Detecting the Area of Bovine Cumulus Oocyte Complexes Using Deep Learning and Semantic Segmentation

Athanasiou, Georgios; Cerquides, Jesús; Raes, Annelies; Azari‐Dolatabad, Nima; Angel‐Velez, Daniel; Soom, Ann Van; Arcos, Josep Lluís

doi:10.3233/faia220346

Cited by 3 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…UNet, with its distinctive U-shaped layout, has become the network of choice for medical image segmentation since this architecture is adept at extracting both low-level and high-level features, thus enhancing the segmentation accuracy. It has been also used previously for similar tasks with COC [6]. Additionally, UNet demonstrates superior performance with smaller datasets, making it the best choice for the current problem.…”

Section: Segmentation Networkmentioning

confidence: 99%

“…To derive the confusion matrices in areas of uncertainty, a pre-trained deep learning model that has achieved a high dice score (Athanasiou et al [6]) for segmenting the COC area is employed. This model is used to pinpoint areas of uncertainty by setting a threshold at 0.05.…”

Section: Confusion Matrices On Uncertaintymentioning

confidence: 99%

“…In a preceding study by Athanasiou et al [6], transfer learning emerged as an indispensable tool to achieve high performance in COC area segmentation. The first approach, despite starting from an advantageous position in training, could not sustain high performance for both the local CM and global CM implementations.…”

Section: Performance Coupled Cnnsmentioning

confidence: 99%

“…A particularly common and straightforward approach utilizes the majority-vote approach [5], whereby the ground truth is derived from the most frequently occurring opinion among the experts. This method has been effectively applied in various contexts, including Assisted Reproductive Technology (ART) for COC, as demonstrated by Athanasiou et al [6]. Furthermore, an advanced variant of this method, which considers class similarities, has demonstrated effectiveness in the aggregation of brain tumor segmentation labels [1].…”

Section: Introductionmentioning

confidence: 99%

“…(Figure 4) • Coupled CNN training with transfer learning: In order to assist the initial models, examining further options was necessitated. We adopted the method proposed by Athanasiou et al [6] and trained a segmenting CNN model to segment the COC area proficiently. Subsequently, the weights of the model were saved to serve as a starting point for disentangling the process from the ground truth, negating the need to train both CNNs simultaneously and offering a promising starting point for the training.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Enhancing Medical Image Segmentation: Ground Truth Optimization through Evaluating Uncertainty in Expert Annotations

Athanasiou,

Arcos,

Cerquides

2023

Mathematics

Self Cite

View full text Add to dashboard Cite

The surge of supervised learning methods for segmentation lately has underscored the critical role of label quality in predicting performance. This issue is prevalent in the domain of medical imaging, where high annotation costs and inter-observer variability pose significant challenges. Acquiring labels commonly involves multiple experts providing their interpretations of the “true” segmentation labels, each influenced by their individual biases. The blind acceptance of these noisy labels as the ground truth restricts the potential effectiveness of segmentation algorithms. Here, we apply coupled convolutional neural network approaches to a small-sized real-world dataset of bovine cumulus oocyte complexes. This is the first time these methods have been applied to a real-world annotation medical dataset, since they were previously tested only on artificially generated labels of medical and non-medical datasets. This dataset is crucial for healthy embryo development. Its application revealed an important challenge: the inability to effectively learn distinct confusion matrices for each expert due to large areas of agreement. In response, we propose a novel method that focuses on areas of high uncertainty. This approach allows us to understand the individual characteristics better, extract their behavior, and use this insight to create a more sophisticated ground truth using maximum likelihood. These findings contribute to the ongoing discussion of leveraging machine learning algorithms for medical image segmentation, particularly in scenarios involving multiple human annotators.

show abstract

Section: Segmentation Networkmentioning

confidence: 99%

Section: Confusion Matrices On Uncertaintymentioning

confidence: 99%

Section: Performance Coupled Cnnsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Enhancing Medical Image Segmentation: Ground Truth Optimization through Evaluating Uncertainty in Expert Annotations

Athanasiou,

Arcos,

Cerquides

2023

Mathematics

Self Cite

View full text Add to dashboard Cite

show abstract

Measuring cumulus expansion of mammalian oocytes: comparing the reliability of methods and how artificial intelligence could automate the measurement

Raes

Azari‐Dolatabad

Athanasiou

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Cumulus expansion is an important indicator of oocyte maturation, often correlated with greater oocyte developmental capacity. Although multiple methods have been described to assess cumulus expansion, none of them is considered a gold standard. Additionally, these methods are subjective and time-consuming. Here, the reliability of three cumulus expansion measurement methods was evaluated and a deep learning model was created to automatically perform the measurement. Cumulus-oocyte complexes were compared before and after in vitro maturation by three independent observers using three methods: (1) measurement of the cumulus area, (2) measurement of three distances between the zona pellucida and outer cumulus, and (3) scoring cumulus expansion on a 5-point Likert scale. Inter- and intra-observer agreements were calculated using intraclass-correlation coefficients (ICC). The area method resulted in the best overall agreement with an ICC of 0.89 versus 0.54 and 0.30 for the 3-distance and scoring method, respectively. Therefore, the area method served as the base to create the deep learning model, which outperformed two observers while equivalent to the third. Measuring the area is the most reliable method to manually evaluate cumulus expansion, whilst deep learning automatically performs the calculation with human-level accuracy and could therefore be a valuable prospective tool for embryologists.

show abstract

Classification of Bovine Cumulus-Oocyte Complexes with Convolutional Neural Networks

et al. 2023

View full text Add to dashboard Cite

Determining oocyte quality is crucial for successful fertilization and embryonic development, and there is a serious correlation between live birth rates and oocyte quality. Parameters such as the regular/irregular formation of the cumulus cell layer around the oocyte, the number of cumulus cell layers and the homogeneity of the appearance of the ooplasm are used to determine the quality of the oocytes to be used in in vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) methods. In this study, classification processes have been carried out using convolutional neural networks (CNN), a deep learning method, on the images of the cumulus-oocyte complex selected based on the theoretical knowledge and professional experience of embryologists. A convolutional neural network with a depth of 4 is used. In each depth level, one convolution, one ReLU and one max-pooling layer are included. The designed network architecture is trained using the Adam optimization algorithm. The cumulus-oocyte complexes (n=400) used in the study were obtained by using the oocyte aspiration method from the ovaries of the bovine slaughtered at the slaughterhouse. The CNN-based classification model developed in this study showed promising results in classifying three-class image data in terms of cumulus-oocyte complex classification. The classification model achieved high accuracy, precision, and sensitivity values on the test dataset. Continuous research and optimization of the model can further improve its performance and benefit the field of cumulus-oocyte complexes classification and oocyte quality assessment.

show abstract

Detecting the Area of Bovine Cumulus Oocyte Complexes Using Deep Learning and Semantic Segmentation

Cited by 3 publications

References 14 publications

Enhancing Medical Image Segmentation: Ground Truth Optimization through Evaluating Uncertainty in Expert Annotations

Enhancing Medical Image Segmentation: Ground Truth Optimization through Evaluating Uncertainty in Expert Annotations

Measuring cumulus expansion of mammalian oocytes: comparing the reliability of methods and how artificial intelligence could automate the measurement

Classification of Bovine Cumulus-Oocyte Complexes with Convolutional Neural Networks

Contact Info

Product

Resources

About