Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
[Preprint]. 2025 Apr 16:arXiv:2504.12438v1.

Hybrid artificial intelligence echogenic components-based diagnosis of adnexal masses on ultrasound

Roni Yoeli-Bik  1 , Heather M Whitney  2 , Hui Li  2 , Agnes Bilecz  1 , Jacques S Abramowicz  1 , Li Lan  2 , Ryan E Longman  1 , Maryellen L Giger  2 , Ernst Lengyel  1
Affiliations

Hybrid artificial intelligence echogenic components-based diagnosis of adnexal masses on ultrasound

Roni Yoeli-Bik et al. ArXiv. .

Update in

Abstract

Background: Adnexal masses are heterogeneous and have varied sonographic presentations, making them difficult to diagnose correctly.

Purpose: Our study aimed to develop an innovative hybrid artificial intelligence/computer aided diagnosis (AI/CADx)-based pipeline to distinguish between benign and malignant adnexal masses on ultrasound imaging based upon automatic segmentation and echogenic-based classification.

Methods: The retrospective study was conducted on a consecutive dataset of patients with an adnexal mass. There was one image per mass. Mass borders were segmented from the background via a supervised U-net algorithm. Masses were spatially subdivided automatically into their hypo- and hyper-echogenic components by a physics-driven unsupervised clustering algorithm. The dataset was separated by patient into a training/validation set (95 masses; 70%) and an independent held-out test set (41 masses; 30%). Eight component-based radiomic features plus a binary measure of the presence or absence of solid components were used to train a linear discriminant analysis classifier to distinguish between malignant and benign masses. Classification performance was evaluated using the area under the receiver operating characteristic curve (AUC), along with sensitivity, specificity, negative predictive value, positive predictive value, and accuracy at target 95% sensitivity.

Results: The cohort included 133 patients with 136 adnexal masses. In distinguishing between malignant and benign masses, the pipeline achieved an AUC of 0.90 [0.84, 0.95] on the training/validation set and 0.93 [0.83, 0.98] on the independent test set. Strong diagnostic performance was observed at the target 95% sensitivity.

Conclusions: A novel hybrid AI/CADx echogenic components-based ultrasound imaging pipeline can distinguish between malignant and benign adnexal masses with strong diagnostic performance.

PubMed Disclaimer

Conflict of interest statement

J.S.A. receives royalties from UpToDate that are unrelated to this work. L.L. and H.L. receive royalties through the University of Chicago Polsky Center for Entrepreneurship and Innovation. M.L.G. is a stockholder in R2 technology/Hologic and shareholder in QView, receives royalties from various companies through the University of Chicago Polsky Center for Entrepreneurship and Innovation, and was a cofounder in Quantitative Insights (now Qlarity Imaging). E.L. receives research funding to study the biology of ovarian cancer from AbbVie through the University of Chicago that is unrelated to this work. Some of the information in this manuscript is the subject of a patent application filed and owned by The University of Chicago. It is in the University of Chicago Conflict of Interest Policy that investigators disclose publicly actual or potential significant financial interest that would reasonably appear to be directly and significantly affected by the research activities. No other disclosures were reported.

Figures

Figure 1:
Figure 1:
Flowchart showing exclusion criteria and resulting eligible cases and masses.
Figure 2:
Figure 2:
AI/CADx pipeline for adnexal mass diagnosis. AI/CADx: Artificial intelligence/computer-aided diagnosis.
Figure 3:
Figure 3:
Shapley bee swarm plots for the features used in the AI/CADx classification of adnexal masses as malignant or benign on ultrasound images. The results are shown (top) color coded by feature value (the traditional presentation of Shapley values) and (bottom) color coded by pathology. Note that in Shapley bee swarm plots, each row is comprised of data points for all of the masses, and the figure format does not track each mass across the rows. The color coding by pathology emphasizes that for this classification task on this modality, the importance of features varies among benign and malignant masses, highlighting the utility of the echogenic component-based approach for heterogeneous adnexal masses. Four example masses (two malignant masses labeled M1 and M2 and two benign masses labeled B1 and B2) are identified for further examination in Figure 4.
Figure 4:
Figure 4:
Shapley feature importance bar charts for two example malignant (M1 and M2) and two example benign (B1 and B2) masses. The mass labels are the same as in Figure 3. These results demonstrate how the importance of the features for classification varies both between and within mass types.
Figure 5:
Figure 5:
ROC analysis in the task of classifying adnexal masses as malignant or benign. Both the proper binormal model and empirical curves are shown. The AUC for the proper binormal model was (median, [95% CI]) 0.90 [0.84, 0.95] in the training/validation set and 0.93 [0.83, 0.98] in the independent test set. ROC: receiver operating characteristic. AUC: area under the receiver operating characteristic curve
Figure 6:
Figure 6:
Sonographic, AI/CADx-based automatic segmentation, component-based clustering, and histopathology examples of individual masses in the test set. Images of two benign (A,B) and two malignant (C,D) ovarian masses and their corresponding likelihood of malignancy (LM) from prediction as malignant or benign by the AI/CADx model are shown. AI/CADx: artificial intelligence/computer-aided diagnosis Note. – Pathology case numbers are obscured from the images according to HIPAA regulations.
See this image and copyright information in PMC

References

    1. Siegel RL, Kratzer TB, Giaquinto AN, Sung H, Jemal A. Cancer statistics, 2025. CA: A Cancer Journal for Clinicians. 2025;75(1):10–45. doi: 10.3322/caac.21871 - DOI - PMC - PubMed
    1. Timmerman D, Planchamp F, Bourne T, et al. ESGO/ISUOG/IOTA/ESGE Consensus Statement on preoperative diagnosis of ovarian tumors. Ultrasound Obstet Gynecol. 2021;58(1):148–168. doi: 10.1002/uog.23635 - DOI - PubMed
    1. Sisodia RC, del Carmen MG. Lesions of the Ovary and Fallopian Tube. New England Journal of Medicine. 2022;387(8):727–736. doi: 10.1056/NEJMra2108956 - DOI - PubMed
    1. Valentin L, Ameye L, Jurkovic D, et al. Which extrauterine pelvic masses are difficult to correctly classify as benign or malignant on the basis of ultrasound findings and is there a way of making a correct diagnosis? Ultrasound Obstet Gynecol. 2006;27(4):438–444. doi: 10.1002/uog.2707 - DOI - PubMed
    1. Sadowski EA, Paroder V, Patel-Lippmann K, et al. Indeterminate Adnexal Cysts at US: Prevalence and Characteristics of Ovarian Cancer. 2018;287(3):9. - PubMed

Publication types

LinkOut - more resources