Background and Purpose— The clinical diagnosis of a transient ischemic attack (TIA) can be difficult. Evidence-based criteria hardly exist. We evaluated if the recently proposed Explicit Diagnostic Criteria for TIA (EDCT), an easy to perform clinical tool focusing on type, duration, and mode of onset of clinical features, would facilitate the clinical diagnosis of TIA. Methods— We used data from patients suspected of a TIA by a general practitioner and referred to a TIA service in the region of Utrecht, the Netherlands, who participated in the MIND-TIA (Markers in the Diagnosis of TIA) study. Information about the clinical features was collected with a standardized questionnaire within 72 hours after onset. A panel of 3 experienced neurologists ultimately determined the definite diagnosis based on all available diagnostic information including a 6-month follow-up period. Two researchers scored the EDCT. Sensitivity, specificity, and predictive values of the EDCT were assessed using the panel diagnosis as reference. A secondary analysis was performed with modified subcriteria of the EDCT. Results— Of the 206 patients, 126 (61%) had a TIA (n=104) or minor stroke (n=22), and 80 (39%) an alternative diagnosis. Most common alternative diagnoses were migraine with aura (n=24; 30.0%), stress related or somatoform symptoms (n=16; 20.0%), and syncope (n=9; 11.3%). The original EDCT had a sensitivity of 98.4% (95% CI, 94.4–99.8) and a specificity of 61.3% (49.7–71.9). Negative and positive predictive values were 96.1% (86.0–99.0) and 80.0% (75.2–84.1), respectively. The modified EDCT showed a higher specificity of 73.8% (62.7–83.0) with the same sensitivity and a similar negative predictive value of 96.7%, but a higher positive predictive value of 85.5% (80.3–89.5). Conclusions— The EDCT has excellent sensitivity and negative predictive value and could be a valuable diagnostic tool for the diagnosis of TIA.

Achieving an adequate resection margin during breast-conserving surgery remains challenging due to the lack of intraoperative feedback. Here, we evaluated the use of hyperspectral imaging to discriminate healthy tissue from tumor tissue in lumpectomy specimens. We first used a dataset obtained on tissue slices to develop and evaluate three convolutional neural networks. Second, we fine-tuned the networks with lumpectomy data to predict the tissue percentages of the lumpectomy resection surface. A MCC of 0.92 was achieved on the tissue slices and an RMSE of 9% on the lumpectomy resection surface. This shows the potential of hyperspectral imaging to classify the resection margins of lumpectomy specimens.

There is an unmet clinical need for an accurate, rapid and reliable tool for margin assessment during breast-conserving surgeries. Ultrasound offers the potential for a rapid, reproducible, and non-invasive method to assess margins. However, it is challenged by certain drawbacks, including a low signal-to-noise ratio, artifacts, and the need for experience with the acquirement and interpretation of images. A possible solution might be computer-aided ultrasound evaluation. In this study, we have developed new ensemble approaches for automated breast tumor segmentation. The ensemble approaches to predict positive and close margins (distance from tumor to margin ≤ 2.0 mm) in the ultrasound images were based on 8 pre-trained deep neural networks. The best optimum ensemble approach for segmentation attained a median Dice score of 0.88 on our data set. Furthermore, utilizing the segmentation results we were able to achieve a sensitivity of 96% and a specificity of 76% for predicting a close margin when compared to histology results. The promising results demonstrate the capability of AI-based ultrasound imaging as an intraoperative surgical margin assessment tool during breast-conserving surgery.