Dmitriy Zinovev

Bio: Dmitriy Zinovev is an academic researcher from DePaul University. The author has contributed to research in topics: Ensemble learning & Scale-space segmentation. The author has an hindex of 3, co-authored 4 publications receiving 62 citations.

Probabilistic lung nodule classification with belief decision trees

Abstract: In reading Computed Tomography (CT) scans with potentially malignant lung nodules, radiologists make use of high level information (semantic characteristics) in their analysis Computer-Aided Diagnostic Characterization (CADc) systems can assist radiologists by offering a “second opinion” — predicting these semantic characteristics for lung nodules In this work, we propose a way of predicting the distribution of radiologists' opinions using a multiple-label classification algorithm based on belief decision trees using the National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) dataset, which includes semantic annotations by up to four human radiologists for each one of the 914 nodules Furthermore, we evaluate our multiple-label results using a novel distance-threshold curve technique — and, measuring the area under this curve, obtain 69% performance on the validation subset We conclude that multiple-label classification algorithms are an appropriate method of representing the diagnoses of multiple radiologists on lung CT scans when ground truth is unavailable

Building an Ensemble of Probabilistic Classifiers for Lung Nodule Interpretation

Abstract: When examining Computed Tomography (CT) scans of lungs for potential abnormalities, radiologists make use of lung nodule's semantic characteristics during the analysis. Computer-Aided Diagnostic Characterization (CADc) systems can act as an aid - predicting ratings of these semantic characteristics to aid radiologists in evaluating the nodule and potentially improve the quality and consistency of diagnosis. In our work, we propose a system for predicting the distribution of radiologists' opinions using a probabilistic multi-class classification approach based on combination of belief decision trees and ADABoost ensemble learning approach. To train and test our system we use the National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) dataset, which includes semantic annotations by up to four radiologists for each one of the 914 nodules. Furthermore, we evaluate our probabilistic multi-class classifications using a novel distance-threshold curve technique intended for assessing the performance of uncertain classification systems. We conclude that for the majority of semantic characteristics there exists a set of parameters that significantly improves the performance of the ensemble over the single classifier.

A texture-based probabilistic approach for lung nodule segmentation

Abstract: Producing consistent segmentations of lung nodules in CT scans is a persistent problem of image processing algorithms. Many hard-segmentation approaches are proposed in the literature, but soft segmentation of lung nodules remains largely unexplored. In this paper, we propose a classification-based approach based on pixel-level texture features that produces soft (probabilistic) segmentations. We tested this classifier on the publicly available Lung Image Database Consortium (LIDC) dataset. We further refined the classification results with a post-processing algorithm based on the variability index. The algorithm performed well on nodules not adjacent to the chest wall, producing a soft overlap between radiologists' based segmentation and computer-based segmentation of 0.52. In the long term, these soft segmentations will be useful for representing the uncertainty in nodule boundaries that is manifest in radiological image segmentations.

Predicting Panel Ratings for Semantic Characteristics of Lung Nodules

Abstract: In reading CT scans with potentially malignant lung nodules, radiologists make use of high level information (semantic characteristics) in their analysis. CAD systems can assist radiologists by offering a “second opinion” predicting these semantic characteristics for lung nodules. In our previous work, we developed such a CAD system, training and testing it on the publicly available Lung Image Database Consortium (LIDC) dataset, which includes semantic annotations by up to four human radiologists for every nodule. However, due to the lack of ground truth and the uncertainty in the dataset, each nodule was viewed as four distinct instances when training the classifier. In this work, we propose a way of predicting the distribution of opinions of the four radiologists using a multiple-label classification algorithm based on belief decision trees. We evaluate our results using a distance-threshold curve and, measuring the area under this curve, obtain 69% accuracy on the testing subset. We conclude that multiple-label classification algorithms are an appropriate method of representing the diagnoses of multiple radiologists on lung CT scans when a single ground truth is not available.

Lung Nodule Classification Using Deep Features in CT Images

Abstract: Early detection of lung cancer can help in a sharp decrease in the lung cancer mortality rate, which accounts for more than 17% percent of the total cancer related deaths. A large number of cases are encountered by radiologists on a daily basis for initial diagnosis. Computer-aided diagnosis (CAD) systems can assist radiologists by offering a "second opinion" and making the whole process faster. We propose a CAD system which uses deep features extracted from an auto encoder to classify lung nodules as either malignant or benign. We use 4303 instances containing 4323 nodules from the National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) dataset to obtain an overall accuracy of 75.01% with a sensitivity of 83.35% and false positive of 0.39/patient over a 10 fold cross validation.

Computer-Aided Diagnosis Systems for Lung Cancer: Challenges and Methodologies

Abstract: This paper overviews one of the most important, interesting, and challenging problems in oncology, the problem of lung cancer diagnosis Developing an effective computer-aided diagnosis (CAD) system for lung cancer is of great clinical importance and can increase the patient's chance of survival For this reason, CAD systems for lung cancer have been investigated in a huge number of research studies A typical CAD system for lung cancer diagnosis is composed of four main processing steps: segmentation of the lung fields, detection of nodules inside the lung fields, segmentation of the detected nodules, and diagnosis of the nodules as benign or malignant This paper overviews the current state-of-the-art techniques that have been developed to implement each of these CAD processing steps For each technique, various aspects of technical issues, implemented methodologies, training and testing databases, and validation methods, as well as achieved performances, are described In addition, the paper addresses several challenges that researchers face in each implementation step and outlines the strengths and drawbacks of the existing approaches for lung cancer CAD systems

Pulmonary nodule classification with deep residual networks

Abstract: Lung cancer has the highest death rate among all cancers in the USA. In this work we focus on improving the ability of computer-aided diagnosis (CAD) systems to predict the malignancy of nodules from cropped CT images of lung nodules. We evaluate the effectiveness of very deep convolutional neural networks at the task of expert-level lung nodule malignancy classification. Using the state-of-the-art ResNet architecture as our basis, we explore the effect of curriculum learning, transfer learning, and varying network depth on the accuracy of malignancy classification. Due to a lack of public datasets with standardized problem definitions and train/test splits, studies in this area tend to not compare directly against other existing work. This makes it hard to know the relative improvement in the new solution. In contrast, we directly compare our system against two state-of-the-art deep learning systems for nodule classification on the LIDC/IDRI dataset using the same experimental setup and data set. The results show that our system achieves the highest performance in terms of all metrics measured including sensitivity, specificity, precision, AUROC, and accuracy. The proposed method of combining deep residual learning, curriculum learning, and transfer learning translates to high nodule classification accuracy. This reveals a promising new direction for effective pulmonary nodule CAD systems that mirrors the success of recent deep learning advances in other image-based application domains.