Deep learning in ovarian cancer diagnosis: a comprehensive review of various imaging modalities

Ovarian masses suggested for MRI examination: assessment of deep learning models based on non-contrast-enhanced MRI sequences for predicting malignancy

PURPOSE

We aims to assessed and compare four deep learning(DL) models using non-contrast-enhanced magnetic resonance imaging(MRI) to differentiate benign from malignant ovarian tumors, considering diagnostic efficacy and associated development costs.

METHODS

526 patients (327 benign lesions vs 199 malignant lesions) who were recommended for MRI due to suspected ovarian masses, confirmed with histopathology, were included in this retrospective study. A training cohort (n=367) and a validation cohort (n=159) were constructed. Based on the images of T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), we evaluated the diagnostic performance of four DL models (ConvNeXt, FBNet, GhostNet, ResNet50) in distinguishing between benign and malignant ovarian tumors. Two radiologists with varying levels of experience independently reviewed all original non-contrast-enhanced MR images from the validation cohort to determine if each case was benign or malignant. The area under the receiver operating characteristic curve (AUC), confusion matrices, accuracy, sensitivity, specificity, positive predictive value(PPV) and negative predictive value(NPV) were used to compare performance.

RESULTS

The study of 526 ovarian mass patients (ages 1-92) evaluated four DL models for predicting malignant tumors, with AUCs ranging from 0.8091 to 0.8572 and accuracy between 81.1% and 85.5%. An experienced radiologist achieved 86.2% accuracy, slightly surpassing the DL models, while a less experienced radiologist had 69.2% accuracy. Resnet50 had the highest sensitivity (78.3%) and NPV (87.3%), while ConvNeXt excelled in specificity and PPV (100%). GhostNet and FBNet are more parameter-efficient than other models.

CONCLUSION

The four DL models effectively distinguished between benign and malignant ovarian tumors using non-contrast MRI. These models outperformed less experienced radiologists and were slightly less accurate than experienced ones. ResNet50 had the best predictive performance, while GhostNet was highly accurate with fewer parameters. Our study indicates that DL models based on non-contrast-enhanced MRI have the potential to assist in diagnosis.

OVision A raspberry Pi powered portable low cost medical device framework for cancer diagnosis

Cancer remains a major global health challenge, with significant disparities in access to advanced diagnostic and prognostic technologies, especially in resource-constrained settings. Existing medical treatments and devices for cancer diagnosis are often prohibitively expensive, limiting their reach and impact. Pathologists' scarcity exacerbates cancer diagnosis accuracy, elevating mortality risks. To address these critical issues, this study presents OVision - a low cost, deep learning-powered framework developed to assist in histopathological diagnosis. The key objective is to leverage the portable, low-power computing Raspberry Pi. By designing standalone devices that eliminate the need for internet connectivity and high-end infrastructure, we can dramatically reduce costs while maintaining accuracy. As a proof of concept, the study demonstrated the viability of this framework through a compact, self-contained device capable of accurately detecting ovarian cancer subtypes with 95% accuracy, on par with traditional methods, while costing a small fraction of the price. This portable, off-grid solution has immense potential to improve access to precision cancer diagnostics, especially in underserved regions of the world that lack the resources to deploy expensive, infrastructure-heavy medical technologies. In addition, by classifying each tile, the tool can provide percentages of each histologic subtype detected within the slide. This capability enhances the diagnostic precision, offering a detailed overview of the heterogeneity within each tissue sample, helps in understanding the complexity of histologic subtypes and tailoring personalized treatment plans. In conclusion, this work proposes a transformative model for developing affordable, accessible medical devices that can bring advanced healthcare benefits to all, laying the foundation for a more equitable, inclusive future of precision medicine.

AI-enhanced PET/CT image synthesis using CycleGAN for improved ovarian cancer imaging

Purpose

Ovarian cancer is the fifth fatal cancer among women. Positron emission tomography (PET), which offers detailed metabolic data, can be effectively used for early cancer screening. However, proper attenuation correction is essential for interpreting the data obtained by this imaging modality. Computed tomography (CT) imaging is commonly performed alongside PET imaging for attenuation correction. This approach may introduce some issues in spatial alignment and registration of the images obtained by the two modalities. This study aims to perform PET image attenuation correction by using generative adversarial networks (GANs), without additional CT imaging.

Material and methods

The PET/CT data from 55 ovarian cancer patients were used in this study. Three GAN architectures: Conditional GAN, Wasserstein GAN, and CycleGAN, were evaluated for attenuation correction. The statistical performance of each model was assessed by calculating the mean squared error (MSE) and mean absolute error (MAE). The radiological performance assessments of the models were performed by comparing the standardised uptake value and the Hounsfield unit values of the whole body and selected organs, in the synthetic and real PET and CT images.

Results

Based on the results, CycleGAN demonstrated effective attenuation correction and pseudo-CT generation, with high accuracy. The MAE and MSE for all images were 2.15 ± 0.34 and 3.14 ± 0.56, respectively. For CT reconstruction, such values were found to be 4.17 ± 0.96 and 5.66 ± 1.01, respectively.

Conclusions

The results showed the potential of deep learning in reducing radiation exposure and improving the quality of PET imaging. Further refinement and clinical validation are needed for full clinical applicability.

PET/CT-based 3D multi-class semantic segmentation of ovarian cancer and the stability of the extracted radiomics features

Accurate segmentation of ovarian cancer (OC) lesions in PET/CT images is essential for effective disease management, yet manual segmentation for radiomics analysis is labor-intensive and time-consuming. This study introduces the application of a 3D U-Net deep learning model, leveraging advanced 3D networks, for multi-class semantic segmentation of OC in PET/CT images and assesses the stability of the extracted radiomics features. Utilizing a dataset of 3120 PET/CT images from 39 OC patients, the dataset was divided into training (70%), validation (15%), and test (15%) subsets to optimize and evaluate the model's performance. The 3D U-Net model, especially with a VGG16 backbone, achieved notable segmentation accuracy with a Dice score of 0.74, Precision of 0.76, and Recall of 0.78. Additionally, the study demonstrated high stability in radiomics features, with over 85% of PET and 84% of CT image features showing high intraclass correlation coefficients (ICCs > 0.8). These results underscore the potential of automated 3D U-Net-based segmentation to significantly enhance OC diagnosis and treatment planning. The reliability of the extracted radiomics features from automated segmentation supports its application in clinical decision-making and personalized medicine. This research marks a significant advancement in oncology diagnostics, providing a robust and efficient method for segmenting OC lesions in PET/CT images. By addressing the challenges of manual segmentation and demonstrating the effectiveness of 3D networks, this study contributes to the growing body of evidence supporting the application of artificial intelligence in improving diagnostic accuracy and patient outcomes in oncology.

Developing a deep learning model for predicting ovarian cancer in Ovarian-Adnexal Reporting and Data System Ultrasound (O-RADS US) Category 4 lesions: A multicenter study

PURPOSE

To develop a deep learning (DL) model for differentiating between benign and malignant ovarian tumors of Ovarian-Adnexal Reporting and Data System Ultrasound (O-RADS US) Category 4 lesions, and validate its diagnostic performance.

METHODS

A retrospective analysis of 1619 US images obtained from three centers from December 2014 to March 2023. DeepLabV3 and YOLOv8 were jointly used to segment, classify, and detect ovarian tumors. Precision and recall and area under the receiver operating characteristic curve (AUC) were employed to assess the model performance.

RESULTS

A total of 519 patients (including 269 benign and 250 malignant masses) were enrolled in the study. The number of women included in the training, validation, and test cohorts was 426, 46, and 47, respectively. The detection models exhibited an average precision of 98.68% (95% CI: 0.95-0.99) for benign masses and 96.23% (95% CI: 0.92-0.98) for malignant masses. Moreover, in the training set, the AUC was 0.96 (95% CI: 0.94-0.97), whereas in the validation set, the AUC was 0.93(95% CI: 0.89-0.94) and 0.95 (95% CI: 0.91-0.96) in the test set. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive values for the training set were 0.943,0.957,0.951,0.966, and 0.936, respectively, whereas those for the validation set were 0.905,0.935, 0.935,0.919, and 0.931, respectively. In addition, the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the test set were 0.925, 0.955, 0.941, 0.956, and 0.927, respectively.

CONCLUSION

The constructed DL model exhibited high diagnostic performance in distinguishing benign and malignant ovarian tumors in O-RADS US category 4 lesions.

Bayesian and deep-learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers

BACKGROUND

Ovarian cancer is the most lethal of all gynecological cancers. Cancer Antigen 125 (CA125) is the best-performing ovarian cancer biomarker which however is still not effective as a screening test in the general population. Recent literature reports additional biomarkers with the potential to improve on CA125 for early detection when using longitudinal multimarker models.

METHODS

Our data comprised 180 controls and 44 cases with serum samples sourced from the multimodal arm of UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS). Our models were based on Bayesian change-point detection and recurrent neural networks.

RESULTS

We obtained a significantly higher performance for CA125-HE4 model using both methodologies (AUC 0.971, sensitivity 96.7% and AUC 0.987, sensitivity 96.7%) with respect to CA125 (AUC 0.949, sensitivity 90.8% and AUC 0.953, sensitivity 92.1%) for Bayesian change-point model (BCP) and recurrent neural networks (RNN) approaches, respectively. One year before diagnosis, the CA125-HE4 model also ranked as the best, whereas at 2 years before diagnosis no multimarker model outperformed CA125.

CONCLUSIONS

Our study identified and tested different combination of biomarkers using longitudinal multivariable models that outperformed CA125 alone. We showed the potential of multivariable models and candidate biomarkers to increase the detection rate of ovarian cancer.