An intelligent detection method for blood smear quality used in laboratory

Abstract

The present invention relates to the field of spectral detection technology, and more specifically to an intelligent blood smear quality detection method for a laboratory. The method comprises: obtaining overall spectral data of a blood smear and spectral signals of various detection positions in different regions of the blood smear; determining the baseline drift fluctuation segment and normal fluctuation segment of the spectral signal at each detection position; performing a primary correction on the spectral signal at the detection position and the overall spectral data to obtain a corrected spectral signal and first corrected overall spectral data; performing a secondary correction on the first corrected overall spectral data using the peak values of the baseline drift fluctuation segments immediately before and after the current baseline drift fluctuation segment and the peak value of the current baseline drift fluctuation segment in the corrected spectral signals at each detection position to obtain final second corrected overall spectral data; and detecting the quality of the blood smear using the second corrected overall spectral data. Thus, the present invention improves the detection accuracy and reliability of blood smear quality detection.

Description

Technical Field

[0001] The present invention relates to the technical field of spectrum detection, and in particular to an intelligent detection method for blood smear quality used in clinical laboratories. Background Art

[0002] A blood smear is made by evenly smearing a blood sample onto a glass slide to create a thin slice. After staining, characteristics such as cell morphology, number, and distribution are observed under a microscope. The quality of the blood smear determines the accuracy of the test. High-quality blood smears can intuitively and accurately reflect the patient's blood quality or physical condition, while poor-quality blood smears will affect test accuracy and efficiency, making it impossible to effectively use the test results for patient condition analysis. To ensure the quality of patients' blood smears and improve test efficiency, blood smear quality testing is necessary.

[0003] In some scenarios, baseline drift caused by thick smears, cell stacking within the area, and chemical changes in the blood during blood smear testing often requires first-order derivative calculations of the spectral signal. Numerical methods such as differential methods or Savitzky-Golay filters are often used to smooth the data and calculate the derivative. The derivative results are then used to identify areas of baseline drift and correct them. While the first-order derivative method can eliminate baseline drift, it amplifies high-frequency noise in the spectral signal, increasing signal background interference. Furthermore, this method weakens spectral characteristic peaks, especially in areas with cell stacking, which can easily cause the loss of key biochemical information in the cell stacking area, resulting in lower accuracy and reliability in blood smear quality testing. Summary of the Invention

[0004] In order to solve the technical problems of low detection accuracy and reliability of blood smear quality detection in the prior art, the purpose of the present invention is to provide an intelligent blood smear quality detection method for clinical laboratory use.

[0005] In order to solve the above technical problems, the technical solutions adopted are as follows:

[0006] An embodiment of the present invention provides an intelligent detection method for the quality of blood smears used in a laboratory, comprising: obtaining overall spectral data of a blood smear and spectral signals of each detection position in different areas of the blood smear; determining the baseline drift fluctuation segment and normal fluctuation segment of the spectral signal of each detection position based on the signal strength of the extreme points of the spectral signal of each detection position in different areas and the baseline position where the extreme points are located; performing an initial correction on the spectral signal of the detection position and the overall spectral data based on the baseline position of the normal fluctuation segment within the detection position and the position where the peak of the normal fluctuation segment is located to obtain a corrected spectral signal and first corrected overall spectral data; performing a secondary correction on the first corrected overall spectral data using the peak values of the baseline drift fluctuation segments adjacent to and before the current baseline drift fluctuation segment in the corrected spectral signals of each detection position and the peak value of the current baseline drift fluctuation segment to obtain final second corrected overall spectral data; and detecting the quality of the blood smear using the second corrected overall spectral data.

[0007] Optionally, determining the baseline drift fluctuation segment and normal fluctuation segment of the spectral signal of each detection position based on the signal strength of the extreme points of the spectral signal of each detection position in different areas and the baseline position where the extreme points are located includes: using the baseline position where the extreme points are located in the middle of the spectral signal of each detection position in each area as the fluctuation start and end positions, and taking the spectral curve segment between the fluctuation start and end positions as the fluctuation segment of the spectral signal of each detection position; determining the baseline drift parameter at the peak point of the current fluctuation segment based on the second baseline position at the peak point of the fluctuation segment adjacent to the current fluctuation segment and the first baseline position of the current fluctuation segment; determining the peak signal drift parameter at the peak point of the current fluctuation segment based on the first signal strength of the peak point of the fluctuation segment adjacent to the current fluctuation segment and the second signal strength of the peak point of the current fluctuation segment; determining the first ratio between the baseline drift parameter and the peak signal drift parameter as the spectral curve drift information of the current fluctuation segment; when the spectral curve drift information of multiple consecutive fluctuation segments is positive, determining the multiple consecutive fluctuation segments as baseline drift fluctuation segments, otherwise determining them as normal fluctuation segments.

[0008] Optionally, based on the second baseline position at the peak point of the fluctuation segment adjacent to the current fluctuation segment and the first baseline position of the current fluctuation segment, determining the baseline drift parameter at the peak point of the current fluctuation segment includes: calculating the first difference between the second baseline position and the first baseline position at the peak point of the next fluctuation segment adjacent to the current fluctuation segment; and determining the second ratio between the first difference and the first baseline position as the baseline drift parameter.

[0009] Optionally, based on the first signal strength of the peak point of the fluctuation segment adjacent to the current fluctuation segment and the second signal strength of the peak point of the current fluctuation segment, determining the peak signal drift parameter at the peak point of the current fluctuation segment includes: calculating the second difference between the first signal strength and the second signal strength of the peak point of the next fluctuation segment adjacent to the current fluctuation segment; and determining the third ratio between the second difference and the second signal strength as the peak signal drift parameter.

[0010] Optionally, based on the baseline position of the normal fluctuation segment in the detection position and the position of the peak of the normal fluctuation segment, the spectral signal and the overall spectral data of the detection position are initially corrected to obtain the corrected spectral signal and the first corrected overall spectral data, including: determining the base-peak relative coefficient between the baseline position in the normal fluctuation segment and the position of the peak of the normal fluctuation segment based on the baseline position of the normal fluctuation segment and the position of the peak of the normal fluctuation segment; determining the baseline drift correction coefficient according to the first time interval at both ends of the normal fluctuation segment, the second time interval at both ends of the baseline drift fluctuation segment and the base-peak relative coefficient; correcting the baseline position of the baseline drift fluctuation segment using the baseline drift correction coefficient to obtain the corrected baseline position of the baseline drift fluctuation segment; correcting the spectral signal of the corresponding detection position based on the corrected baseline position of the baseline drift fluctuation segment of each detection position and performing the initial correction on the overall spectral data of the blood smear to obtain the corrected spectral signal and the first corrected overall spectral data.

[0011] Optionally, based on the baseline position of the normal fluctuation segment and the position of the peak of the normal fluctuation segment, determining the base-peak relative coefficient between the baseline position in the normal fluctuation segment and the position of the peak of the normal fluctuation segment includes: calculating the third difference between the position of the peak of each normal fluctuation segment and the baseline position of the normal fluctuation segment, and superimposing each third difference to obtain a first superimposed value; determining the fourth ratio between the third difference of each normal fluctuation segment and the first superimposed value as the base-peak relative coefficient between the baseline position in the normal fluctuation segment and the position of the peak of the normal fluctuation segment.

[0012] Optionally, determining the baseline drift correction coefficient based on the first time interval at both ends of the normal fluctuation segment, the second time interval at both ends of the baseline drift fluctuation segment, and the base peak relative coefficient includes: calculating the fifth ratio between the second time interval and the mean of the first time interval, and calculating the absolute value of the fourth difference between the fifth ratio and the predetermined value; calculating the first product between the absolute value of the fourth difference and the base peak relative coefficient, and normalizing the first product to obtain the baseline drift correction coefficient.

[0013] Optionally, the first corrected overall spectral data is corrected twice using the peak values of the baseline drift fluctuation segments that are adjacent to the current baseline drift fluctuation segment and the peak value of the current baseline drift fluctuation segment in the corrected spectral signals of each detection position to obtain the final second corrected overall spectral data, including: determining the change trend of the adjacent baseline drift fluctuation segments by using the peak values of the baseline drift fluctuation segments that are adjacent to the current baseline drift fluctuation segment and the peak value of the current baseline drift fluctuation segment in the corrected spectral signals of each detection position; determining the identity of the change trend between different detection positions according to the change trend of each adjacent baseline drift fluctuation segment at different detection positions; and dividing each detection position into two groups based on the identity of the change trend. The detection groups are grouped to obtain a plurality of detection groups; based on the changing trends of each adjacent fluctuation segment of different detection positions in each detection group and the positional relationship between different detection positions, the curve extension slope between different detection positions in each detection group is determined; the detection group corresponding to the minimum value of the curve extension slope is used as the analysis detection group of the blood smear; the relative thickness at each detection position in the analysis detection group is used to determine the thickness weight of each detection position; based on the thickness weight, the correction baseline position is secondary corrected to obtain the relative baseline position of each detection position in the analysis detection group; based on the relative baseline position of each detection position in the analysis detection group, the first corrected overall spectral data is secondary corrected to obtain the final second corrected overall spectral data.

[0014] Optionally, determining the identity of the change trends between different detection positions based on the change trends of each adjacent baseline drift fluctuation segment of different detection positions includes: superimposing the change trends of each adjacent baseline drift fluctuation segment of each detection position to obtain a second superimposed value of each detection position; calculating the second product between the second superimposed values of different detection positions; and using a sign function to perform sign processing on the second product to obtain the identity of the change trends between different detection positions.

[0015] Optionally, based on the changing trends of adjacent fluctuation segments of different detection positions in each detection group and the positional relationship between different detection positions, determining the curve extension slope between different detection positions in each detection group includes: calculating the fifth difference between the second superposition values of different detection positions, and calculating the sixth ratio between the fifth difference and the positional relationship between different detection positions; superimposing each sixth ratio to obtain a third superposition value; calculating the fifth difference between the number of detection positions and a predetermined value, and determining the seventh ratio between the third superposition value and the fifth difference as the curve extension slope.

[0016] The present invention has the following beneficial effects: first, the overall spectral data of a blood smear and the spectral signals of each detection position in different areas of the blood smear are obtained; and based on the signal strength of the extreme points of the spectral signals of each detection position in different areas and the baseline positions where the extreme points are located, the baseline drift fluctuation segment and the normal fluctuation segment of the spectral signal of each detection position are determined; secondly, based on the baseline position of the normal fluctuation segment in the detection position and the position of the peak of the normal fluctuation segment, the spectral signal of the detection position and the overall spectral data are initially corrected to obtain a corrected spectral signal and first corrected overall spectral data; then, using the peak values of the baseline drift fluctuation segments adjacent to and before the current baseline drift fluctuation segment in the corrected spectral signals of each detection position and the peak value of the current baseline drift fluctuation segment, the first corrected overall spectral data are secondary corrected to obtain final second corrected overall spectral data; finally, the second corrected overall spectral data is used to detect the quality of the blood smear.

[0017] In this way, the embodiment of the present invention can perform an initial correction on the spectral signal of each detection position and the overall spectral data through the baseline drift of the spectral signal of a single detection position in different areas of the blood smear, and then perform a secondary correction on the first corrected overall spectral data after the initial correction in combination with the baseline drift and peak change of the corrected spectral signal of each detection position in different areas. While eliminating the baseline drift, it avoids the problem of using the first-order derivative method to amplify the high-frequency noise in the spectral signal and weaken the spectral characteristic peak, thereby avoiding the loss of key biochemical information in the cell stacking area, improving the correction reliability of the spectral data, and improving the accuracy of the spectral data finally obtained, thereby improving the detection accuracy and reliability of the blood smear quality detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A flow chart of an intelligent blood smear quality detection method for laboratory use provided by one embodiment of the present invention;

[0020] Figure 2 A schematic diagram of dividing a fluctuation segment provided by an embodiment of the present invention;

[0021] Figure 3 The present invention provides a schematic structural diagram of an intelligent blood smear quality detection device for clinical laboratory use according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of an intelligent blood smear quality detection method for laboratory use according to the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0023] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0024] The specific scheme of the intelligent detection method for blood smear quality for clinical laboratory provided by the present invention is described in detail below with reference to the accompanying drawings.

[0025] Example 1:

[0026] See also Figure 1 , which shows a flow chart of an intelligent blood smear quality detection method for laboratory use provided by one embodiment of the present invention, including:

[0027] Step S101 : acquiring the overall spectral data of the blood smear and the spectral signals of each detection position in different areas of the blood smear.

[0028] Specifically, during the production of a user's blood smear, whether manually or automatically, there are numerous unstable factors in the amount of blood dripped and the advancement process, which results in the inability to mass-produce high-quality blood smears. Blood smears may be too thick, too thin, or unevenly thick. Therefore, in an embodiment of the present invention, a manually or automatically produced blood smear is placed on a spectrometer testing station for testing, acquiring overall spectral data from the blood smear as well as spectral signals from various test locations within the blood smear.

[0029] More specifically, the embodiment of the present invention collects blood smears from patients, removes some unqualified blood smears based on appearance inspection, and numbers the remaining blood smears according to the order of collection. Then, a handheld Raman spectrometer is used to obtain the overall spectral data of the blood atlas, realizing cloud-network-end IoT Raman monitoring and information retrieval, and performing preliminary preprocessing on the obtained spectral data to remove noise. Secondly, the embodiment of the present invention divides the blood smear into multiple regions, such as the head region, the body region, and the tail region, and uniformly selects each region. detection positions and perform spectral detection on each detection position.

[0030] Step S102 : determining the baseline drift fluctuation segment and the normal fluctuation segment of the spectral signal at each detection position according to the signal strength of the extreme value points of the spectral signal at each detection position in different regions and the baseline position where the extreme value points are located.

[0031] Specifically, thick regions of a blood smear may contain overlapping cells, which can lead to overlapping blood cells and affect the spectral baseline shift of the blood smear, compromising the accuracy of quality testing. Therefore, the embodiments of the present invention utilize spectral signals collected from various detection locations in different regions as a basis to eliminate the effects of baseline shift caused by cell overlap in the spectral signals from these locations, thereby correcting the waveform of the overall spectral data, obtaining true spectral data from the blood smear, and completing the quality testing of the blood smear. During blood smear spectral testing, baseline shift is a regional baseline deviation caused by uneven thickness of the blood smear. Since the biochemical composition of blood undergoes dynamic changes after removal from the body, baseline drift (i.e., irregularly fluctuating baseline shift) may occur during the testing process. Therefore, analysis shows that changes in single-coordinate spectral data are beneficial for analyzing the overall baseline shift of a blood smear. Therefore, the embodiments of the present invention analyze the accuracy of spectral data from individual detection locations by using differences in spectral data changes.

[0032] Furthermore, as an optional embodiment of the present invention, determining the baseline drift fluctuation segment and normal fluctuation segment of the spectral signal of each detection position based on the signal strength of the extreme point of the spectral signal at each detection position in different regions and the baseline position where the extreme point is located includes: using the baseline position where the extreme point is located in the middle of the spectral signal of each detection position in each region as the fluctuation start and end position, and using the spectral curve segment between the fluctuation start and end positions as the fluctuation segment of the spectral signal of each detection position; determining the baseline drift parameter at the peak point of the current fluctuation segment based on the second baseline position at the peak point of the fluctuation segment adjacent to the current fluctuation segment and the first baseline position of the current fluctuation segment; determining the peak signal drift parameter at the peak point of the current fluctuation segment based on the first signal strength of the peak point of the fluctuation segment adjacent to the current fluctuation segment and the second signal strength of the peak point of the current fluctuation segment; determining a first ratio between the baseline drift parameter and the peak signal drift parameter as the spectral curve drift information of the current fluctuation segment; when the spectral curve drift information of multiple consecutive fluctuation segments is positive, determining the multiple consecutive fluctuation segments as baseline drift fluctuation segments, otherwise determining them as normal fluctuation segments.

[0033] Specifically, in the embodiment of the present invention, the thicker the blood smear, the more cells there are in the area, and the more serious the data distortion caused by the cell stacking phenomenon. Therefore, when analyzing a single coordinate of the blood smear, the embodiment of the present invention takes the spectral signal of each detection position in the body area as an example for analysis. The embodiment of the present invention takes the coordinate n of a detection position in the body area as an example, and its baseline position is recorded as . Get the spectral signal curve at coordinate n The fluctuation segment division of the spectrum sequence is realized by the signal fluctuation of the detection position in the body region. In the embodiment of the present invention, based on the variation trend of the spectrum signal intensity at the detection position and the position of the extreme point, the band between the extreme points is regarded as a fluctuation segment. For example, Figure 2 As shown, Figure 2 A schematic diagram of a wave segment division provided by an embodiment of the present invention, wherein the initial position point of the spectrum at a certain detection position is used as the initial extreme point , along the change of the spectral signal at the detection position, the baseline position of the extreme point is obtained, and the position of the extreme point with the same direction change (interval extreme point) is used as the start and end position of the fluctuation, thereby obtaining the fluctuation segment of the spectral signal.

[0034] Furthermore, the spectral signal intensity at any end of the fluctuation segment is compared and extreme points within the fluctuation range The larger the signal strength difference, the If the signal strength at any end of the fluctuation range is , then readjust the initial extreme point Location is (Only for the initial extreme point), continuous detection readjusts the fluctuation segment based on the position of the adjusted initial extreme point, and the signal extreme point in the adjusted fluctuation segment is used as the signal peak .

[0035] Furthermore, the baseline drift in the embodiment of the present invention is a smooth and continuous fluctuation on the spectrum curve. The embodiment of the present invention analyzes the baseline drift phenomenon of the spectrum curve by changing the value between the spectrum curves. Wherein, first, a baseline drift parameter is obtained. As an optional embodiment of the present invention, based on the second baseline position at the peak point of a fluctuation segment adjacent to the current fluctuation segment and the first baseline position of the current fluctuation segment, determining the baseline drift parameter at the peak point of the current fluctuation segment includes: calculating a first difference between the second baseline position at the peak point of a subsequent fluctuation segment adjacent to the current fluctuation segment and the first baseline position; and determining a second ratio between the first difference and the first baseline position as the baseline drift parameter.

[0036] Specifically, the embodiment of the present invention takes the fluctuation segment m as the current fluctuation segment as an example, and the embodiment of the present invention specifically uses the following formula to calculate the baseline drift parameter:

[0037]

[0038] In the above formula, is the baseline drift parameter at the peak point of the current fluctuation segment m. m is the number of the fluctuation segment, is the first baseline position at the peak point of the current fluctuation segment m. It is the second baseline position at the peak point of the fluctuation segment adjacent to the current fluctuation segment m. is the baseline position offset at the peak point of the adjacent fluctuation segment, is the baseline drift parameter at the peak point of the current fluctuation segment m.

[0039] Further, as an optional embodiment of the present invention, based on the first signal strength of the peak point of the fluctuation segment adjacent to the current fluctuation segment and the second signal strength of the peak point of the current fluctuation segment, determining the peak signal drift parameter at the peak point of the current fluctuation segment includes: calculating the second difference between the first signal strength and the second signal strength of the peak point of the next fluctuation segment adjacent to the current fluctuation segment; and determining the third ratio between the second difference and the second signal strength as the peak signal drift parameter.

[0040] Specifically, the embodiment of the present invention takes the fluctuation segment m as the current fluctuation segment as an example, and the embodiment of the present invention specifically uses the following formula to calculate the peak signal drift parameter:

[0041]

[0042] In the above formula, Indicates the peak signal drift parameter at the peak point of the current fluctuation segment m. Indicates the second signal strength at the peak point of the current fluctuation segment m. Indicates the first signal strength of the peak point of the fluctuation segment m+1 adjacent to the current fluctuation segment m. is the difference in signal strength at the peak point.

[0043] Furthermore, the embodiment of the present invention uses the following formula to calculate the spectrum curve drift information of the current fluctuation segment m:

[0044]

[0045] In the above formula, Indicates the spectrum curve drift information of the current fluctuation segment m compared to the adjacent fluctuation segment m+1. Indicates the peak signal drift parameter at the peak point of the current fluctuation segment m. is the baseline drift parameter at the peak point of the current fluctuation segment m.

[0046] Furthermore, when there is a drift in the baseline position, the corresponding absorption peak changes accordingly. When the baseline position and signal intensity change in the same positive or negative direction (at this time is positive), and multiple consecutive fluctuation segments have the same performance, indicating that there is a baseline drift problem in this part of the fluctuation segment, and it is determined to be a baseline drift fluctuation segment, otherwise it is a normal fluctuation segment.

[0047] Step S103 , based on the baseline position of the normal fluctuation segment within the detection position and the position of the peak of the normal fluctuation segment, the spectral signal and the overall spectral data of the detection position are initially corrected to obtain a corrected spectral signal and first corrected overall spectral data.

[0048] Specifically, an embodiment of the present invention uses the baseline of a non-baseline drift fluctuation segment (normal fluctuation segment) as a reference to correct the baseline of a baseline drift fluctuation segment with baseline drift. As an optional embodiment of the present invention, based on the baseline position of the normal fluctuation segment within the detection position and the position of the peak of the normal fluctuation segment, performing an initial correction on the spectral signal and overall spectral data of the detection position to obtain the corrected spectral signal and first corrected overall spectral data includes: determining a base-peak relative coefficient between the baseline position within the normal fluctuation segment and the position of the peak of the normal fluctuation segment based on the baseline position of the normal fluctuation segment and the position of the peak of the normal fluctuation segment; determining a baseline drift correction coefficient based on a first time interval between the two ends of the normal fluctuation segment, a second time interval between the two ends of the baseline drift fluctuation segment, and the base-peak relative coefficient; correcting the baseline position of the baseline drift fluctuation segment using the baseline drift correction coefficient to obtain a corrected baseline position of the baseline drift fluctuation segment; and correcting the spectral signal of the corresponding detection position based on the corrected baseline position of the baseline drift fluctuation segment at each detection position and performing an initial correction on the overall spectral data of the blood smear to obtain the corrected spectral signal and first corrected overall spectral data.

[0049] Specifically, an embodiment of the present invention performs analysis based on the normal fluctuation segment to obtain the base-peak relative coefficient between the baseline position and the fluctuation peak in the normal fluctuation segment. As an optional embodiment of the present invention, based on the baseline position of the normal fluctuation segment and the position of the peak of the normal fluctuation segment, determining the base-peak relative coefficient between the baseline position in the normal fluctuation segment and the position of the peak of the normal fluctuation segment includes: calculating the third difference between the position of the peak of each normal fluctuation segment and the baseline position of the normal fluctuation segment, and superimposing each third difference to obtain a first superimposed value; determining the fourth ratio between the third difference of each normal fluctuation segment and the first superimposed value as the base-peak relative coefficient between the baseline position in the normal fluctuation segment and the position of the peak of the normal fluctuation segment.

[0050] Specifically, the embodiment of the present invention uses the following formula to calculate the base peak relative coefficient:

[0051]

[0052] In the above formula, It represents the base-peak relative coefficient between the baseline position within the normal fluctuation segment and the peak position of the normal fluctuation segment. It is the number of the normal fluctuation segment. is the total number of normal fluctuation segments. It is the location of the peak of the normal fluctuation segment. It is the baseline position of the normal fluctuation segment. It is the fluctuation difference between the peak position of the fluctuation segment and the baseline position.

[0053] Furthermore, when the baseline shifts, the frequency of the spectral curve (the time interval between the two ends of the fluctuation segment) denoted) is affected, therefore, a baseline drift correction coefficient is obtained by comparing the frequency changes and the relative relationship between the fluctuation peaks of the baseline drift fluctuation segment and the normal fluctuation segment. As an optional embodiment of the present invention, determining the baseline drift correction coefficient based on a first time interval at both ends of the normal fluctuation segment, a second time interval at both ends of the baseline drift fluctuation segment, and the base-peak relative coefficient includes: calculating a fifth ratio between the second time interval and the mean of the first time interval, calculating the absolute value of a fourth difference between the fifth ratio and a predetermined value; calculating a first product between the absolute value of the fourth difference and the base-peak relative coefficient, and normalizing the first product to obtain the baseline drift correction coefficient.

[0054] Specifically, the embodiment of the present invention uses the following formula to calculate the baseline drift correction coefficient:

[0055]

[0056] In the above formula, Indicates the baseline drift correction factor. Indicates the second time interval between the two ends of the baseline drift fluctuation segment, that is, the fluctuation frequency. It represents the mean of the fluctuation frequency of the normal fluctuation segment, that is, the mean of the first time intervals at both ends of the normal fluctuation segment. It is the difference in fluctuation frequency between the baseline drift fluctuation segment and the normal fluctuation segment, indicating the deviation coefficient between the baseline drift fluctuation segment and the normal fluctuation segment. It is the relative coefficient of the deviation coefficient and the baseline position, indicating the overall difference between the baseline drift fluctuation segment and the normal fluctuation segment. The function represents the normalization function, which is used to normalize the results and obtain the baseline drift correction coefficient .

[0057] Furthermore, the baseline position of the fluctuation segment with baseline drift is corrected based on the obtained baseline drift correction coefficient. In the embodiment of the present invention, the following formula is specifically used to correct the baseline position of the baseline drift fluctuation segment:

[0058]

[0059] In the above formula, is the corrected baseline position after correction of the baseline drift fluctuation segment m with baseline drift, is the baseline position before correction of baseline drift fluctuation segment m. Indicates the baseline drift correction factor.

[0060] The embodiment of the present invention processes the data of baseline drift at each detection position in each area based on the above steps, obtains the corrected baseline position of each detection position, and ensures the accuracy of the baseline position. The overall spectrum data of the blood smear is corrected in the Spectrum FL software model, and the actual first corrected overall spectrum data is obtained. The peak of the spectrum curve is Absorbance (Indicates corrected absorbance).

[0061] In step S104, the first corrected overall spectral data is corrected twice using the peak values of the baseline drift fluctuation segments before and after the current baseline drift fluctuation segment and the peak value of the current baseline drift fluctuation segment in the corrected spectral signals of each detection position to obtain the final second corrected overall spectral data.

[0062] Specifically, in the embodiments of the present invention, the blood tissue in each area of a blood smear all comes from a single patient and has similar blood components. When the blood smear is tested using spectral technology, the spectral signal intensities of different areas may differ, but the spectral signal change trends are similar, that is, the change trend of the spectral signal at adjacent light wavelengths at one location is similar to the change trend of the spectral curve signal intensity at another location. Furthermore, to ensure the accuracy of the corrected data of the blood smear spectral curve between different areas, the change trend of the spectral curve can be detected by analyzing the change trend of the spectral curve between different detection positions. Based on the operation of the above embodiment, the embodiment of the present invention obtains the first corrected overall spectral data after the initial correction, and traverses the data of the remaining detection positions in the blood smear to achieve baseline drift correction for the spectrum of each detection position on the blood smear.

[0063] Furthermore, as an optional embodiment of the present invention, the first corrected overall spectral data is corrected twice using the peak values of the baseline drift fluctuation segments that are adjacent to the current baseline drift fluctuation segment in the corrected spectral signals of each detection position and the peak value of the current baseline drift fluctuation segment to obtain the final second corrected overall spectral data, including: determining the change trend of the adjacent baseline drift fluctuation segments by using the peak values of the baseline drift fluctuation segments that are adjacent to the current baseline drift fluctuation segment in the corrected spectral signals of each detection position and the peak value of the current baseline drift fluctuation segment; determining the identity of the change trends between different detection positions according to the change trends of the adjacent baseline drift fluctuation segments at different detection positions; and determining the identity of the change trends based on the identity of the change trends. The detection positions are grouped to obtain multiple detection groups; based on the changing trends of each adjacent fluctuation segment of different detection positions in each detection group and the positional relationship between different detection positions, the curve extension slope between different detection positions in each detection group is determined; the detection group corresponding to the minimum value of the curve extension slope is used as the analysis detection group of the blood smear; the relative thickness of each detection position in the analysis detection group is used to determine the thickness weight of each detection position; based on the thickness weight, the corrected baseline position is secondary corrected to obtain the relative baseline position of each detection position in the analysis detection group; based on the relative baseline position of each detection position in the analysis detection group, the first corrected overall spectral data is secondary corrected to obtain the final second corrected overall spectral data.

[0064] Specifically, the embodiment of the present invention extracts the spectral data between the corrected fluctuation segments and extracts the peak value of the corrected baseline drift fluctuation segment based on the peak value of the corrected baseline drift fluctuation segment. , and combined with the fluctuation segments on both sides of the corrected baseline drift fluctuation segment m 、 The peak of the baseline drift fluctuation segment is determined to determine the changing trend of the adjacent baseline drift fluctuation segments.

[0065] Furthermore, the embodiment of the present invention specifically uses the following formula to calculate the variation trend of the adjacent baseline drift fluctuation segments:

[0066]

[0067] In the above formula, It represents the changing trend of the adjacent baseline drift fluctuation segments before and after the corrected baseline drift fluctuation segment m. Indicates the corrected signal intensity of the peak value of the current baseline drift fluctuation segment m. It represents the signal intensity of the peak value of the previous baseline drift fluctuation segment m-1 adjacent to the corrected current baseline drift fluctuation segment m. It represents the signal intensity of the peak value of the next baseline drift fluctuation segment m+1 adjacent to the corrected current baseline drift fluctuation segment m. 、 They are respectively the ratios of the corrected signal intensity of the peak value of the current baseline drift fluctuation segment m to the signal intensity of the peak values of the preceding and following adjacent fluctuation segments. It is the ratio difference, which indicates the change trend between adjacent fluctuation segments. The larger the value is, the more positive it is, and the overall fluctuation segment shows an increasing trend, otherwise it shows a decreasing trend.

[0068] Furthermore, an embodiment of the present invention traverses the change trends of each detection position in each area, and determines the identity of the change trends between different detection positions by obtaining the change trends between the detection positions. As an optional embodiment of the present invention, determining the identity of the change trends between different detection positions based on the change trends of each adjacent baseline drift fluctuation segment of different detection positions includes: superimposing the change trends of each adjacent baseline drift fluctuation segment of each detection position to obtain a second superimposed value of each detection position; calculating a second product between the second superimposed values of different detection positions; and performing a sign extraction process on the second product using a sign extraction function to obtain the identity of the change trends between different detection positions.

[0069] Specifically, the embodiment of the present invention uses the following formula to calculate the identity of the change trend between different detection positions:

[0070]

[0071] In the above formula, Indicates the identity of the change trend between different detection positions. Indicates the superposition value of the change trend of each adjacent baseline drift fluctuation segment at the nth detection position. Indicates the superposition value of the change trend of each adjacent baseline drift fluctuation segment at the (n+1)th detection position. To detect the product of the trend of change between positions, use Character function pair Perform character extraction processing.

[0072] Furthermore, the embodiment of the present invention traverses all detection positions. When the spectral curves of the two corresponding detection positions have the same changing trend, the two detection positions are divided into one detection group. For example, taking the current detection position as an example, if there are N detection positions with the same spectral curves as the current detection position, The N detection positions are divided into a detection group with the current detection position. That is, each detection group includes at least two detection positions.

[0073] Furthermore, as an optional embodiment of the present invention, based on the changing trends of adjacent fluctuation segments of different detection positions in each detection group and the positional relationship between different detection positions, determining the curve extension slope between different detection positions in each detection group includes: calculating the fifth difference between the second superposition values of different detection positions, and calculating the sixth ratio between the fifth difference and the positional relationship between different detection positions; superimposing each sixth ratio to obtain a third superposition value; calculating the fifth difference between the number of detection positions and a predetermined value, and determining the seventh ratio between the third superposition value and the fifth difference as the curve extension slope.

[0074] Specifically, the embodiment of the present invention uses the following formula to calculate the curve extension slope between different detection positions in each detection group:

[0075] Y=

[0076] In the above formula, Y represents the slope of the curve extension between different detection positions in the detection group. Indicates the superposition value of the change trend of each adjacent baseline drift fluctuation segment at the nth detection position in the detection group. Indicates the superposition value of the change trend of each adjacent baseline drift fluctuation segment at the (n+1)th detection position in the detection group. It represents the positional relationship between the nth detection position and the n+1th detection position, that is, the distance between the two. Indicates the number of detection positions in the detection group.

[0077] Furthermore, the embodiment of the present invention adopts The detection group with the minimum value of the extended slope of the function (minimum value function) screening curve is the analysis detection group. .

[0078] Furthermore, based on the spectral data in the above-screened analysis and detection group, the absorbance obtained according to the above embodiment , according to the formula of absorbance: Beer-Lambert law , and then obtain the relative thickness at the detection position n , and then obtain the thickness weight of the detection position ( to a minimum value to prevent the denominator from being 0).

[0079] Furthermore, the embodiment of the present invention performs a secondary correction on the corrected baseline position based on the thickness weight, specifically using the formula Make a second correction, is the relative baseline position, is the thickness weight, To correct the baseline position.

[0080] Furthermore, the embodiment of the present invention will be relative to the baseline position The overall spectral data of the blood smear was corrected by introducing it into the existing Spectrum FL software model, and the second-corrected overall spectral data was placed into the Spectral Residual model for residual analysis. The residual was extracted and the pathological signal was retained through wavelet decomposition to reconstruct the final second-corrected overall spectral data.

[0081] Step S105 : Detecting the quality of the blood smear using the second corrected overall spectrum data.

[0082] Specifically, after obtaining the final second-corrected overall spectral data through the above steps, the embodiment of the present invention introduces the final second-corrected overall spectral data into a Raman spectroscopy model, analyzes the morphology of red blood cells and the integrity of the blood smear to detect the quality of the blood smear, and transmits the test results to the tester.

[0083] The embodiment of the present invention can perform an initial correction on the spectral signal of each detection position and the overall spectral data based on the baseline drift of the spectral signal of a single detection position in different areas of the blood smear, and then perform a secondary correction on the first corrected overall spectral data after the initial correction in combination with the baseline drift and peak change of the corrected spectral signal of each detection position in different areas. While eliminating the baseline drift, it avoids the problem of using the first-order derivative method to amplify the high-frequency noise in the spectral signal and weaken the spectral characteristic peak, thereby avoiding the loss of key biochemical information in the cell stacking area, improving the correction reliability of the spectral data, and improving the accuracy of the spectral data finally obtained, thereby improving the detection accuracy and reliability of the blood smear quality detection.

[0084] Example 2:

[0085] Corresponding to the intelligent blood smear quality detection method for clinical laboratory provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides an intelligent blood smear quality detection device for clinical laboratory, which is used to execute the above intelligent blood smear quality detection method for clinical laboratory. Figure 3 A schematic diagram of a blood smear quality intelligent detection device for a laboratory is provided in accordance with an embodiment of the present invention. Figure 3 As shown. The intelligent blood smear quality detection device for laboratory use may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and memory 302. The memory 302 is used to store computer programs that can be run on the processor 301. The processor 301 is used to execute the program stored in the memory 302 to achieve the above Figure 1The various steps in the method embodiment are described in detail. Memory 302 may be either a temporary or permanent storage device. The application stored in memory 302 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for the intelligent blood smear quality detection device for laboratory use.

[0086] Furthermore, the processor 301 can be configured to communicate with the memory 302, so that the intelligent blood smear quality detection device for clinical laboratory use executes a series of computer-executable instructions stored in the memory 302. The intelligent blood smear quality detection device for clinical laboratory use can also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0087] Specifically in this embodiment, the blood smear quality intelligent detection device for the laboratory department includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to achieve the above Figure 1 The various steps in the method embodiment have the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described again here.

[0088] It should be noted that the intelligent blood smear quality detection device for clinical laboratory provided by the embodiment of the present invention and the intelligent blood smear quality detection method for clinical laboratory provided by the embodiment of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned intelligent blood smear quality detection method for clinical laboratory, and has the same or similar beneficial effects, and the repeated parts will not be repeated.

[0089] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0091] The embodiment of the present invention further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes Figure 1The methods disclosed in the illustrated embodiments implement the functions and beneficial effects of the various methods in the foregoing method embodiments, which will not be described in detail here.

[0092] Among them, the computer readable storage medium includes read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

Claims

1. An intelligent blood smear quality detection method for clinical laboratory use, characterized in that: include: Acquiring overall spectral data of the blood smear and spectral signals of various detection positions in different regions of the blood smear; Determining the baseline drift fluctuation section and the normal fluctuation section of the spectral signal at each detection position according to the signal strength of the extreme value points of the spectral signal at each detection position in different regions and the baseline position where the extreme value points are located; Based on the baseline position of the normal fluctuation segment and the position of the peak of the normal fluctuation segment within the detection position, performing an initial correction on the spectral signal of the detection position and the overall spectral data to obtain a corrected spectral signal and first corrected overall spectral data; Performing a secondary correction on the first corrected overall spectral data using the peak values of the baseline drift fluctuation segments before and after the current baseline drift fluctuation segment and the peak value of the current baseline drift fluctuation segment in the corrected spectral signals at each detection position to obtain final second corrected overall spectral data; The quality of the blood smear is detected using the second corrected overall spectral data.

2. The intelligent blood smear quality detection method for clinical laboratory use according to claim 1, characterized in that: Determining the baseline drift fluctuation section and the normal fluctuation section of the spectral signal at each detection position according to the signal strength of the extreme value point of the spectral signal at each detection position in different regions and the baseline position where the extreme value point is located includes: Using the baseline positions of the interval extreme value points in the spectral signals of each detection position in each area as the fluctuation start and end positions, and using the spectral curve segments between the fluctuation start and end positions as the fluctuation segments of the spectral signals of each detection position; determining a baseline drift parameter at the peak point of the current fluctuation segment based on a second baseline position at the peak point of a fluctuation segment adjacent to the current fluctuation segment and the first baseline position of the current fluctuation segment; determining a peak signal drift parameter at the peak point of the current fluctuation segment based on a first signal strength of a peak point of a fluctuation segment adjacent to the current fluctuation segment and a second signal strength of the peak point of the current fluctuation segment; Determine a first ratio between the baseline drift parameter and the peak signal drift parameter as spectrum curve drift information of the current fluctuation segment; When the spectrum curve drift information of the plurality of continuous fluctuation segments is positive, the plurality of continuous fluctuation segments are determined to be baseline drift fluctuation segments; otherwise, they are determined to be normal fluctuation segments.

3. The intelligent blood smear quality detection method for clinical laboratory use according to claim 2, characterized in that: Determining the baseline drift parameter at the peak point of the current fluctuation segment based on the second baseline position at the peak point of the fluctuation segment adjacent to the current fluctuation segment and the first baseline position of the current fluctuation segment includes: Calculating a first difference between a second baseline position at a peak point of a subsequent fluctuation segment adjacent to the current fluctuation segment and the first baseline position; A second ratio between the first difference value and the first baseline position is determined as the baseline drift parameter.

4. The intelligent blood smear quality detection method for clinical laboratory use according to claim 2, characterized in that: Determining the peak signal drift parameter at the peak point of the current fluctuation segment based on the first signal strength of the peak point of the fluctuation segment adjacent to the current fluctuation segment and the second signal strength of the peak point of the current fluctuation segment includes: Calculating a second difference between the first signal strength and the second signal strength at a peak point of a subsequent fluctuation segment adjacent to the current fluctuation segment; A third ratio between the second difference and the second signal strength is determined as the peak signal drift parameter.

5. The intelligent blood smear quality detection method for clinical laboratory use according to claim 1, characterized in that: The performing of an initial correction on the spectral signal at the detection position and the overall spectral data based on the baseline position of the normal fluctuation segment and the position of the peak of the normal fluctuation segment within the detection position to obtain the corrected spectral signal and the first corrected overall spectral data includes: Determining a base-to-peak relative coefficient between the baseline position in the normal fluctuation segment and the position of the peak of the normal fluctuation segment based on the baseline position of the normal fluctuation segment and the position of the peak of the normal fluctuation segment; determining a baseline drift correction coefficient according to a first time interval between two ends of the normal fluctuation segment, a second time interval between two ends of the baseline drift fluctuation segment, and the base peak relative coefficient; Correcting the baseline position of the baseline drift fluctuation segment using the baseline drift correction coefficient to obtain a corrected baseline position of the baseline drift fluctuation segment; Based on the corrected baseline positions of the baseline drift fluctuation segments of the respective detection positions, the spectral signals of the corresponding detection positions are corrected and the overall spectral data of the blood smear are initially corrected to obtain corrected spectral signals and first corrected overall spectral data.

6. The intelligent blood smear quality detection method for clinical laboratory use according to claim 5, characterized in that: Determining the base-peak relative coefficient between the baseline position in the normal fluctuation segment and the position of the peak of the normal fluctuation segment based on the baseline position of the normal fluctuation segment and the position of the peak of the normal fluctuation segment includes: calculating a third difference between a position of a peak value of each normal fluctuation segment and a baseline position of the normal fluctuation segment, and superimposing the third differences to obtain a first superimposed value; A fourth ratio between the third difference value of each normal fluctuation segment and the first superposition value is determined as a base-peak relative coefficient between a baseline position in the normal fluctuation segment and a position where a peak value of the normal fluctuation segment is located.

7. The intelligent blood smear quality detection method for clinical laboratory use according to claim 5, characterized in that: Determining the baseline drift correction coefficient according to the first time interval between the two ends of the normal fluctuation segment, the second time interval between the two ends of the baseline drift fluctuation segment, and the base peak relative coefficient includes: calculating a fifth ratio between the second time interval and the average of the first time interval, and calculating an absolute value of a fourth difference between the fifth ratio and a predetermined value; A first product between the absolute value of the fourth difference and the base peak relative coefficient is calculated, and the first product is normalized to obtain the baseline drift correction coefficient.

8. The intelligent blood smear quality detection method for clinical laboratory use according to claim 5, characterized in that: The method of performing secondary correction on the first corrected overall spectral data by using the peak values of the baseline drift fluctuation segments before and after the current baseline drift fluctuation segment and the peak value of the current baseline drift fluctuation segment in the corrected spectral signals at each detection position to obtain the final second corrected overall spectral data includes: Determine the variation trend of the baseline drift fluctuation segments adjacent to and preceding the current baseline drift fluctuation segment using the peak values of the baseline drift fluctuation segments in the corrected spectrum signals at each detection position and the peak value of the current baseline drift fluctuation segment; Determining the identity of the changing trends between different detection positions according to the changing trends of adjacent baseline drift fluctuation segments at different detection positions; Grouping the detection positions based on the identity of the change trend to obtain multiple detection groups; Determining, based on the variation trends of adjacent fluctuation segments at different detection positions in each detection group and the positional relationship between the different detection positions, a slope value of the curve extension between the different detection positions in each detection group; The detection group corresponding to the minimum value of the extended slope of the curve is used as the analysis detection group of the blood smear; Determining the thickness weight of each detection position by using the relative thickness at each detection position in the analysis detection group; Performing a secondary correction on the corrected baseline position based on the thickness weight to obtain a relative baseline position of each detection position in the analysis and detection group; The first corrected overall spectral data is corrected twice based on the relative baseline position of each detection position in the analysis and detection group to obtain final second corrected overall spectral data.

9. The intelligent blood smear quality detection method for clinical laboratory use according to claim 8, characterized in that: Determining the identity of the change trends between different detection positions according to the change trends of adjacent baseline drift fluctuation segments at different detection positions includes: Determining a superposition value of the variation trends of adjacent baseline drift fluctuation segments at each detection position to obtain a second superposition value at each detection position; calculating a second product between the second superposition values at different detection positions; The second product is subjected to a sign-taking process using a sign-taking function to obtain the identity of the change trends between the different detection positions.

10. The intelligent blood smear quality detection method for clinical laboratory use according to claim 9, characterized in that: Determining the curve extension slope between different detection positions in each detection group based on the change trend of each adjacent fluctuation segment at different detection positions in each detection group and the positional relationship between different detection positions includes: calculating a fifth difference between the second superposition values of different detection positions, and calculating a sixth ratio between the fifth difference and the positional relationship between the different detection positions; superimposing the sixth ratios to obtain a third superimposed value; A fifth difference between the number of the detection positions and a predetermined value is calculated, and a seventh ratio between the third superposition value and the fifth difference is determined as the curve extension slope.

Images