Tracking temporal progression of benign bone tumors through X-ray based detection and segmentation

X-ray is the most widely used imaging modality for the initial diagnosis of bone tumors due to its accessibility and cost-effectiveness. However, the longitudinal comparison of benign bone tumors, particularly for assessing size and shape progression over time, remains largely manual and subjective. In this study, we propose FusionX-BBTNet, a deep learning-based framework that enables automated detection, segmentation, and time-sequential analysis of BBTs from X-ray images. The framework combines YOLO-based object detection with U-Net segmentation, and utilizes a novel wavelet-enhanced dataset to improve contour accuracy. To enable real-world quantification, an OCR-based module is used to extract the X-ray scale bar and compute the pixel-to-length conversion ratio. With this, tumor size and area are calculated in millimeters, and their changes over time are visualized through centroid-based alignment. The proposed method was validated on a dataset of 466 expert-annotated X-ray images, achieving a mean IoU of 0.9376 and a boundary F1 score of 0.9827. In addition to providing reliable tumor localization and measurement, the system supports clinical decision-making by offering intuitive shape and area comparisons. This approach has the potential to complement expert interpretation and improve diagnostic efficiency, especially in environments with limited radiological expertise.

• Publication year

  2025

• Venue

  Scientific Reports

• Publication date

  2025-11-11

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.1038/s41598-025-23053-4PMID 41219269PMCID 12606321
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Mixture of Expert-Based SoftMax-Weighted Box Fusion for Robust Lesion Detection in Ultrasound Imaging

  2025cited by this paper
• A Radiograph Dataset for the Classification, Localization, and Segmentation of Primary Bone Tumors

  2025cited by this paper
• Automated ultrasonography of hepatocellular carcinoma using discrete wavelet transform based deep-learning neural network

  2025cited by this paper
• Automatic Lower-Limb Length Measurement Network (A3LMNet): A Hybrid Framework for Automated Lower-Limb Length Measurement in Orthopedic Diagnostics

  2025cited by this paper
• Enhanced enchondroma detection from x‐ray images using deep learning: A step towards accurate and cost‐effective diagnosis

  2024cited by this paper
• Conventional radiography for the assessment of focal bone lesions of the appendicular skeleton: fundamental concepts in the modern imaging era

  2024cited by this paper
• Analysis of Optical Character Recognition using EasyOCR under Image Degradation

  2023influential reference
• Deep learning-based detection of primary bone tumors around the knee joint on radiographs: a multicenter study

  2023cited by this paper
• Bone Tumor Risk Stratification and Management System: A Consensus Guideline from the ACR Bone Reporting and Data System Committee.

  2023cited by this paper
• Comparison of clinical effect of MR imaging combined with simulated X-ray and magnetic resonance imaging in patients with benign and malignant bone tumors

  2022cited by this paper
• X-ray and MRI Correlation of Bone Tumors Using Histopathology As Gold Standard

  2022cited by this paper
• Optimisation of postoperative X-ray acquisition for orthopaedic patients

  2022cited by this paper
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

  2021cited by this paper
• Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation

  2021cited by this paper
• The Lodwick classification for grading growth rate of lytic bone tumors: a decision tree approach

  2021cited by this paper
• Multitask Deep Learning for Segmentation and Classification of Primary Bone Tumors on Radiographs.

  2021cited by this paper
• Solitary enchondromas—diagnosis and surveillance

  2020cited by this paper
• Systematic approach to musculoskeletal benign tumors

  2017cited by this paper
• The EANM practice guidelines for bone scintigraphy

  2016cited by this paper
• Periosteal osteosarcoma: a review of clinical evidence.

  2015cited by this paper
• U-Net: Convolutional Networks for Biomedical Image Segmentation

  2015influential reference
• You Only Look Once: Unified, Real-Time Object Detection

  2015influential reference
• The role of magnetic resonance imaging in the evaluation of bone tumours and tumour-like lesions

  2014cited by this paper
• From the radiologic pathology archives: ewing sarcoma family of tumors: radiologic-pathologic correlation.

  2013cited by this paper
• Radiography in the initial diagnosis of primary bone tumors.

  2013cited by this paper
• Benign bone tumors.

  2011cited by this paper
• Periosteal reaction.

  2009cited by this paper
• [Periosteal reaction].

  1999cited by this paper
• A Computational Approach to Edge Detection

  1986cited by this paper
• Determining growth rates of focal lesions of bone from radiographs.

  1980cited by this paper
• Optical Character Recognition

  1972influential reference

• No citing papers are available for this paper.