aceA polyline searching-driven evolutionary AI for disease detection of medical imaging data
Abstract: Objective. Accurate Ultrasound (US) prostate cancer (PCa) segmentation images hold significant value for organ interventional guidance and clinical disease diagnosis. However, this task still poses substantial challenges. The main obstacles include blurred or incomplete boundaries separating PCa from adjacent soft tissues, shadow artifacts inherent to ultrasound imaging, and drastic inter-patient variations in organ morphological shapes. Approach . To address these issues, our method introduces a novel coarse-to…
OhioHealth - Doctors Hospital 1 by Sixflashphoto. CC BY-SA 4.0 · https://creativecommons.org/licenses/by-sa/4.0
Accurate Ultrasound (US) prostate cancer (PCa) segmentation images hold significant value for organ interventional guidance and clinical disease diagnosis. However, this task still poses substantial challenges.
To address these issues, our method introduces a novel coarse-to-fine optimization framework to overcome these challenges on ultrasound data, which comprises four main stages: (1) initial region of interest (ROI) localization using a deep learning model; (2) vertex sequence determination through a principal curve-based polyline search; (3) optimal initialization of the backpropagation neural network (NN) via an enhanced quantum evolutionary algorithm; (4) defining the ROI boundary with a mathematical model based on NN parameters. Our method outperforms current algorithms in ultrasound PCa data, achieving mean Dice similarity coefficient (DSC), Jaccard similarity coefficient (OMG), and accuracy (ACC) of 83.6 ± 3.1%, 71.8 ± 2.5%, and 83.5 ± 3.1%, respectively.
- Accurate Ultrasound (US) prostate cancer (PCa) segmentation images hold significant value for organ interventional guidance and clinical disease diagnosis.
- However, this task still poses substantial challenges.
- The main obstacles include blurred or incomplete boundaries separating PCa from adjacent soft tissues, shadow artifacts inherent to ultrasound imaging, and drastic inter-patient variations in organ morphological shapes.
Our method outperforms current algorithms in ultrasound PCa data, achieving mean Dice similarity coefficient (DSC), Jaccard similarity coefficient (OMG), and accuracy (ACC) of 83.6 ± 3.1%, 71.8 ± 2.5%, and 83.5 ± 3.1%, respectively.
The rundown
The main obstacles include blurred or incomplete boundaries separating PCa from adjacent soft tissues, shadow artifacts inherent to ultrasound imaging, and drastic inter-patient variations in organ morphological shapes. To address these issues, our method introduces a novel coarse-to-fine optimization framework to overcome these challenges on ultrasound data, which comprises four main stages: (1) initial region of interest (ROI) localization using a deep learning model; (2) vertex sequence determination through a principal curve-based polyline search; (3) optimal initialization of the backpropagation neural network (NN) via an enhanced quantum evolutionary algorithm; (4) defining the ROI boundary with a mathematical model based on NN parameters.
Sources
- Peer-reviewedPhysics in Medicine & Biology2026-09-02
How should this claim be treated?
The debate