What is the state of the art of computer vision-assisted cytology? A Systematic Literature Review

Matias, André Victória; Amorim, João Gustavo Atkinson; Macarini, Luiz Antonio Buschetto; Cerentini, Allan; Onofre, Alexandre Sherlley Casimiro; Onofre, Fabiana Botelho de Miranda; Daltoé, Felipe Perozzo; Stemmer, Marcelo Ricardo; Wangenheim, Aldo von

doi:10.1016/j.compmedimag.2021.101934

Cited by 11 publications

(9 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review of such approaches is beyond the scope of this paper. We refer the reader to recent comprehensive reviews for more insights on AI and deep learning in computational pathology [26]- [29], with specific reviews for histology [30]- [34] and cytology [35]- [37]. If some ethical issues have appeared in the use of computational pathology in clinical routine [38], most pathologists are in favor of their use [39].…”

Section: Computational Pathologymentioning

confidence: 99%

Whole Slide Image Quality in Digital Pathology: Review and Perspectives

Brixtel¹,

Bougleux

Lézoray

et al. 2022

IEEE Access

View full text Add to dashboard Cite

With the advent of whole slide image (WSI) scanners, pathology is undergoing a digital revolution. Simultaneously, with the development of image analysis algorithms based on artificial intelligence tools, the application of computerized WSI analysis can now be expected. However, transferring such tools into clinical practice is very challenging as they must deal with many artifacts that can occur during sample preparation and digitization. Therefore, the quality of WSIs is of prime importance, and we propose a review of the state-of-the-art of computational approaches for quality control. In particular, we focus on WSI quality issues related to the presence of sample preparation artifacts, compression artifacts, color variations, and out-of-focus areas. An analysis of the monthly WSI clinical routine in a cytological laboratory confirms the importance of implementing quality control measures. Given this observation, we draw perspectives on how a computational quality process can be included in a computational pathology diagnosis pipeline.

show abstract

Section: Computational Pathologymentioning

confidence: 99%

Whole Slide Image Quality in Digital Pathology: Review and Perspectives

Brixtel¹,

Bougleux

Lézoray

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A systematic literature review made in middle 2020 with the objective of finding what are the current computer-assisted or artificial intelligence-based approaches in computer vision for the support of quantitative cytology and diagnosis of cancer in cytological exams [14]. The studies analyzed was from the beginning of 2016 to middle of 2020.…”

Section: Related Workmentioning

confidence: 99%

“…As demonstrated and discussed in [14], one of the most important factors about the training of the models is to avoid biased results. Considering it was split the dataset into three different groups (train, validation, and test set), where each fold:…”

Section: Metricsmentioning

confidence: 99%

“…As the goal of this paper is object detection, will be used the Average Precision (AP) to measure the performance of the networks. Furthermore, according to [14], the average precision is a convenient metric for object detection. Calculated by the area under the Precision-Recall curve, it is, compute for each image of the test set the precision and recall.…”

Section: Metricsmentioning

confidence: 99%

“…Recently, however, due to the great growth around computer vision, Deep Learning algorithms have been achieving spectacular results in the mission of detecting the most varied types of objects, bringing the possibility of extracting more useful information from data [13]. For this reason, they can be used to assist in the identification and classification of nucleolus organizing regions by cytological analysis [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Nucleus Detection in Cervical Samples Stained With AgNOR

Gustavo Atkinson Amorim,

Moreno Sanches,

Bottamedi

et al. 2022

Anais Do XIII Computer on the Beach - COTB'22

Self Cite

View full text Add to dashboard Cite

Cervical cancer is a public health problem, where the treatment hasa better chance of success if detected early. This paper explores oneway of to analyze argyrophilic nucleolus organizer regions (AgNOR)stained slide using deep learning approaches of object detection fordetecting the different categories of nucleus. Our results show thata balanced dataset between the explored categories was essential,also that a ResNet-50 as backbone of Fast RCNN shows an AP of61.8% and 42.5% to detect nucleus and out of focus nucleus.

show abstract