Classifying breast cancer in ultrahigh-resolution optical coherence tomography images using convolutional neural networks

Design optimization of university ideological and political education system based on deep learning

This study seeks to enhance the effectiveness and student engagement in university ideological and political education (IPE) by leveraging deep learning technology. Traditional IPE approaches often fall short in terms of flexibility and interactivity, resulting in diminished student participation. The advancement of deep learning technology offers new opportunities for IPE due to its powerful capabilities in feature extraction and pattern recognition. This research employs a CNN-LSTM hybrid model, integrating Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM). By analyzing students' learning needs and interests, personalized learning paths and resource recommendations are provided for them. Firstly, this paper introduces the research methods in detail, including deep learning algorithm and model design, as well as the optimization design process of IPE system. The hybrid model combines the advantages of CNN in feature extraction and the ability of LSTM in processing sequence data to realize accurate analysis of IPE data. In the discussion part of experiment and result analysis, the model is trained and verified by collecting multi-channel data related to university IPE and using high-performance server. The results show that CNN-LSTM hybrid model is superior to traditional methods such as SVM and random forest in accuracy, recall and F1 score. This proves the powerful ability of deep learning model in dealing with complex data and capturing the internal laws and relationships of data. This study optimizes the design of university IPE system through deep learning technology, which not only improves the pertinence and effectiveness of education, but also provides new ideas and directions for the application of deep learning in the field of education.

Comparing the diagnostic efficacy of optical coherence tomography and frozen section for margin assessment in breast-conserving surgery: a meta-analysis

AIMS

This meta-analysis assessed the relative diagnostic accuracy of optical coherence tomography (OCT) versus frozen section (FS) in evaluating surgical margins during breast-conserving procedures.

METHODS

PubMed and Embase were searched for relevant studies published up to October 2023. The inclusion criteria encompassed studies evaluating the diagnostic accuracy of OCT or FS in patients undergoing breast-conserving surgery. Sensitivity and specificity were analysed using the DerSimonian and Laird method and subsequently transformed through the Freeman-Tukey double inverse sine method.

RESULTS

The meta-analysis encompassed 36 articles, comprising 16 studies on OCT and 20 on FS, involving 10 289 specimens from 8058 patients. The overall sensitivity of OCT was 0.93 (95% CI: 0.90 to 0.96), surpassing that of FS, which was 0.82 (95% CI: 0.71 to 0.92), indicating a significantly higher sensitivity for OCT (p=0.04). Conversely, the overall specificity of OCT was 0.89 (95% CI: 0.83 to 0.94), while FS exhibited a higher specificity at 0.97 (95% CI: 0.95 to 0.99), suggesting a superior specificity for FS (p＜0.01).

CONCLUSIONS

Our meta-analysis reveals that OCT offers superior sensitivity but inferior specificity compared with FS in assessing surgical margins in breast-conserving surgery patients. Further larger well-designed prospective studies are needed, especially those employing a head-to-head comparison design.

PROSPERO REGISTRATION NUMBER

CRD42023483751.

Polarization-sensitive optical coherence tomography for birefringence measurement of calcite nonlinear uniaxial crystal

We report on the new application, to the best of our knowledge, of a time-domain optical coherence tomography (TD-OCT) device used to measure the ordinary n o and extraordinary n e indices of calcite birefringence crystal at room temperature. A 1.25±0.05m m thick slab of calcite crystal is cut, polished, and used as a sample in the OCT arm. While the calcite slab is axially scanned, the raw carrier ordinary signals that came from its front and rear facets are received and denoised with a set of digital filters. The extraordinary signals are generated by the change of beam polarization using a 90°-rotating polarizer plate. It is found that the wavelet transform is capable of reaching the highest signal-to-noise ratio (SNR) of about 24.50 and 23.91 for denoising the ordinary and extraordinary signals, respectively. Quantitative measurement of n o and n e is carried out by extracting a desired envelope from the denoised signals using standard methods. Average values of 1.660 and 1.444 are obtained for n o and n e, respectively, using the wavelet-denoised signals. The weights of the results are finally searched with ones obtained from two sets of dispersion equations. We found a very good agreement between the wavelet-denoised OCT- and dispersion equation-based values with a very low relative differences of 0.04% and 2.8% for n o and n e, respectively, when the Ghosh equation is used and averaged ones of 1.3% and 4.2% for n o and n e, respectively, when the Zhao et al. equation is applied.

Digital breast tomosynthesis versus X-ray of the breast specimen for intraoperative margin assessment: A randomized trial

BACKGROUND

Involved resection margins after breast conserving surgery (BCS) often require a re-operation with increased patient anxiety and risk of impaired cosmesis. We investigated the number of re-operations due to involved resection margins after BCS comparing digital breast tomosynthesis(DBT) with X-ray for intraoperative margin evaluation. Furthermore, we assessed the diagnostic accuracy of these methods to predict histopathological margin status. Finally, we evaluated risk factors for re-operation.

METHODS

In this randomized, non-blinded study, 250 invasive breast cancer patients were randomized (1:1), whereof 241 were analyzed intraoperatively with either DBT (intervention, n = 119) or X-ray (standard, n = 122). Pearson's chi-squared test, Fisher's exact test, t-test, logistic and ordinal regression analysis was used as appropriate.

RESULTS

No difference was found in the number of re-operations between the DBT and X-ray group (16.8 % vs 19.7 %, p = 0.57), or in diagnostic accuracy to predict histopathological margin status (77.5 %, CI: 68.6-84.9 %) and (67.3 %, CI: 57.7-75.9 %), respectively. We evaluated 5 potential risk factors for re-operation: Ductal carcinoma in situ (DCIS) outside tumor, OR = 9.4 (CI: 4.3-20.6, p < 0.001); high mammographic breast density, OR = 6.1 (CI: 1.0-38.1, p = 0.047); non-evaluable margins on imaging, OR = 3.8 (CI: 1.3-10.8, p = 0.016); neoadjuvant chemotherapy, OR = 3.0 (CI: 1.0-8.8, p = 0.048); and T2 tumor-size, OR = 2.6 (CI: 1.0-6.4, p = 0.045).

CONCLUSIONS

No difference was found in the number of re-operations or in diagnostic accuracy to predict histopathological margin status between DBT and X-ray groups. DCIS outside the tumor showed the highest risk of re-operation. Intraoperative methods with improved visualization of DCIS are needed to obtain tumor free margins in BCS.

Diagnostic accuracy of optical coherence tomography for margin assessment in breast-conserving surgery: A systematic review and meta-analysis

BACKGROUND

Breast cancer is the most common malignant tumor among women, and its incidence is increasing annually. At present, the results of the study on whether optical coherence tomography (OCT) can be used as an intraoperative margin assessment method for breast-conserving surgery (BCS) are inconsistent. We herein conducted this systematic review and meta-analysis to assess the diagnostic value of OCT in BCS.

METHODS

PubMed, Web of Science, Cochrane Library, and Embase were used to search relevant studies published up to September 15, 2022. We used Review Manager 5.4, Meta-Disc 1.4, and STATA 16.0 for statistical analysis.

RESULTS

The results displayed 18 studies with 782 patients included according to the inclusion and exclusion criteria. Meta-analysis showed the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR) and the area under the curve (AUC) of OCT in the margin assessment of BCS were 0.91 (95% CI 0.88-0.93), 0.88 (95% CI 0.83-0.92), 7.53 (95% CI 5.19-10.93), 0.11(95% CI 0.08-0.14), 70.37 (95% CI 39.78-124.47), and 0.94 (95% CI 0.92-0.96), respectively.

CONCLUSIONS

OCT is a promising technique in intraoperative margin assessment of breast cancer patients.