Search Results for author: Nataša Sladoje

Found 13 papers, 11 papers with code

Can representation learning for multimodal image registration be improved by supervision of intermediate layers?

no code implementations1 Mar 2023 Elisabeth Wetzer, Joakim Lindblad, Nataša Sladoje

Contrastive learning can generate representations of multimodal images, reducing the challenging task of multimodal image registration to a monomodal one.

Contrastive Learning Image Classification +3

End-to-end Multiple Instance Learning with Gradient Accumulation

1 code implementation8 Mar 2022 Axel Andersson, Nadezhda Koriakina, Nataša Sladoje, Joakim Lindblad

We conduct experiments on both QMNIST and Imagenette to investigate the performance and training time, and compare with the conventional memory-expensive baseline and a recent sampled-based approach.

Multiple Instance Learning Self-Supervised Learning +1

Oral cancer detection and interpretation: Deep multiple instance learning versus conventional deep single instance learning

1 code implementation3 Feb 2022 Nadezhda Koriakina, Nataša Sladoje, Vladimir Bašić, Joakim Lindblad

Performance at the bag level on real-world cytological data is similar for both methods, yet the single instance approach performs better on average.

Multiple Instance Learning

Cross-Modality Sub-Image Retrieval using Contrastive Multimodal Image Representations

1 code implementation10 Jan 2022 Eva Breznik, Elisabeth Wetzer, Joakim Lindblad, Nataša Sladoje

We propose a new application-independent content-based image retrieval (CBIR) system for reverse (sub-)image search across modalities, which combines deep learning to generate representations (embedding the different modalities in a common space) with classical feature extraction and bag-of-words models for efficient and reliable retrieval.

Content-Based Image Retrieval Retrieval

Cross-Sim-NGF: FFT-Based Global Rigid Multimodal Alignment of Image Volumes using Normalized Gradient Fields

1 code implementation19 Oct 2021 Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje

The method is fast; a 3. 4Mvoxel global rigid alignment requires approximately 40 seconds of computation, and the proposed algorithm outperforms a direct algorithm for the same task by more than three orders of magnitude.

Fast computation of mutual information in the frequency domain with applications to global multimodal image alignment

1 code implementation28 Jun 2021 Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje

We propose an efficient algorithm for computing MI for all discrete displacements (formalized as the cross-mutual information function (CMIF)), which is based on cross-correlation computed in the frequency domain.

Is Image-to-Image Translation the Panacea for Multimodal Image Registration? A Comparative Study

2 code implementations30 Mar 2021 Jiahao Lu, Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje

We compare the performance of four Generative Adversarial Network (GAN)-based I2I translation methods and one contrastive representation learning method, subsequently combined with two representative monomodal registration methods, to judge the effectiveness of modality translation for multimodal image registration.

Generative Adversarial Network Image Registration +3

INSPIRE: Intensity and spatial information-based deformable image registration

1 code implementation14 Dec 2020 Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje

INSPIRE exhibits excellent performance on the FIRE dataset, substantially outperforming several domain-specific methods.}

Computational Efficiency Image Registration

CoMIR: Contrastive Multimodal Image Representation for Registration

1 code implementation NeurIPS 2020 Nicolas Pielawski, Elisabeth Wetzer, Johan Öfverstedt, Jiahao Lu, Carolina Wählby, Joakim Lindblad, Nataša Sladoje

We propose contrastive coding to learn shared, dense image representations, referred to as CoMIRs (Contrastive Multimodal Image Representations).

Image-to-Image Translation

A Deep Learning based Pipeline for Efficient Oral Cancer Screening on Whole Slide Images

2 code implementations23 Oct 2019 Jiahao Lu, Nataša Sladoje, Christina Runow Stark, Eva Darai Ramqvist, Jan-Michaél Hirsch, Joakim Lindblad

The pipeline consists of fully convolutional regression-based nucleus detection, followed by per-cell focus selection, and CNN based classification.

Classification General Classification +3

Stochastic Distance Transform

2 code implementations18 Oct 2018 Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje

We, thus, define a stochastic distance transform (SDT), which has an adjustable robustness to noise.

Template Matching

Fast and Robust Symmetric Image Registration Based on Distances Combining Intensity and Spatial Information

2 code implementations30 Jul 2018 Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje

The method exhibits greater robustness and higher accuracy than similarity measures in common use, when inserted into a standard gradient-based registration framework available as part of the open source Insight Segmentation and Registration Toolkit (ITK).

Image Registration Medical Image Registration

Cannot find the paper you are looking for? You can Submit a new open access paper.