公开(公告)号：US08538119B2

公开(公告)日：2013-09-17

申请号：US12996114

申请日：2009-05-12

申请人： Miki Taki ,  Norio Oowada

发明人： Miki Taki ,  Norio Oowada

IPC分类号： G06K9/00

CPC分类号： G01N15/1459 ,  G01N15/1463 ,  G01N15/147 ,  G01N33/493 ,  G01N2015/1409

摘要： A particle image analyzing method is adapted so that while raising image-reviewing efficiency at a cropped image level of particle components in a sample, the entire sample can be observed without significantly changing a related apparatus configuration. Prior to image reviewing of an imaging region, cropped images thereof are reviewed and, with reference to the images arranged for each kind of particle component, if the operator judges any particles to have been falsely identified, the operator uses an operating unit to modify positions of the particles to those of correct component items. An overall image of the imaging region is displayed and if any components to be added (overlooked components) appear, the kinds of these components are identified and quantitative data on each kind of component is registered. Upon completion of the registration, the concentration of the sample is recalculated and a comment is entered in a comment field.

摘要翻译： 粒子图像分析方法适于在提取样本中的粒子成分的裁剪图像级别的同时提高图像评价效率的同时，可以观察整个样本而不显着改变相关的装置配置。 在对成像区域进行图像检查之前，对其裁剪的图像进行审查，并且参考针对每种颗粒组件布置的图像，如果操作者判断任何颗粒被错误地识别，则操作者使用操作单元来修改位置 的颗粒到正确的组分物品。 显示成像区域的整体图像，并且如果出现任何要添加的组件（被忽视的组件），则识别这些组件的种类，并且登记各种组件的定量数据。 注册完成后，重新计算样本的浓度，并在注释字段中输入评论。

公开(公告)号：US20120134559A1

公开(公告)日：2012-05-31

申请号：US13386846

申请日：2010-07-23

申请人： Akiko Suzuki ,  Norio Oowada ,  Miki Taki ,  Satoshi Mitsuyama ,  Chihiro Manri

发明人： Akiko Suzuki ,  Norio Oowada ,  Miki Taki ,  Satoshi Mitsuyama ,  Chihiro Manri

IPC分类号： G06K9/62

CPC分类号： G01N15/1404 ,  G01N1/30 ,  G01N15/1459 ,  G01N35/00613 ,  G01N2015/1409 ,  G01N2015/1465

摘要： The particle analysis apparatus includes means that perform processes upon image processing of images (110) acquired in a measurement of the sample, simultaneously with a normal image processing for classifying target particles. The means included are: image processing means (110a) for calculating information of RGB density distributions of each whole image; abnormal state determination processing means (110c) for determining whether or not the acquired images are in an abnormal state according to tendencies of the RGB density distributions; and an abnormality judgment process means for making final determination of the existence of an abnormality by calculating an appearance frequency of abnormal images after all measurements for the one sample is completed. These means allow diagnosis of abnormalities to be conducted simultaneously with normal analysis without changing the configuration of the conventional apparatus.

摘要翻译： 粒子分析装置包括与用于分类目标粒子的正常图像处理同时进行在样本测量中获取的图像（110）的图像处理的处理。 包括的装置是：用于计算每个整个图像的RGB密度分布的信息的图像处理装置（110a） 用于根据RGB浓度分布的趋势确定所获取的图像是否处于异常状态的异常状态确定处理装置（110c）; 以及异常判断处理装置，用于通过在完成所述一个样本的所有测量之后计算异常图像的出现频率来最终确定异常的存在。 这些装置允许诊断异常与正常分析同时进行，而不改变常规装置的结构。

公开(公告)号：US20110090247A1

公开(公告)日：2011-04-21

申请号：US12996114

申请日：2009-05-12

申请人： Miki Taki ,  Norio Oowada

发明人： Miki Taki ,  Norio Oowada

IPC分类号： G06K9/46 ,  G09G5/00 ,  G06K9/00

CPC分类号： G01N15/1459 ,  G01N15/1463 ,  G01N15/147 ,  G01N33/493 ,  G01N2015/1409

摘要： A particle image analyzing method is adapted so that while raising image-reviewing efficiency at a cropped image level of particle components in a sample, the entire sample can be observed without significantly changing a related apparatus configuration. Prior to image reviewing of an imaging region, cropped images thereof are reviewed and, with reference to the images arranged for each kind of particle component, if the operator judges any particles to have been falsely identified, the operator uses an operating unit to modify positions of the particles to those of correct component items. An overall image of the imaging region is displayed and if any components to be added (overlooked components) appear, the kinds of these components are identified and quantitative data on each kind of component is registered. Upon completion of the registration, the concentration of the sample is recalculated and a comment is entered in a comment field.

摘要翻译： 粒子图像分析方法适于在提取样本中的粒子成分的裁剪图像级别的同时提高图像评价效率的同时，可以观察整个样本而不显着改变相关的装置配置。 在对成像区域进行图像检查之前，对其裁剪的图像进行审查，并且参考针对每种颗粒组件布置的图像，如果操作者判断任何颗粒被错误地识别，则操作者使用操作单元来修改位置 的颗粒到正确的组分物品。 显示成像区域的整体图像，并且如果出现任何要添加的组件（被忽视的组件），则识别这些组件的种类，并且登记各种组件的定量数据。 注册完成后，重新计算样本的浓度，并在注释字段中输入评论。

公开(公告)号：US06229912B1

公开(公告)日：2001-05-08

申请号：US08943468

申请日：1997-10-03

申请人： Hatsue Katahira ,  Kazuhiro Sano ,  Hideki Asai ,  Norio Oowada

发明人： Hatsue Katahira ,  Kazuhiro Sano ,  Hideki Asai ,  Norio Oowada

IPC分类号： G06K900

CPC分类号： G01N15/1429 ,  G01N15/14 ,  G01N15/1463

摘要： A particle image analyzing apparatus of high classifying accuracy and high efficiency in which a criterion for determining whether fine classification is required or not can be set for every facility such as hospital, or the like. A rough classification unit executes rough classification of particles and supplies results of the rough classification to a fine classification necessity determination unit. The necessity determination unit compares the results of the rough classification with reference values stored in a reference value storage unit and determines from the comparison whether every sample is normal or abnormal to thereby determine whether fine classification is required or not. The reference values stored in the storage unit can be changed in accordance with the subject of examination through an input/output control unit from a keyboard. When the determination unit makes a decision that fine classification is required, the determination unit gives an instruction to an image processing control circuit to execute fine classification. Characteristic parameters for fine classification are supplied to a fine classification unit on the basis of the control instruction of the control circuit. Then, fine classification is executed, so that results of the fine classification are supplied to the determination unit.

摘要翻译： 可以对诸如医院等的每个设施设置具有高分类精度和高效率的粒子图像分析装置，其中确定是否需要精细分类的标准。 粗略分类单元执行粗粒度分级，将粗分类的结果提供给精细分类必要性判定单元。 必要性确定单元将粗略分类的结果与存储在参考值存储单元中的参考值进行比较，并且从比较中确定每个样本是正常还是异常，从而确定是否需要精细分类。 可以通过来自键盘的输入/输出控制单元根据检查对象来改变存储在存储单元中的参考值。 当确定单元作出需要精细分类的决定时，确定单元向图像处理控制电路发出指令以执行精细分类。 基于控制电路的控制指令将精细分类的特征参数提供给精细分类单元。 然后，执行精细分类，从而将精细分类的结果提供给确定单元。

公开(公告)号：US20120076349A1

公开(公告)日：2012-03-29

申请号：US13375249

申请日：2010-05-17

申请人： Chihiro Manri ,  Norio Oowada ,  Satoshi Mitsuyama

发明人： Chihiro Manri ,  Norio Oowada ,  Satoshi Mitsuyama

IPC分类号： G06K9/00

CPC分类号： G01N15/1459 ,  G01N2015/1452

摘要： At each of mutually different multiple focal positions, focal adjustment parameter values are obtained from images of standard particles made of the same substance. Each focal adjustment parameter value is figured out as any one of the ratio between the density value around the center of the standard particle image and the density value around the outline, the difference therebetween, and the density value around the center. The in-focus position is adjusted on the basis of the relationship between the obtained focal adjustment parameter values and the focal positions. Moreover, on the basis of the relationship between the focal adjustment parameter values and the focal positions, the parameter values are converted into focal positions, and the focal positions and dispersion thereof are used to check the displacement of the in-focus position and the thickness of the sample liquid.

摘要翻译： 在每个相互不同的多个焦点位置，从相同物质制成的标准颗粒的图像中获得焦点调整参数值。 每个焦点调整参数值被计算为标准颗粒图像的中心附近的密度值与轮廓周围的密度值之间的比率，它们之间的差异以及围绕中心的密度值之间的任何一个。 基于获得的焦点调整参数值和焦点位置之间的关系来调整对焦位置。 另外，根据焦点调整参数值与焦点位置之间的关系，将参数值转换为焦点位置，并将其焦点位置和色散用于检查对焦位置和厚度的位移 的样品液体。

公开(公告)号：US5561517A

公开(公告)日：1996-10-01

申请号：US303236

申请日：1994-09-08

申请人： Hideyuki Horiuchi ,  Norio Oowada ,  Hideki Asai ,  Ryohei Yabe

发明人： Hideyuki Horiuchi ,  Norio Oowada ,  Hideki Asai ,  Ryohei Yabe

IPC分类号： G01N15/02 ,  G01N15/14 ,  G01N33/48 ,  G01N33/49

CPC分类号： G01N15/14

摘要： A method and an apparatus for flow type particle image analysis generate a pulse light emission in any one of the odd and the even field image reading-out periods, and multiple exposure is prevented by prohibiting the next pulse light emission in the predetermined period after the emission. The method includes the steps of flowing a sample liquid in a flow cell, detecting particles passing through the flow cell by a laser beam, making a flash lamp emit light after the predetermined period from the particle detection, picking up a particle still image by a TV camera, and further preventing the multiple exposure by providing emission-prohibiting periods which are established by controlling the timings of flash lamp emission and image transfer with the TV camera, a flash lamp emission control circuit, and an image processing control circuit which are controlled by a central control part.

摘要翻译： 用于流式粒子图像分析的方法和装置在奇数和偶数场图像读出周期中的任何一个中产生脉冲发光，并且通过在预定时间段之后禁止下一个脉冲发光来防止多次曝光 排放。 该方法包括以下步骤：将流动池中的样品液体流动，通过激光束检测通过流动池的颗粒，使得闪光灯在从颗粒检测起的预定时间后发光，通过一个 通过提供通过控制闪光灯发射和图像传输的定时而建立的禁止发射周期，通过电视摄像机，闪光灯发射控制电路和图像处理控制电路进行控制，从而进一步防止多次曝光 由中央控制部分。

公开(公告)号：US08831306B2

公开(公告)日：2014-09-09

申请号：US13375249

申请日：2010-05-17

申请人： Chihiro Manri ,  Norio Oowada ,  Satoshi Mitsuyama

发明人： Chihiro Manri ,  Norio Oowada ,  Satoshi Mitsuyama

IPC分类号： G06K9/00 ,  G06K9/40 ,  G01N15/14

CPC分类号： G01N15/1459 ,  G01N2015/1452

摘要： At each of mutually different multiple focal positions, focal adjustment parameter values are obtained from images of standard particles made of the same substance. Each focal adjustment parameter value is figured out as any one of the ratio between the density value around the center of the standard particle image and the density value around the outline, the difference therebetween, and the density value around the center. The in-focus position is adjusted on the basis of the relationship between the obtained focal adjustment parameter values and the focal positions. Moreover, on the basis of the relationship between the focal adjustment parameter values and the focal positions, the parameter values are converted into focal positions, and the focal positions and dispersion thereof are used to check the displacement of the in-focus position and the thickness of the sample liquid.

摘要翻译： 在每个相互不同的多个焦点位置，从相同物质制成的标准粒子的图像中获得焦点调整参数值。 每个焦点调整参数值被计算为标准颗粒图像的中心附近的密度值与轮廓周围的密度值之间的比率，它们之间的差异以及围绕中心的密度值之间的任何一个。 基于获得的焦点调整参数值和焦点位置之间的关系来调整对焦位置。 此外，基于焦点调整参数值与焦点位置之间的关系，参数值被转换为焦点位置，并且其焦点位置和色散用于检查对焦位置和厚度的位移 的样品液体。

公开(公告)号：US5878160A

公开(公告)日：1999-03-02

申请号：US589102

申请日：1996-01-23

申请人： Hideyuki Horiuchi ,  Hideki Asai ,  Yasuaki Kojima ,  Norio Oowada ,  Kazuhiro Sano

发明人： Hideyuki Horiuchi ,  Hideki Asai ,  Yasuaki Kojima ,  Norio Oowada ,  Kazuhiro Sano

IPC分类号： G01N15/02 ,  G01N15/14 ,  G06K9/78

CPC分类号： G01N15/1459 ,  G01N15/1463

摘要： A flow type particle image analytical method for feeding a particles-suspended sample by surrounding it by a cleaning solution, imaging particles in the sample by irradiating light to it, and automatically classifying the particles in the sample by analyzing the picked-up particle images, wherein the method comprises a means for designating the kind of particles to be reviewed beforehand among the classified particles, a means for storing only particles which are automatically classified to the designated particle kind in a review image memory, a means for displaying particles of the same kind on a CRT display in batch so as to review particle images, and a means for classifying each of the displayed particles finally by an operator or for changing the particle name.

摘要翻译： 一种流式粒子图像分析方法，用于通过用清洗液包围颗粒悬浮样品，通过对其照射光而对样品中的颗粒进行成像，并通过分析所提取的颗粒图像来自动分类样品中的颗粒， 其特征在于，所述方法包括用于在分类颗粒中预先指定待检查的颗粒的种类的装置，用于仅存储在检查图像存储器中自动分类为指定的颗粒类型的颗粒的装置，用于显示颗粒的装置 批量处理CRT显示器，以便检查粒子图像，以及用于最后由操作者分类每个显示的粒子或用于改变粒子名称的装置。

公开(公告)号：US5911002A

公开(公告)日：1999-06-08

申请号：US715592

申请日：1996-09-18

申请人： Satoshi Mitsuyama ,  Jun Motoike ,  Norio Oowada ,  Yasuaki Kojima

发明人： Satoshi Mitsuyama ,  Jun Motoike ,  Norio Oowada ,  Yasuaki Kojima

IPC分类号： G01N15/02 ,  G01N15/14 ,  G01N33/493 ,  G06F15/18 ,  G06K9/66 ,  G06N3/00 ,  G06T7/00 ,  G06K9/62 ,  G06E1/00

CPC分类号： G06K9/6217 ,  G01N33/493 ,  G06K9/00147 ,  G06K9/6262 ,  G01N15/1463 ,  G01N2015/1488

摘要： In a pattern recognition system provided with a pattern recognition processing unit having a network structure constructed of an input layer for inputting a feature parameter of a subject under recognition as input information an intermediate layer for processing the input information and an output layer for outputting a processed result output values of respective output nodes for constituting the output layer, corresponding to the input information, are compared with each other by the pattern recognition processing unit, and a classification item corresponding to the output node whose output value is maximum is stored into a storage unit as a recognized result with respect to the input information. The pattern recognition system is also provided with a reliability evaluating unit for setting a threshold with respect to an output value of each of the output nodes and for evaluating reliability of the recognized result based upon the output values of the respective output nodes. When the reliability evaluating unit judges that the reliability is high, the recognized result is stored into the storage unit.

摘要翻译： 在具有图案识别处理单元的图案识别系统中，该图案识别处理单元具有由输入层构成的网络结构，该输入层用于输入被识别的被摄体的特征参数作为输入信息，用于处理输入信息的中间层和用于输出处理的输出层 对应于输入信息的用于构成输出层的各个输出节点的结果输出值通过模式识别处理单元相互比较，并且与输出值最大的输出节点对应的分类项目被存储到存储器 单位作为输入信息的公认结果。 模式识别系统还设置有可靠性评估单元，用于相对于每个输出节点的输出值设置阈值，并且用于基于各个输出节点的输出值来评估识别结果的可靠性。 当可靠性评估单元判断可靠性高时，将识别结果存储在存储单元中。

公开(公告)号：US5715182A

公开(公告)日：1998-02-03

申请号：US286257

申请日：1994-08-08

申请人： Hideki Asai ,  Hideyuki Horiuchi ,  Ryohei Yabe ,  Norio Oowada

发明人： Hideki Asai ,  Hideyuki Horiuchi ,  Ryohei Yabe ,  Norio Oowada

IPC分类号： G01N15/14 ,  G06F19/00

CPC分类号： G01N15/14 ,  G01N2201/1296 ,  Y10S706/924

摘要： A particle image in a sample is formed at an imaging position by an objective lens of a microscope, projected on the image picking up plane of a TV camera via a projection lens and is subjected to photo-electric conversion. Image signals from the TV camera are supplied to an image memory via an A/D converter as well as to an image processing control unit. Image signals outputted from the image memory are supplied to a characteristic picking out unit and there a plurality of characteristics of the particle concerned are picked out. The picked-out characteristics are supplied to the classification unit and there classification of the sediment components is perfumed via a neural network with a learning capability. Accordingly, the classification unit performs provisionally an automatic classification of the objective sediment components by making use of the inputted characteristic parameters. The device allows accurate and fast automatic component particle analysis even for patient specimens containing a variety of components in high concentration.

摘要翻译： 通过显微镜的物镜在成像位置形成样品中的粒子图像，通过投影透镜投影在电视摄像机的图像拾取面上，并进行光电转换。 来自TV摄像机的图像信号经由A / D转换器以及图像处理控制单元提供给图像存储器。 从图像存储器输出的图像信号被提供给特征选择单元，并且拾取有关粒子的多个特征。 所选择的特征被提供给分类单元，并且通过具有学习能力的神经网络对沉积物成分进行分类。 因此，分类单元通过使用输入的特征参数临时执行目标沉积物成分的自动分类。 该装置允许准确和快速的自动组分颗粒分析，即使对于含有高浓度各种组分的患者标本也是如此。