. 9 is an explanatory diagram for determining whether or not protrusion is seen in the aorta. DESCRIPTION OF SYMBOLS 1 ... Image input device 2 ... Image storage device 3 ... Image processing device 4 ... Image measuring device 5 ... Judgment device 6 ... Display device
Claims (1)
領域と横隔膜との境界線を抽出する装置と、 抽出された前記肺野領域と横隔膜との境界線の形状に関
し、横隔膜の形がなめらかな円弧状であるかどうか、
右の横隔膜が左のものより高い位置にあるかどうかと
いう、検診項目に相応した所定の計測・演算を行う装置
と、 該計測・演算を行う装置により得られたデータについ
て、下記の〜の判定基準を適用し、その基準の少な
くとも一つに合致する場合に、被検体に異常があると判
定する、正常／異常の判定を行う装置と、 該正常／異常の判定を行う装置による判定結果を知らせ
る装置とからなる、胸部Ｘ線検診支援装置。 （判断基準） 該境界線の両端を結ぶ直線の傾きの値が基準範囲以外
の場合 該境界線の両端を結ぶ直線と実際の境界線とのずれの
量が基準値を越えた場合 該境界線を２次曲線で近似し、近似した２次曲線の係
数の値が基準範囲以外の場合 該境界線を２次曲線で近似し、近似した２次曲線と実
際の境界線とのずれの量が基準値を越えた場合 該境界線の両端の距離の値が基準範囲以外の場合 左横隔膜の境界線が右横隔膜の境界線の位置よりも低
い位置にない場合1. A device for storing X-ray image information, a device for sequentially reading out the X-ray image information stored in the device to extract a boundary line between a lung field region and a diaphragm, and the extracted lung field. Regarding the shape of the boundary line between the region and the diaphragm, whether the shape of the diaphragm is a smooth arc shape,
Regarding the device that performs a predetermined measurement / calculation corresponding to the examination item and whether the right diaphragm is higher than that on the left and the data obtained by the device that performs the measurement / calculation, When a criterion is applied and at least one of the criteria is met, a device for determining whether the subject has an abnormality, a device for determining normality / abnormality, and a determination result by the device for determining normality / abnormality are displayed. Chest X-ray examination support device consisting of a notification device. (Judgment Criteria) When the slope value of the straight line connecting both ends of the boundary line is outside the reference range When the amount of deviation between the straight line connecting both ends of the boundary line and the actual boundary line exceeds the reference value The boundary line Is approximated by a quadratic curve, and the coefficient value of the approximated quadratic curve is outside the reference range. The boundary line is approximated by a quadratic curve, and the amount of deviation between the approximated quadratic curve and the actual boundary line is When it exceeds the reference value When the value of the distance between both ends of the boundary line is outside the reference range When the boundary line of the left diaphragm is not lower than the position of the boundary line of the right diaphragm
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP60166265A JPH06123B2 (en) | 1985-07-26 | 1985-07-26 | Chest X-ray examination support device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP60166265A JPH06123B2 (en) | 1985-07-26 | 1985-07-26 | Chest X-ray examination support device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPS6226047A JPS6226047A (en) | 1987-02-04 |
| JPH06123B2 true JPH06123B2 (en) | 1994-01-05 |
Family
ID=15828175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP60166265A Expired - Lifetime JPH06123B2 (en) | 1985-07-26 | 1985-07-26 | Chest X-ray examination support device |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH06123B2 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07100061B2 (en) * | 1987-03-30 | 1995-11-01 | コニカ株式会社 | Image measurement method to determine spinal curvature |
| US5578137A (en) * | 1993-08-31 | 1996-11-26 | E. I. Du Pont De Nemours And Company | Azeotropic or azeotrope-like compositions including 1,1,1,2,3,4,4,5,5,5-decafluoropentane |
| JP4554921B2 (en) * | 2003-12-25 | 2010-09-29 | 富士フイルム株式会社 | Method of operating abnormal shadow detection device, abnormal shadow detection device, and program |
| JP5406499B2 (en) * | 2008-10-01 | 2014-02-05 | インフォコム株式会社 | Chest X-ray image conversion method, apparatus, system, computer program, and medium |
| JP7456928B2 (en) * | 2018-05-16 | 2024-03-27 | パナソニックホールディングス株式会社 | Abnormal display control method of chest X-ray image, abnormal display control program, abnormal display control device, and server device |
-
1985
- 1985-07-26 JP JP60166265A patent/JPH06123B2/en not_active Expired - Lifetime
Non-Patent Citations (1)
| Title |
|---|
| 尾上守夫「医用画像処理」（１９８２−２−２５）朝倉書店Ｐ．１２１−１３３ |
Also Published As
| Publication number | Publication date |
|---|---|
| JPS6226047A (en) | 1987-02-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7885438B2 (en) | Methods and apparatuses for analyzing images | |
| Forsyth et al. | Assessment of an automated cephalometric analysis system | |
| JP3400008B2 (en) | An automated method and system for selecting a region of interest and detecting a septum in a digital chest radiograph | |
| JP4604451B2 (en) | Medical image processing apparatus and malignancy determination method | |
| JP2778707B2 (en) | Tomographic image diagnostic equipment | |
| Nakamori et al. | Image feature analysis and computer‐aided diagnosis in digital radiography: Automated analysis of sizes of heart and lung in chest images | |
| JPH01125675A (en) | Method and device for automatic analysis of digital x-ray picture | |
| JPH08335271A (en) | Image processing method of image diagnosis support apparatus | |
| CN109003269A (en) | A kind of mark extracting method for the medical image lesion that can improve doctor's efficiency | |
| CN116739989B (en) | Method, device and equipment for collecting and analyzing pressure damage image | |
| US9763636B2 (en) | Method and system for spine position detection | |
| KR101162599B1 (en) | An automatic detection method of Cardiac Cardiomegaly through chest radiograph analyses and the recording medium thereof | |
| CN118446978B (en) | Method and device for evaluating nasal septum deviation based on image recognition | |
| JP2005028037A (en) | Medical image processing device and medical image processing method | |
| JPH06123B2 (en) | Chest X-ray examination support device | |
| CN113269747A (en) | Pathological picture liver cancer diffusion detection method and system based on deep learning | |
| EP0702321A1 (en) | Method and apparatus for classifying picture elements in radiation images | |
| CN119887630A (en) | Tooth root angle three-dimensional intelligent measurement method based on oral cavity CBCT image | |
| JP3945622B2 (en) | Image evaluation method, apparatus, and program | |
| CN115797339B (en) | Centrum central point positioning method, system, equipment and storage medium | |
| JP5904548B2 (en) | Bone mineral quantitative analysis method, bone mineral quantitative analysis system, and recording medium | |
| Supriyanti et al. | Comparison of conventional edge detection methods performance in lung segmentation of COVID19 patients | |
| Mol et al. | Digital image analysis for the diagnosis of periapical bone lesions: a preliminary study | |
| CN115631232B (en) | Method for determining radial position of double-probe detector | |
| Fontanella et al. | Challenges of building medical image datasets for development of deep learning software in stroke |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| EXPY | Cancellation because of completion of term |