Cascade learning in multi-task encoder-decoder networks for concurrent bone segmentation and glenohumeral joint assessment in shoulder CT scans

• URL: http://arxiv.org/abs/2410.12641v1
• Date: Wed, 16 Oct 2024 15:00:31 GMT
• Title: Cascade learning in multi-task encoder-decoder networks for concurrent bone segmentation and glenohumeral joint assessment in shoulder CT scans
• Authors: Luca Marsilio, Davide Marzorati, Matteo Rossi, Andrea Moglia, Luca Mainardi, Alfonso Manzotti, Pietro Cerveri,
• Abstract summary: This work introduces an innovative deep-learning framework processing shoulder CT scans. It features the semantic segmentation of the humerus and scapula, the 3D reconstruction of bone surfaces, and the identification of the glenohumeral joint region. The pipeline comprises two cascaded CNN architectures: 3D CEL-UNet for segmentation and 3D Arthro-Net for threefold classification.
• Score: 0.8974531206817744
• License:
• Abstract: Osteoarthritis is a degenerative condition affecting bones and cartilage, often leading to osteophyte formation, bone density loss, and joint space narrowing. Treatment options to restore normal joint function vary depending on the severity of the condition. This work introduces an innovative deep-learning framework processing shoulder CT scans. It features the semantic segmentation of the proximal humerus and scapula, the 3D reconstruction of bone surfaces, the identification of the glenohumeral (GH) joint region, and the staging of three common osteoarthritic-related pathologies: osteophyte formation (OS), GH space reduction (JS), and humeroscapular alignment (HSA). The pipeline comprises two cascaded CNN architectures: 3D CEL-UNet for segmentation and 3D Arthro-Net for threefold classification. A retrospective dataset of 571 CT scans featuring patients with various degrees of GH osteoarthritic-related pathologies was used to train, validate, and test the pipeline. Root mean squared error and Hausdorff distance median values for 3D reconstruction were 0.22mm and 1.48mm for the humerus and 0.24mm and 1.48mm for the scapula, outperforming state-of-the-art architectures and making it potentially suitable for a PSI-based shoulder arthroplasty preoperative plan context. The classification accuracy for OS, JS, and HSA consistently reached around 90% across all three categories. The computational time for the inference pipeline was less than 15s, showcasing the framework's efficiency and compatibility with orthopedic radiology practice. The outcomes represent a promising advancement toward the medical translation of artificial intelligence tools. This progress aims to streamline the preoperative planning pipeline delivering high-quality bone surfaces and supporting surgeons in selecting the most suitable surgical approach according to the unique patient joint conditions.

Related papers

• Anatomy-guided Pathology Segmentation [56.883822515800205]
  We develop a generalist segmentation model that combines anatomical and pathological information, aiming to enhance the segmentation accuracy of pathological features. Our Anatomy-Pathology Exchange (APEx) training utilizes a query-based segmentation transformer which decodes a joint feature space into query-representations for human anatomy. In doing so, we are able to report the best results across the board on FDG-PET-CT and Chest X-Ray pathology segmentation tasks with a margin of up to 3.3% as compared to strong baseline methods.
  arXiv  Detail & Related papers  (2024-07-08T11:44:15Z)
• HCA-Net: Hierarchical Context Attention Network for Intervertebral Disc Semantic Labeling [3.485615723221064]
  We present HCA-Net, a novel contextual attention network architecture for semantic labeling of IVDs. Our approach excels at processing features across different scales and effectively consolidating them to capture the intricate spatial relationships within the spinal cord. In addition, we introduce a skeletal loss term to reinforce the model's geometric dependence on the spine.
  arXiv  Detail & Related papers  (2023-11-21T09:58:39Z)
• 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)
• WSC-Trans: A 3D network model for automatic multi-structural segmentation of temporal bone CT [5.821303529939008]
  We propose a 3D network model for automatic segmentation of multi-structural targets in temporal bone CT. The algorithm combines CNN and Transformer for feature extraction and takes advantage of spatial attention and channel attention mechanisms to further improve the segmentation effect.
  arXiv  Detail & Related papers  (2022-11-14T06:44:37Z)
• CNN-based fully automatic wrist cartilage volume quantification in MR Image [55.41644538483948]
  The U-net convolutional neural network with additional attention layers provides the best wrist cartilage segmentation performance. The error of cartilage volume measurement should be assessed independently using a non-MRI method.
  arXiv  Detail & Related papers  (2022-06-22T14:19:06Z)
• SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae [54.751251046196494]
  We propose a one-stage detection framework termed SpineOne to simultaneously localize and classify degenerative discs and vertebrae from MRI slices. SpineOne is built upon the following three key techniques: 1) a new design of the keypoint heatmap to facilitate simultaneous keypoint localization and classification; 2) the use of attention modules to better differentiate the representations between discs and vertebrae; and 3) a novel gradient-guided objective association mechanism to associate multiple learning objectives at the later training stage.
  arXiv  Detail & Related papers  (2021-10-28T12:59:06Z)
• A Deep Learning-Based Approach to Extracting Periosteal and Endosteal Contours of Proximal Femur in Quantitative CT Images [25.76523855274612]
  A three-dimensional (3D) end-to-end fully convolutional neural network was developed for our segmentation task. Two models with the same network structures were trained and they achieved a dice similarity coefficient (DSC) of 97.87% and 96.49% for the periosteal and endosteal contours, respectively. It demonstrated a strong potential for clinical use, including the hip fracture risk prediction and finite element analysis.
  arXiv  Detail & Related papers  (2021-02-03T10:23:41Z)
• Three-dimensional Segmentation of the Scoliotic Spine from MRI using Unsupervised Volume-based MR-CT Synthesis [3.6273410177512275]
  We present an unsupervised, fully three-dimensional (3D) cross-modality synthesis method for segmenting scoliotic spines. A 3D CycleGAN model is trained for an unpaired volume-to-volume translation across MR and CT domains. The resulting segmentation is used to reconstruct a 3D model of the spine.
  arXiv  Detail & Related papers  (2020-11-25T18:34:52Z)
• 3D Convolutional Sequence to Sequence Model for Vertebral Compression Fractures Identification in CT [1.7372615815088566]
  An osteoporosis-related fracture occurs every three seconds worldwide, affecting one in three women and one in five men aged over 50. In this study, we present an automatic system for identification of vertebral compression fractures on Computed Tomography images. The system integrates a compact 3D representation of the spine, utilizing a Convolutional Neural Network (CNN) for spinal cord detection and a novel end-to-end sequence to sequence 3D architecture.
  arXiv  Detail & Related papers  (2020-10-08T02:39:40Z)
• Deep Negative Volume Segmentation [60.44793799306154]
  We propose a new angle to the 3D segmentation task: segment empty spaces between all the tissues surrounding the object. Our approach is an end-to-end pipeline that comprises a V-Net for bone segmentation. We validate the idea on the CT scans in a 50-patient dataset, annotated by experts in maxillofacial medicine.
  arXiv  Detail & Related papers  (2020-06-22T16:55:23Z)
• 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.