Popliteal artery injury following knee dislocation is associated with significant morbidity and high amputation rates. The complex and multi-disciplinary input required to manage this injury effectively can take time to arrange, prolonging the time to revascularization. Furthermore, open surgical bypass or interposition graft can be technically challenging in the acute setting, further prolonging ischemic time.Temporary intravascular shunts can be used to temporarily restore flow but require surgical exposure which takes time. Endovascular techniques can decrease the time to revascularization; however, endovascular popliteal stent-grafting is controversial because the biomechanical forces relating to flexion and extension of the knee may increase the risk of stent thrombosis. An ideal operation would result in rapid revascularization, eventually leading to a definitive and durable surgical solution.We hypothesize that a staged approach combing extracorporeal shunting, temporary endovascular covered stent placement, external fixation of bony injury, and definitive open repair provides for a superior approach to popliteal artery injury than current standard of care. We term this approach lower extremity staged revascularization (LESR) and the aim is to minimize the known factors contributing to poor outcomes after traumatic popliteal artery injury.
Background: The Gleason grading system is an important clinical practice for diagnosing prostate cancer in pathology images. However, this analysis results in significant variability among pathologists, hence creating possible negative clinical impacts. Artificial intelligence methods can be an important support for the pathologist, improving Gleason grade classifications. Consequently, our purpose is to construct and evaluate the potential of a Convolutional Neural Network (CNN) to classify Gleason patterns.
Methods: The methodology included 6982 image patches with cancer, extracted from radical prostatectomy specimens previously analyzed by an expert uropathologist. A CNN was constructed to accurately classify the corresponding Gleason. The evaluation was carried out by computing the corresponding 3 classes confusion matrix; thus, calculating the percentage of precision, sensitivity, and specificity, as well as the overall accuracy. Additionally, k-fold three-way cross-validation was performed to enhance evaluation, allowing better interpretation and avoiding possible bias.
Results: The overall accuracy reached 98% for the training and validation stage, and 94% for the test phase. Considering the test samples, the true positive ratio between pathologist and computer method was 85%, 93%, and 96% for specific Gleason patterns. Finally, precision, sensitivity, and specificity reached values up to 97%.
Conclusion: The CNN model presented and evaluated has shown high accuracy for specifically pattern neighbors and critical Gleason patterns. The outcomes are in line and complement others in the literature. The promising results surpassed current inter-pathologist congruence in classical reports, evidencing the potential of this novel technology in daily clinical aspects.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：