A first glance on the enhancement of digital cell activity videos from glioblastoma cells with nuclear staining

Calderón, Saúl; Cerdà, Artemi; Cruz, Juan C.; Valverde, Juan Manuel

doi:10.1109/concapan.2016.7942344

Cited by 6 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…with − → η (ω, m) being the vectorized neighborhood of |ω| = W pixels for the pixel m within U , and h the parameter for controlling filter smoothing. NLM kernel showed superior denoising and enhancement results when compared with other kernels as the bilateral filter [2].…”

Section: A Dnlm Descriptionmentioning

confidence: 97%

“…It is a well addressed problem in literature, with vast number of techniques proposed [1]. Noisy input images decrease the performance of common image processing tasks such as segmentation, object tracking and classification [2]- [4]. Thus, it becomes an important issue to incorporate denoising and enhancement techniques as a preprocessing stage, to increase performance of latter steps.…”

Section: Introductionmentioning

confidence: 99%

“…DNLM brute force implementation presents a high computational cost, which has been addressed previously [9], but still is not suitable for preprocessing large data sets. For example in the case of the automatic segmentation of cell activity videos, researchers need to analyze hundreds of thousands of images [2]. Also, preprocessing large datasets for CNN models is useful as recent work reveals [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DNLM-MA-P: A Parallelization of the Deceived Non Local Means Filter with Moving Average and Symmetric Weighting

Calderón

Castro

Zurnbado

2018

2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)

Self Cite

View full text Add to dashboard Cite

This paper presents a novel computational optimization of the deceived non local means filter using moving average and symmetric weighting. The proposed optimization is compared with different approaches that reduce the computational cost of the deceived non local means filter. Furthermore, the impact of parallelizing different optimization approaches is assessed by evaluating the execution time and scalability in Xeon Phi KNL architecture. The proposed optimization for the sequential implementation achieved a 90x speedup, while its parallelized implementation yielded a speedup of up to 1662x.

show abstract

Section: A Dnlm Descriptionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DNLM-MA-P: A Parallelization of the Deceived Non Local Means Filter with Moving Average and Symmetric Weighting

Calderón

Castro

Zurnbado

2018

2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI)

Self Cite

View full text Add to dashboard Cite

show abstract

Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification

Carranza-Rojas

Calderón-Ramírez

Mora-Fallas

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Enforcing Morphological Information in Fully Convolutional Networks to Improve Cell Instance Segmentation in Fluorescence Microscopy Images

Zamora-Cárdenas

Mendez

Calderón-Ramírez

et al. 2021

Advances in Computational Intelligence

View full text Add to dashboard Cite

Cell instance segmentation in fluorescence microscopy images is becoming essential for cancer dynamics and prognosis. Data extracted from cancer dynamics allows to understand and accurately model different metabolic processes such as proliferation. This enables customized and more precise cancer treatments. However, accurate cell instance segmentation, necessary for further cell tracking and behavior analysis, is still challenging in scenarios with high cell concentration and overlapping edges. Within this framework, we propose a novel cell instance segmentation approach based on the well-known U-Net architecture. To enforce the learning of morphological information per pixel, a deep distance transformer (DDT) acts as a back-bone model. The DDT output is subsequently used to train a top-model. The following top-models are considered: a three-class (e.g., foreground, background and cell border) U-net, and a watershed transform. The obtained results suggest a performance boost over traditional U-Net architectures. This opens an interesting research line around the idea of injecting morphological information into a fully convolutional model.

show abstract

A first glance on the enhancement of digital cell activity videos from glioblastoma cells with nuclear staining

Cited by 6 publications

References 28 publications

DNLM-MA-P: A Parallelization of the Deceived Non Local Means Filter with Moving Average and Symmetric Weighting

DNLM-MA-P: A Parallelization of the Deceived Non Local Means Filter with Moving Average and Symmetric Weighting

Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification

Enforcing Morphological Information in Fully Convolutional Networks to Improve Cell Instance Segmentation in Fluorescence Microscopy Images

Contact Info

Product

Resources

About