E-learning module for cytopathology education based on virtual microscopy

INTRODUCTION

In cytopathology education, Virtual Microscopy e-learning modules (VM-eLM) have achieved remarkable results in the improvement and personalization of learning. However, it remains to be determined whether these modules can significantly contribute to improving the accuracy of cytological diagnosis. The aim of this work was to create a VM-eLM for gynecologic cytopathology education designed to improve screening and interpretation skills in two groups of cytologists: experienced and nonexperienced.

MATERIALS AND METHODS

The module was designed in Moodle with both Whole Slide Images and Static Images taken from Papanicolaou smears that were diagnosed as: negative for intraepithelial lesion, low-grade squamous intraepithelial lesion, high-grade squamous intraepithelial lesion, squamous cell carcinoma, or adenocarcinoma. We assessed the effectiveness of the module using 1) clinical quality indicators to measure skill development and 2) a user survey.

RESULTS

After training, participants significantly improved their cytological screening skills, decreasing their false negative diagnosis by 78% in the non-experienced group and eliminating them entirely in the experienced group. Nonexperienced participants also significantly increased their recognition of low-grade squamous intraepithelial lesion and high-grade squamous intraepithelial lesion by 31% and 50%, respectively. Participants positively evaluated the module, highlighting its novelty, the possibility to train remotely, the immediate feedback and the quality of the Whole Slide Images.

CONCLUSIONS

We designed, implemented and tested a VM-eLM for Gynecologic Cytopathology Education that improved cytological screening skills for both non-experienced and experienced cytologists, also increasing the diagnostic accuracy of preinvasive lesions by less experienced cytologists. The module was positively evaluated by participants, who perceived an improvement in their interpretive skills.

Automatic Detection of Distant Metastasis Mentions in Radiology Reports in Spanish

PURPOSE

A critical task in oncology is extracting information related to cancer metastasis from electronic health records. Metastasis-related information is crucial for planning treatment, evaluating patient prognoses, and cancer research. However, the unstructured way in which findings of distant metastasis are often written in radiology reports makes it difficult to extract information automatically. The main aim of this study was to extract distant metastasis findings from free-text imaging and nuclear medicine reports to classify the patient status according to the presence or absence of distant metastasis.

MATERIALS AND METHODS

We created a distant metastasis annotated corpus using positron emission tomography-computed tomography and computed tomography reports of patients with prostate, colorectal, and breast cancers. Entities were labeled M1 or M0 according to affirmative or negative metastasis descriptions. We used a named entity recognition model on the basis of a bidirectional long short-term memory model and conditional random fields to identify entities. Mentions were subsequently used to classify whole reports into M1 or M0.

RESULTS

The model detected distant metastasis mentions with a weighted average F1 score performance of 0.84. Whole reports were classified with an F1 score of 0.92 for M0 documents and 0.90 for M1 documents.

CONCLUSION

These results show the usefulness of the model in detecting distant metastasis findings in three different types of cancer and the consequent classification of reports. The relevance of this study is to generate structured distant metastasis information from free-text imaging reports in Spanish. In addition, the manually annotated corpus, annotation guidelines, and code are freely released to the research community.

[Construction of text resources for automatic identification of clinical information in unstructured narratives]

BACKGROUND

A significant proportion of the clinical record is in free text format, making it difficult to extract key information and make secondary use of patient data. Automatic detection of information within narratives initially requires humans, following specific protocols and rules, to identify medical entities of interest.

AIM

To build a linguistic resource of annotated medical entities on texts produced in Chilean hospitals.

MATERIAL AND METHODS

A clinical corpus was constructed using 150 referrals in public hospitals. Three annotators identified six medical entities: clinical findings, diagnoses, body parts, medications, abbreviations, and family members. An annotation scheme was designed, and an iterative approach to train the annotators was applied. The F1-Score metric was used to assess the progress of the annotator's agreement during their training.

RESULTS

An average F1-Score of 0.73 was observed at the beginning of the project. After the training period, it increased to 0.87. Annotation of clinical findings and body parts showed significant discrepancy, while abbreviations, medications, and family members showed high agreement.

CONCLUSIONS

A linguistic resource with annotated medical entities on texts produced in Chilean hospitals was built and made available, working with annotators related to medicine. The iterative annotation approach allowed us to improve performance metrics. The corpus and annotation protocols will be released to the research community.

TRPM4 regulates Akt/GSK3-β activity and enhances β-catenin signaling and cell proliferation in prostate cancer cells

Increased expression of the TRPM4 channel has been reported to be associated with the progression of prostate cancer. However, the molecular mechanism underlying its effect remains unknown. This work found that decreasing TRPM4 levels leads to the reduced proliferation of PC3 cells. This effect was associated with a decrease in total β‐catenin protein levels and its nuclear localization, and a significant reduction in Tcf/Lef transcriptional activity. Moreover, TRPM4 silencing increases the Ser33/Ser37/Thr41 β‐catenin phosphorylated population and reduces the phosphorylation of GSK‐3β at Ser9, suggesting an increase in β‐catenin degradation as the underlying mechanism. Conversely, TRPM4 overexpression in LNCaP cells increases the Ser9 inhibitory phosphorylation of GSK‐3β and the total levels of β‐catenin and its nonphosphorylated form. Finally, PC3 cells with reduced levels of TRPM4 showed a decrease in basal and stimulated phosphoactivation of Akt1, which is likely responsible for the decrease in GSK‐3β activity in these cells. Our results also suggest that the effect of TRPM4 on Akt1 is probably mediated by an alteration in the calcium/calmodulin‐EGFR axis, linking TRPM4 activity with the observed effects in β‐catenin‐related signaling pathways. These results suggest a role for TRPM4 channels in β‐catenin oncogene signaling and underlying mechanisms, highlighting this ion channel as a new potential target for future therapies in prostate cancer.