Diagnosis of endometrium hyperplasia and screening of endometrial intraepithelial neoplasia in histopathological images using a global-to-local multi-scale convolutional neural network

Zhao, Fengjun; Dong, Didi; Du, Hongyan; Guo, Yufeng; Xue, Songbai; Wang, Zhiwei; Xie, Xiaoyang; Wang, Mingjuan; Zhang, Haiyan; Cao, Xin; He, Xiaowei

doi:10.1016/j.cmpb.2022.106906

Cited by 11 publications

(21 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results presented by Sun et al [8] predict classifications at the patch level rather than at the whole slide level as is undertaken in the current project. Zhao et al [9] use a global to local CNN to differentiate between types of endometrial hyperplasia, that is changes which can precede the development of cancer, their results are a similar accuracy to pathologists.…”

Section: Introductionmentioning

confidence: 98%

Detection of malignancy in whole slide images of endometrial cancer biopsies using artificial intelligence

et al. 2023

View full text Add to dashboard Cite

In this study we use artificial intelligence (AI) to categorise endometrial biopsy whole slide images (WSI) from digital pathology as either “malignant”, “other or benign” or “insufficient”. An endometrial biopsy is a key step in diagnosis of endometrial cancer, biopsies are viewed and diagnosed by pathologists. Pathology is increasingly digitised, with slides viewed as images on screens rather than through the lens of a microscope. The availability of these images is driving automation via the application of AI. A model that classifies slides in the manner proposed would allow prioritisation of these slides for pathologist review and hence reduce time to diagnosis for patients with cancer. Previous studies using AI on endometrial biopsies have examined slightly different tasks, for example using images alongside genomic data to differentiate between cancer subtypes. We took 2909 slides with “malignant” and “other or benign” areas annotated by pathologists. A fully supervised convolutional neural network (CNN) model was trained to calculate the probability of a patch from the slide being “malignant” or “other or benign”. Heatmaps of all the patches on each slide were then produced to show malignant areas. These heatmaps were used to train a slide classification model to give the final slide categorisation as either “malignant”, “other or benign” or “insufficient”. The final model was able to accurately classify 90% of all slides correctly and 97% of slides in the malignant class; this accuracy is good enough to allow prioritisation of pathologists’ workload.

show abstract

Section: Introductionmentioning

confidence: 98%

Detection of malignancy in whole slide images of endometrial cancer biopsies using artificial intelligence

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Publication year ranged from 2005 to 2022, and the majority of studies were conducted in Europe and the USA. Five of the included studies were multi-centre [ 26 , 28 – 31 ], with the remaining three studies all single centre [ 24 , 25 , 27 ]. The majority of included studies had less than 10 reviewing pathologists, although two larger studies included 20 and 78 reviewing pathologists respectively [ 29 , 30 ].…”

Section: Resultsmentioning

confidence: 99%

“…Extensive pathologist characteristics in conjunction with overall agreement could only be extracted from two studies [ 29 , 30 ], with the other studies providing minimal detail regarding pathologist speciality, location or practice settings. Some novel working practices/methods were assessed in some of the studies, such as grading the degree of nuclear atypia [ 26 ], and subjective diagnosis in addition to/in comparison with objective methods of diagnosis (semi-automated quantitative image analysis, deep learning models) [ 24 , 25 ], as shown in Table 1 . One study assessed pathologist diagnosis using both the EIN and WHO criteria but simplified the WHO categorisation into two categories, benign hyperplasia or atypical hyperplasia/grade 1 EC [ 28 ].…”

Section: Resultsmentioning

confidence: 99%

“…Three studies assessed methods of objective diagnosis that could help overcome issues associated with subjective diagnosis [ 24 , 25 , 31 ]. Sanderson et al, undertook semi-automated computerised image analysis to aid in the quantification of volume percentage stroma (VPS), using 21 consensus EIN (n = 10) and hyperplasia without atypia (n = 11) cases, with the “most abnormal” regions of interest used for the analysis.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Factors associated with interobserver variation amongst pathologists in the diagnosis of endometrial hyperplasia: A systematic review

McCoy,

Coleman,

McShane

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Objective Reproducible diagnoses of endometrial hyperplasia (EH) remains challenging and has potential implications for patient management. This systematic review aimed to identify pathologist-specific factors associated with interobserver variation in the diagnosis and reporting of EH. Methods Three electronic databases, namely MEDLINE, Embase and Web of Science, were searched from 1st January 2000 to 25th March 2023, using relevant key words and subject headings. Eligible studies reported on pathologist-specific factors or working practices influencing interobserver variation in the diagnosis of EH, using either the World Health Organisation (WHO) 2014 or 2020 classification or the endometrioid intraepithelial neoplasia (EIN) classification system. Quality assessment was undertaken using the QUADAS-2 tool, and findings were narratively synthesised. Results Eight studies were identified. Interobserver variation was shown to be significant even amongst specialist gynaecological pathologists in most studies. Few studies investigated pathologist-specific characteristics, but pathologists were shown to have different diagnostic styles, with some more likely to under-diagnose and others likely to over-diagnose EH. Some novel working practices were identified, such as grading the “degree” of nuclear atypia and the incorporation of objective methods of diagnosis such as semi-automated quantitative image analysis/deep learning models. Conclusions This review highlighted the impact of pathologist-specific factors and working practices in the accurate diagnosis of EH, although few studies have been conducted. Further research is warranted in the development of more objective criteria that could improve reproducibility in EH diagnostic reporting, as well as determining the applicability of novel methods such as grading the degree of nuclear atypia in clinical settings.

show abstract

“…In practical application, histopathological images are stored in pyramid form [19], in which each layer has images with different magnifications. In recent years, the research hotspots utilizing the different magnification information in histopathological images mainly focused on multi-scale image processing [20] or multi-scale feature utilization [21]. This paper distinguishes the difference between multi-scale and multi-magnification images in the A part of the Method.…”

Section: Introductionmentioning

confidence: 99%

Deep Multi-Magnification Similarity Learning for Histopathological Image Classification

Diao

Luo

Hou

et al. 2023

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Precise classification of histopathological images is crucial to computer-aided diagnosis in clinical practice. Magnification-based learning networks have attracted considerable attention for their ability to improve performance in histopathological classification. However, the fusion of pyramids of histopathological images at different magnifications is an under-explored area. In this paper, we proposed a novel deep multi-magnification similarity learning (DSML) approach that can be useful for the interpretation of multi-magnification learning framework and easy to visualize feature representation from low-dimension (e.g., cell-level) to high-dimension (e.g., tissue-level), which has overcome the difficulty of understanding cross-magnification information propagation. It uses a similarity cross entropy loss function designation to simultaneously learn the similarity of the information among cross-magnifications. In order to verify the effectiveness of DMSL, experiments with different network backbones and different magnification combinations were designed, and its ability to interpret was also investigated through visualization. Our experiments were performed on two different histopathological datasets: a clinical nasopharyngeal carcinoma and a public breast cancer BCSS2021 dataset.The results show that our method achieved outstanding performance in classification with a higher value of area under curve, accuracy, and F-score than other comparable methods. Moreover, the reasons behind multimagnification effectiveness were discussed.

show abstract

Diagnosis of endometrium hyperplasia and screening of endometrial intraepithelial neoplasia in histopathological images using a global-to-local multi-scale convolutional neural network

Cited by 11 publications

References 51 publications

Detection of malignancy in whole slide images of endometrial cancer biopsies using artificial intelligence

Detection of malignancy in whole slide images of endometrial cancer biopsies using artificial intelligence

Factors associated with interobserver variation amongst pathologists in the diagnosis of endometrial hyperplasia: A systematic review

Deep Multi-Magnification Similarity Learning for Histopathological Image Classification

Contact Info

Product

Resources

About