Puncture needle navigation system based on cnb catapult mechanism

Abstract

The application discloses a puncture needle navigation system based on CNB ejection mechanism and belongs to the technical field of ultrasonic auxiliary diagnosis. The system establishes a mathematical model of the ejection process through an ejection trajectory calculation function, including physical coordinate conversion, direction vector calculation, ejection endpoint calculation and target distance calculation. The physical coordinate conversion converts the needle tip position and the target center from a pixel coordinate system into a physical coordinate system. The direction vector calculation calculates the direction vector of the puncture needle based on the needle tip angle, converts the angle from degrees to radians, and obtains the unit vector components in the x and y directions through trigonometric function calculation. The direction vector calculation is used for the conversion of the angle to the direction vector. The ejection endpoint calculation calculates the physical coordinates of the ejection endpoint through the physical coordinates of the needle tip starting position and the ejection distance. The target distance calculation is used for calculating the straight line distance from the needle tip to the target center. Therefore, the millimeter-level trajectory calculation precision is realized through the accurate mathematical modeling and high-precision numerical calculation, and a reliable mathematical basis is provided for the CNB ejection operation diagnosis.

Description

Technical Field

[0001] This invention relates to the field of ultrasound-assisted diagnostic technology, and in particular to a puncture needle navigation system based on the CNB ejection mechanism. Background Technology

[0002] The CNB ejection mechanism is the core technology of the cutting-type automatic biopsy gun used in ultrasound-guided puncture biopsy. It achieves tissue cutting or tissue sampling through high-speed ejection with a built-in spring for diagnosis.

[0003] During the ejection of the puncture needle, the ejection distance is predetermined and cannot be adjusted in real time after firing. At the same time, the corresponding firing trajectory is also predetermined. Therefore, the accuracy of the ejection trajectory calculation and the ejection safety assessment and risk management of the CNB ejection mechanism are essential core technologies. Summary of the Invention

[0004] This application provides a puncture needle navigation system based on the CNB ejection mechanism, which provides a reliable mathematical basis for CNB ejection operations. The calculation results are used to control the ejection distance setting, needle insertion angle setting, or needle insertion point selection of the CNB device before firing, thereby changing the actual physical puncture path.

[0005] This application provides a system that establishes a mathematical model of the ejection process through an ejection trajectory calculation function, including:

[0006] Physical coordinate transformation converts the needle tip position and target center from the pixel coordinate system to the physical coordinate system. The transformation ratio is determined by the pixel spacing parameter. Then, the direction vector of the puncture needle is calculated based on the needle tip angle, converting the angle from degrees to radians. The unit vector components in the x and y directions are calculated using trigonometric functions.

[0007] The direction vector is calculated using the following formulas: angle_rad = needle_angle × π / 180; direction_x = cos(angle_rad); direction_y = sin(angle_rad), where angle_rad is the angle of the needle tip in radians, needle_angle is the angle of the needle tip, π is pi, direction_x is the unit vector component in the x-direction, direction_y is the unit vector component in the y-direction, and cos and sin are trigonometric functions used for converting angles to direction vectors.

[0008] The calculation formula for the ejection endpoint is: fire_end_x = tip_x + direction_x × throw_distance; fire_end_y = tip_y + direction_y × throw_distance, where fire_end_x, fire_end_y are the physical coordinates of the ejection endpoint, tip_x, tip_y are the physical coordinates of the starting position of the needle tip, and throw_distance is the ejection distance;

[0009] Target distance calculation includes axial distance and lateral offset:

[0010] d_along=(target_x-tip_x)×direction_x+(target_y-tip_y)×direction_y;

[0011] d_cross=|(target_x-tip_x)×direction_y-(target_y-tip_y)×direction_x|;

[0012] Where d_along is the axial distance of the target relative to the needle tip along the needle insertion direction, and d_cross is the lateral offset perpendicular to the needle insertion direction; when d_cross≤target_radius and d_along≥0, the ejection trajectory is considered to have geometric feasibility of hitting the target.

[0013] Meanwhile, a reference distance distance_to_target=√[(target_x-tip_x)²+(target_y-tip_y)²] is defined to represent the straight-line distance from the needle tip to the center of the target; target_x and target_y are the physical coordinates of the target center, and target_radius is the equivalent radius of the target area, which is output by the detection module or preset.

[0014] In one possible implementation, the system establishes a geometric distance calculation algorithm based on parameterized line equations, with the calculation formula as follows:

[0015] d1 = √[(px - projection_x)² + (py - projection_y)²], where:

[0016] d1 is the shortest distance from the point to be evaluated to the line segment;

[0017] px and py are the coordinates of the point to be evaluated (the center point of the anatomical structure);

[0018] projection_x = x1 + t × (x2 - x1), projection_y = y1 + t × (y2 - y1), where x1 and y1 are the coordinates of the starting point of the line segment, x2 and y2 are the coordinates of the ending point of the line segment, and t is the projection parameter, which represents the relative position of the projection point on the line segment. t = max(0, min(1, [(px - x1) × (x2 - x1) + (py - y1) × (y2 - y1)] / line_length²)), where the value of t is in the range of 0-1. line_length is the length of the line segment, line_length = √[(x2 - x1)² + (y2 - y1)²]. max and min are the maximum and minimum value functions, respectively, to ensure that the projection point is within the range of the line segment.

[0019] The clearance distance from the anatomical structure to the ejection trajectory is calculated using the following steps:

[0020] 1. First, calculate the shortest distance from the projectile trajectory line segment to the center point of the anatomical structure: distance_center = √[(px-projection_x)²+(py-projection_y)²];

[0021] 2. The boundary of the anatomical structure is represented by its geometric radius, structure_radius. First, the boundary safety distance d_boundary = distance_center − structure_radius is calculated, and then the non-negative gap distance distance_to_trajectory = max(0, d_boundary) is calculated. When d_boundary ≤ 0, it indicates that the trajectory intersects or contacts (or intrudes into) the structure boundary. When d_boundary > 0, it indicates that the minimum gap between the trajectory and the structure boundary is d_boundary. When the boundary of the anatomical structure is represented by the true boundary of the segmentation mask, d_boundary can also be calculated from the "signed minimum distance from the ejection trajectory to the structure boundary". The above d_boundary = distance_center − structure_radius is a special case when using an equivalent circle (center point + geometric radius) approximation.

[0022] Where projection_x and projection_y are the projected coordinates of the center of the anatomical structure onto the projectile trajectory line segment. This calculation method ensures the minimum clearance distance between the projectile trajectory and the actual boundary of the anatomical structure, providing an accurate geometric basis for risk classification and safety assessment.

[0023] This system abstracts the anatomical structure into a region with a center point and a geometric radius. distance_to_trajectory represents the minimum gap distance from the ejection trajectory to the boundary of this region; the critical / warning threshold is the safety margin requirement for this gap distance.

[0024] The risk classification threshold is a threshold for the aforementioned gap distance distance_to_trajectory, where critical_clearance and warning_clearance are threshold parameters corresponding to the structure type, which can be expressed as critical_clearance(type), warning_clearance(type), or preset values ​​from the threshold table: distance_to_trajectory≤critical_clearance(type) is a critical risk; critical_clearance(type)<distance_to_trajectory≤warning_clearance(type) is a warning; distance_to_trajectory>warning_clearance(type) is safe.

[0025] The anatomical structure detection results can be provided by the detection module integrated into this system or by an external detection module. This invention does not necessarily limit the detection algorithm itself. The geometric radius of the anatomical structure (structure_radius) can be output by the detection module (e.g., calculated based on the segmented contour) or, if unavailable, preset a default value according to the target category. This invention does not necessarily limit the radius acquisition method. The critical / warning thresholds (safety margin requirements) are preset and defined according to the medical safety requirements of seven types of detection targets, specifically configured as follows:

[0026] Artery: critical_clearance 5.0mm, warning_clearance 8.0mm, classified as a first-level contraindication zone, with the highest risk priority of 9;

[0027] Vein: critical_clearance 3.0mm, warning_clearance 5.0mm, as a secondary contraindication area, with a high risk priority of 7;

[0028] Esophagus: critical_clearance 3.0mm, warning_clearance 5.0mm, as a secondary contraindication area, with a high risk priority of 7;

[0029] Diaphragm: critical_clearance 2.0mm, warning_clearance 4.0mm, as a secondary contraindication zone, with a medium risk priority of 6;

[0030] Skeleton: critical_clearance 0.0mm, warning_clearance 1.0mm, serving as a physical obstacle zone with a physical blocking priority of 8;

[0031] Lesion: critical_clearance 0.0mm, warning_clearance 0.0mm, as the target area, no need to avoid it at all, priority 1;

[0032] - Lymph nodes: critical_clearance 0.0mm, warning_clearance 0.0mm, as the target area, no need to avoid them at all, priority 1;

[0033] The acquisition of the structure's geometric radius (structure_radius) and the setting of critical / warning thresholds can be based on medical clinical experience and safe operating procedures. The aforementioned critical / warning thresholds are exemplary safety parameters and can be adjusted according to different clinical guidelines, equipment models, or application scenarios; among them, arteries are given a larger safety margin requirement due to the serious consequences of damage, while bones are given a threshold boundary where contact with them is considered a risk due to their physical impermeability.

[0034] In one possible implementation, the graded risk assessment model is a multi-level risk assessment model based on distance thresholds. The system establishes risk threshold configurations for seven types of anatomical structures and performs risk assessment based on the shortest distance from the ejection trajectory to the anatomical structure.

[0035] Artery, Category 0, Critical Risk Threshold 5.0 mm, Warning Threshold 8.0 mm, Priority 9 (Highest Risk).

[0036] Vein, Category 1, critical risk threshold 3.0mm, warning threshold 5.0mm, priority 7 (high risk).

[0037] Esophagus, Category 5, Critical Risk Threshold 3.0 mm, Warning Threshold 5.0 mm, Priority 7 (High Risk);

[0038] Diaphragm, Category 6, Critical Risk Threshold 2.0mm, Warning Threshold 4.0mm, Priority 6 (Medium Risk).

[0039] Skeleton, Category 3, Critical Risk Threshold 0.0mm, Warning Threshold 1.0mm, Priority 8 (Physical Obstacle).

[0040] Lesion, Category 4, danger threshold 0.0mm, is a puncture target, no need to avoid it, warning threshold 0.0mm (target area).

[0041] Lymph node, Category 2, danger threshold 0.0 mm, is a puncture target, no avoidance required, warning threshold 0.0 mm (target area).

[0042] In one possible implementation, the system establishes a multi-dimensional safety assessment framework including an overall safety score and a critical risk list. The critical risk list is a collection of all anatomical structures that reach a critical risk level detected by the system during the projectile trajectory safety assessment. The determination rule for the critical risk list is: when the gap distance between the anatomical structure and the projectile trajectory is less than the critical risk threshold of the structure, the structure is added to the critical risk list; an empty critical risk list indicates no critical risk, while a non-empty list indicates the existence of critical risks that need to be addressed. The overall safety score adopts a standardized scoring system from 1.0 to 0.0, where 1.0 represents the safest state and 0.0 represents the most dangerous state. The system automatically triggers an adjustment suggestion generation process based on the status of the critical risks in the critical risk list. The adjustment suggestions include adjusting the projectile distance, changing the needle insertion angle, and selecting different needle insertion points. The system uses a cumulative penalty model to calculate the overall safety score. The base score is 1.0 in the safest state, representing no risk, and the penalty coefficient is adjusted according to the detected risk level.

[0043] Overall safety score = base score × penalty;

[0044] Penalty is the penalty coefficient, which is set according to the risk level: critical risk penalty = 0.1, warning risk penalty = 0.7, and safety penalty = 1.0. When multiple risks exist at the same time, the penalty is the minimum value of the penalty coefficient of each risk.

[0045] In one possible implementation, the adjustment of the ejection distance specifically involves: the system sorting the set of feasible ejection distances that meet the hit constraint and safety threshold constraint from the adjustable ejection distance options based on a preset priority sorting rule, and selecting the preferred scheme; when a critical risk occurs, the shorter feasible ejection distance is preferred. In the set of feasible ejection distances, the system prioritizes the following sorting rules: (1) Hit geometric feasibility priority: the scheme that meets the hit geometric constraint is preferred, where the scheme under the optimal sampling condition has a higher priority than the general hit condition; (2) Safety level priority: under the premise of meeting the hit constraint, the scheme with a larger safety margin (corresponding to a higher overall safety score) is preferred; (3) Distance preference rule: under the same conditions, the scheme with an ejection distance closer to the preset standard distance of 22.0 mm is preferred, where the distance preference is defined as: preference = 1.0−|current ejection distance−22.0| / 22.0.

[0046] In one possible implementation, the system establishes a comprehensive scoring model for CNB ejection configurations to perform multi-dimensional comprehensive quality evaluation of different ejection configuration schemes while meeting safety constraints. This comprehensive scoring model, together with the cumulative penalty model, forms a two-layer evaluation architecture.

[0047] The first layer is the overall safety scoring system, which uses a cumulative penalty model to evaluate the absolute safety of the ejection trajectory and serves as a safety constraint for configuration optimization.

[0048] The second layer is the CNB comprehensive scoring system, which comprehensively evaluates the target hit accuracy, safety margin, ease of operation, and clinical preference of the configuration scheme while meeting safety constraints.

[0049] The comprehensive scoring model under the multi-dimensional comprehensive quality assessment adopts a multi-factor weighted summation method, and the calculation formula is as follows:

[0050] CNB Comprehensive Score = Target Score × 0.3 + Safety Score × 0.4 + Distance Factor × 0.2 + Angle Factor × 0.1; where:

[0051] Target score: Based on the accuracy of the ejection trajectory in hitting the target area, the value ranges from 0 to 1. When the ejection trajectory completely passes through the target area and the sampling length meets the standard, the score is 1.0; when it partially hits, the score is 0.3-0.7; and when it completely deviates, the score is 0.1.

[0052] Safety score: The overall safety score calculated using the cumulative penalty model, with a value range of 0-1, is output from the overall safety score under the standardized scoring system;

[0053] Distance factor: The score is based on the operating distance from the needle insertion point to the target center. The value range is 0-1. The ideal operating distance is 50mm and the score is 1.0. The greater the distance deviates from the ideal value, the lower the score.

[0054] Angle factor: A clinical preference score based on the needle insertion angle, with a value range of 0-1. The score is 1.0 when the needle is inserted perpendicularly at 90 degrees, and the larger the angle deviates from 90 degrees, the lower the score.

[0055] The system provides four scoring modes based on different optimization scenarios:

[0056] (1) Comprehensive mode: Uses a complete four-factor formula to comprehensively evaluate the overall configuration of the needle entry point and angle;

[0057] (2) Ejection distance optimization mode: Only target score, safety score and distance factor are used, and the weights are renormalized to 0.333, 0.444 or 0.222, which are used to optimize the ejection distance selection under the premise of fixed needle entry point and angle;

[0058] (3) Angle optimization mode: Only target score, safety score and angle factor are used, and the weights are renormalized to 0.375, 0.500 or 0.125, which is used to optimize the needle entry angle under the premise of fixed needle entry point;

[0059] (4) Basic mode: Only target score and safety score are used, and the weights are renormalized to 0.429 or 0.571 for rapid assessment of the feasibility of the scheme.

[0060] In one possible implementation, the distance factor is calculated as follows:

[0061] Scoring is based on the deviation between the actual operating distance (distance_mm) from the needle insertion point to the target center and the ideal operating distance (50mm). The specific rules are as follows:

[0062] When 30mm ≤ distance_mm ≤ 80mm, it is within the acceptable range. The score decreases linearly based on the deviation from the ideal distance: distance_score = 1.0 - |distance_mm - 50| / max(20, 30) × 0.3, with a maximum deduction of 30%.

[0063] When 20mm≤distance_mm<30mm or 80mm<distance_mm≤100mm, it is within the tolerance range, and the score decreases linearly to the range of 0.5-0.7.

[0064] When distance_mm < 20mm or distance_mm > 100mm, it exceeds the tolerance range and the score is 0.1, indicating that the operating distance is extremely inconvenient.

[0065] The angle factor is calculated as follows:

[0066] Scoring is based on the angle deviation (angle_deviation) between the needle insertion angle and the ideal perpendicular angle of 90 degrees. The specific rules are as follows:

[0067] When angle_deviation ≤ 15 degrees, it is within the acceptable deviation range, and the score decreases linearly: angle_score = 1.0 - angle_deviation / 15 × 0.2, with a maximum deduction of 20%;

[0068] When 15 degrees < angle_deviation ≤ 30 degrees, it is within the tolerance deviation range, and the score rapidly decreases to the 0.3-0.8 range;

[0069] When angle_deviation > 30 degrees, the score decreases further but maintains some flexibility, with a minimum of 0.1.

[0070] In one possible implementation, the selection of different needle entry points specifically involves determining a feasible search space based on the current distance from the needle tip to the target and the maximum needle length limit, including grid search and radial search.

[0071] In one possible implementation, the change in needle insertion angle specifically involves: the system combining the angle constraints in the medical A* algorithm, and providing angle adjustment guidance to the operator based on the recommended maximum angle change of 30 degrees (soft constraint) in the medical constraints. The medical A* algorithm is a specialized algorithm designed for medical puncture scenarios based on the classic A* path search algorithm. The algorithm establishes a medical grid space as the search basis, discretizing the continuous image space into a searchable node network through gridding. Pixel spacing parameters are set for physical-pixel coordinate transformation. Medical constraint parameters include angle change limit: maximum angle change 30.0 degrees; step size control: minimum step size 1 grid unit, maximum step size 3 grid units; grid division... Resolution: 4 pixels / grid unit; Connectivity: 8-connected neighborhood search; Weighting: Risk weight factor 5.0, Path smoothing weight factor 2.0; A five-level medical safety threshold system is constructed, setting a comfortable operation range (0-10 degrees), a clinically acceptable range (10-20 degrees), a high-risk operation range (20-30 degrees), an extremely dangerous operation range (30-45 degrees), and a technically prohibited range (above 45 degrees). When the angle change of a path segment exceeds 30 degrees, the search is not directly prohibited, but the path cost is increased by significantly increasing the angle change penalty term; when the angle change reaches or exceeds 45 degrees, it is regarded as a technically prohibited range, and the corresponding path cost tends to infinity, thus being excluded from the search space. Enhanced movement cost = basic movement cost + risk cost + smoothness cost, where risk cost = neighbor node risk value × 5.0 × 0.001, and smoothness cost is calculated by vector dot product and magnitude when the angle change is > 30 degrees, using the cosine of the path segment angle. Direct angle calculation: α = arctan2(Δy,Δx) × 180° / π, where α is the needle entry angle, Δx = target x coordinate - needle entry point x coordinate, and Δy = target y coordinate - needle entry point y coordinate.

[0072] In one possible implementation, the multi-dimensional security assessment framework further includes a warning message list. This list outputs a graded hierarchy of the gap distance (distance_to_trajectory) based on the detected anatomical structure type and its preset risk distance threshold, with each level mutually exclusive.

[0073] (1) Arteries: distance_to_trajectory≤5.0mm is "critical risk"; 5.0mm<distance_to_trajectory≤8.0mm is "warning"; distance_to_trajectory>8.0mm is "safe";

[0074] (2) Veins: distance_to_trajectory≤3.0mm is "critical risk"; 3.0mm<distance_to_trajectory≤5.0mm is "warning"; distance_to_trajectory>5.0mm is "safe";

[0075] (3) Esophagus: distance_to_trajectory≤3.0mm is "critical risk"; 3.0mm<distance_to_trajectory≤5.0mm is "warning"; distance_to_trajectory>5.0mm is "safe";

[0076] (4) Diaphragm: distance_to_trajectory≤2.0mm is "critical risk"; 2.0mm<distance_to_trajectory≤4.0mm is "warning"; distance_to_trajectory>4.0mm is "safe";

[0077] (5) Skeleton: As a physical obstacle zone, when distance_to_trajectory = 0.0mm (i.e., the boundary safety distance d_boundary≤0, indicating that the ejection trajectory intersects, contacts, or invades the interior of the skeleton boundary), it is a "critical risk"; when 0.0mm<distance_to_trajectory≤1.0mm, it is a "warning"; when distance_to_trajectory>1.0mm, it is a "safe";

[0078] (6) Lesions and lymph nodes: These are the target areas and are not to be avoided. Their critical_clearance and warning_clearance are both 0.0 mm, and they are marked as "safe / crossable" by default. When multiple risks exist at the same time, the warning message list will output multiple risk level labels and prompts simultaneously, with the highest priority risk as the main prompt. The risk level is adjusted for the overall safety score using a post-processing penalty coefficient.

[0079] Final safety score = Base score × Penalty;

[0080] The base score is 1.0 in the safest state with no risk; the penalty coefficient is determined according to the risk level: critical risk penalty = 0.1, warning risk penalty = 0.7, and safe penalty = 1.0; when multiple risks exist at the same time, the penalty coefficient is the minimum of the penalty coefficients of each risk; in obstacle areas, skeletal structures are used as physical obstacles and are completely bypassed during path planning.

[0081] In one possible implementation, the system establishes differentiated technical alternatives based on seven types of anatomical structures, including artery-specific treatment, intermediate-risk structure treatment, and obstacle structure treatment. For the artery-specific treatment, Doppler ultrasound is used to confirm the artery location before CNB is performed. For the intermediate-risk structure treatment, the needle insertion path is adjusted to avoid the intermediate-risk structure. For the obstacle structure treatment, the needle insertion path or point is modified.

[0082] In one possible implementation, the system establishes a ballistic error calculation model for the ejection trajectory, including position error calculation, relative error calculation, and angle error calculation;

[0083] In the CNB trajectory validator, the position error is calculated using the Euclidean distance formula:

[0084] Position E = √[(predicted x - actual x)² + (predicted y - actual y)²] × k; where...

[0085] E position: Position error, in millimeters (mm);

[0086] x-prediction, y-prediction: The coordinates of the launch endpoint predicted by the algorithm (pixel coordinates).

[0087] x actual, y actual: The actual recorded coordinates of the needle tip impact point (pixel coordinates).

[0088] k=0.208998: Pixel pitch calibration coefficient, in mm / pixel. This coefficient is based on the standard image resolution and physical size calibration of the ultrasound equipment to ensure the accuracy of coordinate transformation.

[0089] Relative error reflects the proportional relationship between prediction error and launch distance:

[0090] E relative = (E position / D ejection) × 100;

[0091] E-relative: Relative error, expressed as a percentage (%);

[0092] D ejection: ejection distance, set to 22.0mm in the CNB system;

[0093] The angle error is obtained by calculating the angle between the predicted trajectory vector and the actual impact trajectory vector:

[0094] Angle E = arccos[cos(θ)] × (180° / π), cos(θ) = (Vpredicted·Vactual) / (|Vpredicted| × |Vactual|). The cosine value cos(θ) needs to be protected by the numerical domain, i.e., cos(θ) = max(-1.0, min(1.0, cos(θ))). The numerical domain protection mechanism forces cos(θ) to be within the range of [-1.0, 1.0] to prevent floating-point operation errors from causing the calculation failure of the inverse cosine function and improve the numerical stability of the algorithm. When |Vpredicted| = 0 or |Vactual| = 0, the denominator is 0. The system marks the angle error as unusable and skips the calculation (or sets it to 0 according to the preset rules), thereby avoiding division by zero.

[0095] V-prediction: The vector pointing from the tip of the needle to the predicted ejection endpoint, V-prediction = (x-prediction - x-tip, y-prediction - y-tip);

[0096] Vactual: The vector from the needle tip to the actual point of impact, Vactual = (xactual - xneedle tip, yactual - yneedle tip).

[0097] E angle: angular error, in degrees (°);

[0098] x needle tip, y needle tip: Coordinates of the needle tip position at the start of ejection;

[0099] ·: Vector dot product operation;

[0100] |Vprediction|: Euclidean magnitude of the prediction vector;

[0101] |Vactual|: Euclidean magnitude of the actual vector;

[0102] max, min: Numerical constraint functions that ensure the cosine value is within the valid range [-1, 1].

[0103] Beneficial effects: Compared with the prior art, the puncture needle navigation system based on CNB ejection mechanism provided in this application calculates the straight-line distance from the needle tip to the target center, and through precise mathematical modeling and high-precision numerical calculation, it can achieve millimeter-level trajectory calculation accuracy, providing a reliable mathematical basis for diagnosing CNB ejection operations;

[0104] It can deeply integrate the AI ​​detection results of anatomical structures with the medical safety distance model, realize personalized risk level assessment based on distance threshold, and provide a scientific risk quantification basis for CNB ejection operation;

[0105] Furthermore, it can achieve deep integration of the system with medical safety requirements, providing scientific, practical, and operable safety optimization guidance for CNB ejection operations through standardized adjustment strategies and personalized technical alternatives, ensuring the safety and effectiveness of clinical operations.

[0106] The system adopts a hierarchical risk assessment model rather than a probabilistic prediction model. By setting two levels of distance thresholds, namely critical and warning, it achieves differentiated risk management for different anatomical structures, ensuring the certainty and operability of the assessment results.

[0107] These and other objects, features and advantages of the present invention will become fully apparent from the following detailed description. Detailed Implementation

[0108] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0109] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0110] This application provides a puncture needle navigation system based on the CNB ejection mechanism. The system establishes a mathematical model of the ejection process through an ejection trajectory calculation function, including:

[0111] Physical coordinate transformation converts the needle tip position and target center from the pixel coordinate system to the physical coordinate system. The transformation ratio is determined by the pixel spacing parameter (default 0.208998mm / pixel). Then, the direction vector of the puncture needle is calculated based on the needle tip angle, converting the angle from degrees to radians, and the unit vector components in the x and y directions are calculated through trigonometric functions.

[0112] Assuming an input ultrasound image of 1920×1080 resolution, a needle tip position of (320, 240) pixels, a needle tip angle of 45°, a target center of (400, 300) pixels, and a standard ejection distance of 22.0 mm:

[0113] Physical coordinate transformation:

[0114] -Needle tip physical coordinates: (320×k (k=0.208998), 240×k (k=0.208998))=(66.88mm, 50.16mm);

[0115] - Target physical coordinates: (400×k (k=0.208998), 300×k (k=0.208998))=(83.60mm, 62.70mm).

[0116] The direction vector is calculated using the following formulas: angle_rad = needle_angle × π / 180; direction_x = cos(angle_rad); direction_y = sin(angle_rad), where angle_rad is the angle of the needle tip in radians, needle_angle is the angle of the needle tip, π is pi, direction_x is the unit vector component in the x-direction, direction_y is the unit vector component in the y-direction, and cos and sin are trigonometric functions used for converting angles to direction vectors.

[0117] The calculation formula for the ejection endpoint is: fire_end_x = tip_x + direction_x × throw_distance; fire_end_y = tip_y + direction_y × throw_distance, where fire_end_x, fire_end_y are the physical coordinates of the ejection endpoint, tip_x, tip_y are the physical coordinates of the starting position of the needle tip, and throw_distance is the ejection distance; the specific calculation is: fire_end_x = 66.88 + 0.7071 × 22.0 = 82.44 mm, fire_end_y = 50.16 + 0.7071 × 22.0 = 65.72 mm.

[0118] Target distance calculation includes axial distance and lateral offset:

[0119] d_along=(target_x-tip_x)×direction_x+(target_y-tip_y)×direction_y;

[0120] d_cross=| (target_x-tip_x)×direction_y-(target_y-tip_y)×direction_x|;

[0121] Where d_along is the axial distance of the target relative to the needle tip along the needle insertion direction, and d_cross is the lateral offset perpendicular to the needle insertion direction; when d_cross≤target_radius and d_along≥0, the ejection trajectory is considered to have geometric feasibility of hitting the target.

[0122] Simultaneously, a reference distance, distance_to_target = √[(target_x - tip_x)² + (target_y - tip_y)²], is defined to represent the straight-line distance from the needle tip to the target center; target_x and target_y are the physical coordinates of the target center, and target_radius is the equivalent radius of the target area, output by the detection module or preset. Specifically, distance_to_target = √[(83.60 - 66.88)² + (62.70 - 50.16)²] = √[279.22 + 157.35] = 20.89 mm.

[0123] CNB needle type support:

[0124] -14G needle: 2.1mm in diameter, the most common specification, suitable for most CNB operations;

[0125] -16G needle: 1.6mm in diameter, medium specification;

[0126] -18G needles: 1.2mm in diameter, a finer specification;

[0127] Security parameter configuration:

[0128] - Minimum target thickness: 10.0mm, ensuring sufficient space for sample acquisition;

[0129] - Safety boundary behind the target: 5.0mm, to prevent excessive penetration;

[0130] - Maximum penetration depth: 50.0mm, limiting the maximum ejection distance;

[0131] - Expected sample length: 15.0 mm, to ensure the sample volume required for pathological diagnosis.

[0132] Based on the accuracy analysis of the actual parameters in the code: the coordinate transformation error is ±0.075mm, and the trigonometric function calculation accuracy in the direction vector is ±1×10⁻¹. 5 (Double-precision floating-point precision);

[0133] Overall accuracy error analysis, sources of cumulative error:

[0134] 1. Pixel quantization error: ±0.075mm;

[0135] 2. Floating-point operation error: ±1×10⁻¹ 5 mm (negligible);

[0136] 3. Angle discretization error: Δ≈D·sin(Δθ). For example, when the launch distance D=22.0mm and the angle discretization step length Δθ=1°, the end-effector lateral discretization error is approximately 22·sin(1°)≈0.38mm;

[0137] 4. Launch distance setting error: ±0.1mm (equipment mechanical precision);

[0138] Overall theoretical error: √(0.075²+0.38²+0.1²)≈±0.40mm (This mainly comes from the angle step size; it can be further reduced by using a finer angle step size or continuous angle input).

[0139] The accuracy improvement method adopted by the system:

[0140] 1. Use the standard math library π constant: The math.pi library provides double-precision π values, eliminating calculation errors caused by manual approximation;

[0141] 2. Real-time trigonometric function calculation: The direction vector is calculated in real time using the cos() and sin() functions, avoiding the discretization error of the angle lookup table;

[0142] 3. Double-precision floating-point arithmetic: 64-bit double-precision floating-point numbers are used for coordinate transformation and trajectory calculation to ensure the stability of numerical calculations;

[0143] 4. Pixel pitch calibration: Physical-to-pixel coordinate transformation is performed using a precise pixel pitch parameter of 0.208998mm / pixel.

[0144] The system calculates the straight-line distance from the needle tip to the target center, serving as a fundamental parameter for evaluating ejection effectiveness. Through precise mathematical modeling and high-precision numerical calculations, the system achieves millimeter-level trajectory calculation accuracy, providing a reliable mathematical foundation for CNB ejection operations.

[0145] In one embodiment, the system establishes a geometric distance calculation algorithm based on parameterized line equations, and the calculation formula is as follows:

[0146] d1 = √[(px - projection_x)² + (py - projection_y)²], where:

[0147] d1 is the shortest distance from the point to be evaluated to the line segment;

[0148] px and py are the coordinates of the point to be evaluated (the center point of the anatomical structure);

[0149] projection_x = x1 + t × (x2 - x1), projection_y = y1 + t × (y2 - y1), where x1 and y1 are the coordinates of the starting point of the line segment, x2 and y2 are the coordinates of the ending point of the line segment, and t is the projection parameter, which represents the relative position of the projection point on the line segment. t = max(0, min(1, [(px - x1) × (x2 - x1) + (py - y1) × (y2 - y1)] / line_length²)), where the value of t is in the range of 0-1. line_length is the length of the line segment, line_length = √[(x2 - x1)² + (y2 - y1)²]. max and min are the maximum and minimum value functions, respectively, to ensure that the projection point is within the range of the line segment.

[0150] With a target radius of 5.0mm, the parameters of the ejection trajectory line segment are as follows: starting point coordinates are (66.88mm, 50.16mm), ending point coordinates are (82.44mm, 65.72mm), and line segment length is: √[(82.44-66.88)²+(65.72-50.16)²]=√[242.21+242.21]=22.0mm.

[0151] Assuming the target point coordinates are (75.0mm, 60.0mm), calculate the shortest distance from it to the trajectory line segment:

[0152] 1. Calculation of projection parameters:

[0153] t=[(75.0-66.88)×(82.44-66.88)+(60.0-50.16)×(65.72-50.16)] / (22.0)²;

[0154] =[8.12×15.56+9.84×15.56] / 484.0;

[0155] =[126.35+153.11] / 484.0=279.46 / 484.0=0.577.

[0156] 2. Constraint Check:

[0157] t=max(0,min(1,0.577))=0.577 (within the range [0,1], no constraints are needed).

[0158] 3. Calculation of projection points:

[0159] projection_x=66.88+0.577×(82.44-66.88)=66.88+0.577×15.56=66.88+8.98=75.86mm;

[0160] projection_y=50.16+0.577×(65.72-50.16)=50.16+0.577×15.56=50.16+8.98=59.14mm.

[0161] 4. Shortest distance calculation:

[0162] d1=√[(75.0-75.86)²+(60.0-59.14)²]=√[0.74+0.74]=√1.48=1.22mm.

[0163] Since the distance of 1.22mm is less than the target radius of 5.0mm, the target is determined to have been hit by the trajectory. Calculating the shortest distance from the target point to the line segment ensures that the CNB needle can accurately collect pathological samples, thus assessing the clinical effectiveness of the ejection operation—that is, evaluating whether valuable pathological samples can be successfully obtained.

[0164] In addition, the boundary safety distance can assess the risk of damage to dangerous anatomical structures (such as arteries and veins) by the ejection trajectory. As a safety assessment, it determines whether ejection is allowed to miss any risk factors, thereby ensuring that the CNB ejection process does not accidentally damage important anatomical structures.

[0165] In one embodiment, the graded risk assessment model is a multi-level risk assessment model based on distance thresholds. The system establishes risk threshold configurations for seven types of anatomical structures and performs risk assessment based on the shortest distance from the ejection trajectory to the anatomical structure.

[0166] Artery, Category 0, Critical Risk Threshold 5.0 mm, Warning Threshold 8.0 mm, Priority 9 (Highest Risk).

[0167] Vein, Category 1, critical risk threshold 3.0mm, warning threshold 5.0mm, priority 7 (high risk).

[0168] Esophagus, Category 5, Critical Risk Threshold 3.0 mm, Warning Threshold 5.0 mm, Priority 7 (High Risk);

[0169] Diaphragm, Category 6, Critical Risk Threshold 2.0mm, Warning Threshold 4.0mm, Priority 6 (Medium Risk).

[0170] Skeleton, Category 3, Critical Risk Threshold 0.0mm, Warning Threshold 1.0mm, Priority 8 (Physical Obstacle).

[0171] Lesion, Category 4, danger threshold 0.0mm, is a puncture target, no need to avoid it, warning threshold 0.0mm (target area).

[0172] Lymph node, Category 2, danger threshold 0.0 mm, is a puncture target, no avoidance required, warning threshold 0.0 mm (target area).

[0173] This enables the deep integration of AI detection results of anatomical structures with medical safety distance models, achieving personalized risk level assessment based on distance thresholds and providing a scientific basis for quantifying risks in CNB ejection operations.

[0174] In one embodiment, the system establishes a multi-dimensional safety assessment framework that includes an overall safety score and a list of critical risks. The list of critical risks is a set of anatomical information that the system detects during the ejection trajectory safety assessment process, all of which reach a critical risk level. Each critical risk entry in the list contains the following fields:

[0175] - structure (structure type): The type identifier of the anatomical structure, which can be one of the following: artery, vein, esophagus, diaphragm, or bone;

[0176] - distance_mm (distance): The shortest distance from this anatomical structure to the ejection trajectory, in millimeters;

[0177] - risk_description: A textual description of the risk, such as "The ejection trajectory is too close to the artery, posing a risk of vascular damage";

[0178] - avoidance_priority: The medical avoidance priority of this structure. The higher the value, the more necessary it is to avoid. The value range is 1-9.

[0179] The criteria for determining the critical risk list are as follows: when the gap distance between the anatomical structure and the ejection trajectory is less than the critical risk threshold of the structure, the structure is added to the critical risk list; an empty critical risk list indicates no critical risk, while a non-empty list indicates the presence of a critical risk that needs to be addressed. The overall safety score uses a standardized scoring system from 1.0 to 0.0, where 1.0 represents the safest state and 0.0 represents the most dangerous state. Based on the status of the critical risks in the critical risk list, the system automatically triggers an adjustment suggestion generation process. Adjustment suggestions include adjusting the ejection distance, changing the needle insertion angle, and selecting different needle insertion points (all planned / set before firing), thereby establishing a complete ejection safety management system. This allows for deep integration of the seven types of anatomical structure recognition results from multimodal AI detection with the physical characteristics of CNB ejection, achieving intelligent ejection safety management and providing comprehensive safety assurance for clinical CNB operations.

[0180] The overall safety score is calculated based on a cumulative penalty mechanism, with an initial value of 1.0 representing the safest state. That is, the base score is 1.0 in the safest state, representing no risk. When a critical risk is detected, a penalty factor of 0.1 is applied; when a warning risk is detected, a penalty factor of 0.7 is applied. The calculation formula is as follows:

[0181] Overall safety score = base score × penalty;

[0182] The initial base score is 1.0. The penalty coefficient is determined based on the distance (distance_to_trajectory) between the ejection trajectory and the anatomical structure, and the corresponding risk threshold: when distance_to_trajectory ≤ critical_clearance, penalty = 0.1 (critical risk); when critical_clearance < critical_to_trajectory ≤ warning_clearance, penalty = 0.7 (warning risk); when distance_to_trajectory > warning_clearance, penalty = 1.0 (safe). When multiple anatomical structures exist, the system takes the minimum penalty value among all penalty values ​​as the final penalty coefficient, ensuring that any critical risk is correctly identified and reflected in the safety score.

[0183] Specifically, the adjustment of the ejection distance involves the system sorting the feasible ejection distances from the adjustable ejection distance options that satisfy both the hit constraint and the safety threshold constraint according to a preset priority sorting rule, and selecting the preferred option. When a critical risk occurs, the shorter feasible ejection distance is preferred. In the set of feasible ejection distances, the system prioritizes the following sorting rules: (1) Hit geometric feasibility priority: the scheme that satisfies the hit geometric constraint is selected first, and the scheme under the optimal sampling condition has a higher priority than the general hit condition; (2) Safety level priority: under the premise of satisfying the hit constraint, the scheme with a larger safety margin (corresponding to a higher overall safety score) is selected first; (3) Distance preference rule: under the same conditions, the scheme with an ejection distance closer to the preset standard distance of 22.0 mm is selected first, where the distance preference is defined as: preference = 1.0−|current ejection distance−22.0| / 22.0.

[0184] Example: Assume the current ejection distance is 22.0mm (standard distance), and the candidate adjustable distances are 15, 18, 22, 25, 29, and 32mm. After safety assessment, the current plan's distance_to_trajectory at the artery is 3.0mm, which is less than the critical risk threshold of 5.0mm, and is therefore deemed a critical risk. The system prioritizes searching for shorter distance plans in the candidate set and re-evaluates them. If the 15mm plan meets the hit constraint and its corresponding distance_to_trajectory > 5.0mm, an adjustment suggestion is generated: "It is recommended to adjust the ejection distance to 15mm to eliminate the critical risk and improve the overall safety score."

[0185] Specifically, the selection of different needle entry points involves determining the feasible search space based on the current distance from the needle tip to the target and the maximum needle length limit, including grid search and radial search.

[0186] Specifically, changing the needle insertion angle involves the system combining the angle constraints in the medical A* algorithm with the recommended maximum angle change of 30 degrees (soft constraint) in the medical constraints to provide the operator with angle adjustment guidance.

[0187] Direct angle calculation: α=arctan2(Δy,Δx)×180° / π, where α is the needle entry angle, Δx=target x coordinate - needle entry point x coordinate, Δy=target y coordinate - needle entry point y coordinate.

[0188] Feasibility verification of angle adjustment:

[0189] The system incorporates angle constraints from the medical A* algorithm to ensure that the suggested angle adjustment range conforms to actual operational limitations: max_angle_change=30.0° #Configuration based on medical constraints;

[0190] recommended_angle_range=[current_angle-30°, current_angle+30°] (recommended adjustment range, soft constraint); search_angle_range=[current_angle-45°, current_angle+45°] (upper bound of the search limit), where the angle can still be searched beyond 30° but the penalty in the cost function increases sharply; when the angle change is ≥45°, an infinite penalty value is set to prevent the path from expanding.

[0191] The specific application of the cumulative penalty calculation is as follows: when the overall safety score is below 0.3, the system automatically generates high-priority adjustment suggestions, including "suggesting to change the needle insertion point position" or "suggesting to adjust the needle insertion angle to the vertical direction"; when the overall safety score is in the range of 0.3-0.7, the system generates medium-priority suggestions, such as "considering to reduce the ejection distance" or "suggesting to confirm the location of the anatomical structure"; when the overall safety score is above 0.7, the system confirms that the current configuration is safe and feasible, and generates a confirmatory suggestion "the current ejection configuration is safe and the operation can be performed", thereby ensuring that the system can identify potential risks and provide appropriate safety reminders, while not completely preventing ejection operations.

[0192] Calculation example:

[0193] By aggregating multiple risk alerts into levels (critical / warning / info) and combining them with the overall security score to generate recommendations, the system can improve the alert level and recommendation priority in complex risk scenarios. This alert / label system is only used for risk explanation and interactive prompts and does not deduct from the overall security score.

[0194] In one embodiment, the multi-dimensional security assessment framework further includes a warning information list. This list outputs a graded distribution of the gap distance (distance_to_trajectory) based on the detected anatomical structure type and its preset risk distance threshold, with each grade mutually exclusive.

[0195] (1) Arteries: distance_to_trajectory≤5.0mm is "critical risk"; 5.0mm<distance_to_trajectory≤8.0mm is "warning"; distance_to_trajectory>8.0mm is "safe";

[0196] (2) Veins: distance_to_trajectory≤3.0mm is "critical risk"; 3.0mm<distance_to_trajectory≤5.0mm is "warning"; distance_to_trajectory>5.0mm is "safe";

[0197] (3) Esophagus: distance_to_trajectory≤3.0mm is "critical risk"; 3.0mm<distance_to_trajectory≤5.0mm is "warning"; distance_to_trajectory>5.0mm is "safe";

[0198] (4) Diaphragm: distance_to_trajectory≤2.0mm is "critical risk"; 2.0mm<distance_to_trajectory≤4.0mm is "warning"; distance_to_trajectory>4.0mm is "safe";

[0199] (5) Skeleton: As a physical obstacle zone, when distance_to_trajectory = 0.0mm (i.e., the boundary safety distance d_boundary≤0, indicating that the ejection trajectory intersects, contacts, or invades the interior of the skeleton boundary), it is a "critical risk"; when 0.0mm<distance_to_trajectory≤1.0mm, it is a "warning"; when distance_to_trajectory>1.0mm, it is a "safe";

[0200] (6) Lesions and lymph nodes: These are the target areas and are not to be avoided. Their critical_clearance and warning_clearance are both 0.0 mm, and they are marked as "safe / crossable" by default. When multiple risks exist at the same time, the warning message list will output multiple risk level labels and prompts simultaneously, with the highest priority risk as the main prompt. The risk level is adjusted for the overall safety score using a post-processing penalty coefficient.

[0201] Final safety score = Base score × Penalty;

[0202] The base score is 1.0 in the safest state with no risk; the penalty coefficient is determined according to the risk level: critical risk penalty = 0.1, warning risk penalty = 0.7, and safe penalty = 1.0; when multiple risks exist at the same time, the penalty coefficient is the minimum of the penalty coefficients of each risk; in obstacle areas, skeletal structures are used as physical obstacles and are completely bypassed during path planning.

[0203] Rules for generating warning message list level labels:

[0204] When a critical risk exists (e.g., any structure whose distance_to_trajectory ≤ critical risk threshold), output the "critical risk" label and display it according to risk priority; when only a warning risk exists (critical risk threshold < distance_to_trajectory ≤ warning threshold), output the "warning" label; when all structures are in the safe zone (distance_to_trajectory > warning threshold), output the "safe" label.

[0205] When multiple risks exist simultaneously, the system outputs multiple risk labels and prompts at the same time, and displays them in order of preset priority. When a critical risk is detected, the overall security score will be reduced to 10% of the original value, and when a warning risk is detected, the overall security score will be reduced to 70% of the original value.

[0206] In one embodiment, the system establishes differentiated technical alternatives based on seven types of anatomical structures, including artery-specific treatment, intermediate-risk structure treatment, and obstacle structure treatment. For the artery-specific treatment, Doppler ultrasound is used to confirm the artery location before CNB (Neural Nucleation Bypass). For the intermediate-risk structure treatment, the needle insertion path is adjusted to avoid the intermediate-risk structure. For the obstacle structure treatment, the needle insertion path or point is modified. Specific implementation examples of the technical alternatives are provided below.

[0207] Assuming two key risk structures, arteries and bones, are detected:

[0208] Step 1: Arterial risk management;

[0209] The system detected a critical risk with structure_type 'artery' and automatically generated a Doppler ultrasound recommendation:

[0210] "Consider using Doppler ultrasound to confirm the artery location before performing CNB";

[0211] Step 2: Treatment of skeletal disorders;

[0212] The system detected a critical risk with structure_type 'bone' and automatically generated mandatory adjustment requirements:

[0213] "If there is a bone obstruction, the needle path or insertion point must be changed."

[0214] Step 3: Generate a comprehensive list of recommendations;

[0215] The system integrates all types of adjustment suggestions into a complete list of recommended_adjustments:

[0216] recommended_adjustments =["It is recommended to reduce the ejection distance to 15mm to avoid high-risk structures", "Consider adjusting the needle insertion angle to avoid key anatomical structures", "It is recommended to choose different needle insertion points to obtain a safer ejection path", "Consider using Doppler ultrasound to confirm the artery location before performing CNB", "Bone obstruction necessitates changing the needle path or needle insertion point"].

[0217] In one embodiment, the system establishes a comprehensive scoring model for CNB ejection configurations to perform multi-dimensional comprehensive quality assessments of different ejection configuration schemes while meeting safety constraints. This comprehensive scoring system, together with the aforementioned overall safety scoring system, forms a two-layer architecture to jointly support intelligent decision-making for CNB ejection. The two-layer assessment architecture design is as follows:

[0218] The first layer: the overall safety scoring system (cumulative penalty model), has the following functions;

[0219] Functional role: To assess the absolute safety of the ejection trajectory;

[0220] Evaluation Dimension: Single Dimension (Security);

[0221] Output: 0-1 standardized score, serving as a hard safety constraint;

[0222] Decision-making function: Determines whether a plan can be executed (safety threshold).

[0223] The second layer: The CNB Comprehensive Scoring System (multi-factor weighted model) has the following functions:

[0224] Functional positioning: To optimize the quality of configuration solutions while ensuring safety;

[0225] Evaluation dimensions: Four dimensions (target, safety, distance, angle);

[0226] Output: 0-1 standardized score, used as the basis for ranking the merits of the solutions;

[0227] Decision-making role: Selecting the optimal solution from multiple security options.

[0228] The following is a detailed explanation of the comprehensive scoring formula and factors:

[0229] The standard formula for calculating the CNB comprehensive score is: CNB comprehensive score = target score × 0.3 + safety score × 0.4 + distance factor × 0.2 + angle factor × 0.1;

[0230] The physical meaning and calculation method of each factor are as follows:

[0231] 1. Target Score (Weight 0.3): Evaluates the accuracy of the ejection trajectory in hitting the target area. 1.0 points: The ejection trajectory completely passes through the target area, and the sampling length meets the standard (optimal sampling); 0.3-0.7 points: The trajectory partially passes through the target area (general hit); 0.1 points: The trajectory completely deviates from the target area (miss).

[0232] 2. Safety Score (Weight 0.4, highest weight): Derived from the overall safety score at the first level, directly using the output of the cumulative penalty model. 1.0 points: No risk, distance from all hazardous structures exceeds the warning threshold; 0.7 points: Warning-level risk exists; 0.1 points: Critical-level risk exists. This reflects the medical principle of "safety first."

[0233] 3. Distance Factor (Weight 0.2): Assessing the ease of operation from the needle insertion point to the target center. Ideal operation distance: 50mm (based on clinical experience); Acceptable range: 30-80mm (score 0.7-1.0); Tolerable range: 20-100mm (score 0.5-0.7); Extreme distance: <20mm or >100mm (score 0.1). Calculation method: distance_score = f(|actual distance - 50mm|), the closer to the ideal value, the higher the score.

[0234] 4. Angle Factor (Weight 0.1): Assessing clinical preference for needle insertion angle. Ideal insertion angle: 90 degrees (vertical insertion); Acceptable deviation: ±15 degrees (score 0.8-1.0); Tolerant deviation: ±30 degrees (score 0.3-0.8); Extreme angle: >30 degrees deviation (score 0.1-0.3). Calculation method: angle_score = f(|actual angle - 90 degrees|), the closer to vertical, the higher the score.

[0235] The medical basis for the weighting allocation is as follows: The weighting allocation (0.3, 0.4, 0.2, 0.1) reflects the following clinical decision-making levels:

[0236] Safety First (0.4): This has the highest weight, ensuring that any optimization scheme meets safety requirements first, which is consistent with the medical ethical principle of "do no harm first".

[0237] Target effectiveness (0.3): The second most important factor is ensuring successful acquisition of pathological samples to achieve the diagnostic objective;

[0238] Ease of operation (0.3 = 0.2 distance + 0.1 angle): Lowest weight, optimize the operation experience while satisfying the first two.

[0239] The multi-mode scoring system provides four scoring modes based on different optimization scenarios:

[0240] (1) Comprehensive mode:

[0241] Use the complete four-factor formula;

[0242] Applicable scenarios: Comprehensive evaluation of the overall configuration of needle entry point and angle;

[0243] Weighting configuration: 0.3, 0.4, 0.2, 0.1 (standard weights);

[0244] (2) Catapult distance optimization mode (distance_only):

[0245] Use target score, safety score, and distance factor;

[0246] Applicable scenarios: Fixed needle entry point and angle, only optimizing ejection distance selection;

[0247] Weight normalization: 0.333, 0.444, 0.222 (original weight 0.3+0.4+0.2=0.9 normalized to 1.0);

[0248] (3) Angle optimization mode (angle_only):

[0249] Use target scoring, safety scoring, and angle factors;

[0250] Applicable scenarios: Fixed needle entry point, only needle entry angle optimized;

[0251] Weight normalization: 0.375, 0.500, 0.125 (original weight 0.3+0.4+0.1=0.8 normalized to 1.0);

[0252] (4) Basic mode:

[0253] Only target score and safety score are used;

[0254] Applicable scenarios: rapid feasibility assessment;

[0255] Weight normalization: 0.429, 0.571 (original weight 0.3+0.4=0.7 normalized to 1.0).

[0256] Computational example: Suppose the system evaluates three candidate catapult configurations:

[0257] Option A:

[0258] Target score: 1.0 (perfect hit);

[0259] Safety score: 0.8 (No critical risks, but there are warning risks).

[0260] Distance factor: 0.9 (actual distance 55mm, close to the ideal value of 50mm);

[0261] Angle factor: 0.85 (actual angle 85 degrees, close to perpendicular);

[0262] Using the comprehensive model for calculation: CNB comprehensive score A = 1.0×0.3 + 0.8×0.4 + 0.9×0.2 + 0.85×0.1 = 0.30 + 0.32 + 0.18 + 0.085 = 0.885

[0263] Option B:

[0264] Target score: 1.0 (perfect hit);

[0265] Safety rating: 1.0 (No risk whatsoever);

[0266] Distance factor: 0.5 (actual distance 25mm, too close);

[0267] Angle factor: 0.6 (actual angle 70 degrees, significant deviation);

[0268] Using the comprehensive model for calculation: CNB comprehensive score B = 1.0×0.3 + 1.0×0.4 + 0.5×0.2 + 0.6×0.1 = 0.30 + 0.40 + 0.10 + 0.06=0.86.

[0269] Option C:

[0270] Target score: 0.7 (partial hit);

[0271] Safety rating: 1.0 (No risk whatsoever);

[0272] Distance factor: 1.0 (actual distance 50mm, ideal value);

[0273] Angle factor: 1.0 (actual angle 90 degrees, perpendicular);

[0274] Using the comprehensive model for calculation: CNB comprehensive score C = 0.7×0.3 + 1.0×0.4 + 1.0×0.2 + 1.0×0.1 = 0.21 + 0.40 + 0.20 + 0.10 = 0.91.

[0275] Decision on the best option:

[0276] Overall score ranking: Option C (0.91) > Option A (0.885) > Option B (0.86);

[0277] Decision conclusion: Option C is selected. Although the target hit score is slightly lower (0.7), it has a perfect safety score and the best ease of operation, resulting in the highest overall quality.

[0278] The system, through a two-layer evaluation architecture, is able to:

[0279] 1. The first layer ensures that all solutions meet the minimum security standards (security thresholds);

[0280] 2. The second layer comprehensively weighs multiple objectives in the safety scheme and selects the scheme with the best overall quality;

[0281] 3. Avoid suboptimal decisions caused by single-dimensional optimization (such as excessively pursuing target accuracy while ignoring operational convenience);

[0282] 4. The weights are interpretable and align with the thinking habits of medical clinical decision-making.

[0283] In one embodiment, the system establishes a ballistic error calculation model for the ejection trajectory, including position error calculation, relative error calculation, and angle error calculation, which can further improve the accuracy of the CNB ejection trajectory.

[0284] In the CNB trajectory validator, the position error is calculated using the Euclidean distance formula:

[0285] Position E = √[(predicted x - actual x)² + (predicted y - actual y)²] × k; where...

[0286] E position: Position error, in millimeters (mm);

[0287] x-prediction, y-prediction: the coordinates of the launch endpoint predicted by the algorithm;

[0288] x_actual, y_actual: The actual recorded coordinates of the needle impact point;

[0289] k=0.208998: Pixel pitch calibration coefficient, in mm / pixel. This coefficient is based on the standard image resolution and physical size calibration of the ultrasound equipment to ensure the accuracy of coordinate transformation.

[0290] For example: In a test, if the predicted endpoint of a certain ejection is (252, 218) pixels, but the actual endpoint is (250, 220) pixels, then the position error is:

[0291] E position = √[(252-250)²+(218-220)²]×k (k=0.208998) = 2.83×k (k=0.208998) = 0.59mm.

[0292] Relative error reflects the proportional relationship between prediction error and launch distance:

[0293] E relative = (E position / D ejection) × 100;

[0294] E-relative: Relative error, expressed as a percentage (%);

[0295] D ejection: ejection distance, set to 22.0mm in the CNB system;

[0296] The relative error corresponding to the above-mentioned positional error of 0.59mm is:

[0297] E relative = (0.59 / 22.0) × 100 = 2.68%.

[0298] The angle error is obtained by calculating the angle between the predicted trajectory vector and the actual impact trajectory vector:

[0299] Angle E = arccos[cos(θ)] × (180° / π), cos(θ) = (Vpredicted·Vactual) / (|Vpredicted| × |Vactual|), where the cosine value cos(θ) needs to be protected by the numerical domain, i.e., cos(θ) = max(-1.0, min(1.0, cos(θ))), where the cos(θ) on the left side of the equal sign is the corrected value, and the cos(θ) on the right side is the original value;

[0300] V-prediction: The vector pointing from the tip of the needle to the predicted ejection endpoint, V-prediction = (x-prediction - x-tip, y-prediction - y-tip);

[0301] Vactual: The vector from the needle tip to the actual point of impact, Vactual = (xactual - xneedle tip, yactual - yneedle tip).

[0302] E angle: angular error, in degrees (°);

[0303] x needle tip, y needle tip: Coordinates of the needle tip position at the start of ejection;

[0304] ·: Vector dot product operation;

[0305] |Vprediction|: Euclidean magnitude of the prediction vector;

[0306] |Vactual|: Euclidean magnitude of the actual vector;

[0307] max, min: Numerical constraint functions that ensure the cosine value is within the valid range [-1, 1].

[0308] By protecting the numerical domain of the cosine value cos(θ), the cosine value cos(θ) is forcibly constrained to the range of [-1.0, 1.0], which is mainly used to prevent floating-point operation errors from causing the calculation failure of the inverse cosine function. When |Vpredicted|=0 or |Vactual|=0, the system first determines and skips the angle error calculation (or sets it to 0 according to the preset rules), thereby avoiding division by zero errors.

[0309] Assume the actual data from a certain CNB ejection operation:

[0310] - Tip starting position: (120, 150) pixels;

[0311] - Predicted ejection endpoint: (200, 180) pixels;

[0312] - Actual impact point: (205, 185) pixels;

[0313] Step 1: Construct the trajectory vector;

[0314] V prediction = (200-120, 180-150) = (80, 30);

[0315] Vactual = (205-120, 185-150) = (85, 35);

[0316] Step 2: Calculate the vector magnitude;

[0317] |V prediction| = √(80² + 30²) = √(6400 + 900) = √7300 = 85.44;

[0318] |Vactual| = √(85² + 35²) = √(7225 + 1225) = √8450 = 91.93;

[0319] Step 3: Calculate the vector dot product;

[0320] Vpredicted·Vactual = 80×85 + 30×35 = 6800 + 1050 = 7850;

[0321] Step 4: Calculate the cosine value;

[0322] cos(θ)=7850 / (85.44×91.93)=7850 / 7852.16=0.9997;

[0323] Step 5: Apply value protection;

[0324] cos(θ)=max(-1.0,min(1.0,0.9997))=0.9997;

[0325] Step 6: Calculate the angle error;

[0326] θ = arccos(0.9997) = 0.0245 radians;

[0327] E angle=0.0245×(180° / π)=1.40°.

[0328] Calculation results: The angle error of this ejection was 1.40°, indicating that there was a small deviation between the actual ejection direction and the predicted direction, which is within the acceptable accuracy range.

[0329] The system also establishes a precision improvement mechanism based on the collaboration of three modules, including:

[0330] 1. Data acquisition mechanism of CNB trajectory verifier:

[0331] The trajectory validator, acting as an "intelligent medical recording system," is responsible for accurately recording and validating the predicted and actual results of each ejection. Its validation process is as follows:

[0332] 1.1 Prediction and Recording Stage: Record the tip position (x_{tip}, y_{tip}), tip angle θ, target point position (x_{target}, y_{target}), ejection distance D_{throw}, and predicted endpoint (x_{pred}, y_{pred});

[0333] 1.2 Verification of actual results: Record the actual endpoint (x_{actual}, y_{actual}), surgical success status S, and sample quality grade Q;

[0334] 1.3 Error Calculation and Classification: Calculate position error, angle error and target offset distance, and classify and statistically analyze them according to conditions such as needle specifications, ejection distance, and target distance;

[0335] Validation results: In system testing, the validator recorded 7109 predictions and 76 actual results, and calculated the average error to be 0.55 mm, the standard deviation to be 0.22 mm, and the maximum error to be 1.05 mm.

[0336] 2. Trend analysis algorithm of CNB error collector:

[0337] The error collector, acting as the "hospital quality control center," employs an intelligent time window adaptation algorithm for error trend analysis.

[0338] R_trend = [1 / (n-1)] × Σ(E(i+1)-Ei), (i=1 to n-1);

[0339] Symbol meaning:

[0340] -R Trend: Rate of change of trend, in mm / time window;

[0341] -Ei: The average error of the i-th time window;

[0342] -n: Number of time windows;

[0343] Time window adaptive selection strategy:

[0344] - When the time span is less than 1 hour: use minute-level grouping;

[0345] - When the time span is 1-24 hours: use hourly grouping;

[0346] - When the time span exceeds 24 hours: use daily grouping;

[0347] Example Analysis: The system detected an improving trend with a change rate of -10.000 mm / hour, indicating that the accuracy is continuously improving. However, due to the detection of an abnormal change rate, the system adopts a change rate limiting strategy to restrict it to a reasonable range: R_trend = clip(R_trend, -Rmax, Rmax), where Rmax is the preset maximum allowable change rate (e.g., ±1.0 mm / hour, which can be configured according to the equipment / department quality control requirements).

[0348] 3. Systematic bias correction of the CNB calibration algorithm:

[0349] The calibration algorithm uses statistical methods to distinguish between systematic errors and random errors, and only corrects confirmed systematic deviations.

[0350] 3.1 Formula for systematic deviation test:

[0351] One-sample t-test: t = (X̄ - μ0) / (S / √n); Coefficient of variation criterion: CV = S / |X̄|;

[0352] Symbol meaning:

[0353] -X̄: Sample mean (e.g., distance ratio or angle offset);

[0354] -μ0: Theoretical expected value (distance ratio is 1.0, angle offset is 0°);

[0355] -S: Sample standard deviation;

[0356] -n: Number of samples;

[0357] -CV: Coefficient of variation;

[0358] Systematic bias determination criteria: When |t|>2.0 and CV<0.5, a systematic bias is determined to exist.

[0359] 3.2 Distance Correction Algorithm:

[0360] For confirmed systematic deviations in distance, apply a scaling factor for correction:

[0361] D-correction = D-prediction × λ, where the scaling factor is calculated as follows:

[0362] λ = (1 / n) × Σ(D_actual, i / D_predicted, i), (i = 1 to n);

[0363] Symbol meaning:

[0364] -D correction: Corrected ejection distance;

[0365] -D prediction: Original prediction distance;

[0366] -λ: Distance scaling factor;

[0367] -Dactual, i: The actual launch distance of the i-th launch;

[0368] -D prediction, i: the predicted launch distance for the i-th time;

[0369] Safety constraint: 0.95≤λ≤1.05, which means a maximum distance correction of 5% is allowed.

[0370] 3.3 Angle Correction Algorithm:

[0371] For systematic angular deviations, apply offset correction:

[0372] θ correction = θ prediction + Δθ; where the angular offset is: Δθ = (1 / n) × Σ(θ actual, i - θ prediction, i), (i = 1 to n), where:

[0373] -θ correction: Corrected needle tip angle;

[0374] -θ prediction: Original prediction angle;

[0375] -Δθ: Angle offset correction amount;

[0376] -θactual, i: The actual launch angle of the i-th launch;

[0377] -θ prediction, i: the prediction angle of the i-th time;

[0378] Safety constraint: |Δθ|≤2°, meaning a maximum angle correction of 2 degrees is allowed.

[0379] 4. Cross-validation to prevent overfitting:

[0380] K-fold cross-validation (K=5) was used to evaluate the correction effect:

[0381] R(k) = (Ēoriginal(k) - Ēcorrected(k)) / Ēoriginal(k);

[0382] Symbol meaning:

[0383] -R(k): The improvement rate at the k-th fold;

[0384] -E_original(k): Mean of the original error at the k-th fold;

[0385] -E correction(k): Mean error after k-th correction;

[0386] Overfitting detection metrics:

[0387] σR=√{(1 / K)×Σ[R(k)-R̄]²}, (k=1 to K);

[0388] When σR > 0.5 or R(k) < -0.3, it is determined that there is a risk of overfitting.

[0389] Those skilled in the art should understand that the embodiments of the present invention shown in the above description are merely examples and do not limit the invention. The advantages of the present invention have been fully and effectively realized. The functional and structural principles of the present invention have been demonstrated and described in the embodiments; any variations or modifications can be made to the implementation of the present invention without departing from these principles.

Claims

1. A puncture needle navigation system based on the CNB ejection mechanism, characterized in that, The system establishes a mathematical model of the ejection process through an ejection trajectory calculation function, including: Physical coordinate transformation converts the needle tip position and target center from the pixel coordinate system to the physical coordinate system. The transformation ratio is determined by the pixel spacing parameter. Subsequently, the direction vector of the puncture needle is calculated based on the needle tip angle. The angle is converted from degrees to radians, and the unit vector components in the x and y directions are calculated through trigonometric functions. The needle tip angle and the needle insertion angle are equivalent in the two-dimensional ultrasound imaging plane. Both represent the direction angle of the puncture needle axis relative to the positive x-axis of the ultrasound image. The angle is positive in the counterclockwise direction. When performing direction vector calculation or trigonometric function operation, the angle is converted from degrees to radians for calculation. The direction vector is calculated using the following formulas: angle_rad = needle_angle × π / 180; direction_x = cos(angle_rad); direction_y = sin(angle_rad), where angle_rad is the angle of the needle tip in radians, needle_angle is the angle of the needle tip (i.e., the angle of needle insertion), π is the mathematical constant pi, direction_x is the unit vector component in the x-direction, direction_y is the unit vector component in the y-direction, and cos and sin are trigonometric functions used for converting angles to direction vectors. The calculation formula for the ejection endpoint is: fire_end_x = tip_x + direction_x × throw_distance; fire_end_y = tip_y + direction_y × throw_distance, where fire_end_x, fire_end_y are the physical coordinates of the ejection endpoint, tip_x, tip_y are the physical coordinates of the starting position of the needle tip, and throw_distance is the ejection distance; The target distance calculation includes axial distance and lateral offset: d_along = (target_x - tip_x) × direction_x + (target_y - tip_y) × direction_y; d_cross = |(target_x - tip_x) × direction_y - (target_y - tip_y) × direction_x|; where d_along is the axial distance of the target relative to the needle tip along the needle insertion direction, and d_cross is the lateral offset perpendicular to the needle insertion direction; when d_cross ≤ target_radius and d_along ≥ 0, the ejection trajectory is considered to have geometric feasibility of hitting the target; Meanwhile, a reference distance distance_to_target=√[(target_x-tip_x)²+(target_y-tip_y)²] is defined to represent the straight-line distance from the needle tip to the center of the target; target_x and target_y are the physical coordinates of the target center, and target_radius is the equivalent radius of the target area, which is output by the detection module or preset.

2. The puncture needle navigation system based on the CNB ejection mechanism as described in claim 1, characterized in that, The system establishes a geometric distance calculation algorithm based on parameterized line equations, and the calculation formula is as follows: d1 = √[(px - projection_x)² + (py - projection_y)²], where: d1 is the shortest distance from the point to be evaluated to the line segment; px and py are the coordinates of the point to be evaluated; projection_x = x1 + t × (x2 - x1), projection_y = y1 + t × (y2 - y1), where x1 and y1 are the coordinates of the starting point of the line segment, x2 and y2 are the coordinates of the ending point of the line segment, and t is the projection parameter, which represents the relative position of the projection point on the line segment. t = max(0, min(1, [(px - x1) × (x2 - x1) + (py - y1) × (y2 - y1)] / line_length²)), where the value of t is in the range of 0-1. line_length is the length of the line segment, line_length = √[(x2 - x1)² + (y2 - y1)²]. max and min are the maximum and minimum value functions, respectively, to ensure that the projection point is within the range of the line segment. The clearance distance from the anatomical structure to the ejection trajectory is calculated using the following steps: First, calculate the shortest distance from the projectile trajectory line segment to the center point of the anatomical structure: distance_center = √[(px-projection_x)²+(py-projection_y)²]; The boundary of the anatomical structure is represented by its geometric radius, structure_radius. The boundary safety distance d_boundary = distance_center − structure_radius is defined, and the non-negative gap distance from the trajectory to the structure boundary, distance_to_trajectory = max(0, d_boundary), is defined accordingly. Here, d_boundary ≤ 0 indicates that the trajectory intersects, contacts, or intrudes into the structure boundary, and d_boundary > 0 indicates that the trajectory is outside the structure boundary and the minimum gap is d_boundary. Here, projection_x and projection_y are the projection coordinates of the center of the anatomical structure on the trajectory line segment.

3. The puncture needle navigation system based on the CNB ejection mechanism as described in claim 2, characterized in that, The graded risk assessment model is a multi-level risk assessment model based on distance thresholds. The system establishes risk threshold configurations for 7 types of anatomical structure targets and performs risk assessment based on the shortest distance from the ejection trajectory to the anatomical structure. Artery, Category 0, Critical Risk Threshold 5.0 mm, Warning Threshold 8.0 mm, Priority 9; Vein, Category 1, Critical Risk Threshold 3.0mm, Warning Threshold 5.0mm, Priority 7; Esophagus, Category 5, Critical Risk Threshold 3.0 mm, Warning Threshold 5.0 mm, Priority 7; Diaphragm, Category 6, Critical Risk Threshold 2.0 mm, Warning Threshold 4.0 mm, Priority 6; Skeleton, Category 3, Critical Risk Threshold 0.0mm, Warning Threshold 1.0mm, Priority 8; Lesion, Category 4, danger threshold 0.0mm, is a puncture target, no need to avoid it, warning threshold 0.0mm; Lymph node, Category 2, danger threshold 0.0 mm, is a puncture target, no avoidance required, warning threshold 0.0 mm.

4. The puncture needle navigation system based on the CNB ejection mechanism as described in claim 3, characterized in that, The system establishes a multi-dimensional safety assessment framework that includes an overall safety score and a critical risk list. The critical risk list is a collection of anatomical structure information that has reached the critical risk level detected by the system during the catapult trajectory safety assessment process. The judgment rule for the critical risk list is: when the gap distance between the anatomical structure and the catapult trajectory is less than the critical risk threshold of the structure, the structure is added to the critical risk list. An empty critical risk list indicates no critical risks, while a non-empty list indicates the presence of critical risks requiring attention. The overall safety score uses a standardized scoring system from 1.0 to 0.0, where 1.0 represents the safest state and 0.0 represents the most dangerous state. The system automatically triggers an adjustment suggestion generation process based on the status of critical risks in the critical risk list. Adjustment suggestions include adjusting the ejection distance, changing the needle insertion angle, and selecting different needle insertion points. The system uses a cumulative penalty model to calculate the overall safety score. The base score is 1.0 in the safest state (no risk), and the penalty coefficient is adjusted according to the detected risk level. Overall safety score = base score × penalty; Penalty is the penalty coefficient, which is set according to the risk level: critical risk penalty = 0.1, warning risk penalty = 0.7, and safety penalty = 1.

0. When multiple risks exist at the same time, the penalty is the minimum value of the penalty coefficient of each risk.

5. The puncture needle navigation system based on the CNB ejection mechanism as described in claim 4, characterized in that, The adjustment of the ejection distance is specifically as follows: the system sorts and selects the preferred scheme from the set of feasible ejection distances that meet the hit constraint and safety threshold constraint from the adjustable ejection distance options according to the preset distance preference rule; when a critical risk occurs, the shorter feasible ejection distance is selected first. In the set of feasible ejection distances, the system prioritizes the following sorting rules: (1) Hit geometric feasibility priority: the scheme that meets the hit geometric constraint is selected first, and the scheme under the optimal sampling condition has a higher priority than the general hit condition; (2) Safety level priority: under the premise of meeting the hit constraint, the scheme with a higher overall safety score is selected first; (3) Distance preference rule: under the same conditions, the scheme with an ejection distance closer to the preset standard distance of 22.0mm is selected first, and the distance preference degree is defined as: preference=1.0−|current ejection distance−22.0| / 22.

0.

6. The puncture needle navigation system based on the CNB ejection mechanism as described in claim 4, characterized in that, The system establishes a comprehensive scoring model for CNB catapult configurations to conduct multi-dimensional comprehensive quality assessments of different catapult configuration schemes while meeting safety constraints. The comprehensive scoring model adopts a multi-factor weighted summation method, and the calculation formula is as follows: CNB Comprehensive Score = Target Score × 0.3 + Safety Score × 0.4 + Distance Factor × 0.2 + Angle Factor × 0.1; where: Target score: Based on the accuracy of the ejection trajectory in hitting the target area, the value ranges from 0 to 1. When the ejection trajectory completely passes through the target area and the sampling length meets the standard, the score is 1.0; when it partially hits, the score is 0.3-0.7; and when it completely deviates, the score is 0.

1. Safety score: The overall safety score calculated using the cumulative penalty model, with a value range of 0-1, is output from the overall safety score under the standardized scoring system; Distance factor: The score is based on the operating distance from the needle insertion point to the target center. The value range is 0-1. The ideal operating distance is 50mm and the score is 1.

0. The greater the distance deviates from the ideal value, the lower the score. Angle factor: A clinical preference score based on the needle insertion angle, with a value range of 0-1. The score is 1.0 when the needle is inserted perpendicularly at 90 degrees, and the larger the angle deviates from 90 degrees, the lower the score. The system provides four scoring modes based on different optimization scenarios: (1) Comprehensive mode: Uses a complete four-factor formula to comprehensively evaluate the overall configuration of the needle entry point and angle; (2) Ejection distance optimization mode: Only target score, safety score and distance factor are used, and the weights are renormalized to 0.333, 0.444 or 0.222, which are used to optimize the ejection distance selection under the premise of fixed needle entry point and angle; (3) Angle optimization mode: Only target score, safety score and angle factor are used, and the weights are renormalized to 0.375, 0.500 or 0.125, which is used to optimize the needle entry angle under the premise of fixed needle entry point; (4) Basic mode: Only target score and safety score are used, and the weights are renormalized to 0.429 or 0.571 for rapid assessment of the feasibility of the scheme.

7. The puncture needle navigation system based on the CNB ejection mechanism as described in claim 6, characterized in that, The distance factor is calculated as follows: Scoring is based on the deviation between the actual operating distance (distance_mm) from the needle insertion point to the target center and the ideal operating distance (50mm). The specific rules are as follows: When 30mm ≤ distance_mm ≤ 80mm, it is within the acceptable range. The score decreases linearly based on the deviation from the ideal distance: distance_score = 1.0 - |distance_mm - 50| / max(20, 30) × 0.3, with a maximum deduction of 30%. When 20mm≤distance_mm<30mm or 80mm<distance_mm≤100mm, it is within the tolerance range, and the score decreases linearly to the range of 0.5-0.

7. When distance_mm < 20mm or distance_mm > 100mm, it exceeds the tolerance range and the score is 0.1, indicating that the operating distance is extremely inconvenient. The angle factor is calculated as follows: Scoring is based on the angle deviation (angle_deviation) between the needle insertion angle and the ideal perpendicular angle of 90 degrees. The specific rules are as follows: When angle_deviation ≤ 15 degrees, it is within the acceptable deviation range, and the score decreases linearly: angle_score = 1.0 - angle_deviation / 15 × 0.2, with a maximum deduction of 20%; When 15 degrees < angle_deviation ≤ 30 degrees, it is within the tolerance deviation range, and the score rapidly decreases to the 0.3-0.8 range; When angle_deviation > 30 degrees, the score decreases further but maintains some flexibility, with a minimum of 0.

1.

8. The puncture needle navigation system based on the CNB ejection mechanism as described in claim 4, characterized in that, The change in needle insertion angle specifically involves the system combining the angle constraints in the medical A* algorithm with the recommended maximum angle change of 30 degrees to provide angle adjustment guidance to the operator. The medical A* algorithm is a specialized algorithm designed for medical puncture scenarios based on the classic A* path search algorithm. It establishes a medical grid space as the search basis and integrates medical constraint parameters. The algorithm includes a five-level medical safety threshold system, setting comfortable operation range, clinically acceptable range, high-risk operation range, extremely dangerous operation range, and technically prohibited range. When the angle change between path segments exceeds the preset maximum angle change limit, an angle change penalty is applied. The angle is calculated directly as follows: α = arctan2(Δy,Δx) × 180° / π, where α is the needle tip angle, i.e., the needle insertion angle, Δx = target x-coordinate - needle insertion point x-coordinate, and Δy = target y-coordinate - needle insertion point y-coordinate.

9. The puncture needle navigation system based on the CNB ejection mechanism as described in any one of claims 5 to 8, characterized in that, The multi-dimensional security assessment framework also includes a warning information list. This list outputs the gap distance (distance_to_trajectory) in a tiered manner based on the detected anatomical structure type and its preset risk distance threshold, with each tier mutually exclusive. (1) Arteries: distance_to_trajectory≤5.0mm is "critical risk"; 5.0mm<distance_to_trajectory≤8.0mm is "warning"; distance_to_trajectory>8.0mm is "safe"; (2) Veins: distance_to_trajectory≤3.0mm is "critical risk"; 3.0mm<distance_to_trajectory≤5.0mm is "warning"; distance_to_trajectory>5.0mm is "safe"; (3) Esophagus: distance_to_trajectory≤3.0mm is "critical risk"; 3.0mm<distance_to_trajectory≤5.0mm is "warning"; distance_to_trajectory>5.0mm is "safe"; (4) Diaphragm: distance_to_trajectory≤2.0mm is "critical risk"; 2.0mm<distance_to_trajectory≤4.0mm is "warning"; distance_to_trajectory>4.0mm is "safe"; (5) Skeleton: As a physical obstacle area, when distance_to_trajectory = 0.0mm (that is, the boundary safety distance d_boundary≤0, indicating that the ejection trajectory intersects, contacts or invades the interior of the skeleton boundary), it is a "critical risk"; 0.0mm < distance_to_trajectory ≤ 1.0mm indicates a "warning"; distance_to_trajectory > 1.0mm indicates a "safe" condition. (6) Lesions and lymph nodes: As the target area, they are not to be avoided. Their critical_clearance and warning_clearance are both 0.0mm. They are marked as "safe / crossable" by default. When multiple risks exist at the same time, the warning information list will output multiple risk level labels and prompts at the same time, and the highest priority risk will be used as the main prompt. The risk level is adjusted for the overall safety score using a post-processing penalty factor: Final safety score = Base score × Penalty; The base score is 1.0 in the safest state with no risk; the penalty coefficient is determined according to the risk level: critical risk penalty = 0.1, warning risk penalty = 0.7, and safe penalty = 1.0; when multiple risks exist at the same time, the penalty coefficient is the minimum value of the penalty coefficients of each risk. In obstacle zones, skeletal structures act as physical barriers, and are completely bypassed during path planning.

10. The puncture needle navigation system based on the CNB ejection mechanism as described in claim 1, characterized in that, The system establishes a ballistic error calculation model for the ejection trajectory, including position error calculation, relative error calculation, and angle error calculation; In the CNB trajectory validator, the position error is calculated using the Euclidean distance formula: Position E = √[(predicted x - actual x)² + (predicted y - actual y)²] × k; where... E position: Position error, in millimeters; x-prediction, y-prediction: The coordinates of the launch endpoint predicted by the algorithm, in pixels; x_actual, y_actual: The actual recorded coordinates of the needle tip impact point, in pixels; k=0.208998: Pixel pitch calibration coefficient, in mm / pixel. This coefficient is based on the standard image resolution and physical size calibration of the ultrasound equipment to ensure the accuracy of coordinate transformation. Relative error reflects the proportional relationship between prediction error and launch distance: E relative = (E position / D ejection) × 100; E-relative: Relative error, expressed as a percentage (%); D ejection: ejection distance, set to 22.0mm in the CNB system; The angle error is obtained by calculating the angle between the predicted trajectory vector and the actual impact trajectory vector: Angle E = arccos[cos(θ)] × (180° / π), cos(θ) = (Vpredicted·Vactual) / (|Vpredicted| × |Vactual|), where the cosine value cos(θ) needs to be protected by the numerical domain, i.e., cos(θ) = max(-1.0, min(1.0, cos(θ))). The numerical domain protection mechanism forces cos(θ) to be within the range of [-1.0, 1.0] to prevent floating-point operation errors from causing the inverse cosine function calculation to fail, thus improving the numerical stability of the algorithm. When |Vpredicted| = 0 or |Vactual| = 0, the denominator is 0. The system marks the angle error as unusable and skips the calculation, or sets it to 0 according to the preset rules, thereby avoiding division by zero. V-prediction: The vector pointing from the tip of the needle to the predicted ejection endpoint, V-prediction = (x-prediction - x-tip, y-prediction - y-tip); Vactual: The vector from the needle tip to the actual point of impact, Vactual = (xactual - xneedle tip, yactual - yneedle tip). E angle: angular error, in degrees (°); x needle tip, y needle tip: Coordinates of the needle tip position at the start of ejection; ·: Vector dot product operation; |Vprediction|: Euclidean magnitude of the prediction vector; |Vactual|: Euclidean magnitude of the actual vector; max, min: Numerical constraint functions that ensure the cosine value is within the valid range [-1, 1].