Household sperm DFI detection system and method

Abstract

The invention relates to the technical field of medical detection, in particular to a household sperm DFI detection system and method. The invention aims to solve the problems in the background technology, and provides a household sperm DFI detection system and method, and is characterized in that the detection system comprises a hardware system, an AI algorithm and a mobile phone APP; the hardware system comprises a micro-fluidic chip, an optical module and a control module, the optical module comprises an objective lens, a CMOS sensor and a light source, and the control module realizes data transmission and equipment control based on an ARM processor; the AI algorithm comprises preprocessing, segmentation and identification, and feature extraction. The flow cytometer has the beneficial effects that 1, a miniaturized design is adopted: the volume of the flow cytometer is only 15cm * 8cm * 5cm, the weight is 300g, and the cost is 1 / 50 of that of a traditional flow cytometer; 2, an anti-interference technology: adding an RNA enzyme digestion step before dyeing to eliminate the interference of RNA on a detection result; and 3, AI optimization: introducing an attention mechanism to improve the small target (fragment) recognition capability, wherein the DFI calculation error is less than or equal to 2%.

Description

Technical Field

[0001] This invention relates to the field of medical testing technology, specifically to a home-use sperm DFI testing system and method. Background Technology

[0002] Traditional sperm DFI detection relies on flow cytometry (such as the Beckman Coulter FC500), which has a large device size (approximately 1.5m). 3 Existing home testing equipment suffers from drawbacks such as high cost (≥500,000 RMB) and complex operation, failing to meet the needs of home use. Existing home testing equipment (such as microscope + mobile phone solutions) has the following shortcomings:

[0003] 1. Insufficient detection accuracy: Relying on manual observation, the DFI calculation error is as high as 15%-20%;

[0004] 2. High operational threshold: Requires professional personnel to perform sample staining, image acquisition, and data analysis;

[0005] 3. Limited functionality: It can only provide qualitative results and lacks trend analysis and anomaly warning functions;

[0006] Furthermore, existing technologies have not solved the problem of RNA interference with detection results. For example, Zhejiang Xingbo Biotechnology's patent (CN202010196442.3) points out that sperm RNA can bind to acridine orange to produce false positive signals, leading to higher DFI detection values. Summary of the Invention

[0007] The purpose of this invention is to solve the problems in the background art mentioned above, and to provide a home-use sperm DFI detection system and method, characterized in that the detection system includes a hardware system, an AI algorithm, and a mobile APP;

[0008] The hardware system includes a microfluidic chip, an optical module, and a control module. The optical module includes an objective lens, a CMOS sensor, and a light source. The control module is based on an ARM processor to realize data transmission and device control.

[0009] The AI ​​algorithm includes preprocessing, segmentation and recognition, and feature extraction;

[0010] The mobile app includes AR guidance, real-time analysis, and data management.

[0011] A home-use sperm DFI detection method, characterized by comprising:

[0012] S1: Sample collection and staining: Semen and acridine orange staining agent are mixed using a microfluidic chip;

[0013] S2: Image Acquisition: The optical module acquires sperm fluorescence images;

[0014] S3: AI Analysis: The mobile app uses a local model to calculate the DFI index;

[0015] S4: Results Presentation: AR guides the operation process, generates a test report, and stores it in the cloud.

[0016] Preferably, the microfluidic chip is made of PDMS material and includes a sample chamber, a staining channel and a waste liquid chamber, with a built-in micro Peltier module to maintain a reaction environment of 37℃±0.5℃.

[0017] Preferably, the AI ​​algorithm includes an improved U-Net model and an SVM classifier to achieve the segmentation of sperm cell nuclei and fragments and DFI calculation.

[0018] The beneficial effects of this invention are:

[0019] 1. Miniaturized design: The device measures only 15cm × 8cm × 5cm and weighs 300g, with a cost that is 1 / 50th that of a traditional flow cytometer;

[0020] 2. Anti-interference technology: An RNase digestion step is added before staining to eliminate the interference of RNA on the detection results;

[0021] 3. AI Optimization: An attention mechanism is introduced to improve the recognition ability of small targets (fragments), and the DFI calculation error is ≤2%.

[0022] Obviously, based on the above description of the present invention, and according to common technical knowledge and conventional methods in the field, various other modifications, substitutions or alterations can be made without departing from the basic technical concept of the present invention.

[0023] The following detailed embodiments further illustrate the above-described content of the present invention. However, this should not be construed as limiting the scope of the present invention to the following examples. All technologies implemented based on the above-described content of the present invention fall within the scope of the present invention. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0025] The present invention is illustrated below with specific embodiments, which are not intended to limit the scope of the invention.

[0026] like Figure 1 As shown, a home-use sperm DFI detection system and method, the hardware system includes:

[0027] Microfluidic chip: Made of PDMS material, it includes a sample chamber (50μL), a staining channel (integrated acridine orange reagent pack) and a waste liquid chamber. It achieves 1:1 mixing of semen and staining agent (0.1mg / mL acridine orange) through capillary action, and has a built-in micro Peltier module to maintain a reaction environment of 37℃±0.5℃.

[0028] Optical module: 100x objective lens + 5-megapixel CMOS sensor, combined with LED ring light source (530nm±10nm) to achieve fluorescence imaging of sperm cell nuclei;

[0029] Control module: Based on ARM Cortex-M7 processor, supports Bluetooth 5.0 / Wi-Fi data transmission, and has a built-in lithium battery (3.7V / 2000mAh) that can work continuously for 4 hours;

[0030] AI algorithms:

[0031] Preprocessing: Adaptive histogram equalization (AHE) enhances contrast, and median filtering removes noise;

[0032] Segmentation and Recognition: An improved U-Net model (with the addition of the CBAM attention module) achieves pixel-level segmentation of sperm cell nuclei and fragments with an accuracy of ≥95%;

[0033] Feature extraction: 12 features, including cell nucleus aspect ratio, ellipticity, and fluorescence intensity distribution, were extracted and combined with an SVM classifier to calculate the DFI index;

[0034] Mobile App:

[0035] AR guidance: Augmented reality animation guides users through the sample collection, staining, and loading process, increasing the success rate from 65% to 91%.

[0036] Real-time analysis: Run TensorFlow Lite models (≤10MB) locally and generate a DFI report within 15 seconds;

[0037] Data management: cloud storage (Alibaba Cloud / Tencent Cloud), historical trend analysis, and outlier alerts (push notifications when DFI > 30%). Detailed implementation method:

[0039] Hardware System

[0040] Microfluidic chip manufacturing: PDMS material is shaped using soft photolithography, and a one-way valve is integrated to prevent sample backflow, ensuring single-use and avoiding cross-contamination;

[0041] Optical system calibration: Droplet delay time is optimized using BDAccudrop technology to ensure laser focusing accuracy;

[0042] AI model training

[0043] Data source: 2000 clinical samples (DFI range 5%-80%) obtained in cooperation with tertiary hospitals, including normal sperm (40%), mild fragmentation (30%), and severe fragmentation (30%);

[0044] Training parameters: ResNet-50 transfer learning, FocalLoss (α=0.25, γ=2), Adam optimizer (lr=1e-4);

[0045] Performance metrics: Accuracy 92.3% (validation set), Sensitivity 91.5% (DFI>30%), Specificity 93.7% (DFI≤30%);

[0046] Mobile APP integration

[0047] Cross-platform development: Uses the Flutter framework, compatible with iOS 13+ and Android 8.0+;

[0048] Image processing: OpenCV implements CLAHE enhancement, and TensorFlow Lite supports multi-threaded parallel computing;

[0049] Privacy protection: AES-256 encryption for local data storage, TLS 1.3 protocol for cloud data transmission.

[0050] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0051] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

[0052] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A home-use sperm DFI detection system, characterized in that, The detection system includes a hardware system, AI algorithms, and a mobile app; The hardware system includes a microfluidic chip, an optical module, and a control module. The optical module includes an objective lens, a CMOS sensor, and a light source. The control module is based on an ARM processor to realize data transmission and device control. The AI ​​algorithm includes preprocessing, segmentation and recognition, and feature extraction; The mobile app includes AR guidance, real-time analysis, and data management.

2. A home-use sperm DFI detection method, characterized in that, include: S1: Sample collection and staining: Semen and acridine orange staining agent are mixed using a microfluidic chip; S2: Image Acquisition: The optical module acquires sperm fluorescence images; S3: AI Analysis: The mobile app uses a local model to calculate the DFI index; S4: Results Presentation: AR guides the operation process, generates a test report, and stores it in the cloud.

3. The home-use sperm DFI detection system according to claim 1, characterized in that, The microfluidic chip is made of PDMS material and includes a sample chamber, a staining channel and a waste liquid chamber. It has a built-in micro Peltier module to maintain a reaction environment of 37℃±0.5℃.

4. The home-use sperm DFI detection system according to claim 1, characterized in that, The AI ​​algorithm includes an improved U-Net model and an SVM classifier to achieve the segmentation of sperm cell nuclei and fragments and DFI calculation.

Images