Imaging in gynecological disease (12): clinical and ultrasound features of invasive and non‐invasive malignant serous ovarian tumors

Moro, Francesca; Poma, Cinzia Baima; Zannoni, Gian Franco; Urbinati, Ailyn Mariela Vidal; Pasciuto, Tina; Ludovisi, M.; Moruzzi, Maria Cristina; Carinelli, Silvestro; Franchi, D.; Scambia, Giovanni; Testa, Antonia Carla

doi:10.1002/uog.17414

Cited by 48 publications

(47 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ultrasound characteristics of endometrioid ovarian cancers differ from those of mucinous and serous ovarian carcinomas described previously 29,30 (Table S5). Whether it is possible to discriminate correctly between different types of ovarian malignancy on the basis of ultrasound images and clinical information can only be determined in a prospective study.…”

Section: Discussionmentioning

confidence: 83%

“…However, before starting any prospective study, the typical ultrasound appearance of different types of ovarian malignancy must be known. The typical ultrasound appearance of several different adnexal pathologies, including various types of malignancy, has been described in the 'imaging in gynecological disease' series of this journal [29][30][31][32][33][34][35][36][37][38] (also see Virtual Issue https://obgyn .onlinelibrary.wiley.com/doi/toc/10.1002/(ISSN)1469-0705.IMAGINGINGYNECOLOGICALDISEASE).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Imaging in gynecological disease (13): clinical and ultrasound characteristics of endometrioid ovarian cancer

Moro

Magoga

Pasciuto

et al. 2018

Ultrasound in Obstet & Gyne

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 83%

Section: Discussionmentioning

confidence: 99%

Imaging in gynecological disease (13): clinical and ultrasound characteristics of endometrioid ovarian cancer

Moro

Magoga

Pasciuto

et al. 2018

Ultrasound in Obstet & Gyne

Self Cite

View full text Add to dashboard Cite

show abstract

“…Clear cell carcinomas have some clinical and pathological features similar to those of endometrioid carcinomas. Both are diagnosed more often in premenopausal patients than are the much more common serous carcinomas and both are frequently found at an early stage (FIGO Stage I). Both histotypes are considered Type‐I tumors with indolent behavior, and endometriosis has been described as a possible precursor for both.…”

Section: Discussionmentioning

confidence: 99%

“…Because endometrioid and clear cell cancers of the ovary present similarly clinically and look similar on ultrasound, we do not believe that it would be possible to discriminate between these two cancer types preoperatively. However, it should be possible to distinguish endometrioid or clear cell cancer of the ovary from serous ovarian cancer (especially high‐grade serous cancer) and mucinous ovarian cystadenocarcinoma because of differences in clinical presentation and ultrasound features. It should at least be possible to evaluate which diagnosis is the most likely.…”

Section: Discussionmentioning

confidence: 99%

“…It should at least be possible to evaluate which diagnosis is the most likely. High‐grade serous carcinomas are more often bilateral than clear cell carcinomas; they are multilocular‐solid or solid lesions that very rarely contain papillary projections. Mucinous ovarian carcinomas are much larger than serous, endometrioid and clear cell carcinomas, virtually always unilateral and contain a very large number of cyst locules, but papillary projections are very rare.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Imaging in gynecological disease (14): clinical and ultrasound characteristics of ovarian clear cell carcinoma

Pozzati

Moro

Pasciuto

et al. 2018

Ultrasound in Obstet & Gyne

Self Cite

View full text Add to dashboard Cite

Ovarian pure clear cell carcinoma is usually diagnosed at an early stage and typically appears as a large unilateral mass with solid components. Patients with clear cell carcinoma developing from endometriosis are younger than other patients with clear cell carcinoma, and clear cell cancers developing from endometriosis more often manifest ground-glass echogenicity of cyst fluid. Copyright © 2018 ISUOG. Published by John Wiley & Sons Ltd.

show abstract

An explainable machine learning model to solid adnexal masses diagnosis based on clinical data and qualitative ultrasound indicators

Fanizzi,

Arezzo,

Cormio

et al. 2024

Cancer Medicine

View full text Add to dashboard Cite

BackgroundAccurate characterization of newly diagnosed a solid adnexal lesion is a key step in defining the most appropriate therapeutic approach. Despite guidance from the International Ovarian Tumor Analyzes Panel, the evaluation of these lesions can be challenging. Recent studies have demonstrated how machine learning techniques can be applied to clinical data to solve this diagnostic problem. However, ML models can often consider as black‐boxes due to the difficulty of understanding the decision‐making process used by the algorithm to obtain a specific result.AimsFor this purpose, we propose an Explainable Artificial Intelligence model trained on clinical characteristics and qualitative ultrasound indicators to predict solid adnexal masses diagnosis.Materials & MethodsSince the diagnostic task was a three‐class problem (benign tumor, invasive cancer, or ovarian metastasis), we proposed a waterfall classification model: a first model was trained and validated to discriminate benign versus malignant, a second model was trained to distinguish nonmetastatic versus metastatic malignant lesion which occurs when a patient is predicted to be malignant by the first model. Firstly, a stepwise feature selection procedure was implemented. The classification performances were validated on Leave One Out scheme.ResultsThe accuracy of the three‐class model reaches an overall accuracy of 86.36%, and the precision per‐class of the benign, nonmetastatic malignant, and metastatic malignant classes were 86.96%, 87.27%, and 77.78%, respectively. Discussion: SHapley Additive exPlanations were performed to visually show how the machine learning model made a specific decision. For each patient, the SHAP values expressed how each characteristic contributed to the classification result. Such information represents an added value for the clinical usability of a diagnostic system.ConclusionsThis is the first work that attempts to design an explainable machine‐learning tool for the histological diagnosis of solid masses of the ovary.

show abstract

Imaging in gynecological disease (12): clinical and ultrasound features of invasive and non‐invasive malignant serous ovarian tumors

Cited by 48 publications

References 34 publications

Imaging in gynecological disease (13): clinical and ultrasound characteristics of endometrioid ovarian cancer

Imaging in gynecological disease (13): clinical and ultrasound characteristics of endometrioid ovarian cancer

Imaging in gynecological disease (14): clinical and ultrasound characteristics of ovarian clear cell carcinoma

An explainable machine learning model to solid adnexal masses diagnosis based on clinical data and qualitative ultrasound indicators

Contact Info

Product

Resources

About