Prediction of lymphoma response to CAR T cells by deep learning-based image analysis.

Clinical prognostic scoring systems have limited utility for predicting treatment outcomes in lymphomas. We therefore tested the feasibility of a deep-learning (DL)-based image analysis methodology on pre-treatment diagnostic computed tomography (dCT), low-dose CT (lCT), and 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) images and rule-based reasoning to predict treatment response to chimeric antigen receptor (CAR) T-cell therapy in B-cell lymphomas. Pre-treatment images of 770 lymph node lesions from 39 adult patients with B-cell lymphomas treated with CD19-directed CAR T-cells were analyzed. Transfer learning using a pre-trained neural network model, then retrained for a specific task, was used to predict lesion-level treatment responses from separate dCT, lCT, and FDG-PET images. Patient-level response analysis was performed by applying rule-based reasoning to lesion-level prediction results. Patient-level response prediction was also compared to prediction based on the international prognostic index (IPI) for diffuse large B-cell lymphoma. The average accuracy of lesion-level response prediction based on single whole dCT slice-based input was 0.82+0.05 with sensitivity 0.87+0.07, specificity 0.77+0.12, and AUC 0.91+0.03. Patient-level response prediction from dCT, using the "Majority 60%" rule, had accuracy 0.81, sensitivity 0.75, and specificity 0.88 using 12-month post-treatment patient response as the reference standard and outperformed response prediction based on IPI risk factors (accuracy 0.54, sensitivity 0.38, and specificity 0.61 (p = 0.046)). Prediction of treatment outcome in B-cell lymphomas from pre-treatment medical images using DL-based image analysis and rule-based reasoning is feasible. This approach can potentially provide clinically useful prognostic information for decision-making in advance of initiating CAR T-cell therapy.

CT image crack segmentation method based on linear feature enhancement.

Industrial computed tomography (CT) crack segmentation is a key technology in industrial CT image processing. Unfortunately, the interference of artifact and noise in CT image often bring great trouble to the crack segmentation. In order to improve the segmentation accuracy of cracks in CT images, we propose to develop and test a new crack segmentation algorithm based on linear feature enhancement by analyzing the features of cracks in CT images. Firstly, the total variational model is used to denoise the input image. Next, a Frangi multiscale filter is used to extract linear structures in the image, and then the extracted linear structures are used to enhance the contrast of the image. Finally, the cracks in the image are detected and segmented by Otsu algorithm. By comparing with the manual segmentation results, the average intersection-over-union (IOU) reaches 86.10% and the average F1 score reaches 92.44%, which verifies the effectiveness and correctness of the algorithm developed in this study. Overall, experiments demonstrate that the new algorithm improves the accuracy of crack segmentation and it is effective applying to industry CT images.

Research on 3D crack segmentation of CT images of oil rock core.

In this paper, we propose a framework for CT image segmentation of oil rock core. According to the characteristics of CT image of oil rock core, the existing level set segmentation algorithm is improved. Firstly, an algorithm of Chan-Vese (C-V) model is carried out to segment rock core from image background. Secondly the gray level of image background region is replaced by the average gray level of rock core, so that image background does not affect the binary segmentation. Next, median filtering processing is carried out. Finally, an algorithm of local binary fitting (LBF) model is executed to obtain the crack region. The proposed algorithm has been applied to oil rock core CT images with promising results.

Fully automated registration of 3D CT data to CAD model for surface deviation measurement.

The aim of this study is to present a fully automated registration algorithm that allows for alignment and errors analysis of the 3D surface model obtained from industrial computed tomography (CT) images with the computer-aided design (CAD) model. First, two pre-processing steps are executed by the algorithm namely, CAD model subdivision and representing models. Next, two improved registration procedures are applied including covariance descriptors-based coarse registration with a novel and automatic calibration, followed by a fine registration technique that utilizes an improved iterative closest points (ICP) algorithm, which is what we proposed with a novel estimation method for registration error. Finally, using a novel strategy that we proposed for error display, the quantitative data analysis results can simultaneously estimate both positive and negative deviation of the surface registration errors more precisely and fully expressed. Comparing to the original ICP algorithm, the quantitative data of experimental results demonstrate that the average registration errors of carburetors and valves are reduced by 0.80 millimeter at least. Therefore, this study demonstrates that the proposed new algorithm is not only capable of fully automating the registration of 3D surface model to a CAD model but also beneficial for quantitatively determining the surface manufacturing error more precisely.

3D defect segmentation on CT volume data using morphology and resample techniques.

Segmentation of CT volume data is important and useful in non-destructive testing and evaluating. To eliminate the artifacts influence, we propose a new approach of 3D defect segmentation using two steps. First of all, an initial segmentation using 3D morphological method is performed. The initial segmentation results include false defects. Secondly, resample in polar coordinates method is performed. The experimental results prove that our method is effective to correctly segment 3D defects and eliminate false segmentation. Some experiments on CT volume data with noise are made, the results show that our method is also useful.