Haiming Li

Ovarian tumour management has increasingly relied on multidisciplinary tumour board (MDT) deliberation to address treatment complexity and disease heterogeneity. However, most patients worldwide lack access to timely expert consensus, particularly in resource-constrained centres where MDT resources are scarce or unavailable. Here we present OMGs (Ovarian tumour Multidisciplinary intelligent aGent System), a multi-agent AI framework where domain-specific agents deliberate collaboratively to integrate multidisciplinary evidence and generate MDT-style recommendations with transparent rationales. To systematically evaluate MDT recommendation quality, we developed SPEAR (Safety, Personalization, Evidence, Actionability, Robustness) and validated OMGs across diverse clinical scenarios spanning the care continuum. In multicentre re-evaluation, OMGs achieved performance comparable to expert MDT consensus ($4.45 \pm 0.30$ versus $4.53 \pm 0.23$), with higher Evidence scores (4.57 versus 3.92). In prospective multicentre evaluation (59 patients), OMGs demonstrated high concordance with routine MDT decisions. Critically, in paired human-AI studies, OMGs most substantially enhanced clinicians' recommendations in Evidence and Robustness, the dimensions most compromised when multidisciplinary expertise is unavailable. These findings suggest that multi-agent deliberative systems can achieve performance comparable to expert MDT consensus, with potential to expand access to specialized oncology expertise in resource-limited settings.

Ovarian cancer is a commonly encountered gynecological malignancy and an important health problem in the female population worldwide. Artificial intelligence (AI) has been rapidly developing in oncology, with promising achievements in terms of facilitating personalized care and improving patient survival in women with ovarian cancer. This review summarizes the present application of AI‐based techniques in ovarian cancer, with a focus on radiological imaging. It provides detailed information on the use of radiomics and deep learning‐based models in the clinical management of this disease. It also discusses current challenges, including interpretability, generalizability, and ethical and regulatory considerations, as well as future perspectives regarding the clinical use of AI‐powered tools in ovarian cancer.

We developed an MRI-based habitat radiomics model (HRM) to predict p53-abnormal (p53abn) molecular subtypes of endometrial cancer (EC). Patients with pathologically confirmed EC were retrospectively enrolled from three hospitals and categorized into a training cohort (n = 270), test cohort 1 (n = 70), and test cohort 2 (n = 154). The tumour was divided into habitat sub-regions using diffusion-weighted imaging (DWI) and contrast-enhanced (CE) images with the K-means algorithm. Radiomics features were extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), DWI, and CE images. Three machine learning classifiers-logistic regression, support vector machines, and random forests-were applied to develop predictive models for p53abn EC. Model performance was validated using receiver operating characteristic (ROC) curves, and the model with the best predictive performance was selected as the HRM. A whole-region radiomics model (WRM) was also constructed, and a clinical model (CM) with five clinical features was developed. The SHApley Additive ExPlanations (SHAP) method was used to explain the outputs of the models. DeLong's test evaluated and compared the performance across the cohorts. A total of 1920 habitat radiomics features were considered. Eight features were selected for the HRM, ten for the WRM, and three clinical features for the CM. The HRM achieved the highest AUC: 0.855 (training), 0.769 (test1), and 0.766 (test2). The AUCs of the WRM were 0.707 (training), 0.703 (test1), and 0.738 (test2). The AUCs of the CM were 0.709 (training), 0.641 (test1), and 0.665 (test2). The MRI-based HRM successfully predicted p53abn EC. The results indicate that habitat combined with machine learning, radiomics, and SHAP can effectively predict p53abn EC, providing clinicians with intuitive insights and interpretability regarding the impact of risk factors in the model.

Purpose To evaluate the value of multiparametric MRI (mpMRI)-based habitat analysis for predicting prognoses in patients with high-grade serous ovarian cancer (HGSOC), and to develop combined models by integrating habitat analysis with clinical predictors. Methods This retrospective study included 503 HGSOC patients from four centers. A K-means algorithm was used to identify voxel clusters and generate habitats on mpMRI. Radiomics features were extracted from each habitat sub-region. After feature selection, habitat models were developed to predict overall survival (OS) and progression-free survival (PFS). Cox regression analyses were performed to identify clinical predictors and construct clinical models. Combined models were developed by integrating habitat signatures with clinical predictors. Model performance was evaluated using C-index and time-dependent receiver operating characteristic area under the curves (AUCs). Results Compared with the clinical models (OS: 0.713 and 0.695; PFS: 0.727 and 0.700) and habitat models (OS: 0.707 and 0.672; PFS: 0.627 and 0.641), the combined models integrating habitat features and clinical independent predictors such as neoadjuvant chemotherapy (OS: 0.752 and 0.745; PFS: 0.784 and 0.754) achieved the highest C-indices for predicting OS and PFS in the internal validation cohort and external test cohort. The combined models also achieved the highest AUCs in all cohorts. Conclusion The habitat models based on mpMRI demonstrated potential value in predicting the prognoses of HGSOC patients, but no significant advantages over the clinical models. The combined models were expected to improve the prognoses from the level of individual clinical characteristics and habitat features reflecting intratumoral heterogeneity.

Background: Platinum resistance of high-grade serous ovarian cancer (HGSOC) cannot currently be recognized by specific molecular biomarkers. We aimed to compare the predictive capacity of various models integrating MRI habitat, whole slide images (WSIs), and clinical parameters to predict platinum sensitivity in HGSOC patients. Methods: A retrospective study involving 998 eligible patients from four hospitals was conducted. MRI habitats were clustered using K-means algorithm on multi-parametric MRI. Following feature extraction and selection, a Habitat model was developed. Vision Transformer (ViT) and multi-instance learning were trained to derive the patch-level prediction and WSI-level prediction on hematoxylin and eosin (H&E)-stained WSIs, respectively, forming a Pathology model. Logistic regression (LR) was used to create a Clinic model. A multi-modal model integrating Clinic, Habitat, and Pathology (CHP) was constructed using Multi-Head Attention (MHA) and compared with the unimodal models and Ensemble multi-modal models. The area under the curve (AUC) and integrated discrimination improvement (IDI) value were used to assess model performance and gains. Results: In the internal validation cohort and the external test cohort, the Habitat model showed the highest AUCs (0.722 and 0.685) compared to the Clinic model (0.683 and 0.681) and the Pathology model (0.533 and 0.565), respectively. The AUCs (0.789 and 0.807) of the multi-modal model interating CHP based on MHA were highest than those of any unimodal models and Ensemble multi-modal models, with positive IDI values. Conclusion: MRI-based habitat imaging showed potentials to predict platinum sensitivity in HGSOC patients. Multi-modal integration of CHP based on MHA was helpful to improve prediction performance.

High-grade serous ovarian cancer (HGSOC) presents challenges in prognostic prediction. This study aimed to develop a universal foundation model-driven multimodal model (FoMu model) to assess the prognosis of HGSOC patients. We conducted a retrospective cohort study involving 712 eligible patients across four centers, collecting clinical, MRI, and hematoxylin and eosin (H&E)-stained whole slide images (WSIs) data. Pre-trained radiological and pathological foundation models were employed for feature precoding. Subsequently, we introduced unimodal and cross-modal adaptive aggregation networks to comprehensively model the features derived from each modality. Our findings revealed that both unimodal and cross-modal FoMu models exhibited superior and stable predictive capabilities for overall survival (OS) and progression-free survival (PFS). In summary, our study successfully developed a FoMu model that effectively integrates multimodal data to assess the prognoses of HGSOC patients, highlighting its potential for improving individualized patient management and clinical decision-making in future applications.

In the study of the deep learning classification of medical images, deep learning models are applied to analyze images, aiming to achieve the goals of assisting diagnosis and preoperative assessment. Currently, most research classifies and predicts normal and cancer cells by inputting single-parameter images into trained models. However, for ovarian cancer (OC), identifying its different subtypes is crucial for predicting disease prognosis. In particular, the need to distinguish high-grade serous carcinoma from clear cell carcinoma preoperatively through non-invasive means has not been fully addressed. This study proposes a deep learning (DL) method based on the fusion of multi-parametric magnetic resonance imaging (mpMRI) data, aimed at improving the accuracy of preoperative ovarian cancer subtype classification. By constructing a new deep learning network architecture that integrates various sequence features, this architecture achieves the high-precision prediction of the typing of high-grade serous carcinoma and clear cell carcinoma, achieving an AUC of 91.62% and an AP of 95.13% in the classification of ovarian cancer subtypes.