ABSTRACT
[This corrects the article DOI: 10.3389/fonc.2022.951973.].
ABSTRACT
Background: Continuous contrast-enhanced ultrasound (CEUS) video is a challenging direction for radiomics research. We aimed to evaluate machine learning (ML) approaches with radiomics combined with the XGBoost model and a convolutional neural network (CNN) for discriminating between benign and malignant lesions in CEUS videos with a duration of more than 1 min. Methods: We gathered breast CEUS videos of 109 benign and 81 malignant tumors from two centers. Radiomics combined with the XGBoost model and a CNN was used to classify the breast lesions on the CEUS videos. The lesions were manually segmented by one radiologist. Radiomics combined with the XGBoost model was conducted with a variety of data sampling methods. The CNN used pretrained 3D residual network (ResNet) models with 18, 34, 50, and 101 layers. The machine interpretations were compared with prospective interpretations by two radiologists. Breast biopsies or pathological examinations were used as the reference standard. Areas under the receiver operating curves (AUCs) were used to compare the diagnostic performance of the models. Results: The CNN model achieved the best AUC of 0.84 on the test cohort with the 3D-ResNet-50 model. The radiomics model obtained AUCs between 0.65 and 0.75. Radiologists 1 and 2 had AUCs of 0.75 and 0.70, respectively. Conclusions: The 3D-ResNet-50 model was superior to the radiomics combined with the XGBoost model in classifying enhanced lesions as benign or malignant on CEUS videos. The CNN model was superior to the radiologists, and the radiomics model performance was close to the performance of the radiologists.
ABSTRACT
Stevens-Johnson syndrome/toxic epidermal necrolysis (SJS/TEN) is a rare adverse cutaneous reaction with a low incidence and high mortality. Despite posing a serious threat to patients' health and lives, there is no high-quality evidence for a standard treatment regimen. Here we report the case of a 62-year-old man with stage IV pancreatic cancer who experienced immunotherapy-induced SJS/TEN. After consensus-based regular treatments at a local hospital, his symptoms became worse. Thus, he consented to receive Chinese herbal medicine (CHM) therapy. The affected parts of the patient were treated with the CHM Pi-Yan-Ning which was applied externally for 20 min twice a day. After 7 days of treatment, the dead skin began peeling away from the former lesions that had covered his hands, feet, and lips, indicating that skin had regenerated. After 12 days of treatment, the patient's skin was completely recovered. In this case, SJS/TEN was successfully treated with Pi-Yan-Ning, suggesting that there might be tremendous potential for the use of Pi-Yan-Ning in the treatment of severe skin reactions to drug treatments. Further basic investigations and clinical trials to explore the mechanism and efficacy are needed.
