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.

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.

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.