Skip to main content

CIALAB cervical cancer research to be published in the Journal of Digital Imaging

Jeff Prescott, an MD/PhD student in the lab, has had his research accepted from publication in JDI. The article, entitled, "Temporal Analysis of Tumor Heterogeneity and Volume for Cervical Cancer Treatment Outcome Prediction: Preliminary Evaluation," explores the efficacy of using wavelet coefficient measures of tumor perfusion on dynamic contrast-enhanced MR images of cervical tumors to predict the outcome of radiation treatment of the tumors. Subscribers to JDI can access the full text online at http://dx.doi.org/10.1007/s10278-009-9179-7. The publication abstract appears below.

Temporal Analysis of Tumor Heterogeneity and Volume for Cervical Cancer Treatment Outcome Prediction: Preliminary Evaluation

In this paper we present a method of quantifying the heterogeneity of cervical cancer tumors for use in radiation treatment outcome prediction. Features based on the distribution of masked wavelet decomposition coefficients in the tumor region of interest (ROI) of temporal dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) studies were used along with the imaged tumor volume to assess the response of the tumors to treatment. The wavelet decomposition combined with ROI masking was used to extract local intensity variations in the tumor. The developed method was tested on a data set consisting of 23 patients with advanced cervical cancer who underwent radiation therapy; 18 of these patients had local control of the tumor and five had local recurrence. Each patient participated in two DCE-MRI studies: one prior to treatment, and another early into treatment (2 - 4 weeks). An outcome of local control or local recurrence of the tumor was assigned to each patient based on a post-therapy follow-up at least 2 years after the end of treatment. Three different supervised classifiers were trained on combinational subsets of the full wavelet and volume feature set. The best performing linear discriminant analysis (LDA) and support vector machine (SVM) classifiers each had mean prediction accuracies of 95.7%, with the LDA classifier being more sensitive (100% vs. 80%) and the SVM classifier being more specific (100% vs. 94.4%) in those cases. The K-nearest neighbor classifier performed the best out of all three classifiers, having multiple feature sets that were used to achieve 100% prediction accuracy. The use of distribution measures of the masked wavelet coefficients as features resulted in much better predictive performance than those of previous approaches based on tumor intensity values and their distributions or tumor volume alone.

Keywords: cervical cancer, treatment outcome prediction, dynamic contrast enhanced MRI, wavelet.
Labels:

Comments

Post a Comment

Popular posts from this blog

CIALAB encouraging talented young minds with summer internships

CIALAB is pleased to introduce the three interns namely Tong Gan, Rosana Rodriguez Milanes and Michael Priddy working through summer’09. Rosana Rodriguez Milanes - I am a third year undergraduate student in Electronic Engineering from Universidad del Norte, Colombia. My experience as a volunteer foreign student in the Clinical Image Analysis Laboratory has been an edifying, gratifying and enriching. Being able to participate, to learn and to collaborate in the Clinical Image Analysis Laboratory during the past two weeks has allowed me to improve my analytical and interpretative skills in processing histopathological and MRI images. I have been able to learn about segmentation, region growing, splitting and merging algorithms development. I have also had the privilege of knowing and interacting with excellent engineers who have helped me improve my skills as a foreign student. I am grateful for the opportunity that the Ohio State University has given me to collaborate and to learn with...
1 comment
Read more

Dr. Gurcan to present a tutorial at IEEE ICASSP 2010

Dr. Gurcan will present a tutorial at IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2010 entitled “Biomedical Image Processing and Analysis Techniques.” ( http://www.icassp2010.org/Tutorial_03.asp) Biomedical image processing and analysis requires coordinated efforts of medical professionals, algorithmic and software engineers, and statisticians. Basic image processing techniques are frequently used in every aspect of the development from initial pre-processing techniques for noise reduction, to segmentation of lesions, to registration of lesions. Recent advances in hardware and software have made it possible to create digital scans of whole slides. These images are relatively large (100k x 100k) and in color, hence processing them present new challenges. Similarly, new computed tomography and magnetic resonance imaging scanners produce thousands of slices of images. The processing need for these images are enormous. Although biomedical image analy...
Post a Comment
Read more

Recent publications

The CIA lab has recently had 4 articles published in PLOS One and the Journal of Urology. Automated Staging Of T1 Bladder Cancer Using Digital Pathologic H&E Images: A Deep Learning approach (Journal of Urology). The paper discusses the need for accurately gauging tumor cell intrusion into Lamina Propria in an effort to substage bladder cancer. It explains how transfer learning in conjunction with Convolutional Neural Networks can be used to accurately identify different bladder layers and then compute the distance between tumor nuclei and Lamina Propria. The article is available here:  https://www.jurology.com/article/S0022-5347(18)41148-2/pdf Identifying tumor in pancreatic neuroendocrine neoplasms from Ki67 images using transfer learning (PLOS One). This paper examines a proposed methodology to automatically differentiate between NET and non-tumor regions based on images of Ki67 stained biopsies. It also uses transfer learning to exploit a rich set of features ...
6 comments
Read more