Related Experiment Video
Updated: Feb 12, 2026
Generation and Culturing of High-Grade Serous Ovarian Cancer Patient-Derived Organoids
Published on: January 6, 2023
Histopathologic basis of a deep learning pelvic computed tomography model for prognostic prediction among patients
Rui Yin1,2, Jianming Lin2, Jing Huang2
1Department of Radiology, Tianjin Chest Hospital, Tianjin, China.
Background:
A deep learning (DL) model based on preoperative computed tomography (CT) has been proposed for estimating recurrence in patients with ovarian cancer. However, the inherent opacity of DL models complicates the interpretation of their output, limiting their clinical applicability. The aim of this study was thus to generate histopathologic evidence supporting such DL prediction models and to construct a clustering-based analytical framework for identifying patients with risk factors for ovarian cancer.
Methods:
A retrospective study was conducted in which preoperative CT data were collected from patients with high-grade serous ovarian cancer treated with radical tumor resection from January 2013 to December 2019 at three tertiary care centers. Unsupervised clustering was performed with 1,280 DL model-driven features, and the associations between clusters and histopathological features were analyzed. Multivariate regression was used to investigate the added value of DL outputs for histopathologic correlations.
Results:
A total of 418 patients [median age 55 years, interquartile range (IQR), 30-77 years] were evaluated. Unsupervised clusters 3 and 4 were associated with the positive status of P53, P16, and Ki-67, along with invasion of the omentum, rectum, and pelvic wall (P<0.05). In the multivariate logistic regression, the DL output, when adjusted for International Federation of Gynecology and Obstetrics (FIGO) stage, was independently associated with P53 [odd ratios (OR) 1.9642; 95% confidence interval (CI): 1.2412-3.1082; P=0.0039], P16 (OR 2.3446; 95% CI: 1.5445-3.5592; P=0.0001), Ki-67 (OR 10.0433; 95% CI: 5.3525-18.8450; P<0.001), invasion of the omentum (OR 2.5995; 95% CI: 1.7175-3.9342; P<0.001), invasion of the rectum (OR 2.3568; 95% CI: 1.5614-3.5574; P<0.001), and pelvic wall effusion (OR 2.0779; 95% CI: 1.3769-3.1360; P=0.0005). Unsupervised cluster 4 and patients with lower principal component analysis (PCA) scores were associated with worse survival (P<0.0001).
Conclusions:
The DL model could effectively extract histopathological features of high-grade serous ovarian cancer from CT images.
More Related Videos
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
04:48Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Related Concept Videos
01:10Computed Tomography
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
01:27Imaging Studies III: Computed Tomography
01:19Graded Potential
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
02:27Predicting Molecular Geometry
01:26Muscles of the Pelvic Floor and Perineum
Perineal Layer
The perineum is a diamond-shaped area below the pelvic diaphragm, divided into an anterior urogenital triangle that contains the external genitals and a posterior anal triangle housing the anus. The urogenital...
01:15Types of Aggregate Grading
Well-graded aggregates include a complete range of necessary size fractions that fit together to create a dense matrix with minimal voids, represented by a smooth, continuous gradation curve. This type of grading ensures good...