We have discovered that ultrasound-mediated microbubble vascular disruption can enhance tumor responses to radiation in vivo. We demonstrate this effect using a human PC3 prostate cancer xenograft model. Results indicate a synergistic effect in vivo with combined single treatments of ultrasound-stimulated microbubble vascular perturbation and radiation inducing an over 10-fold greater cell kill with combined treatments. We further demonstrate with experiments in vivo that induction of ceramide-related endothelial cell apoptosis, leading to vascular disruption, is a causative mechanism. In vivo experiments with ultrasound and bubbles permit radiation doses to be decreased significantly for comparable effect. We envisage this unique combined ultrasound-based vascular perturbation and radiation treatment method being used to enhance the effects of radiation in a tumor, leading to greater tumor eradication.

Breast cancer is currently the second most common cause of cancer-related death in women. Presently, the clinical benchmark in cancer diagnosis is tissue biopsy examination. However, the manual process of histopathological analysis is laborious, time-consuming, and limited by the quality of the specimen and the experience of the pathologist. This study's objective was to determine if deep convolutional neural networks can be trained, with transfer learning, on a set of histopathological images independent of breast tissue to segment tumor nuclei of the breast. Various deep convolutional neural networks were evaluated for the study, including U-Net, Mask R-CNN, and a novel network (GB U-Net). The networks were trained on a set of Hematoxylin and Eosin (H&E)-stained images of eight diverse types of tissues. GB U-Net demonstrated superior performance in segmenting sites of invasive diseases (AJI = 0.53, mAP = 0.39 & AJI = 0.54, mAP = 0.38), validated on two hold-out datasets exclusively containing breast tissue images of approximately 7,582 annotated cells. The results of the networks, trained on images independent of breast tissue, demonstrated that tumor nuclei of the breast could be accurately segmented.

Breast cancer screening has been shown to significantly reduce mortality in women. The increased utilization of screening examinations has led to growing demands for rapid and accurate diagnostic reporting. In modern breast imaging centers, full-field digital mammography (FFDM) has replaced traditional analog mammography, and this has opened new opportunities for developing computational frameworks to automate detection and diagnosis. Artificial intelligence (AI), and its subdomain of deep learning, is showing promising results and improvements on diagnostic accuracy, compared to previous computer-based methods, known as computer-aided detection and diagnosis. In this commentary, we review the current status of computational radiology, with a focus on deep neural networks used in breast cancer screening and diagnosis. Recent studies are developing a new generation of computer-aided detection and diagnosis systems, as well as leveraging AI-driven tools to efficiently interpret digital mammograms, and breast tomosynthesis imaging. The use of AI in computational radiology necessitates transparency and rigorous testing. However, the overall impact of AI to radiology workflows will potentially yield more efficient and standardized processes as well as improve the level of care to patients with high diagnostic accuracy.

PURPOSE: Radiation dermatitis (RD) is common in patients undergoing breast radiotherapy. Mepitel film (MF) can reduce RD, but the results from two randomized controlled trials are conflicting. We aimed to conduct a confirmatory randomized controlled trial in patients at risk of RD. METHODS: Patients were randomly assigned to receive MF or standard care (2:1 ratio). Patients with large breasts after lumpectomy (bra size ≥ 36 inches or cup size ≥ C) or after mastectomy were eligible. Stratification factors included surgery type, dose fractionation, and administration of boost/bolus. The primary end point was grade (G) 2 or 3 RD using the Common Terminology Criteria for Adverse Events v5.0. Secondary end points included patient- and clinician-reported outcomes. RESULTS: Between January 2020 and May 2022, 376 patients were included in the modified intention-to-treat analysis. The incidence of G2 or 3 RD was significantly lower in MF patients compared with standard care (n = 39/251, 15.5%; 95% CI, 11.3 to 20.6% v n = 57/125, 45.6%; 95% CI, 36.7 to 54.8% respectively, odds ratio (OR): 0.20, P < .0001). Benefits of MF remained significant in patients who developed G 3 RD (n = 7, 2.8%; 95% CI, 1.1 to 5.7% v n = 17, 13.6%; 95% CI, 8.1 to 20.9%, OR: 0.19) and moist desquamation (n = 20, 8.0%; 95% CI, 4.9 to 12.0% v n = 24, 19.2%; 95% CI, 12.7 to 27.1%, OR: 0.36). When evaluating the combined patient and health care provider score using Radiation-Induced Skin Reaction Assessment Scale, the MF arm had significantly lower scores ( P < .0001). Individual items on the Radiation-Induced Skin Reaction Assessment Scale also favored the MF for both patient- and clinician-reported outcomes. Blistering/peeling, erythema, pigmentation, and edema were significantly reduced in the MF arm. Three patients removed the film prematurely because of rash (n = 2) and excessive pruritus (n = 1). CONCLUSION: MF significantly reduces RD in patients undergoing breast radiotherapy.