SearcharxivSearch

arXiv subjects

Saad Shaikh

Publications and source records attributed to Saad Shaikh.

3 recordsLinked to original sources

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

The Rise of Creative Machines: Exploring the Impact of Generative AI

This study looks at how generative artificial intelligence (AI) can revolutionize marketing, product development, and research. It discusses the latest developments in the field, easy-to-use resources, and moral and social hazards. In addition to addressing mitigating techniques for issues like prejudice and disinformation, the debate emphasizes the significance of responsible development through continual stakeholder communication and ethical principles.

cs.AI

Simultaneous Detection and Quantification of Retinal Fluid with Deep Learning

We propose a new deep learning approach for automatic detection and segmentation of fluid within retinal OCT images. The proposed framework utilizes both ResNet and Encoder-Decoder neural network architectures. When training the network, we apply a novel data augmentation method called myopic warping together with standard rotation-based augmentation to increase the training set size to 45 times the original amount. Finally, the network output is post-processed with an energy minimization algorithm (graph cut) along with a few other knowledge guided morphological operations to finalize the segmentation process. Based on OCT imaging data and its ground truth from the RETOUCH challenge, the proposed system achieves dice indices of 0.522, 0.682, and 0.612, and average absolute volume differences of 0.285, 0.115, and 0.156 mm$^3$ for intaretinal fluid, subretinal fluid, and pigment epithelial detachment respectively.

cs.CV