Tracing 3D Anatomy in 2D Strokes: A Multi-Stage Projection Driven Approach to Cervical Spine Fracture Identification

• URL: http://arxiv.org/abs/2601.15235v1
• Date: Wed, 21 Jan 2026 18:15:47 GMT
• Title: Tracing 3D Anatomy in 2D Strokes: A Multi-Stage Projection Driven Approach to Cervical Spine Fracture Identification
• Authors: Fabi Nahian Madhurja, Rusab Sarmun, Muhammad E. H. Chowdhury, Adam Mushtak, Israa Al-Hashimi, Sohaib Bassam Zoghoul,
• Abstract summary: This study explores the viability of 2D projection-based vertebra segmentation for vertebra-level fracture detection in 3D CT volumes.<n>Regions of interest are identified using the YOLOv8 model from all views and combined to approximate the 3D cervical spine area.<n>A DenseNet121-Unet-based multi-label segmentation leveraging variance- and energy-based projections achieves a Dice score of 87.86 percent.
• Score: 6.060672815761177
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Cervical spine fractures are critical medical conditions requiring precise and efficient detection for effective clinical management. This study explores the viability of 2D projection-based vertebra segmentation for vertebra-level fracture detection in 3D CT volumes, presenting an end-to-end pipeline for automated analysis of cervical vertebrae (C1-C7). By approximating a 3D volume through optimized 2D axial, sagittal, and coronal projections, regions of interest are identified using the YOLOv8 model from all views and combined to approximate the 3D cervical spine area, achieving a 3D mIoU of 94.45 percent. This projection-based localization strategy reduces computational complexity compared to traditional 3D segmentation methods while maintaining high performance. It is followed by a DenseNet121-Unet-based multi-label segmentation leveraging variance- and energy-based projections, achieving a Dice score of 87.86 percent. Strategic approximation of 3D vertebral masks from these 2D segmentation masks enables the extraction of individual vertebra volumes. The volumes are analyzed for fractures using an ensemble of 2.5D Spatio-Sequential models incorporating both raw slices and projections per vertebra for complementary evaluation. This ensemble achieves vertebra-level and patient-level F1 scores of 68.15 and 82.26, and ROC-AUC scores of 91.62 and 83.04, respectively. We further validate our approach through an explainability study that provides saliency map visualizations highlighting anatomical regions relevant for diagnosis, and an interobserver variability analysis comparing our model's performance with expert radiologists, demonstrating competitive results.

Related papers

• 3DLAND: 3D Lesion Abdominal Anomaly Localization Dataset [8.974431489804337]
  3DLAND is a large-scale benchmark dataset comprising over 6,000 contrast-enhanced CT volumes with over 20,000 high-fidelity 3D lesion annotations linked to seven abdominal organs: liver, pancreas, kidneys, spleen, stomach, and gallbladder.<n>Our pipeline integrates automated spatial reasoning, prompt-optimized 2D segmentation, and memory-guided 3D propagation, validated by expert radiologists with surface dice scores exceeding 0.75.<n>Our dataset establishes a new benchmark for evaluating organ-aware 3D segmentation models, paving the way for advancements in healthcare-oriented AI.
  arXiv  Detail & Related papers  (2026-02-13T11:08:15Z)
• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• 3D Spine Shape Estimation from Single 2D DXA [49.53978253009771]
  We propose an automated framework to estimate the 3D spine shape from 2D DXA scans.<n>We achieve this by explicitly predicting the sagittal view of the spine from the DXA scan.
  arXiv  Detail & Related papers  (2024-12-02T13:58:26Z)
• Triage of 3D pathology data via 2.5D multiple-instance learning to guide pathologist assessments [7.735043623909641]
  We present CARP3D, a deep learning triage approach that automatically identifies the highest-risk 2D slices within 3D volumetric biopsy. For prostate cancer risk stratification, CARP3D achieves an area under the curve (AUC) of 90.4% for triaging slices, outperforming methods relying on independent analysis of 2D sections.
  arXiv  Detail & Related papers  (2024-06-11T08:42:07Z)
• VertDetect: Fully End-to-End 3D Vertebral Instance Segmentation Model [0.0]
  This paper proposes VertDetect, a fully automated end-to-end 3D vertebral instance segmentation Convolutional Neural Network (CNN) model. The utilization of a shared CNN backbone provides the detection and segmentation branches of the network with feature maps containing both spinal and vertebral level information. This model achieved state-of-the-art performance for an end-to-end architecture, whose design facilitates the extraction of features that can be subsequently used for downstream tasks.
  arXiv  Detail & Related papers  (2023-11-16T15:29:21Z)
• Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labeling [66.75096111651062]
  We created a large-scale dataset of 10,021 thoracic CTs with 157 labels. We applied an ensemble of 3D anatomy segmentation models to extract anatomical pseudo-labels. Our resulting segmentation models demonstrated remarkable performance on CXR.
  arXiv  Detail & Related papers  (2023-06-06T18:01:08Z)
• propnet: Propagating 2D Annotation to 3D Segmentation for Gastric Tumors on CT Scans [16.135854257728337]
  This study introduces a model, utilizing human-guided knowledge and unique modules, to address the challenges of 3D tumor segmentation. With 98 patient scans for training and 30 for validation, our method achieves a significant agreement with manual annotation (Dice of 0.803) and improves efficiency.
  arXiv  Detail & Related papers  (2023-05-29T03:24:02Z)
• Semi-Supervised Hybrid Spine Network for Segmentation of Spine MR Images [14.190504802866288]
  We propose a two-stage algorithm, named semi-supervised hybrid spine network (SSHSNet) to achieve simultaneous vertebral bodies (VBs) and intervertebral discs (IVDs) segmentation. In the first stage, we constructed a 2D semi-supervised DeepLabv3+ by using cross pseudo supervision to obtain intra-slice features and coarse segmentation. In the second stage, a 3D full-resolution patch-based DeepLabv3+ was built to extract inter-slice information. Results show that the proposed method has great potential in dealing with the data imbalance problem
  arXiv  Detail & Related papers  (2022-03-23T02:57:14Z)
• A unified 3D framework for Organs at Risk Localization and Segmentation for Radiation Therapy Planning [56.52933974838905]
  Current medical workflow requires manual delineation of organs-at-risk (OAR) In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation. Our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging.
  arXiv  Detail & Related papers  (2022-03-01T17:08:41Z)
• Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices [48.85784310158493]
  We propose a Modified Pseudo-3D Feature Pyramid Network (MP3D FPN) to efficiently extract 3D context enhanced 2D features for universal lesion detection in CT slices. With the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset. The proposed 3D pre-trained weights can potentially be used to boost the performance of other 3D medical image analysis tasks.
  arXiv  Detail & Related papers  (2020-12-16T07:11:16Z)
• VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images [121.31355003451152]
  Large Scale Vertebrae Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020. We present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view.
  arXiv  Detail & Related papers  (2020-01-24T21:09:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.