Mikael Simard | Searcharxiv

arXiv2026

Mixed Ion Beams Enable Simultaneous Treatment and Real-Time Imaging in Carbon Ion Therapy

Carbon ion therapy is one of the most advanced forms of radiotherapy, promising improved efficacy against resistant cancers. However, the high precision offered by the carbon ion Bragg peak requires precise knowledge of the beam range inside the patient. We report the first experimental realization of range monitoring and portal imaging with a mixed ion beam, where carbon ions are treating the tumor while helium ions simultaneously accelerated to the same velocity fully traverse the patient and provide treatment feedback. Using the GSI synchrotron, a beam of 12C3+ and 4He1+ ions is accelerated, exploiting their nearly identical charge-to-mass ratios. Stable extraction with controlled helium fractions down to 7% is demonstrated. Beam characterization reveals that the helium ion Bragg peak can be cleanly separated from the carbon ion fragment background which enables accurate detection of sub-millimeter Bragg peak displacements. Mixed-beam radiographs of a lung-cancer-like phantom offer target position detection to better than 0.5 mm accuracy. This establishes mixed beams as a powerful modality for real-time image guidance in carbon ion therapy, uniquely providing simultaneous treatment delivery, range probing, and portal imaging. By overcoming range uncertainty inside the patient, mixed beams will enable to fully exploit the precision of carbon ion therapy.

physics.med-ph↗

arXiv2024

OMG-Net: A Deep Learning Framework Deploying Segment Anything to Detect Pan-Cancer Mitotic Figures from Haematoxylin and Eosin-Stained Slides

Mitotic activity is an important feature for grading several cancer types. Counting mitotic figures (MFs) is a time-consuming, laborious task prone to inter-observer variation. Inaccurate recognition of MFs can lead to incorrect grading and hence potential suboptimal treatment. In this study, we propose an artificial intelligence (AI)-aided approach to detect MFs in digitised haematoxylin and eosin-stained whole slide images (WSIs). Advances in this area are hampered by the limited number and types of cancer datasets of MFs. Here we establish the largest pan-cancer dataset of mitotic figures by combining an in-house dataset of soft tissue tumours (STMF) with five open-source mitotic datasets comprising multiple human cancers and canine specimens (ICPR, TUPAC, CCMCT, CMC and MIDOG++). This new dataset identifies 74,620 MFs and 105,538 mitotic-like figures. We then employed a two-stage framework (the Optimised Mitoses Generator Network (OMG-Net) to classify MFs. The framework first deploys the Segment Anything Model (SAM) to automate the contouring of MFs and surrounding objects. An adapted ResNet18 is subsequently trained to classify MFs. OMG-Net reaches an F1-score of 0.84 on pan-cancer MF detection (breast carcinoma, neuroendocrine tumour and melanoma), largely outperforming the previous state-of-the-art MIDOG++ benchmark model on its hold-out testing set (e.g. +16% F1-score on breast cancer detection, p<0.001) thereby providing superior accuracy in detecting MFs on various types of tumours obtained with different scanners.

cs.CV↗