Characterization of Heart Diseases per Single Lead Using ECG Images and CNN-2D.

Cardiopathy has become one of the predominant global causes of death. The timely identification of different types of heart diseases significantly diminishes mortality risk and enhances the efficacy of treatment. However, fast and efficient recognition necessitates continuous monitoring, encompassing not only specific clinical conditions but also diverse lifestyles. Consequently, an increasing number of studies are striving to automate and progress in the identification of different cardiopathies. Notably, the assessment of electrocardiograms (ECGs) is crucial, given that it serves as the initial diagnostic test for patients, proving to be both the simplest and the most cost-effective tool. This research employs a customized architecture of Convolutional Neural Network (CNN) to forecast heart diseases by analyzing the images of both three bands of electrodes and of each single electrode signal of the ECG derived from four distinct patient categories, representing three heart-related conditions as well as a spectrum of healthy controls. The analyses are conducted on a real dataset, providing noteworthy performance (recall greater than 80% for the majority of the considered diseases and sometimes even equal to 100%) as well as a certain degree of interpretability thanks to the understanding of the importance a band of electrodes or even a single ECG electrode can have in detecting a specific heart-related pathology.

Reproducibility of the principal component analysis (PCA)-based data-driven respiratory gating on texture features in non-small cell lung cancer patients with 18 F-FDG PET/CT.

OBJECTIVE: Texture analysis is one of the lung cancer countermeasures in the field of radiomics. Even though image quality affects texture features, the reproducibility of principal component analysis (PCA)-based data-driven respiratory gating (DDG) on texture features remains poorly understood. Hence, this study aimed to clarify the reproducibility of PCA-based DDG on texture features in non-small cell lung cancer (NSCLC) patients with 18 F-Fluorodeoxyglucose (18 F-FDG) Positron emission tomography/computed tomography (PET/CT). METHODS: Twenty patients with NSCLC who underwent 18 F-FDG PET/CT in routine clinical practice were retrospectively analyzed. Each patient's PET data were reconstructed in two PET groups of no gating (NG-PET) and PCA-based DDG gating (DDG-PET). Forty-six image features were analyzed using LIFEx software. Reproducibility was evaluated using Lin's concordance correlation coefficient ( ρ c ${\rho _c}$ ) and percentage difference (%Diff). Non-reproducibility was defined as having unacceptable strength ( ρ c $({\rho _c}$  < 0.8) and a %Diff of >10%. NG-PET and DDG-PET were compared using the Wilcoxon signed-rank test. RESULTS: A total of 3/46 (6.5%) image features had unacceptable strength, and 9/46 (19.6%) image features had a %Diff of >10%. Significant differences between the NG-PET and DDG-PET groups were confirmed in only 4/46 (8.7%) of the high %Diff image features. CONCLUSION: Although the DDG application affected several texture features, most image features had adequate reproducibility. PCA-based DDG-PET can be routinely used as interchangeable images for texture feature extraction from NSCLC patients.

A Two-Stage Network for Zero-Shot Low-Illumination Image Restoration.

Due to the influence of poor lighting conditions and the limitations of existing imaging equipment, captured low-illumination images produce noise, artifacts, darkening, and other unpleasant visual problems. Such problems will have an adverse impact on the following high-level image understanding tasks. To overcome this, a two-stage network is proposed in this paper for better restoring low-illumination images. Specifically, instead of manipulating the raw input directly, our network first decomposes the low-illumination image into three different maps (i.e., reflectance, illumination, and feature) via a Decom-Net. During the decomposition process, only reflectance and illumination are further denoised to suppress the effect of noise, while the feature is preserved to reduce the loss of image details. Subsequently, the illumination is deeply adjusted via another well-designed subnetwork called Enhance-Net. Finally, the three restored maps are fused together to generate the final enhanced output. The entire proposed network is optimized in a zero-shot fashion using a newly introduced loss function. Experimental results demonstrate that the proposed network achieves better performance in terms of both objective evaluation and visual quality.

A Soft Sensor Model of Sintering Process Quality Index Based on Multi-Source Data Fusion.

In complex industrial processes such as sintering, key quality variables are difficult to measure online and it takes a long time to obtain quality variables through offline testing. Moreover, due to the limitations of testing frequency, quality variable data are too scarce. To solve this problem, this paper proposes a sintering quality prediction model based on multi-source data fusion and introduces video data collected by industrial cameras. Firstly, video information of the end of the sintering machine is obtained via the keyframe extraction method based on the feature height. Secondly, using the shallow layer feature construction method based on sinter stratification and the deep layer feature extraction method based on ResNet, the feature information of the image is extracted at multi-scale of the deep layer and the shallow layer. Then, combining industrial time series data, a sintering quality soft sensor model based on multi-source data fusion is proposed, which makes full use of multi-source data from various sources. The experimental results show that the method effectively improves the accuracy of the sinter quality prediction model.

Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features.

Nearest neighbor search, also known as NNS, is a technique used to locate the points in a high-dimensional space closest to a given query point. This technique has multiple applications in medicine, such as searching large medical imaging databases, disease classification, and diagnosis. However, when the number of points is significantly large, the brute-force approach for finding the nearest neighbor becomes computationally infeasible. Therefore, various approaches have been developed to make the search faster and more efficient to support the applications. With a focus on medical imaging, this paper proposes DenseLinkSearch (DLS), an effective and efficient algorithm that searches and retrieves the relevant images from heterogeneous sources of medical images. Towards this, given a medical database, the proposed algorithm builds an index that consists of pre-computed links of each point in the database. The search algorithm utilizes the index to efficiently traverse the database in search of the nearest neighbor. We also explore the role of medical image feature representation in content-based medical image retrieval tasks. We propose a Transformer-based feature representation technique that outperformed the existing pre-trained Transformer-based approaches on benchmark medical image retrieval datasets. We extensively tested the proposed NNS approach and compared the performance with state-of-the-art NNS approaches on benchmark datasets and our created medical image datasets. The proposed approach outperformed the existing approaches in terms of retrieving accurate neighbors and retrieval speed. In comparison to the existing approximate NNS approaches, our proposed DLS approach outperformed them in terms of lower average time per query and ≥ 99% R@10 on 11 out of 13 benchmark datasets. We also found that the proposed medical feature representation approach is better for representing medical images compared to the existing pre-trained image models. The proposed feature extraction strategy obtained an improvement of 9.37%, 7.0%, and 13.33% in terms of P@5, P@10, and P@20, respectively, in comparison to the best-performing pre-trained image model. The source code and datasets of our experiments are available at https://github.com/deepaknlp/DLS.

A new froth image classification method based on the MRMR-SSGMM hybrid model for recognition of reagent dosage condition in the coal flotation process.

Intelligent separation is a core technology in the transformation, upgradation, and high-quality development of coal. Realising the intelligent recognition and accurate classification of coal flotation froth is a key technology of intelligent separation. At present, the coal flotation process relies on artificial recognition of froth features for adjusting the reagent dosage. However, owing to the low accuracy and subjectivity of artificial recognition, some problems arise, such as reagent wastage and unqualified product quality. Thus, this paper proposes a new froth image classification method based on the maximal-relevance-minimal-redundancy (MR MR)-semi-supervised Gaussian mixture model (SSGMM) hybrid model for recognition of reagent dosage condition in the coal flotation process. First, the features of morphology, colour, and texture are extracted, and the optimal froth image features are screened out using the maximal-relevance-minimal-redundancy (MRMR) feature selection algorithm based on class information. Second, the traditional GMM clusterer is improved, called SSGMM, by introducing a small number of marked samples, the traditional GMM' problems of unclear training goals, invisible clustering results, and artificially judged clustering results are solved. Then a new hybrid classification model is proposed by combining the MRMR with the modified GMM (SSGMM) which can be named as (MRMR - SSGMM). The optimal froth image features are screened by MRMR to provide the SSGMM classifier. In the process of training and learning the feature samples, using the marked feature samples of froth images to guide the unmarked feature samples. The information of marked feature samples of froth images is mapped to the unmarked feature samples, the classification of the froth images were realised. Finally, the accuracy of the SSGMM classifier is used as the evaluation criterion for the screened features by MRMR. By automatically executing the entire learning process to find the best number of froth image features and the optimal image features, so that the classifier achieves the maximum classification accuracy. Experimental results show that the proposed classification method achieves the best results in accuracy and time, compared with other benchmark classification methods. Application results show that the method can provide reliable guidance for the adjustment of the reagent dosage, realize the accurate and timely control of the reagent dosage, reduce the consumption of the reagent and the incidence of production accidents, and stabilize the product quality in the coal flotation production process.

Unilateral absence of pulmonary artery analysis based on echocardiographic feature.

The unilateral absence of pulmonary artery (UAPA) is a rare congenital cardiovascular malformation, which is asymptomatic and easy to be ignored in early stage. A large number of complications may occur in the later stage. Therefore, early diagnosis and treatment is of great significance. The imaging data of 49 patients with UAPA discovered and confirmed clinically by the echocardiography in our hospital are analyzed. The results show that left pulmonary artery absence is more common (55%) and most of them are associated with other cardiovascular malformations (92%). Atrial septal defect and patent foramen ovale were most common in 56%. In which the absence of isolated pulmonary artery was 8% (4/49), and the absence of right pulmonary artery was 75% (3/4). Especially in the patients with tetralogy of Fallot, 77% (5/9) of them miss the diagnosis of UAPA. This suggests that doctors and sonographers should pay attention to the development of pulmonary artery bifurcation and left and right branches in multi-section, and strengthen the scanning of short axis section of high large artery.

A Weld Joint Type Identification Method for Visual Sensor Based on Image Features and SVM.

In the field of welding robotics, visual sensors, which are mainly composed of a camera and a laser, have proven to be promising devices because of their high precision, good stability, and high safety factor. In real welding environments, there are various kinds of weld joints due to the diversity of the workpieces. The location algorithms for different weld joint types are different, and the welding parameters applied in welding are also different. It is very inefficient to manually change the image processing algorithm and welding parameters according to the weld joint type before each welding task. Therefore, it will greatly improve the efficiency and automation of the welding system if a visual sensor can automatically identify the weld joint before welding. However, there are few studies regarding these problems and the accuracy and applicability of existing methods are not strong. Therefore, a weld joint identification method for visual sensor based on image features and support vector machine (SVM) is proposed in this paper. The deformation of laser around a weld joint is taken as recognition information. Two kinds of features are extracted as feature vectors to enrich the identification information. Subsequently, based on the extracted feature vectors, the optimal SVM model for weld joint type identification is established. A comparative study of proposed and conventional strategies for weld joint identification is carried out via a contrast experiment and a robustness testing experiment. The experimental results show that the identification accuracy rate achieves 98.4%. The validity and robustness of the proposed method are verified.

An automatic restoration framework based on GPU-accelerated collateral filtering in brain MR images.

BACKGROUND: Image restoration is one of the fundamental and essential tasks within image processing. In medical imaging, developing an effective algorithm that can automatically remove random noise in brain magnetic resonance (MR) images is challenging. The collateral filter has been shown a more powerful algorithm than many existing methods. However, the computation of the collateral filter is more time-consuming and the selection of the filter parameters is also laborious. This paper proposes an automatic noise removal system based on the accelerated collateral filter for brain MR images. METHODS: To solve these problems, we first accelerated the collateral filter with parallel computing using the graphics processing unit (GPU) architecture. We adopted the compute unified device architecture (CUDA), an application programming interface for the GPU by NVIDIA, to hasten the computation. Subsequently, the optimal filter parameters were selected and the automation was achieved by artificial neural networks. Specifically, an artificial neural network system associated with image feature analysis was adopted to establish the automatic image restoration framework. The best feature combination was selected by the paired t-test and the sequential forward floating selection (SFFS) methods. RESULTS: Experimental results indicated that not only did the proposed automatic image restoration algorithm perform dramatically faster than the traditional collateral filter, but it also effectively removed the noise in a wide variety of brain MR images. A speed up gain of 34 was attained to process an MR image, which completed within 0.1 s. Representative illustrations of brain tumor images demonstrated the capability of identifying lesion boundaries, which outperformed many existing methods. CONCLUSIONS: We believe that our accelerated and automated restoration framework is promising for achieving robust filtering in many brain MR image restoration applications.

3D Affine: An Embedding of Local Image Features for Viewpoint Invariance Using RGB-D Sensor Data.

Local image features are invariant to in-plane rotations and robust to minor viewpoint changes. However, the current detectors and descriptors for local image features fail to accommodate out-of-plane rotations larger than 25°­30°. Invariance to such viewpoint changes is essential for numerous applications, including wide baseline matching, 6D pose estimation, and object reconstruction. In this study, we present a general embedding that wraps a detector/descriptor pair in order to increase viewpoint invariance by exploiting input depth maps. The proposed embedding locates smooth surfaces within the input RGB-D images and projects them into a viewpoint invariant representation, enabling the detection and description of more viewpoint invariant features. Our embedding can be utilized with different combinations of descriptor/detector pairs, according to the desired application. Using synthetic and real-world objects, we evaluated the viewpoint invariance of various detectors and descriptors, for both standalone and embedded approaches. While standalone local image features fail to accommodate average viewpoint changes beyond 33.3°, our proposed embedding boosted the viewpoint invariance to different levels, depending on the scene geometry. Objects with distinct surface discontinuities were on average invariant up to 52.8°, and the overall average for all evaluated datasets was 45.4°. Similarly, out of a total of 140 combinations involving 20 local image features and various objects with distinct surface discontinuities, only a single standalone local image feature exceeded the goal of 60° viewpoint difference in just two combinations, as compared with 19 different local image features succeeding in 73 combinations when wrapped in the proposed embedding. Furthermore, the proposed approach operates robustly in the presence of input depth noise, even that of low-cost commodity depth sensors, and well beyond.

[Automatic Segmentation of Anatomical Areas in X-ray Images Based on Fully Convolutional Networks].

OBJECTIVE: Medical image segmentation is a key step in medical image processing. An architecture of fully convolutional networks was proposed to realize automatic segmentation of anatomical areas in X-ray images. METHODS: Enlightened by the advantages of convolutional neural networks on features extraction, fully convolutional networks consisting of 9 layers were designed to segment medical images. The networks used convolution kernels of various sizes to extract multi-dimensional image features in the images, meanwhile, eliminated pooling layers to avoid the loss of image details during downsampling procedures. RESULTS: The experiment was conducted in accordance with the specific scene of X-ray images segmentation. Compared with traditional segmentation methods, this approach achieved more accurate segmentation of anatomical areas. CONCLUSIONS: Fully convolutional networks can extract representative and multidimensional features of medical images, avoid the loss of image details during downsampling procedures, and complete automatic segmentation of anatomical areas accurately in X-ray images.

Structural and advanced imaging in predicting MGMT promoter methylation of primary glioblastoma: a region of interest based analysis.

BACKGROUND: The methylation status of oxygen 6-methylguanine-DNA methyltransferase (MGMT) promoter has been associated with treatment response in glioblastoma(GBM). Using pre-operative MRI techniques to predict MGMT promoter methylation status remains inconclusive. In this study, we investigated the value of features from structural and advanced imagings in predicting the methylation of MGMT promoter in primary glioblastoma patients. METHODS: Ninety-two pathologically confirmed primary glioblastoma patients underwent preoperative structural MR imagings and the efficacy of structural image features were qualitatively analyzed using Fisher's exact test. In addition, 77 of the 92 patients underwent additional advanced MRI scans including diffusion-weighted (DWI) and 3-diminsional pseudo-continuous arterial spin labeling (3D pCASL) imaging. Apparent diffusion coefficient (ADC) and relative cerebral blood flow (rCBF) values within the manually drawn region-of-interest (ROI) were calculated and compared using independent sample t test for their efficacies in predicting MGMT promoter methylation. Receiver operating characteristic curve (ROC) analysis was used to investigate the predicting efficacy with the area under the curve (AUC) and cross validations. Multiple-variable logistic regression model was employed to evaluate the predicting performance of multiple variables. RESULTS: MGMT promoter methylation was associated with tumor location and necrosis (P <  0.05). Significantly increased ADC value (P <  0.001) and decreased rCBF (P <  0.001) were associated with MGMT promoter methylation in primary glioblastoma. The ADC achieved the better predicting efficacy than rCBF (ADC: AUC, 0.860; sensitivity, 81.1%; specificity, 82.5%; vs rCBF: AUC, 0.835; sensitivity, 75.0%; specificity, 78.4%; P = 0.032). The combination of tumor location, necrosis, ADC and rCBF resulted in the highest AUC of 0.914. CONCLUSION: ADC and rCBF are promising imaging biomarkers in clinical routine to predict the MGMT promoter methylation in primary glioblastoma patients.

Accurate Smartphone Indoor Visual Positioning Based on a High-Precision 3D Photorealistic Map.

Indoor positioning is in high demand in a variety of applications, and indoor environment is a challenging scene for visual positioning. This paper proposes an accurate visual positioning method for smartphones. The proposed method includes three procedures. First, an indoor high-precision 3D photorealistic map is produced using a mobile mapping system, and the intrinsic and extrinsic parameters of the images are obtained from the mapping result. A point cloud is calculated using feature matching and multi-view forward intersection. Second, top-K similar images are queried using hamming embedding with SIFT feature description. Feature matching and pose voting are used to select correctly matched image, and the relationship between image points and 3D points is obtained. Finally, outlier points are removed using P3P with the coarse focal length. Perspective-four-point with unknown focal length and random sample consensus are used to calculate the intrinsic and extrinsic parameters of the query image and then to obtain the positioning of the smartphone. Compared with established baseline methods, the proposed method is more accurate and reliable. The experiment results show that 70 percent of the images achieve location error smaller than 0.9 m in a 10 m × 15.8 m room, and the prospect of improvement is discussed.

[Using Parallel Convolutional Neural Networks for Treatment Position Recognition in X-ray Images].

Treatment position recognition in medical images is a key technique in medical image processing. Due to the excellent performance of convolutional neural networks on features extraction and classification, an architecture of parallel convolutional neural networks is proposed to recognize treatment positions in X-ray images, which uses convolution kernels of different sizes to extract local features of different sizes in these images. The experimental analysis shows that parallel convolution neural networks, which can extract representative image features with more dimensions, are competent to classify and recognize treatment positions in medical images.

Build a Robust Learning Feature Descriptor by Using a New Image Visualization Method for Indoor Scenario Recognition.

In order to recognize indoor scenarios, we extract image features for detecting objects, however, computers can make some unexpected mistakes. After visualizing the histogram of oriented gradient (HOG) features, we find that the world through the eyes of a computer is indeed different from human eyes, which assists researchers to see the reasons that cause a computer to make errors. Additionally, according to the visualization, we notice that the HOG features can obtain rich texture information. However, a large amount of background interference is also introduced. In order to enhance the robustness of the HOG feature, we propose an improved method for suppressing the background interference. On the basis of the original HOG feature, we introduce a principal component analysis (PCA) to extract the principal components of the image colour information. Then, a new hybrid feature descriptor, which is named HOG-PCA (HOGP), is made by deeply fusing these two features. Finally, the HOGP is compared to the state-of-the-art HOG feature descriptor in four scenes under different illumination. In the simulation and experimental tests, the qualitative and quantitative assessments indicate that the visualizing images of the HOGP feature are close to the observation results obtained by human eyes, which is better than the original HOG feature for object detection. Furthermore, the runtime of our proposed algorithm is hardly increased in comparison to the classic HOG feature.

Computer-aided classification of mammographic masses using visually sensitive image features.

PURPOSE: To develop a new computer-aided diagnosis (CAD) scheme that computes visually sensitive image features routinely used by radiologists to develop a machine learning classifier and distinguish between the malignant and benign breast masses detected from digital mammograms. METHODS: An image dataset including 301 breast masses was retrospectively selected. From each segmented mass region, we computed image features that mimic five categories of visually sensitive features routinely used by radiologists in reading mammograms. We then selected five optimal features in the five feature categories and applied logistic regression models for classification. A new CAD interface was also designed to show lesion segmentation, computed feature values and classification score. RESULTS: Areas under ROC curves (AUC) were 0.786±0.026 and 0.758±0.027 when to classify mass regions depicting on two view images, respectively. By fusing classification scores computed from two regions, AUC increased to 0.806±0.025. CONCLUSION: This study demonstrated a new approach to develop CAD scheme based on 5 visually sensitive image features. Combining with a "visual aid" interface, CAD results may be much more easily explainable to the observers and increase their confidence to consider CAD generated classification results than using other conventional CAD approaches, which involve many complicated and visually insensitive texture features.

Optic nerve head slope-based quantitative parameters for identifying open-angle glaucoma on SPECTRALIS OCT images.

PURPOSE: To investigate monitoring slope-based features of the optic nerve head (ONH) cup as open-angle glaucoma (OAG) occurs. METHOD: A dataset of 46 retrospective OCT cases was acquired from the SPECTRALIS Heidelberg Engineering OCT device. A set of five parameters, which are based on the ONH cup-incline, are measured on the OAG and normal subjects in the dataset. Then, three new ONH cup-shape indices were deduced. The ONH cup-incline parameters and ONH cup-shape indices are analyzed to estimate their clinical value. RESULTS: The statistical difference between measurements on normal and glaucoma eyes was remarkably significant for all of the analyzed parameters and indices (p value < 0.001). CONCLUSIONS: The geometric shape of the ONH cup can be transferred to numerical parameters and indices. The proposed ONH cup-incline parameters and ONH cup-shape indices have shown suggestive clinical value to identify the development of OAG. As OAG appears, the top ONH cup-incline parameters decrease while the bottom ONH cup-incline parameters increase. The ONH cup-shape indices suggest capability to discriminate OAG from normal eyes.

Applying a new quantitative global breast MRI feature analysis scheme to assess tumor response to chemotherapy.

PURPOSE: To develop a new quantitative global kinetic breast magnetic resonance imaging (MRI) features analysis scheme and assess its feasibility to assess tumor response to neoadjuvant chemotherapy. MATERIALS AND METHODS: A dataset involving breast MR images acquired from 151 cancer patients before neoadjuvant chemotherapy was used. Among them, 63 patients had complete response (CR) and 88 had partial response (PR) to chemotherapy based on the RECIST criterion. A computer-aided detection (CAD) scheme was applied to segment breast region depicted on the breast MR images and computed a total of 10 kinetic image features to represent parenchyma enhancement either from the entire two breasts or the bilateral asymmetry between the two breasts. To classify between CR and PR cases, we tested an attribution selected classifier that integrates with an artificial neural network and a Wrapper Subset Evaluator. The classifier was trained and tested using a leave-one-case-out (LOCO)-based cross-validation method. The area under a receiver operating characteristic curve (AUC) was computed to assess classifier performance. RESULTS: From the pool of initial 10 features, four features were selected by more than 90% times in the LOCO cross-validation iterations. Among them, three represent the bilateral asymmetry of kinetic features between two breasts. Using the classifier yielded AUC = 0.83 ± 0.04, which is significantly higher than using each individual feature to classify between CR and PR cases (P < 0.05). CONCLUSION: This study demonstrated that quantitative analysis of global kinetic features computed from breast MRI-acquired prechemotherapy has potential to generate a useful clinical marker that is associated with tumor response to neoadjuvant chemotherapy. J. Magn. Reson. Imaging 2016;44:1099-1106.

Applying a computer-aided scheme to detect a new radiographic image marker for prediction of chemotherapy outcome.

BACKGROUND: To investigate the feasibility of automated segmentation of visceral and subcutaneous fat areas from computed tomography (CT) images of ovarian cancer patients and applying the computed adiposity-related image features to predict chemotherapy outcome. METHODS: A computerized image processing scheme was developed to segment visceral and subcutaneous fat areas, and compute adiposity-related image features. Then, logistic regression models were applied to analyze association between the scheme-generated assessment scores and progression-free survival (PFS) of patients using a leave-one-case-out cross-validation method and a dataset involving 32 patients. RESULTS: The correlation coefficients between automated and radiologist's manual segmentation of visceral and subcutaneous fat areas were 0.76 and 0.89, respectively. The scheme-generated prediction scores using adiposity-related radiographic image features significantly associated with patients' PFS (p < 0.01). CONCLUSION: Using a computerized scheme enables to more efficiently and robustly segment visceral and subcutaneous fat areas. The computed adiposity-related image features also have potential to improve accuracy in predicting chemotherapy outcome.

Early prediction of clinical benefit of treating ovarian cancer using quantitative CT image feature analysis.

BACKGROUND: In current clinical trials of treating ovarian cancer patients, how to accurately predict patients' response to the chemotherapy at an early stage remains an important and unsolved challenge. PURPOSE: To investigate feasibility of applying a new quantitative image analysis method for predicting early response of ovarian cancer patients to chemotherapy in clinical trials. MATERIAL AND METHODS: A dataset of 30 patients was retrospectively selected in this study, among which 12 were responders with 6-month progression-free survival (PFS) and 18 were non-responders. A computer-aided detection scheme was developed to segment tumors depicted on two sets of CT images acquired pre-treatment and 4-6 weeks post treatment. The scheme computed changes of three image features related to the tumor volume, density, and density variance. We analyzed performance of using each image feature and applying a decision tree to predict patients' 6-month PFS. The prediction accuracy of using quantitative image features was also compared with the clinical record based on the Response Evaluation Criteria in Solid Tumors (RECIST) guideline. RESULTS: The areas under receiver operating characteristic curve (AUC) were 0.773 ± 0.086, 0.680 ± 0.109, and 0.668 ± 0.101, when using each of three features, respectively. AUC value increased to 0.831 ± 0.078 when combining these features together. The decision-tree classifier achieved a higher predicting accuracy (76.7%) than using RECIST guideline (60.0%). CONCLUSION: This study demonstrated the potential of using a quantitative image feature analysis method to improve accuracy of predicting early response of ovarian cancer patients to the chemotherapy in clinical trials.