Image segmentation evaluation: a survey of methods

Wang, Zhaobin; Wang, E.; Zhu, Ying

doi:10.1007/s10462-020-09830-9

Cited by 172 publications

(76 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised techniques are considered to be more accurate but interobserver variability will still be present, as the manual part of the segmentation and the settings of the algorithm influence the result [ 12 , 18 ]. Unsupervised segmentation techniques commonly rely on labeled atlases and have been shown to be less accurate than the supervised techniques [ 19 ].…”

Section: Radiomicsmentioning

confidence: 99%

Radiogenomics in Colorectal Cancer

Badic

Tixier

Rest

et al. 2021

Cancers

View full text Add to dashboard Cite

The steady improvement of high-throughput technologies greatly facilitates the implementation of personalized precision medicine. Characterization of tumor heterogeneity through image-derived features—radiomics and genetic profile modifications—genomics, is a rapidly evolving field known as radiogenomics. Various radiogenomics studies have been dedicated to colorectal cancer so far, highlighting the potential of these approaches to enhance clinical decision-making. In this review, a general outline of colorectal radiogenomics literature is provided, discussing the current limitations and suggested further developments.

show abstract

Section: Radiomicsmentioning

confidence: 99%

Radiogenomics in Colorectal Cancer

Badic

Tixier

Rest

et al. 2021

Cancers

View full text Add to dashboard Cite

show abstract

“…We used the same stochastically grouped training and test sets for each method as shown earlier in Fig 2 and used the same or analogous hyperparameters across models wherever possible ( Table 1 ). A diversity of quantitative metrics is required to fully understand a classifier’s ability to correctly perform image segmentation [ 133 ]. We report results across seven standard metrics including accuracy, balanced accuracy, precision, recall, Sørensen-Dice (“Dice”) coefficient [ 81 – 84 ] ( i .…”

Section: Resultsmentioning

confidence: 99%

Deep learning classification of lipid droplets in quantitative phase images

2021

View full text Add to dashboard Cite

We report the application of supervised machine learning to the automated classification of lipid droplets in label-free, quantitative-phase images. By comparing various machine learning methods commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, all implemented machine learning methods, and their performance with respect to computational efficiency, required training resources, and relative method performance measured across multiple metrics. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent alternative of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity, and deeper insight into the thermodynamics of metabolism of single cells.

show abstract

“…We used the same stochastically grouped training and test sets for each method as shown earlier in Figure 2 and used the same or analogous hyperparameters across models wherever possible ( Table 1). A diversity of quantitative metrics is required to fully understand a classifier's ability to correctly perform image segmentation [133]. We report results across seven standard metrics including accuracy, balanced accuracy, precision, recall, Sørensen-Dice ("Dice") coefficient [81][82][83][84] We performed two distinct evaluations of our six machine learning methods: k-fold cross-validation and a separate train-test split against new test data.…”

Section: Resultsmentioning

confidence: 99%

Deep learning classification of lipid droplets in quantitative phase images

Sheneman

Stephanopoulos

Vasdekis

2020

Preprint

View full text Add to dashboard Cite

We report the application of supervised machine learning to the automated classification of lipid-droplets in label-free, quantitative-phase images. By comparing various machine learning methods that are publicly available and commonly used in biomedical imaging and remote sensing, we found convolutional neural networks to outperform others, both quantitatively and qualitatively. We describe our imaging approach, the implementation of all machine learning methods that we compared, and their performance in computational requirements, training resource needs, and accuracy. Overall, our results indicate that quantitative-phase imaging coupled to machine learning enables accurate lipid droplet classification in single living cells. As such, the present paradigm presents an excellent replacement candidate of the more common fluorescent and Raman imaging modalities by enabling label-free, ultra-low phototoxicity and deeper insight into the thermodynamics of metabolism at the single-cell level.

show abstract

Image segmentation evaluation: a survey of methods

Cited by 172 publications

References 121 publications

Radiogenomics in Colorectal Cancer

Radiogenomics in Colorectal Cancer

Deep learning classification of lipid droplets in quantitative phase images

Deep learning classification of lipid droplets in quantitative phase images

Contact Info

Product

Resources

About