Abstract 388P
Background
More and more evidences suggest that circulating tumor cells (CTC) may be a good biomarker, not only as a prognostic indicator for tumors, but also for monitoring therapeutic effect and recurrence. However, the detection of CTC usually requires the final artificial judgment. This requires experienced pathologists and increases their workload. The application of machine learning in medical image recognition can effectively improve the level of automation and reduce the workload. So we hope to use machine learning to identify CTCs.
Methods
First, the python's openCV software package is used to segment the images of CTCs by image denoising, image filtering, edge detection, image expansion and contraction techniques. Secondly, the segmented cell images as a training set are trained using the CNN deep learning network. The CNN deep learning network includes input layer, intermediate hidden layer, and output layer. The middle hidden layer contains three layers, namely layer1, layer2 and lager3. Each intermediate hidden layer further includes convolution layer, excitation layer, and pooling layer. After the input layer, the cell images first enter the first intermediate hidden layer. The convolution layer of the first intermediate hidden layer is composed of 32 5x5 convolution kernels, which are then output to the pooling layer for dimension reduction through the ReLU excitation layer. After dimension reduction, the data is output from the first hidden layer to complete an entire feature extraction process. Then, through the second and third intermediate hidden layers in sequence, all feature extraction is completed. Finally, it enters the output layer and output the result, ie, CTCs or non-CTCs.
Results
We took 2920 cells from 732 patients for training and testing. Among them, 2000 cells were used as training set and 920 cells were used as testing set. The sensitivity and specificity of recognition reached 86.1% and 84.5%, respectively.
Conclusions
To identify CTC by machine learning can reach high sensitivity and specificity. We are further revising our methods of deep learning to achieve greater recognition effect.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
437P - Correlation between bio-impedance analysis and abdominal CT scan to diagnose decreased muscle mass in adult cancer patients
Presenter: Andree Kurniawan
Session: Poster display session
Resources:
Abstract
438P - Evaluating mitochondrial biomarkers between fatigue subclasses identified using latent class analysis in early-stage breast cancer patients
Presenter: Yi Long Toh
Session: Poster display session
Resources:
Abstract
440P - Accuracy of risk scoring system to determine delayed chemotherapy induced nausea and vomiting (CINV) in cancer patients
Presenter: Jada Harika
Session: Poster display session
Resources:
Abstract
441P - A pilot cross-sectional study on incidence of liver toxicity in cancer patients on western anti-cancer drug therapy with or without concurrent Chinese herbal medicine
Presenter: Tsz Him So
Session: Poster display session
Resources:
Abstract
442P - Relationship between QOL and support elderly patients with permanent colostomies
Presenter: Yukiko Orii
Session: Poster display session
Resources:
Abstract
443P - The effectiveness of individual nutritional counselling for patients with advanced cancer undergoing chemotherapy: A preliminary study
Presenter: Saori Koshimoto
Session: Poster display session
Resources:
Abstract
444P - The prophylactic effect of 0.1% fluorometholone eye drops on eye disorders caused by high-dose cytarabine
Presenter: Takayuki Tsuchiya
Session: Poster display session
Resources:
Abstract
445P - Safety and feasibility of extending flushing interval every 3 months for maintenance of TICVPS in CRC patients after completion of curative intended treatments
Presenter: Sang Bo Oh
Session: Poster display session
Resources:
Abstract
446P - Accuracy of risk scoring system to determine chemotherapy induced nausea and vomiting (CINV) in cancer patients receiving first cycle chemotherapy
Presenter: Jada Harika
Session: Poster display session
Resources:
Abstract
447P - Hypomagnesaemia: An unnoticed problem in lung cancer patients treated with concurrent chemoradiation
Presenter: Sharif Ahmed
Session: Poster display session
Resources:
Abstract