Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0826
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-08-18T06:06:03.799739Z
status: published
lens: g_space
sector: health
headline: IShuffleNet-PCNN hybrid classifier within an MResU-Net-based framework for spinal cord injury detection and classification using CT images
dek: Spinal cord injury (SCI) is a serious medical condition. Spinal Cord Injury limits the movement of the body, blocks the nervous system and affects the quality of life of an injured patient. Accurate detection and classification of these fractures are essential for timely diagnosis and treatment planning; however, conventional assessment methods often struggle with noise, variability, and subtle injury patterns in CT imaging.This study aimed to develop an integrated deep learning framework for accurate and robust…
gain_title: An integrated framework using WBAF preprocessing, MResU-Net segmentation, IPHOG feature extraction and IShuffleNet-PCNN classification achieved 0.933 accuracy and 0.991 NPV for spinal cord injury-related fracture classification from CT images.
problem_title: (none)
trace_subject: (none)
gain_reading: An integrated framework using WBAF preprocessing, MResU-Net segmentation, IPHOG feature extraction and IShuffleNet-PCNN classification achieved 0.933 accuracy and 0.991 NPV for spinal cord injury-related fracture classification from CT images.
gain_evidence: The proposed IShuffleNet-PCNN achieved an accuracy of 0.933, precision of 0.937, and negative predictive value (NPV) of 0.991, demonstrating effective classification performance. | The proposed deep learning framework demonstrated promising performance for CT-based spinal cord injury classification.
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers developed a four-stage deep learning framework for CT-based spinal cord injury fracture assessment, combining Weighted Balanced Anisotropic Filtering for denoising, Modified Residual U-Net for spinal cord segmentation, Improved Pyramid Histogram of Oriented Gradients for feature extraction, and a new IShuffleNet-Parallel CNN classifier with Group Normalization and Adaptive Swish-Mish activation.

By publication on 2026-08-17 the framework had shown measured classification results of 0.933 accuracy, 0.937 precision and 0.991 NPV in the study evaluation, suggesting potential to assist automated fracture assessment, though the text presents this as promising performance rather than validated clinical deployment or prospective patient outcomes.
limitation: 
tag: Evidence-backed gain
key_points: Preprocessing used Weighted Balanced Anisotropic Filtering (WBAF) to reduce CT image noise while preserving structural information. | Segmentation of spinal cord regions was performed with Modified Residual U-Net (MResU-Net). | Feature extraction used Improved Pyramid Histogram of Oriented Gradients (IPHOG) with Gaussian smoothing and adaptive weighting. | Classifier IShuffleNet-PCNN incorporated Group Normalization and Adaptive Swish-Mish activation to improve training stability and feature discrimination.
rundown: The pipeline was organized in four stages: WBAF for noise reduction, MResU-Net for anatomical segmentation, IPHOG for discriminative structural and fracture-related feature extraction, and IShuffleNet-PCNN for final classification.

The authors report the classifier reached precision of 0.937 alongside accuracy of 0.933 and NPV of 0.991, and describe the integration as providing potential support for timely clinical decision-making in fracture assessment.
sources:
- peer_reviewed | European Spine Journal | https://doi.org/10.1007/s00586-026-10260-4 | 2026-08-17
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

d9088095b99d3515a9f2484b6269cb6c083f4669901a40f95d5d201f0ca784c3

previous

0000000000000000000000000000000000000000000000000000000000000000