Ovarian cancer is the most lethal gynecological malignancy. Timely diagnosis of ovarian cancer is difficult due to the lack of effective biomarkers. Laboratory tests are widely applied in clinical practice, and some have shown diagnostic and prognostic relevance to ovarian cancer. We aimed to systematically evaluate the value of routine laboratory tests on the prediction of ovarian cancer, and develop a robust and generalisable ensemble artificial intelligence (AI) model to assist in identifying patients with ovarian cancer. In this multicentre, retrospective cohort study, we collected 98 laboratory tests and clinical features of women with or without ovarian cancer admitted to three hospitals in China during Jan 1, 2012 and April 4, 2021. A multi-criteria decision making-based classification fusion (MCF) risk prediction framework was used to make a model that combined estimations from 20 AI classification models to reach an integrated prediction tool developed for ovarian cancer diagnosis. It was evaluated on an internal validation set (3007 individuals) and two external validation sets (5641 and 2344 individuals). The primary outcome was the prediction accuracy of the model in identifying ovarian cancer. Based on 52 features (51 laboratory tests and age), the MCF achieved an area under the receiver-operating characteristic curve (AUC) of 0·949 (95% CI 0·948-0·950) in the internal validation set, and AUCs of 0·882 (0·880-0·885) and 0·884 (0·882-0·887) in the two external validation sets. The model showed higher AUC and sensitivity compared with CA125 and HE4 in identifying ovarian cancer, especially in patients with early-stage ovarian cancer. The MCF also yielded acceptable prediction accuracy with the exclusion of highly ranked laboratory tests that indicate ovarian cancer, such as CA125 and other tumour markers, and outperformed state-of-the-art models in ovarian cancer prediction. The MCF was wrapped as an ovarian cancer prediction tool, and made publicly available to provide estimated probability of ovarian cancer with input laboratory test values. The MCF model consistently achieved satisfactory performance in ovarian cancer prediction when using laboratory tests from the three validation sets. This model offers a low-cost, easily accessible, and accurate diagnostic tool for ovarian cancer. The included laboratory tests, not only CA125 which was the highest ranked laboratory test in importance of diagnostic assistance, contributed to the characterisation of patients with ovarian cancer. Ministry of Science and Technology of China; National Natural Science Foundation of China; Natural Science Foundation of Guangdong Province, China; and Science and Technology Project of Guangzhou, China. For the Chinese translation of the abstract see Supplementary Materials section.

Better knowledge of the dose-toxicity relationship is essential for safe dose escalation to improve local control in cervical cancer radiotherapy. The conventional dose-toxicity model is based on the dose volume histogram, which is the parameter lacking spatial dose information. To overcome this limit, we explore a comprehensive rectal dose-toxicity model based on both dose volume histogram and dose map features for accurate radiation toxicity prediction. Forty-two cervical cancer patients treated with combined external beam radiotherapy (EBRT) and brachytherapy (BT) were retrospectively studied, including 12 with Grade ≥ 2 rectum toxicity and 30 patients with Grade 0–1 toxicity (non-toxicity patients). The cumulative equivalent 2-Gy rectal surface dose was deformably summed using the deformation vector fields obtained through a recent developed local topology preserved non-rigid point matching algorithm. The cumulative three-dimensional (3D) dose was flattened and mapped to a two-dimensional (2D) plane to obtain the rectum surface dose map (RSDM). The dose volume parameters (DVPs) were calculated from the 3D rectum surface, while the texture features and the dose geometric parameters (DGPs) were extracted from the 2D RSDM. Representative features further computed from DVPs, textures and DGPs by principle component analysis (PCA) and statistical analysis were respectively fed into a support vector machine equipped with a sequential feature selection procedure. The predictive powers of the representative features were compared with the GEC-ESTRO dosimetric parameters D0.1/1/2cm3. Satisfactory predictive accuracy of sensitivity 74.75 and 84.75%, specificity 72.67 and 79.87%, and area under the receiver operating characteristic curve (AUC) 0.82 and 0.91 were respectively achieved by the PCA features and statistical significant features, which were superior to the D0.1/1/2cm3 (AUC 0.71). The relative area in dose levels of 64Gy, 67Gy, 68Gy, 87Gy, 88Gy and 89Gy, perimeters in dose levels of 89Gy, as well as two texture features were ranked as the important factors that were closely correlated with rectal toxicity. Our extensive experimental results have demonstrated the feasibility of the proposed scheme. A future large patient cohort study is still needed for model validation.

Deformable image registration (DIR) is a critical technic in adaptive radiotherapy (ART) for propagating contours between planning computerized tomography (CT) images and treatment CT/cone-beam CT (CBCT) images to account for organ deformation for treatment re-planning. To validate the ability and accuracy of DIR algorithms in organ at risk (OAR) contour mapping, ten intensity-based DIR strategies, which were classified into four categories—optical flow-based, demons-based, level-set-based and spline-based—were tested on planning CT and fractional CBCT images acquired from twenty-one head & neck (H&N) cancer patients who underwent 6~7-week intensity-modulated radiation therapy (IMRT). Three similarity metrics, i.e., the Dice similarity coefficient (DSC), the percentage error (PE) and the Hausdorff distance (HD), were employed to measure the agreement between the propagated contours and the physician-delineated ground truths of four OARs, including the vertebra (VTB), the vertebral foramen (VF), the parotid gland (PG) and the submandibular gland (SMG). It was found that the evaluated DIRs in this work did not necessarily outperform rigid registration. DIR performed better for bony structures than soft-tissue organs, and the DIR performance tended to vary for different ROIs with different degrees of deformation as the treatment proceeded. Generally, the optical flow-based DIR performed best, while the demons-based DIR usually ranked last except for a modified demons-based DISC used for CT-CBCT DIR. These experimental results suggest that the choice of a specific DIR algorithm depends on the image modality, anatomic site, magnitude of deformation and application. Therefore, careful examinations and modifications are required before accepting the auto-propagated contours, especially for automatic re-planning ART systems.

Deep learning has recently been extensively investigated to remove artifacts in low-dose computed tomography (LDCT). However, the power of transfer learning for medical image denoising tasks has not been fully explored. In this work, we proposed a transfer learning residual convolutional neural network (TLR-CNN) to restore LDCT images at single and blind noise levels. A residual network was implemented to effectively estimate the difference between denoised image and its original map, and a noise-free image was obtained by subtracting the residual map from the LDCT image. The results were compared to competing baseline denoising methods in terms of quantitative metrics including the PSNR, RMSE, SSIM and FSIM. For the single noise level, the proposed method demonstrated better denoising performance than the other algorithms for both simulation data and clinical data. As for the blind denoising, the image qualities were improved for all noise levels for all the quantitative metrics, but such improvements were decreasing as the noise level decrease (higher mAs). Comparative experiments suggested that the proposed network could effectively suppress artifacts and preserve image details with faster converge rate and reduced computational time.