Deep learning to assess microsatellite instability directly from histopathological whole slide images in endometrial cancer.

Molecular classification, particularly microsatellite instability-high (MSI-H), has gained attention for immunotherapy in endometrial cancer (EC). MSI-H is associated with DNA mismatch repair defects and is a crucial treatment predictor. The NCCN guidelines recommend pembrolizumab and nivolumab for advanced or recurrent MSI-H/mismatch repair deficient (dMMR) EC. However, evaluating MSI in all cases is impractical due to time and cost constraints. To overcome this challenge, we present an effective and efficient deep learning-based model designed to accurately and rapidly assess MSI status of EC using H&E-stained whole slide images. Our framework was evaluated on a comprehensive dataset of gigapixel histopathology images of 529 patients from the Cancer Genome Atlas (TCGA). The experimental results have shown that the proposed method achieved excellent performances in assessing MSI status, obtaining remarkably high results with 96%, 94%, 93% and 100% for endometrioid carcinoma G1G2, respectively, and 87%, 84%, 81% and 94% for endometrioid carcinoma G3, in terms of F-measure, accuracy, precision and sensitivity, respectively. Furthermore, the proposed deep learning framework outperforms four state-of-the-art benchmarked methods by a significant margin (p < 0.001) in terms of accuracy, precision, sensitivity and F-measure, respectively. Additionally, a run time analysis demonstrates that the proposed method achieves excellent quantitative results with high efficiency in AI inference time (1.03 seconds per slide), making the proposed framework viable for practical clinical usage. These results highlight the efficacy and efficiency of the proposed model to assess MSI status of EC directly from histopathological slides.

Deep Learning Can Predict Bevacizumab Therapeutic Effect and Microsatellite Instability Directly from Histology in Epithelial Ovarian Cancer.

Epithelial ovarian cancer (EOC) remains a significant cause of mortality among gynecologic cancers, with the majority of cases being diagnosed at an advanced stage. Before targeted therapies were available, EOC treatment relied largely on debulking surgery and platinum-based chemotherapy. Vascular endothelial growth factors have been identified as inducing tumor angiogenesis. According to several clinical trials, anti-vascular endothelial growth factor-targeted therapy with bevacizumab was effective in all phases of EOC treatment. However, there are currently no biomarkers accessible for regular therapeutic use despite the importance of patient selection. Microsatellite instability (MSI), caused by a deficiency of the DNA mismatch repair system, is a molecular abnormality observed in EOC associated with Lynch syndrome. Recent evidence suggests that angiogenesis and MSI are interconnected. Developing predictive biomarkers, which enable the selection of patients who might benefit from bevacizumab-targeted therapy or immunotherapy, is critical for realizing personalized precision medicine. In this study, we developed 2 improved deep learning methods that eliminate the need for laborious detailed image-wise annotations by pathologists and compared them with 3 state-of-the-art methods to not only predict the efficacy of bevacizumab in patients with EOC using mismatch repair protein immunostained tissue microarrays but also predict MSI status directly from histopathologic images. In prediction of therapeutic outcomes, the 2 proposed methods achieved excellent performance by obtaining the highest mean sensitivity and specificity score using MSH2 or MSH6 markers and outperformed 3 state-of-the-art deep learning methods. Moreover, both statistical analysis results, using Cox proportional hazards model analysis and Kaplan-Meier progression-free survival analysis, confirm that the 2 proposed methods successfully differentiate patients with positive therapeutic effects and lower cancer recurrence rates from patients experiencing disease progression after treatment (P < .01). In prediction of MSI status directly from histopathology images, our proposed method also achieved a decent performance in terms of mean sensitivity and specificity score even for imbalanced data sets for both internal validation using tissue microarrays from the local hospital and external validation using whole section slides from The Cancer Genome Atlas archive.

Strategies for facilitating processing of transient information in instructional videos by using learner control mechanisms.

Learner control of video presentations by using pause buttons or timeline scrollbars was suggested as helpful for learning from sources of transient information such as dynamic visualizations and spoken words. However, effective learner control could be difficult to attain without sufficient instructional support. This study developed strategies for facilitating processing and integration of transient information based on cognitive load theory by providing learners with explicit guidance in when and how to use pausing and timeline scrollbars while watching instructional videos. A single-factor between-subjects experiment was conducted to examine the effects of the proposed strategies. Ninety undergraduates were randomly assigned to one of three groups - strategy guidance group (learners were provided with guidance in strategies), learner control group (learners were allowed to control the video but without any guidance in strategies), and continuous presentation group (without any learner control mechanism). The results revealed that compared to the learner control group, the strategy guidance group had a greater number of pauses and scrollbacks on the timeline, demonstrated significantly better performance in the immediate comprehension test and higher performance efficiency in the immediate recall and comprehension tests. Compared to the continuous presentation group, the strategy guidance group demonstrated significantly better performance in the immediate recall and comprehension tests and higher performance efficiency in both these tests, as well as better performance in the delayed recall test and higher performance efficiency in the delayed recall test.

A new application of the temporal contiguity effect in designing narrated slideshows.

We investigated whether the temporal contiguity effect, which holds that information sources, such as visual information and narration need to be temporally coordinated for learning to be effective, can also be found in narrated slideshows. A concurrent presentation-key point format (CPK), in which visual information sequentially appeared as key points on the slide with corresponding narration, was compared to a concurrent presentation-whole format (CPW), in which visual information was shown all at once on the slide with corresponding narration, and a sequential presentation format (SP), in which the narration was played first before all the corresponding visual information was presented at once. Ninety-nine undergraduates were randomly divided across the CPK, CPW and SP conditions. Results revealed that participants in the CPK group had higher post-test performance and learning efficiency than participants in the CPW and SP conditions. Performance in the CPW condition was higher than in the SP conditions, but only in terms of learning efficiency. The results suggested that the occurrence of the temporal contiguity effect not only depends on whether the presentation of narration and visual information in narrated slideshows is concurrent or not, but also on how concurrent it is.