• Corpus ID: 204576075

CNN-based Automatic Detection of Bone Conditions via Diagnostic CT Images for Osteoporosis Screening.

  title={CNN-based Automatic Detection of Bone Conditions via Diagnostic CT Images for Osteoporosis Screening.},
  author={Chao Tang and Wenkun Zhang and Hai-ting Li and Lei Li and Ziheng Li and Ailong Cai and Linyuan Wang and Dapeng Shi and Bin Yan},
  journal={arXiv: Medical Physics},
Purpose: The purpose is to design a novelty automatic diagnostic method for osteoporosis screening by using the potential capability of convolutional neural network (CNN) in feature representation and extraction, which can be incorporated into the procedure of routine CT diagnostic in physical examination thereby improving the osteoporosis diagnosis and reducing the patient burden. Methods: The proposed convolutional neural network-based method mainly comprises two functional modules to perform… 

Computer-aided diagnosis systems for osteoporosis detection: a comprehensive survey

The aim of this paper is to survey the vision-based CAD systems especially focusing on the segmentation techniques for the pathological bone disease known as osteoporosis, and gives the future directions to improve the osteopOrosis diagnosis.

A comparative study on detection of osteoporosis using deep learning methods: A review

The combination of clinical data and images are fed to deep leaning models specifically CNN-Convolutional Neural Network, RNN-Recurrent Neural Network may result in completely automatic detection and diagnosis of osteoporosis.

Classification of Osteoporosis in the Lumbar Vertebrae using L2 Regularized Neural Network based on PHOG Features

The Diagnostic accuracy of the proposed method is higher than that of the existing DXA with X-ray, and the area under the Receiver Operating Characteristic (ROC) curve for L1-L4 had a significantly higher sensitivity for osteoporosis.

Detection of osteoporosis in lumbar spine [L1-L4] trabecular bone: a review article

The various segmentation techniques are explored to examine osteoporosis in particular region of the image and further significant attributes are extracted using different methods to classify normal and abnormal (osteoporotic) bones.

Mask R‐CNN‐based feature extraction and three‐dimensional recognition of rice panicle CT images

A method based on a mask region convolutional neural network (Mask R‐CNN) for feature extraction and three‐dimensional (3‐D) recognition of CT images of rice panicles is proposed and showed that the proposed method can efficiently identify and count plump grains and blighted grains to achieve an accuracy above 99% for the seed setting rate.

Osteoporosis diagnosis in knee X-rays by transfer learning based on convolution neural network

Osteoporosis degrades the quality of bones and is the primary cause of fractures in the elderly and women after menopause. The high diagnostic and treatment costs urge the researchers to find a



DRINet for Medical Image Segmentation

This paper proposes a novel CNN architecture, called Dense-Res-Inception Net (DRINet), which outperforms the U-Net in three different challenging applications, namely multi-class segmentation of cerebrospinal fluid on brain CT images, multi-organ segmentation on abdominalCT images, and multi- class brain tumor segmentsation on MR images.

Automatic detection of osteoporotic vertebral fractures in routine thoracic and abdominal MDCT

This prototype algorithm for automatic spine segmentation in MDCT images may support radiologists in reporting currently underdiagnosed osteoporotic vertebral fractures so that appropriate therapy can be initiated.

Compression fractures detection on CT

An automated method for detecting spine compression fractures in Computed Tomography (CT) scans that is composed of three processes: the spinal column is segmented and sagittal patches are extracted, and a Recurrent Neural Network is utilized to predict whether a vertebral fracture is present in the series of patches.

UNet++: A Nested U-Net Architecture for Medical Image Segmentation

This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar.

Automatic lumbar vertebra segmentation from clinical CT for wedge compression fracture diagnosis

This work presents a fully automated method for robustly localizing and segmenting the vertebrae for preparation of vertebral fracture diagnosis and presents promising preliminary results for automatic wedge compression fracture diagnosis.

Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling

Convolutional neural network based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer based on Convolutional Neural Network was chosen as the method to detect AUD.

Performance of Osteoporosis Self-Assessment Tool (OST) in Predicting Osteoporosis—A Review

OST is a simple and economical screening tool to predict osteoporosis and it can help to optimize the use of DXA, but its performance varies according to ethnicity, gender, and age.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Classification of Osteoporosis Based on Bone Mineral Densities

  • Y. LuH. Genant S. Cummings
  • Medicine
    Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research
  • 2001
It is concluded that standardization of normative data, perhaps referenced to an older population, may be necessary when applying T scores as diagnostic criteria in patient management and a risk‐based osteoporosis classification does not depend on the manufacturers' reference data and may be more consistent and efficient for patient diagnosis.