A comprehensive AI model development framework for consistent Gleason grading.

BACKGROUND: Artificial Intelligence(AI)-based solutions for Gleason grading hold promise for pathologists, while image quality inconsistency, continuous data integration needs, and limited generalizability hinder their adoption and scalability. METHODS: We present a comprehensive digital pathology workflow for AI-assisted Gleason grading. It incorporates A!MagQC (image quality control), A!HistoClouds (cloud-based annotation), Pathologist-AI Interaction (PAI) for continuous model improvement, Trained on Akoya-scanned images only, the model utilizes color augmentation and image appearance migration to address scanner variations. We evaluate it on Whole Slide Images (WSI) from another five scanners and conduct validations with pathologists to assess AI efficacy and PAI. RESULTS: Our model achieves an average F1 score of 0.80 on annotations and 0.71 Quadratic Weighted Kappa on WSIs for Akoya-scanned images. Applying our generalization solution increases the average F1 score for Gleason pattern detection from 0.73 to 0.88 on images from other scanners. The model accelerates Gleason scoring time by 43% while maintaining accuracy. Additionally, PAI improve annotation efficiency by 2.5 times and led to further improvements in model performance. CONCLUSIONS: This pipeline represents a notable advancement in AI-assisted Gleason grading for improved consistency, accuracy, and efficiency. Unlike previous methods limited by scanner specificity, our model achieves outstanding performance across diverse scanners. This improvement paves the way for its seamless integration into clinical workflows.

Gleason grading is a well-accepted diagnostic standard to assess the severity of prostate cancer in patients' tissue samples, based on how abnormal the cells in their prostate tumor look under a microscope. This process can be complex and time-consuming. We explore how artificial intelligence (AI) can help pathologists perform Gleason grading more efficiently and consistently. We build an AI-based system which automatically checks image quality, standardizes the appearance of images from different equipment, learns from pathologists' feedback, and constantly improves model performance. Testing shows that our approach achieves consistent results across different equipment and improves efficiency of the grading process. With further testing and implementation in the clinic, our approach could potentially improve prostate cancer diagnosis and management.

A deep learning-based 3D Prompt-nnUnet model for automatic segmentation in brachytherapy of postoperative endometrial carcinoma.

PURPOSE: To create and evaluate a three-dimensional (3D) Prompt-nnUnet module that utilizes the prompts-based model combined with 3D nnUnet for producing the rapid and consistent autosegmentation of high-risk clinical target volume (HR CTV) and organ at risk (OAR) in high-dose-rate brachytherapy (HDR BT) for patients with postoperative endometrial carcinoma (EC). METHODS AND MATERIALS: On two experimental batches, a total of 321 computed tomography (CT) scans were obtained for HR CTV segmentation from 321 patients with EC, and 125 CT scans for OARs segmentation from 125 patients. The numbers of training/validation/test were 257/32/32 and 87/13/25 for HR CTV and OARs respectively. A novel comparison of the deep learning neural network 3D Prompt-nnUnet and 3D nnUnet was applied for HR CTV and OARs segmentation. Three-fold cross validation and several quantitative metrics were employed, including Dice similarity coefficient (DSC), Hausdorff distance (HD), 95th percentile of Hausdorff distance (HD95%), and intersection over union (IoU). RESULTS: The Prompt-nnUnet included two forms of parameters Predict-Prompt (PP) and Label-Prompt (LP), with the LP performing most similarly to the experienced radiation oncologist and outperforming the less experienced ones. During the testing phase, the mean DSC values for the LP were 0.96 ± 0.02, 0.91 ± 0.02, and 0.83 ± 0.07 for HR CTV, rectum and urethra, respectively. The mean HD values (mm) were 2.73 ± 0.95, 8.18 ± 4.84, and 2.11 ± 0.50, respectively. The mean HD95% values (mm) were 1.66 ± 1.11, 3.07 ± 0.94, and 1.35 ± 0.55, respectively. The mean IoUs were 0.92 ± 0.04, 0.84 ± 0.03, and 0.71 ± 0.09, respectively. A delineation time < 2.35 s per structure in the new model was observed, which was available to save clinician time. CONCLUSION: The Prompt-nnUnet architecture, particularly the LP, was highly consistent with ground truth (GT) in HR CTV or OAR autosegmentation, reducing interobserver variability and shortening treatment time.

Genetic architecture of the inflammatory bowel diseases across East Asian and European ancestries.

Inflammatory bowel diseases (IBDs) are chronic disorders of the gastrointestinal tract with the following two subtypes: Crohn's disease (CD) and ulcerative colitis (UC). To date, most IBD genetic associations were derived from individuals of European (EUR) ancestries. Here we report the largest IBD study of individuals of East Asian (EAS) ancestries, including 14,393 cases and 15,456 controls. We found 80 IBD loci in EAS alone and 320 when meta-analyzed with ~370,000 EUR individuals (~30,000 cases), among which 81 are new. EAS-enriched coding variants implicate many new IBD genes, including ADAP1 and GIT2. Although IBD genetic effects are generally consistent across ancestries, genetics underlying CD appears more ancestry dependent than UC, driven by allele frequency (NOD2) and effect (TNFSF15). We extended the IBD polygenic risk score (PRS) by incorporating both ancestries, greatly improving its accuracy and highlighting the importance of diversity for the equitable deployment of PRS.

Fine-mapping across diverse ancestries drives the discovery of putative causal variants underlying human complex traits and diseases.

Genome-wide association studies (GWAS) of human complex traits or diseases often implicate genetic loci that span hundreds or thousands of genetic variants, many of which have similar statistical significance. While statistical fine-mapping in individuals of European ancestries has made important discoveries, cross-population fine-mapping has the potential to improve power and resolution by capitalizing on the genomic diversity across ancestries. Here we present SuSiEx, an accurate and computationally efficient method for cross-population fine-mapping, which builds on the single-population fine-mapping framework, Sum of Single Effects (SuSiE). SuSiEx integrates data from an arbitrary number of ancestries, explicitly models population-specific allele frequencies and LD patterns, accounts for multiple causal variants in a genomic region, and can be applied to GWAS summary statistics. We comprehensively evaluated SuSiEx using simulations, a range of quantitative traits measured in both UK Biobank and Taiwan Biobank, and schizophrenia GWAS across East Asian and European ancestries. In all evaluations, SuSiEx fine-mapped more association signals, produced smaller credible sets and higher posterior inclusion probability (PIP) for putative causal variants, and captured population-specific causal variants.

Identification of misdiagnosis by deep neural networks on a histopathologic review of breast cancer lymph node metastases.

The frozen section (FS) diagnoses of pathology experts are used in China to determine whether sentinel lymph nodes of breast cancer have metastasis during operation. Direct implementation of a deep neural network (DNN) in clinical practice may be hindered by misdiagnosis of the algorithm, which affects a patient's treatment decision. In this study, we first obtained the prediction result of the commonly used patch-DNN, then we present a relative risk classification and regression tree (RRCART) to identify the misdiagnosed whole-slide images (WSIs) and recommend them to be reviewed by pathologists. Applying this framework to 2362 WSIs of breast cancer lymph node metastasis, test on frozen section results in the mean area under the curve (AUC) reached 0.9851. However, the mean misdiagnosis rate (0.0248), was significantly higher than the pathologists' misdiagnosis rate (p < 0.01). The RRCART distinguished more than 80% of the WSIs as a high-accuracy group with an average accuracy reached to 0.995, but the difference with the pathologists' performance was not significant (p > 0.01). However, the other low-accuracy group included most of the misdiagnoses of DNN models. Our research shows that the misdiagnosis from deep learning model can be further enriched by our method, and that the low-accuracy WSIs must be selected for pathologists to review and the high-accuracy ones may be ready for pathologists to give diagnostic reports.

Preparation of High Thermo-Stability and Compactness Microencapsulated Phase Change Materials with Polyurea/Polyurethane/Polyamine Three-Composition Shells through Interfacial Polymerization.

In the preparation of microencapsulated phase change materials (MicroPCMs) with a three-composition shell through interfacial polymerization, the particle size, phase change behaviors, core contents, encapsulation efficiency morphology, thermal stability and chemical structure were investigated. The compactness of the MicroPCMs was analyzed through high-temperature drying and weighing. The effect of the core/shell ratio and stirring rate of the system was studied. The results indicated that the microcapsules thus-obtained possessed a spherical shape and high thermal stability and the surfaces were intact and compact. Furthermore, in the emulsification stage, the stirring speed had a significant influence on the microcapsules' particle size, and smaller particles could be obtained under the higher stirring speed, and the distributions were more uniform in these cases. When the core/shell ratio was lower than 4, both the core content and the encapsulation efficiency was high. Additionally, when the core/shell ratio was higher than 4, the encapsulation efficiency was decreased significantly. The three-composition shell greatly increased the compactness of microcapsules, and when the core/shell ratio was adjusted to 3, the mass loss of the MicroPCMs was lower than 6% after drying at 120 °C for 1 h. After the microencapsulation, double exothermic peaks appeared on the crystallization curve of the MicroPCMs, the crystallization mechanism was changed from the heterogeneous nucleation to the homogeneous nucleation and the super cooling degree was enhanced.

Application of informatics in cancer research and clinical practice: Opportunities and challenges.

Cancer informatics has significantly progressed in the big data era. We summarize the application of informatics approaches to the cancer domain from both the informatics perspective (e.g., data management and data science) and the clinical perspective (e.g., cancer screening, risk assessment, diagnosis, treatment, and prognosis). We discuss various informatics methods and tools that are widely applied in cancer research and practices, such as cancer databases, data standards, terminologies, high-throughput omics data mining, machine-learning algorithms, artificial intelligence imaging, and intelligent radiation. We also address the informatics challenges within the cancer field that pursue better treatment decisions and patient outcomes, and focus on how informatics can provide opportunities for cancer research and practices. Finally, we conclude that the interdisciplinary nature of cancer informatics and collaborations are major drivers for future research and applications in clinical practices. It is hoped that this review is instrumental for cancer researchers and clinicians with its informatics-specific insights.

Development and Validation of a Deep Learning-Based Model Using Computed Tomography Imaging for Predicting Disease Severity of Coronavirus Disease 2019.

OBJECTIVES: Coronavirus disease 2019 (COVID-19) is sweeping the globe and has resulted in infections in millions of people. Patients with COVID-19 face a high fatality risk once symptoms worsen; therefore, early identification of severely ill patients can enable early intervention, prevent disease progression, and help reduce mortality. This study aims to develop an artificial intelligence-assisted tool using computed tomography (CT) imaging to predict disease severity and further estimate the risk of developing severe disease in patients suffering from COVID-19. MATERIALS AND METHODS: Initial CT images of 408 confirmed COVID-19 patients were retrospectively collected between January 1, 2020 and March 18, 2020 from hospitals in Honghu and Nanchang. The data of 303 patients in the People's Hospital of Honghu were assigned as the training data, and those of 105 patients in The First Affiliated Hospital of Nanchang University were assigned as the test dataset. A deep learning based-model using multiple instance learning and residual convolutional neural network (ResNet34) was developed and validated. The discrimination ability and prediction accuracy of the model were evaluated using the receiver operating characteristic curve and confusion matrix, respectively. RESULTS: The deep learning-based model had an area under the curve (AUC) of 0.987 (95% confidence interval [CI]: 0.968-1.00) and an accuracy of 97.4% in the training set, whereas it had an AUC of 0.892 (0.828-0.955) and an accuracy of 81.9% in the test set. In the subgroup analysis of patients who had non-severe COVID-19 on admission, the model achieved AUCs of 0.955 (0.884-1.00) and 0.923 (0.864-0.983) and accuracies of 97.0 and 81.6% in the Honghu and Nanchang subgroups, respectively. CONCLUSION: Our deep learning-based model can accurately predict disease severity as well as disease progression in COVID-19 patients using CT imaging, offering promise for guiding clinical treatment.