• Home
  • Search
  • Evaluation of Deep Learning Architectures for Complex Immunofluorescence Nuclear Image Segmentation.
  • Cite Icon73
  • https://doi.org/10.1109/tmi.2021.3069558Copy DOI Icon

Evaluation of Deep Learning Architectures for Complex Immunofluorescence Nuclear Image Segmentation.

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Separating and labeling each nuclear instance (instance-aware segmentation) is the key challenge in nuclear image segmentation. Deep Convolutional Neural Networks have been demonstrated to solve nuclear image segmentation tasks across different imaging modalities, but a systematic comparison on complex immunofluorescence images has not been performed. Deep learning based segmentation requires annotated datasets for training, but annotated fluorescence nuclear image datasets are rare and of limited size and complexity. In this work, we evaluate and compare the segmentation effectiveness of multiple deep learning architectures (U-Net, U-Net ResNet, Cellpose, Mask R-CNN, KG instance segmentation) and two conventional algorithms (Iterative h-min based watershed, Attributed relational graphs) on complex fluorescence nuclear images of various types. We propose and evaluate a novel strategy to create artificial images to extend the training set. Results show that instance-aware segmentation architectures and Cellpose outperform the U-Net architectures and conventional methods on complex images in terms of F1 scores, while the U-Net architectures achieve overall higher mean Dice scores. Training with additional artificially generated images improves recall and F1 scores for complex images, thereby leading to top F1 scores for three out of five sample preparation types. Mask R-CNN trained on artificial images achieves the overall highest F1 score on complex images of similar conditions to the training set images while Cellpose achieves the overall highest F1 score on complex images of new imaging conditions. We provide quantitative results demonstrating that images annotated by under-graduates are sufficient for training instance-aware segmentation architectures to efficiently segment complex fluorescence nuclear images.

Loading PDF

Similar Papers
  • Research Article

TTDCapsNet: Tri Texton-Dense Capsule Network for complex and medical image recognition

  • Mar 15, 2024
  • PLOS ONE
  • Vivian Akoto-Adjepong +9
  • Conference Article
  • Citations8

Experimental Analysis of U-Net and Mask R-CNN for Segmentation of Synthetic Liquid Spray

  • Nov 14, 2022
  • Refat Khan Pathan +5
  • Research Article
  • Citations128

Performance of a Convolutional Neural Network and Explainability Technique for 12-Lead Electrocardiogram Interpretation

  • Aug 04, 2021
  • JAMA Cardiology
  • J Weston Hughes +10
  • Research Article
  • Citations18

Classifying functional nuclear images with convolutional neural networks: a survey

  • Oct 21, 2020
  • IET Image Processing
  • Qiang Lin +11
  • Research Article
  • Citations2

Pneumothorax Detection System in Thoracic Radiography Images Using CNN Method

  • Jan 13, 2025
  • Scientific Journal of Informatics
  • Nouvel Izza Fardana +2
  • Research Article
  • Citations129

Fusion of Mask RCNN and attention mechanism for instance segmentation of apples under complex background

  • May 01, 2022
  • Computers and Electronics in Agriculture
  • Dandan Wang +1
  • Research Article

Comparing machine learning models with established risk scores in predicting bleeding and ischaemic stroke in patients with atrial fibrillation undergoing transcatheter aortic valve implantation

  • Nov 05, 2025
  • European Heart Journal
  • D Dangas +9
  • Research Article
  • Citations28

Exploring the performance of LBP-capsule networks with K-Means routing on complex images

  • Oct 15, 2020
  • Journal of King Saud University - Computer and Information Sciences
  • Patrick Mensah Kwabena +2
  • Research Article
  • Citations2

Glacial cirque identification based on Convolutional Neural Networks

  • Oct 24, 2024
  • Geomorphology
  • Dongxue Mao +4
  • PDF
  • Research Article
  • Citations23

Effect of transfer learning on the performance of VGGNet-16 and ResNet-50 for the classification of organic and residual waste

  • Oct 31, 2022
  • Frontiers in Environmental Science
  • Fangfang Wu +1
  • Book Chapter
  • Citations18

WiP: Generative Adversarial Network for Oversampling Data in Credit Card Fraud Detection

  • Jan 01, 2019
  • Akhilesh Kumar Gangwar +1
  • Research Article
  • Citations8

MaskDis R‐CNN: An instance segmentation algorithm with adversarial network for herd pigs

  • Jul 20, 2023
  • IET Image Processing
  • Shuqin Tu +6
  • Book Chapter
  • Citations791

SOLO: Segmenting Objects by Locations

  • Jan 01, 2020
  • Xinlong Wang +4
  • Conference Article
  • Citations348

Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up

  • Jun 01, 2019
  • Weifeng Ge +2
  • PDF
  • Research Article
  • Citations26

Crop Organ Segmentation and Disease Identification Based on Weakly Supervised Deep Neural Network

  • Nov 10, 2019
  • Agronomy
  • Yang Wu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.