Dose Reduction Strategies for Pregnant Women in Emergency Settings

Deep learning-based segmentation of ultra-low-dose CT images using an optimized nnU-Net model

PURPOSE

Low-dose CT protocols are widely used for emergency imaging, follow-ups, and attenuation correction in hybrid PET/CT and SPECT/CT imaging. However, low-dose CT images often suffer from reduced quality depending on acquisition and patient attenuation parameters. Deep learning (DL)-based organ segmentation models are typically trained on high-quality images, with limited dedicated models for noisy CT images. This study aimed to develop a DL pipeline for organ segmentation on ultra-low-dose CT images.

MATERIALS AND METHODS

274 CT raw datasets were reconstructed using Siemens ReconCT software with ADMIRE iterative algorithm, generating full-dose (FD-CT) and simulated low-dose (LD-CT) images at 1%, 2%, 5%, and 10% of the original tube current. Existing FD-nnU-Net models segmented 22 organs on FD-CT images, serving as reference masks for training new LD-nnU-Net models using LD-CT images. Three models were trained for bony tissue (6 organs), soft-tissue (15 organs), and body contour segmentation. The segmented masks from LD-CT were compared to FD-CT as standard of reference. External datasets with actual LD-CT images were also segmented and compared.

RESULTS

FD-nnU-Net performance declined with reduced radiation dose, especially below 10% (5 mAs). LD-nnU-Net achieved average Dice scores of 0.937 ± 0.049 (bony tissues), 0.905 ± 0.117 (soft-tissues), and 0.984 ± 0.023 (body contour). LD models outperformed FD models on external datasets.

CONCLUSION

Conventional FD-nnU-Net models performed poorly on LD-CT images. Dedicated LD-nnU-Net models demonstrated superior performance across cross-validation and external evaluations, enabling accurate segmentation of ultra-low-dose CT images. The trained models are available on our GitHub page.

Malignant Pleural Mesothelioma CT Imaging: How to Measure It Correctly?

Background: Malignant pleural mesothelioma is the most common primary tumor of the pleura. The unique growth pattern of malignant pleural mesothelioma makes it difficult to apply the Response Evaluation Criteria for Solid Tumors (RECIST). Hence the need to use modified RECIST (mRECIST) criteria, as they better fit the unique growth pattern of malignant pleural mesothelioma. The thickness of the tumor perpendicular to the chest wall or mediastinum is measured at 2 points at 3 separate levels at least 1 cm apart on chest CT scans, and summed to obtain a one-dimensional pleural measurement. The same criterion has also been used to assess response to treatment. RECIST 1.1 represents a further update, taking into account new concepts such as revised minimum dimensions for lymph nodes and an approach to lesions that become non-measurable. Based on experience and published literature, the hypothesis of merging the 2 above-mentioned criteria in mRECIST 1.1 for mesothelioma and the use of iRECIST for the application to immune-based therapies (iRECIST) was considered. Purpose: Support the importance of studying pleural mesothelioma in a reliable and reproducible way, through a scrupulous methodology, applying the mRECIST1.1 and iRECIST criteria. Conclusions: Adoption of a standardized study metodology can make the study of PM reproducible and correct.

A Comprehensive Review on Stereotactic Arrhythmia Radioablation (STAR): Pioneering a New Era in Arrhythmia Management

Stereotactic arrhythmia radioablation (STAR) is an innovative treatment modality that leverages advanced imaging techniques and focused radiation to target arrhythmogenic foci within the heart, offering a non-invasive alternative to traditional catheter ablation methods. Arrhythmias, characterized by irregular heartbeats, pose significant health risks, including heart failure and stroke, particularly among older adults. Traditional management approaches, such as pharmacological therapies and catheter ablation, often face efficacy, safety, and recurrence limitations. STAR addresses these challenges by utilizing high-precision stereotactic technology to deliver targeted radiation, minimizing damage to surrounding tissues while maximizing therapeutic effects. This review explores the mechanisms, clinical indications, procedural techniques, and outcomes associated with STAR. Recent clinical studies demonstrate that STAR provides comparable efficacy to catheter ablation, with a favorable safety profile, making it a promising option for patients who have not responded to conventional treatments. Integrating STAR into arrhythmia management protocols may enhance patient outcomes and reduce the burden of recurrent arrhythmias. As research in this field advances, STAR holds the potential to reshape the landscape of arrhythmia treatment, providing new hope for patients suffering from these complex conditions. This review aims to elucidate the significance of STAR in modern arrhythmia management and to encourage further exploration and clinical application of this pioneering technique.

Lifetime attributable risks (LARs) of cancer in the fetus associated with maternal radiography examinations

PURPOSE

For various reasons, pregnant women are occasionally exposed to ionizing radiation during radiology examinations. In these situations, it is essential to determine the radiation dose to the fetus and any associated risks. The present study attempts to calculate the mean dose for the fetus to estimate the possible cancer induction and cancer mortality risks resulting from maternal radiography exams.

MATERIAL AND METHODS

The GATE Monte Carlo platform and a standard voxelized pregnant phantom were employed to calculate fetal radiation dose during maternal radiography exams. The data published in Biological Effects of Ionizing Radiation VII were used to convert fetal dose to lifetime attributable risks (LARs) of cancer incidence and cancer-related mortality.

RESULTS

The fetal doses and LARs of cancer incidence and cancer-related mortality for the radiographs of the chest and skull were negligible. The maximum LAR values for the lateral view of the abdomen in computed and digital radiography are 5598.29 and 2238.95 per 100,000 individuals, respectively. The computed radiography of the lateral view of the abdomen revealed the highest LAR of cancer-related mortality (2074.30 deaths for every 100,000 people).

CONCLUSION

The radiation dose incurred by the fetus due to chest and skull radiographs was minimal and unlikely to cause any abnormalities in the fetus. The discernible elevation in the lifetime attributable risk associated with cancer incidence and mortality arising from lateral computed radiography examinations of the abdomen warrants careful consideration within the realm of maternal radiography examinations.

Looking for appropriateness in follow-up CT of oncologic patients: Results from a cross-sectional study

PURPOSE

The objective of this study was to assess the inappropriateness rate of oncological follow-up CT examinations.

METHODS

Out of 7.000 oncology patients referred for follow-up CT examinations between March and October 2022, a random sample of 10 % was included. Radiology residents assessed the appropriateness using the Italian Society of Medical Oncology (AIOM) guidelines, supervised by senior radiologists. Association between inappropriateness and clinical variables was investigated and variables influencing inappropriateness were analyzed through a binary logistic regression.

RESULTS

Three-hundred-eighty-eight examinations (56.1 %) were consistent with AIOM guidelines. An additional 100 (14.5  %) examinations did not follow the recommended schedule but were nevertheless considered appropriate because of suspected recurrence/progression (10.7 %) or adverse event requiring imaging assessment (3.8 %). Two-hundred-four (29.4 %) examinations were rated as inappropriate. Inappropriateness causes were as follows: CT not included in the relevant guideline (n = 47); CT extended to additional anatomical regions (n = 59); CT requested at a shorter time-interval (n = 98). No statistically significant difference was found in age, sex, scan region, and primary cancer between appropriate and inappropriate examinations. The only variable significantly associated with inappropriateness was being referred by a specific hospital unit named "unit 2" in the study (p = 0.009), which was demonstrated to be the only appropriateness independent predictor (OR 1.952).

CONCLUSION

This study shows that majority of oncological patients referred for follow-up CT follows standard guidelines. However, a non-negligible proportion was rated as inappropriate, mainly due to the shorter time-interval. No clinical variable was associated with inappropriateness, except for referral by a specific hospital unit.