Yinsheng Zhang

Accurate assessment and surveillance of retinoblastoma (RB) require more efficient and objective measurements. This study aims to develop an artificial intelligence (AI) system, named RB-Care, for automatic classification and quantitative assessment of RB. A total of 3730 wide-field fundus images were included for the development and validation of 2 models in RB-Care. The first model was trained to automatically classify the images into "normal," "unseeded RB," and "seeded RB." The second model performed quantitative assessment on unseeded RB by detecting and segmenting tumors and optic discs. The classification model of RB-Care can accurately classify fundus images into 3 categories with an accuracy of 0.9734 and an area under the curve (AUC) of 0.9970. The segmentation model can make precise boundary detection and quantitative measurement on tumors and optic discs, achieving mean Intersection over Union (mIoU) of 0.9670 and Dice similarity coefficient (DSC) of 0.9780 for tumor segmentation, and mIoU of 0.9999 and DSC of 0.9999 for optic disc segmentation, which reaches a comparable level with ophthalmologists. The RB-Care achieved excellent performance in both RB classification and segmentation. Consequently, the tumor size and the distance between tumor and optic disc can be quantified, which provides an objective measurement tool for quantitative assessment and surveillance of RB in clinical settings. Developing a clinically relevant technologies for objective quantitative assessment of RB.

This study established a method for rapid classification of milk products by combining MALDI-TOF MS analysis with machine learning techniques. The analysis of 2 different types of milk products was used as an example. To select key variables as potential markers, integrated machine learning strategies based on 6 feature selection techniques combined with support vector machine (SVM) classifier were implemented to screen the informative features and classify the milk samples. The models were evaluated and compared by accuracy, Akaike information criterion (AIC), and Bayesian information criterion (BIC). The results showed the least absolute shrinkage and selection operator (LASSO) combined with SVM performs best, with prediction accuracy of 100% ± 0%, AIC of -360 ± 22, and BIC of -345 ± 22. Six features were selected by LASSO and identified based on the available protein molecular mass data. These results indicate that MALDI-TOF MS coupled with machine learning technique could be used to search for potential key targets for authentication and quality control of food products.

The detection of optic disc and macula is an essential step for ROP (Retinopathy of prematurity) zone segmentation and disease diagnosis. This paper aims to enhance deep learning-based object detection with domain-specific morphological rules. Based on the fundus morphology, we define five morphological rules, i.e., number restriction (maximum number of optic disc and macula is one), size restriction (e.g., optic disc width: 1.05 +/- 0.13 mm), distance restriction (distance between the optic disc and macula/fovea: 4.4 +/- 0.4 mm), angle/slope restriction (optic disc and macula should roughly be positioned in the same horizontal line), position restriction (In OD, the macula is on the left side of the optic disc; vice versa for OS). A case study on 2953 infant fundus images (with 2935 optic disc instances and 2892 macula instances) proves the effectiveness of the proposed method. Without the morphological rules, naïve object detection accuracies of optic disc and macula are 0.955 and 0.719, respectively. With the proposed method, false-positive ROIs (region of interest) are further ruled out, and the accuracy of the macula is raised to 0.811. The IoU (intersection over union) and RCE (relative center error) metrics are also improved.