Literature DB >> 33979039

A deep learning system to diagnose the malignant potential of urothelial carcinoma cells in cytology specimens.

Satoshi Nojima1, Kei Terayama2,3,4,5, Saeko Shimoura3, Sachiko Hijiki1, Norio Nonomura6, Eiichi Morii1, Yasushi Okuno3,5, Kazutoshi Fujita6,7.   

Abstract

BACKGROUND: Although deep learning algorithms for clinical cytology have recently been developed, their application to practical assistance systems has not been achieved. In addition, whether deep learning systems (DLSs) can perform diagnoses that cannot be performed by pathologists has not been fully evaluated.
METHODS: The authors initially obtained low-power field cytology images from archived Papanicolaou-stained urinary cytology glass slides from 232 patients. To aid in the development of a diagnosis support system that could identify suspicious atypical cells, the images were divided into high-power field panel image sets for training and testing of the 16-layer Visual Geometry Group convolutional neural network. The DLS was trained using linked information pertaining to whether urothelial carcinoma (UC) in the corresponding histology specimen was invasive or noninvasive, or high-grade or low-grade, followed by an evaluation of whether the DLS could diagnose these characteristics.
RESULTS: The DLS achieved excellent performance (eg, an area under the curve [AUC] of 0.9890; F1 score, 0.9002) when trained on high-power field images of malignant and benign cases. The DLS could diagnose whether the lesions were invasive UC (AUC, 0.8628; F1 score, 0.8239) or high-grade UC (AUC, 0.8661; F1 score, 0.8218). Gradient-weighted class activation mapping of these images indicated that the diagnoses were based on the color of tumor cell nuclei.
CONCLUSIONS: The DLS could accurately screen UC cells and determine the malignant potential of tumors more accurately than classical cytology. The use of a DLS during cytopathology screening could help urologists plan therapeutic strategies, which, in turn, may be beneficial for patients.
© 2021 American Cancer Society.

Entities:  

Keywords:  artificial intelligence; deep learning; novel diagnostic system; urine cytology; urothelial carcinoma

Mesh:

Year:  2021        PMID: 33979039     DOI: 10.1002/cncy.22443

Source DB:  PubMed          Journal:  Cancer Cytopathol        ISSN: 1934-662X            Impact factor:   5.284


  3 in total

1.  A Deep Learning System to Predict the Histopathological Results From Urine Cytopathological Images.

Authors:  Yixiao Liu; Shen Jin; Qi Shen; Lufan Chang; Shancheng Fang; Yu Fan; Hao Peng; Wei Yu
Journal:  Front Oncol       Date:  2022-05-24       Impact factor: 5.738

Review 2.  Recent Application of Artificial Intelligence in Non-Gynecological Cancer Cytopathology: A Systematic Review.

Authors:  Nishant Thakur; Mohammad Rizwan Alam; Jamshid Abdul-Ghafar; Yosep Chong
Journal:  Cancers (Basel)       Date:  2022-07-20       Impact factor: 6.575

Review 3.  Non-Invasive Biomarkers in the Diagnosis of Upper Urinary Tract Urothelial Carcinoma-A Systematic Review.

Authors:  Łukasz Białek; Konrad Bilski; Jakub Dobruch; Wojciech Krajewski; Tomasz Szydełko; Piotr Kryst; Sławomir Poletajew
Journal:  Cancers (Basel)       Date:  2022-03-16       Impact factor: 6.639

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.