Usefulness of Clinical, Ultrasonographic, Hysteroscopic, and Immunohistochemical Parameters in Differentiating Endometrial Polyps From Endometrial Cancer

2014 ◽  
Vol 21 (2) ◽  
pp. 296-302 ◽  
Author(s):  
Daniel Spadoto Dias ◽  
Flávia Neves Bueloni-Dias ◽  
Rogério Dias ◽  
Jorge Nahás-Neto ◽  
Eliana Aguiar Petri Nahás ◽  
...  
2021 ◽  
Vol 19 (1) ◽  
Author(s):  
YunZheng Zhang ◽  
ZiHao Wang ◽  
Jin Zhang ◽  
CuiCui Wang ◽  
YuShan Wang ◽  
...  

Abstract Background Hysteroscopy is a commonly used technique for diagnosing endometrial lesions. It is essential to develop an objective model to aid clinicians in lesion diagnosis, as each type of lesion has a distinct treatment, and judgments of hysteroscopists are relatively subjective. This study constructs a convolutional neural network model that can automatically classify endometrial lesions using hysteroscopic images as input. Methods All histopathologically confirmed endometrial lesion images were obtained from the Shengjing Hospital of China Medical University, including endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyps, and submucous myomas. The study included 1851 images from 454 patients. After the images were preprocessed (histogram equalization, addition of noise, rotations, and flips), a training set of 6478 images was input into a tuned VGGNet-16 model; 250 images were used as the test set to evaluate the model’s performance. Thereafter, we compared the model’s results with the diagnosis of gynecologists. Results The overall accuracy of the VGGNet-16 model in classifying endometrial lesions is 80.8%. Its sensitivity to endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyp, and submucous myoma is 84.0%, 68.0%, 78.0%, 94.0%, and 80.0%, respectively; for these diagnoses, the model’s specificity is 92.5%, 95.5%, 96.5%, 95.0%, and 96.5%, respectively. When classifying lesions as benign or as premalignant/malignant, the VGGNet-16 model’s accuracy, sensitivity, and specificity are 90.8%, 83.0%, and 96.0%, respectively. The diagnostic performance of the VGGNet-16 model is slightly better than that of the three gynecologists in both classification tasks. With the aid of the model, the overall accuracy of the diagnosis of endometrial lesions by gynecologists can be improved. Conclusions The VGGNet-16 model performs well in classifying endometrial lesions from hysteroscopic images and can provide objective diagnostic evidence for hysteroscopists.


Medicina ◽  
2019 ◽  
Vol 55 (9) ◽  
pp. 543 ◽  
Author(s):  
Adomaitienė ◽  
Nadišauskienė ◽  
Nickkho-Amiry ◽  
Čižauskas ◽  
Palubinskienė ◽  
...  

Background and objectives: Endometrial polyps in asymptomatic postmenopausal women are often incidentally found, yet only 1.51% of them are malignant. Their potential for malignant transformation has not been adequately addressed. The aim of this study was to investigate the proliferation within endometrial polyps as one of the indicators of their malignization potential in asymptomatic postmenopausal women. Materials and Methods: Immunohistochemical studies of Ki-67 were performed. Cases included 52 benign postmenopausal polyps, 19 endometrioid carcinoma with coexisting benign polyps, 12 polyps with foci of carcinoma and 4 cases of polyps, which later developed carcinoma. The control group included 31 atrophic endometria and 32 benign premenopausal polyps. Ki-67 was scored in either 10 or 20 “hot spot” fields, as percentage of positively stained cells. Results: The median epithelial Ki-67 score in postmenopausal benign polyps (4.7%) was significantly higher than in atrophic endometria (2.41%, p < 0.0001) and significantly lower than in premenopausal benign polyps (11.4%, p = 0.003) and endometrial cancer (8.3%, p < 0.0001). Where endometrial polyps were found in association with endometrial carcinoma, Ki-67 was significantly higher in cancer (p < 0.0001). No significant difference was found between Ki-67 scores of cancer focus and of the polyps tissue itself, respectively 2.8% and 4.55%, p = 0.37. Ki-67 expression, where polyps were resected and women later developed cancer, was not significantly different (p = 0.199). Conclusion: Polyps from asymptomatic postmenopausal women showed significantly more proliferation in both epithelial and stromal components than inactive atrophic endometria but less than premenopausal benign polyps and/or endometrial cancer. Benign postmenopausal endometrial polyps exhibit low proliferative activity, suggesting low malignant potential and may not require resection in asymptomatic women.


2016 ◽  
Vol 128 (3) ◽  
pp. 519-525 ◽  
Author(s):  
Simone R. de Rijk ◽  
Marlie E. Steenbergen ◽  
Theodoor E. Nieboer ◽  
Sjors F. Coppus

1995 ◽  
Vol 113 (5) ◽  
pp. 987-991 ◽  
Author(s):  
Luiz Cavalcanti de Albuquerque Neto ◽  
Marair Gracio Ferreira Sartori ◽  
Edmund Chada Baracat ◽  
Manoel João Batista Castello Girão ◽  
Geraldo Rodrigues de Lima

The study was conducted on 748 women who reported genital bleeding occurring at least one year after the last menstruation. Benign causes were most frequent than malignant causes. Among the benign causes, the most frequent were cervicitis (19,95%), prolapsed uterus with decubitus ulcer (19,41%), dysfunctional hemorrhage (13,29%) and endometrial polyps (12,77%). In the group of malignant causes, cancer of the cervix was the neoplasm most often detected (59,26%); endometrial cancer was next, affecting 29,63%. The cancer of the cervix/ cancer of the body ratio was 2:1. In summary, many causes, both benign and malignant, can provoke abnormal postmenopausal bleeding. Thus, curettage of the uterus should be reserved for doubtful cases, i.e., in situations in which, after all non invasive methods of investigations have been exhausted, the possibility of the occurrence of malignant lesions still persist.


2018 ◽  
Vol 25 (7) ◽  
pp. S123-S124
Author(s):  
T.A. Ikejiri ◽  
L. Oliveira Brito ◽  
C.L. Benetti-Pinto ◽  
C.M. Ribeiro ◽  
D.A. Yela

2018 ◽  
Vol Volume 11 ◽  
pp. 3949-3958 ◽  
Author(s):  
Gustavo Filipov Peres ◽  
Daniel Spadoto-Dias ◽  
Flávia Neves Bueloni-Dias ◽  
Nilton Leite ◽  
Leonardo Elias ◽  
...  

2020 ◽  
Vol 127 (8) ◽  
pp. 994-999
Author(s):  
ISM Jacobs ◽  
RMG Tibosch ◽  
PMAJ Geomini ◽  
SFPJ Coppus ◽  
MY Bongers ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document