Dosimetric comparison of different multileaf collimator leaves in treatment planning of intensity-modulated radiotherapy for cervical cancer

Enhancing the Accuracy of Lymph-Node-Metastasis Prediction in Gynecologic Malignancies Using Multimodal Federated Learning: Integrating CT, MRI, and PET/CT

Gynecological malignancies, particularly lymph node metastasis, have presented a diagnostic challenge, even with traditional imaging techniques such as CT, MRI, and PET/CT. This study was conceived to explore and, subsequently, to bridge this diagnostic gap through a more holistic and innovative approach. By developing a comprehensive framework that integrates both non-image data and detailed MRI image analyses, this study harnessed the capabilities of a multimodal federated-learning model. Employing a composite neural network within a federated-learning environment, this study adeptly merged diverse data sources to enhance prediction accuracy. This was further complemented by a sophisticated deep convolutional neural network with an enhanced U-NET architecture for meticulous MRI image processing. Traditional imaging yielded sensitivities ranging from 32.63% to 57.69%. In contrast, the federated-learning model, without incorporating image data, achieved an impressive sensitivity of approximately 0.9231, which soared to 0.9412 with the integration of MRI data. Such advancements underscore the significant potential of this approach, suggesting that federated learning, especially when combined with MRI assessment data, can revolutionize lymph-node-metastasis detection in gynecological malignancies. This paves the way for more precise patient care, potentially transforming the current diagnostic paradigm and resulting in improved patient outcomes.

Failure modes and downtime of radiotherapy LINACs and multileaf collimators in Indonesia

BACKGROUND AND PURPOSE

The lack of equitable access to radiotherapy (RA) linear accelerators (LINACs) is a substantial barrier to cancer care in low- and middle-income countries (LMICs). These nations are expected to bear up to 75% of cancer-related deaths globally by 2030. State-of-the-art LINACs in LMICs experience major issues in terms of robustness, with mechanical and electrical breakdowns resulting in downtimes ranging from days to months. While existing research has identified the higher failure frequency and downtimes between LMICs (Nigeria, Botswana) compared to high-income countries (HICs, the UK), there has been a need for additional data and study particularly relating to multileaf collimators (MLCs).

MATERIALS AND METHODS

This study presents for the first time the analysis of data gathered through a dedicated survey and workshop including participants from 14 Indonesian hospitals, representing a total of 19 LINACs. We show the pathways to failure of radiotherapy LINACs and frequency of breakdowns with a focus on the MLC subsystem.

RESULTS

This dataset shows that LINACs throughout Indonesia are out of operation for seven times longer than HICs, and the mean time between failures of a LINAC in Indonesia is 341.58 h or about 14 days. Furthermore, of the LINACs with an MLC fitted, 59 . 02 - 1.61 + 1.98 $59.02_{ - 1.61}^{ + 1.98}$ % of all mechanical faults are due to the MLC, and 57 . 14 - 1.27 + 0.78 $57.14_{ - 1.27}^{ + 0.78}$ % of cases requiring a replacement component are related to the MLC.

CONCLUSION

These results highlight the pressing need to improve robustness of RT technology for use in LMICs, highlighting the MLC as a particularly problematic component. This work motivates a reassessment of the current generation of RT LINACs and demonstrates the need for dedicated efforts toward a future where cancer treatment technology is robust for use in all environments where it is needed.