Weakly supervised instance learning for thyroid malignancy prediction from whole slide cytopathology images

Dov, David; Kovalsky, Shahar Z.; Assaad, Serge; Cohen, Jonathan; Range, Danielle Elliott; Pendse, Avani A.; Henao, Ricardo; Carin, Lawrence

doi:10.1016/j.media.2020.101814

Cited by 71 publications

(41 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the most used methods for analyzing digital images, the authors indicate various filtering methods, segmentation methods to highlight areas of interest. Similar studies can also be found in [14]- [16].…”

Section: The Generalized Characteristics Of Digital Image Analysis Procedures and The Possibility Of Its Use For Analysis Of Medical Imagsupporting

confidence: 86%

General Ideology of Analysis Digital Medical Images in RGB Format

Lyashenko¹

2020

IJETER

View full text Add to dashboard Cite

Methods, technologies and various digital image processing procedures are one of the data analysis tools. At the same time, digital images can be considered as data that belong to the Big Data group. This fully applies to digital color images of cytological preparations. Thus, digital image processing techniques are one of the Big Data analysis tools. A feature of such a tool is the specificity of its use for various types of data, which are presented in the form of digital images. To do this, we examined the problematic aspects of the analysis of cytological specimens of images that are marked in the works of other authors. The paper also examined the issues of complex analysis of color images of cytological preparations. For this analysis, we used the decomposition of the original image into separate color channels, applied the ideology of wavelets to determine areas of interest and a set of morphological operations to specify such areas of interest. These methods are selected taking into account the peculiarities of images of cytological preparations. The results are shown on the example of images of cytological preparations, where megaloblastic anemia cells are also present.

show abstract

Section: The Generalized Characteristics Of Digital Image Analysis Procedures and The Possibility Of Its Use For Analysis Of Medical Imagsupporting

confidence: 86%

General Ideology of Analysis Digital Medical Images in RGB Format

Lyashenko¹

2020

IJETER

View full text Add to dashboard Cite

show abstract

“…The authors of [ 8 ] used weakly supervised instance learning to predict the malignancy of thyroid tumor from whole slide images. The Bethesda System (TBS) diagnostic score is used as a classification target.…”

Section: Introductionmentioning

confidence: 99%

Machine learning methods for automated classification of tumors with papillary thyroid carcinoma-like nuclei: A quantitative analysis

et al. 2021

View full text Add to dashboard Cite

When approaching thyroid gland tumor classification, the differentiation between samples with and without “papillary thyroid carcinoma-like” nuclei is a daunting task with high inter-observer variability among pathologists. Thus, there is increasing interest in the use of machine learning approaches to provide pathologists real-time decision support. In this paper, we optimize and quantitatively compare two automated machine learning methods for thyroid gland tumor classification on two datasets to assist pathologists in decision-making regarding these methods and their parameters. The first method is a feature-based classification originating from common image processing and consists of cell nucleus segmentation, feature extraction, and subsequent thyroid gland tumor classification utilizing different classifiers. The second method is a deep learning-based classification which directly classifies the input images with a convolutional neural network without the need for cell nucleus segmentation. On the Tharun and Thompson dataset, the feature-based classification achieves an accuracy of 89.7% (Cohen’s Kappa 0.79), compared to the deep learning-based classification of 89.1% (Cohen’s Kappa 0.78). On the Nikiforov dataset, the feature-based classification achieves an accuracy of 83.5% (Cohen’s Kappa 0.46) compared to the deep learning-based classification 77.4% (Cohen’s Kappa 0.35). Thus, both automated thyroid tumor classification methods can reach the classification level of an expert pathologist. To our knowledge, this is the first study comparing feature-based and deep learning-based classification regarding their ability to classify samples with and without papillary thyroid carcinoma-like nuclei on two large-scale datasets.

show abstract

“…Finally, in the recent years, ANNs have been again in the front line, and there are more efforts reported, for example, to distinguish follicular adenomas from follicular carcinomas [ 90 ] or papillary carcinomas [ 91 ]. Interestingly, whole slide imaging applications started to appear, and deep learning approaches have been introduced [ 92 , 93 ].…”

Section: Discussionmentioning

confidence: 99%

Radial Basis Function Artificial Neural Network for the Investigation of Thyroid Cytological Lesions

Fragopoulos

Pouliakis

Meristoudis

et al. 2020

Journal of Thyroid Research

View full text Add to dashboard Cite

Objective. This study investigates the potential of an artificial intelligence (AI) methodology, the radial basis function (RBF) artificial neural network (ANN), in the evaluation of thyroid lesions. Study Design. The study was performed on 447 patients who had both cytological and histological evaluation in agreement. Cytological specimens were prepared using liquid-based cytology, and the histological result was based on subsequent surgical samples. Each specimen was digitized; on these images, nuclear morphology features were measured by the use of an image analysis system. The extracted measurements (41,324 nuclei) were separated into two sets: the training set that was used to create the RBF ANN and the test set that was used to evaluate the RBF performance. The system aimed to predict the histological status as benign or malignant. Results. The RBF ANN obtained in the training set has sensitivity 82.5%, specificity 94.6%, and overall accuracy 90.3%, while in the test set, these indices were 81.4%, 90.0%, and 86.9%, respectively. Algorithm was used to classify patients on the basis of the RBF ANN, the overall sensitivity was 95.0%, the specificity was 95.5%, and no statistically significant difference was observed. Conclusion. AI techniques and especially ANNs, only in the recent years, have been studied extensively. The proposed approach is promising to avoid misdiagnoses and assists the everyday practice of the cytopathology. The major drawback in this approach is the automation of a procedure to accurately detect and measure cell nuclei from the digitized images.

show abstract

Weakly supervised instance learning for thyroid malignancy prediction from whole slide cytopathology images

Cited by 71 publications

References 27 publications

General Ideology of Analysis Digital Medical Images in RGB Format

General Ideology of Analysis Digital Medical Images in RGB Format

Machine learning methods for automated classification of tumors with papillary thyroid carcinoma-like nuclei: A quantitative analysis

Radial Basis Function Artificial Neural Network for the Investigation of Thyroid Cytological Lesions

Contact Info

Product

Resources

About