Translator Disclaimer
Presentation
5 March 2021 Assessing rectal cancer treatment response using photoacoustic microscopy: deep learning CNN outperforms supervised machine learning model
Author Affiliations +
Abstract
Rectal adenocarcinoma is a common cancer in the United States. Current standard of care techniques (colonoscopy and MRI) have notable drawbacks and surgeons have aggressively put most patients into surgical intervention. Here we have developed a new handheld co-registered ultrasound and acoustic-resolution photoacoustic endoscope (AR-PAE) to evaluate rectal cancer in vivo. The PAE - convolutional neuron network (PAE-CNN) models were trained, validated, and tested. Hyperparameters of PAE-CNN including convolutional kernel size, max pooling kernel size, convolution layers and fully connected layers which connect to amount of imaging information preserved were carefully tuned to optimize classification performance.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiandong Leng, Eghbal Amidi, K. M. Shihab Uddin, William C. Chapman Jr., Hongbo Luo, Sitai Kou, Steve Hunt, Matthew Mutch, and Quing Zhu "Assessing rectal cancer treatment response using photoacoustic microscopy: deep learning CNN outperforms supervised machine learning model", Proc. SPIE 11642, Photons Plus Ultrasound: Imaging and Sensing 2021, 116420S (5 March 2021); https://doi.org/10.1117/12.2578017
PROCEEDINGS
PRESENTATION


SHARE
Advertisement
Advertisement
Back to Top