we propose a novel deep network, named feature aggregation and refinement network (FARNet), for the automatic detection of anatomical landmarks.

Related tags

Deep LearningFARNet
Overview

Feature Aggregation and Refinement Network for 2D Anatomical Landmark Detection

Overview

Localization of anatomical landmarks is essential for clinical diagnosis, treatment planning, and research. In this paper, we propose a novel deep network, named feature aggregation and refinement network (FARNet), for the automatic detection of anatomical landmarks. To alleviate the problem of limited training data in the medical domain, our network adopts a CNN pre-trained on natural images as the backbone network and several popular networks have been compared. Our FARNet also includes a multi-scale feature aggregation module for multiscale feature fusion and a feature refinement module for high-resolution heatmap regression. Coarse-to-fine supervisions are applied to the two modules to facilitate the endto-end training. We further propose a novel loss function named Exponential Weighted Center loss for more accurate heatmap regression, which focuses on the losses from the pixels near landmarks and suppresses the ones from far away. Our network has been evaluated on three publicly available anatomical landmark detection datasets, including cephalometric radiographs, hand radiographs, and spine radiographs, and achieves state-of-art performances on all three datasets.

The architecture of the feature aggregation and refinement network (FARNet). FARNet includes a backbone network (in the pink dashed box), a multi-scale feature aggregation (MSFA) module (in the blue dashed box) and a feature refinement (FR) module (in the brown dashed box). We also give the feature level labels {L0, L1, L2, L3, L4, L5} at the left side of the figure, and all feature maps at the same horizontal level have the same spatial resolution.

Data

In this paper, we evaluate our landmark detection network on three public benchmark data sets, a cephalometric X-rays dataset [1], a hand X-rays dataset [2] and a Spinal AnteriorPosterior (AP) X-rays dataset [3].

How to use

Dependencies

This tutorial depends on the following libraries:

  • pytorch = 1.0.1
  • numpy = 1.18.5
  • python >= 3.6
  • xlwt

config.py

You should set the image path in config by yourself

Run main.py

Run main.py to train the model and test its performance

Some results

 Illustration of landmark detection results by our proposed method on three public datasets. The first row is the task of cephalometric landmark detetcion(19 landmarks), the second row is the task of hand radiographs landmark detection(37 landmarks) and the last row is the task of spinal anterior-posterior x-ray landmark detection(68 landmarks). The red points denote our detected landmarks via our framework, while blue points represent the ground-truth landmarks.

Reference

[1] C.-W. Wang, C.-T. Huang, J.-H. Lee, C.-H. Li, S.-W. Chang, M.-J.Siao, T.-M. Lai, B. Ibragimov, T. Vrtovec, O. Ronneberger, et al., “A benchmark for comparison of dental radiography analysis algorithms,” Medical image analysis, vol. 31, pp. 63–76, 2016.
[2] C. Payer, D. ˇStern, H. Bischof, and M. Urschler, “Integrating spatial configuration into heatmap regression based cnns for landmark localization,” Medical Image Analysis, vol. 54, pp. 207–219, 2019.
[3] H. Wu, C. Bailey, P. Rasoulinejad, and S. Li, “Automatic landmark estimation for adolescent idiopathic scoliosis assessment using boostnet,” in International Conference on Medical Image Computing and ComputerAssisted Intervention, 2017.

Owner
aoyueyuan
aoyueyuan
This repository compare a selfie with images from identity documents and response if the selfie match.

aws-rekognition-facecompare This repository compare a selfie with images from identity documents and response if the selfie match. This code was made

1 Jan 27, 2022
Supervised forecasting of sequential data in Python.

Supervised forecasting of sequential data in Python. Intro Supervised forecasting is the machine learning task of making predictions for sequential da

The Alan Turing Institute 54 Nov 15, 2022
git《Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction》(ECCV 2020) GitHub:

Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction Code for the ECCV 2020 paper by Yiming Qian and Yasutaka Furukawa Getting

37 Dec 04, 2022
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation (CVPR'21)

EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation (CVPR'21) Citation If y

addisonwang 18 Nov 11, 2022
Optical Character Recognition + Instance Segmentation for russian and english languages

Распознавание рукописного текста в школьных тетрадях Соревнование, проводимое в рамках олимпиады НТО, разработанное Сбером. Платформа ODS. Результаты

Gerasimov Maxim 21 Dec 19, 2022
Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes (CVPR2021)

RSCD (BS-RSCD & JCD) Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes (CVPR2021) by Zhihang Zhong, Yinqiang Zheng, Imari Sato We co

81 Dec 15, 2022
A lossless neural compression framework built on top of JAX.

Kompressor Branch CI Coverage main (active) main development A neural compression framework built on top of JAX. Install setup.py assumes a compatible

Rosalind Franklin Institute 2 Mar 14, 2022
Extreme Dynamic Classifier Chains - XGBoost for Multi-label Classification

Extreme Dynamic Classifier Chains Classifier chains is a key technique in multi-label classification, sinceit allows to consider label dependencies ef

6 Oct 08, 2022
Pomodoro timer that acknowledges the inexorable, infinite passage of time

Pomodouroboros Most pomodoro trackers assume you're going to start them. But time and tide wait for no one - the great pomodoro of the cosmos is cold

Glyph 66 Dec 13, 2022
Playing around with FastAPI and streamlit to create a YoloV5 object detector

FastAPI-Streamlit-based-YoloV5-detector Playing around with FastAPI and streamlit to create a YoloV5 object detector It turns out that a User Interfac

2 Jan 20, 2022
Deep Learning GPU Training System

DIGITS DIGITS (the Deep Learning GPU Training System) is a webapp for training deep learning models. The currently supported frameworks are: Caffe, To

NVIDIA Corporation 4.1k Jan 03, 2023
PyTorch implementation of TSception V2 using DEAP dataset

TSception This is the PyTorch implementation of TSception V2 using DEAP dataset in our paper: Yi Ding, Neethu Robinson, Su Zhang, Qiuhao Zeng, Cuntai

Yi Ding 27 Dec 15, 2022
This is the source code for the experiments related to the paper Unsupervised Audio Source Separation Using Differentiable Parametric Source Models

Unsupervised Audio Source Separation Using Differentiable Parametric Source Models This is the source code for the experiments related to the paper Un

30 Oct 19, 2022
WSDM2022 "A Simple but Effective Bidirectional Extraction Framework for Relational Triple Extraction"

BiRTE WSDM2022 "A Simple but Effective Bidirectional Extraction Framework for Relational Triple Extraction" Requirements The main requirements are: py

9 Dec 27, 2022
git《Investigating Loss Functions for Extreme Super-Resolution》(CVPR 2020) GitHub:

Investigating Loss Functions for Extreme Super-Resolution NTIRE 2020 Perceptual Extreme Super-Resolution Submission. Our method ranked first and secon

Sejong Yang 0 Oct 17, 2022
This is Official implementation for "Pose-guided Feature Disentangling for Occluded Person Re-Identification Based on Transformer" in AAAI2022

PFD:Pose-guided Feature Disentangling for Occluded Person Re-identification based on Transformer This repo is the official implementation of "Pose-gui

Tao Wang 93 Dec 18, 2022
Official code repository for Continual Learning In Environments With Polynomial Mixing Times

Official code for Continual Learning In Environments With Polynomial Mixing Times Continual Learning in Environments with Polynomial Mixing Times This

Sharath Raparthy 1 Dec 19, 2021
code for paper "Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?"

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search? Code for paper: Does Unsupervised Architecture Representation

39 Dec 17, 2022
Alias-Free Generative Adversarial Networks (StyleGAN3) Official PyTorch implementation

Alias-Free Generative Adversarial Networks (StyleGAN3) Official PyTorch implementation

NVIDIA Research Projects 4.8k Jan 09, 2023
Official PyTorch implementation of the paper: DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample

DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample (ICCV 2021 Oral) Project | Paper Official PyTorch implementation of the pape

Eliahu Horwitz 393 Dec 22, 2022