1. A kidney stone detection system comprising: a CT image acquisition module (101) configured to capture computed tomography scans of renal regions; a preprocessing unit (102) configured to normalize CT images and extract regions of interest; a deep learning segmentation module (103) comprising architectures selected from RepVIT, ConvNeXtV2, and FocalNet, trained to identify kidney stones; a classification unit (104) configured to distinguish stone types based on extracted features; and an evaluation module (105) configured to compute performance metrics including accuracy, precision, recall, F1-score, and ROC-AUC.

2. A method for detecting kidney stones from CT images, comprising: acquiring CT images using the CT image acquisition module (101); preprocessing the images with normalization and region-of-interest extraction using the preprocessing unit (102); segmenting kidney stones using the deep learning segmentation module (103); classifying stone types with the classification unit (104); and evaluating detection performance using the evaluation module (105).

3. The system as claimed in Claim 1, wherein ConvNeXtV2 (103a) achieves superior accuracy and generalization compared to RepVIT (103b) and FocalNet (103c).

4. The system as claimed in Claim 1, wherein RepVIT (103b) provides faster inference with reduced computational overhead.

5. The system as claimed in Claim 1, wherein FocalNet (103c) employs transformer-inspired attention mechanisms for multi-scale feature extraction.

6. The method as claimed in Claim 2, wherein preprocessing (102) includes standardized normalization and removal of irrelevant background regions.

7. The system as claimed in Claim 1, wherein the evaluation module (105) outputs Dice and IoU scores for segmentation accuracy.

8. The system as claimed in Claim 1, wherein the classification unit (104) distinguishes mineral-specific texture variations between stone types.

9. The system as claimed in Claim 1, wherein the detection framework supports near real-time clinical use in CT workflows

Description:FIELD OF THE INVENTION
This invention relates to kidney stone detection from computed tomography images using deep learning segmentation methods.
BACKGROUND OF THE INVENTION
Traditional image analysis methods and manual interpretation by radiologists can be slow, inconsistent, and prone to subjective bias, especially when dealing with fine-grained mineral variations that require precise feature understanding. Conventional deep learning models may struggle to capture these subtle patterns due to limited receptive fields and inadequate global feature representation, resulting in reduced classification accuracy. An automated, reliable, and highly accurate kidney stone detection system capable of distinguishing various stone types from CT images using advanced deep learning architectures is developed
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
Kidney stone identification is critical for guiding appropriate treatment decisions and preventing long-term renal complications. Computed tomography (CT) imaging is widely used for diagnosing kidney stones. Manual interpretation of CT scans is time-consuming, prone to subjectivity, and may fail to capture subtle textural differences between stone types. To address these challenges, this study presents an automated kidney stone detection framework using three modern deep learning architectures: RepVIT, ConvNeXtV2, and Focal Net. Each model is trained on pre-processed CT images after applying standardized normalization and region-of-interest extraction techniques. Performance is evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics. Among the three architectures, ConvNeXtV2 consistently achieves the highest classification accuracy and strongest generalization, demonstrating superior capability in capturing fine-grained CT texture patterns essential for distinguishing stone types. RepVIT provides competitive performance with faster inference, while Focal Net shows limitations in learning mineral-specific texture variations. The study highlights the potential of modern CNN architectures, particularly ConvNeXtV2, in developing reliable, automated kidney stone detection systems that can support clinical decision-making and improve diagnostic efficiency. To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: System Architecture
FIGURE 2: Dataflow diagram
FIGURE 3: Class Diagram
FIGURE 4: Sequence Diagram
FIGURE 1: Dataflow diagram
FIGURE 5: Stone is detected in the above simulation
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The present invention relates to an automated kidney stone detection framework that leverages deep learning segmentation methods to improve diagnostic accuracy and efficiency. The system begins with a CT image acquisition module (101) that captures high-resolution scans of renal regions. These images are processed by a preprocessing unit (102), which performs normalization and region-of-interest extraction to ensure consistent input quality and removal of irrelevant background data.
The processed images are then analyzed by a deep learning segmentation module (103), which incorporates modern architectures such as ConvNeXtV2 (103a), RepVIT (103b), and FocalNet (103c). ConvNeXtV2 demonstrates superior accuracy and generalization in capturing fine-grained CT texture patterns, RepVIT provides competitive performance with faster inference, and FocalNet applies transformer-inspired attention mechanisms for multi-scale feature extraction.
Following segmentation, a classification unit (104) distinguishes between different stone types based on mineral-specific texture variations. The system’s performance is validated by an evaluation module (105), which computes metrics including accuracy, precision, recall, F1-score, ROC-AUC, Dice, and IoU scores.
Experimental results confirm that ConvNeXtV2 achieves the highest classification accuracy, while RepVIT offers low computational overhead suitable for near real-time clinical workflows. The integration of these modules enables robust detection of kidney stones across diverse CT variations, reducing subjectivity and time delays associated with manual interpretation.
By combining CT imaging (101), preprocessing (102), advanced segmentation (103), classification (104), and evaluation (105), the invention provides a reliable, automated diagnostic tool that supports clinical decision-making, enhances diagnostic efficiency, and minimizes long-term renal complications.
Kidney stone identification is critical for guiding appropriate treatment decisions and preventing long-term renal complications. Computed tomography (CT) imaging is widely used for diagnosing kidney stones. Manual interpretation of CT scans is time-consuming, prone to subjectivity, and may fail to capture subtle textural differences between stone types. To address these challenges, this study presents an automated kidney stone detection framework using three modern deep learning architectures: RepVIT, ConvNeXtV2, and Focal Net. Each model is trained on pre-processed CT images after applying standardized normalization and region-of-interest extraction techniques. Performance is evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics. Among the three architectures, ConvNeXtV2 consistently achieves the highest classification accuracy and strongest generalization, demonstrating superior capability in capturing fine-grained CT texture patterns essential for distinguishing stone types. RepVIT provides competitive performance with faster inference, while Focal Net shows limitations in learning mineral-specific texture variations. The study highlights the potential of modern CNN architectures, particularly ConvNeXtV2, in developing reliable, automated kidney stone detection systems that can support clinical decision-making and improve diagnostic efficiency.
The proposed system captures multi-scale, high-resolution stone features with superior accuracy and robustness across challenging CT variations
ADVANTAGES OF THE INVENTION
Enhanced Multi-Scale Representation
Improved Robustness to CT Variability
Transformer-inspired attention (FocalNet) and optimized convolutional blocks (ConvNeXtV2, RepViT) deliver better Dice/IoU scores compared to classical U-Net–style networks.
RepViT and ConvNeXtV2 offer fast inference with low computational overhead, enabling near real-time clinical use in CT workflows.
 
, Claims:1. A kidney stone detection system comprising:
a CT image acquisition module (101) configured to capture computed tomography scans of renal regions;
a preprocessing unit (102) configured to normalize CT images and extract regions of interest;
a deep learning segmentation module (103) comprising architectures selected from RepVIT, ConvNeXtV2, and FocalNet, trained to identify kidney stones;
a classification unit (104) configured to distinguish stone types based on extracted features; and
an evaluation module (105) configured to compute performance metrics including accuracy, precision, recall, F1-score, and ROC-AUC.
2. A method for detecting kidney stones from CT images, comprising:
acquiring CT images using the CT image acquisition module (101);
preprocessing the images with normalization and region-of-interest extraction using the preprocessing unit (102);
segmenting kidney stones using the deep learning segmentation module (103);
classifying stone types with the classification unit (104); and
evaluating detection performance using the evaluation module (105).
3. The system as claimed in Claim 1, wherein ConvNeXtV2 (103a) achieves superior accuracy and generalization compared to RepVIT (103b) and FocalNet (103c).
4. The system as claimed in Claim 1, wherein RepVIT (103b) provides faster inference with reduced computational overhead.
5. The system as claimed in Claim 1, wherein FocalNet (103c) employs transformer-inspired attention mechanisms for multi-scale feature extraction.
6. The method as claimed in Claim 2, wherein preprocessing (102) includes standardized normalization and removal of irrelevant background regions.
7. The system as claimed in Claim 1, wherein the evaluation module (105) outputs Dice and IoU scores for segmentation accuracy.
8. The system as claimed in Claim 1, wherein the classification unit (104) distinguishes mineral-specific texture variations between stone types.
9. The system as claimed in Claim 1, wherein the detection framework supports near real-time clinical use in CT workflows