Preliminary quantitative evaluation of radiation-induced DNA damage in peripheral blood lymphocytes after cardiac dual-isotope imaging

Deep Learning Assessment for Mining Important Medical Image Features of Various Modalities

Deep learning (DL) is a well-established pipeline for feature extraction in medical and nonmedical imaging tasks, such as object detection, segmentation, and classification. However, DL faces the issue of explainability, which prohibits reliable utilisation in everyday clinical practice. This study evaluates DL methods for their efficiency in revealing and suggesting potential image biomarkers. Eleven biomedical image datasets of various modalities are utilised, including SPECT, CT, photographs, microscopy, and X-ray. Seven state-of-the-art CNNs are employed and tuned to perform image classification in tasks. The main conclusion of the research is that DL reveals potential biomarkers in several cases, especially when the models are trained from scratch in domains where low-level features such as shapes and edges are not enough to make decisions. Furthermore, in some cases, device acquisition variations slightly affect the performance of DL models.

DNA Damage in Blood Leukocytes of Prostate Cancer Patients Undergoing PET/CT Examinations with [68Ga]Ga-PSMA I&T

The aim was to investigate the induction and repair of radiation-induced DNA double-strand breaks (DSBs) as a function of the absorbed dose to the blood of patients undergoing PET/CT examinations with [⁶⁸Ga]Ga-PSMA. Blood samples were collected from 15 patients before and at four time points after [⁶⁸Ga]Ga-PSMA administration, both before and after the PET/CT scan. Absorbed doses to the blood were calculated. In addition, blood samples with/without contrast agent from five volunteers were irradiated ex vivo by CT while measuring the absorbed dose. Leukocytes were isolated, fixed, and stained for co-localizing γ-H2AX+53BP1 DSB foci that were enumerated manually. In vivo, a significant increase in γ-H2AX+53BP1 foci compared to baseline was observed at all time points after administration, although the absorbed dose to the blood by ⁶⁸Ga was below 4 mGy. Ex vivo, the increase in radiation-induced foci depended on the absorbed dose and the presence of contrast agent, which could have caused a dose enhancement. The CT-dose contribution for the patients was estimated at about 12 mGy using the ex vivo calibration. The additional number of DSB foci induced by CT, however, was comparable to the one induced by ⁶⁸Ga. The significantly increased foci numbers after [⁶⁸Ga]Ga-PSMA administration may suggest a possible low-dose hypersensitivity.