Exploit 18F-FDG enhanced urinary bladder in PET data for deep learning ground truth generation in CT scans

There have been few anatomical structure segmentation studies using deep learning. Numbers of training and ground truth images applied were small and the accuracies of which were low or inconsistent. For a surgical video anatomy analysis, various obstacles, including a variable fast-changing view, large deformations, occlusions, low illumination, and inadequate focus occur. In addition, it is difficult and costly to obtain a large and accurate dataset on operational video anatomical structures, including arteries. In this study, we investigated cerebral artery segmentation using an automatic ground-truth generation method. Indocyanine green (ICG) fluorescence intraoperative cerebral videoangiography was used to create a ground-truth dataset mainly for cerebral arteries and partly for cerebral blood vessels, including veins. Four different neural network models were trained using the dataset and compared. Before augmentation, 35,975 training images and 11,266 validation images were used. After augmentation, 260,499 training and 90,129 validation images were used. A Dice score of 79% for cerebral artery segmentation was achieved using the DeepLabv3+ model trained using an automatically generated dataset. Strict validation in different patient groups was conducted. Arteries were also discerned from the veins using the ICG videoangiography phase. We achieved fair accuracy, which demonstrated the appropriateness of the methodology. This study proved the feasibility of operating field view of the cerebral artery segmentation using deep learning, and the effectiveness of the automatic blood vessel ground truth generation method using ICG fluorescence videoangiography. Using this method, computer vision can discern blood vessels and arteries from veins in a neurosurgical microscope field of view. Thus, this technique is essential for neurosurgical field vessel anatomy-based navigation. In addition, surgical assistance, safety, and autonomous surgery neurorobotics that can detect or manipulate cerebral vessels would require computer vision to identify blood vessels and arteries.

Download Full-text

Franken-CT: Head and Neck MR-Based Pseudo-CT Synthesis Using Diverse Anatomical Overlapping MR-CT Scans

Applied Sciences ◽

10.3390/app11083508 ◽

2021 ◽

Vol 11 (8) ◽

pp. 3508

Author(s):

Pedro Miguel Martinez-Girones ◽

Javier Vera-Olmos ◽

Mario Gil-Correa ◽

Ana Ramos ◽

Lina Garcia-Cañamaque ◽

...

Keyword(s):

Deep Learning ◽

Confidence Interval ◽

Head And Neck ◽

Similarity Index ◽

Ground Truth ◽

Structural Similarity ◽

Absolute Error ◽

Ct Scans ◽

Learning Methods ◽

Index Measure

Typically, pseudo-Computerized Tomography (CT) synthesis schemes proposed in the literature rely on complete atlases acquired with the same field of view (FOV) as the input volume. However, clinical CTs are usually acquired in a reduced FOV to decrease patient ionization. In this work, we present the Franken-CT approach, showing how the use of a non-parametric atlas composed of diverse anatomical overlapping Magnetic Resonance (MR)-CT scans and deep learning methods based on the U-net architecture enable synthesizing extended head and neck pseudo-CTs. Visual inspection of the results shows the high quality of the pseudo-CT and the robustness of the method, which is able to capture the details of the bone contours despite synthesizing the resulting image from knowledge obtained from images acquired with a completely different FOV. The experimental Zero-Normalized Cross-Correlation (ZNCC) reports 0.9367 ± 0.0138 (mean ± SD) and 95% confidence interval (0.9221, 0.9512); the experimental Mean Absolute Error (MAE) reports 73.9149 ± 9.2101 HU and 95% confidence interval (66.3383, 81.4915); the Structural Similarity Index Measure (SSIM) reports 0.9943 ± 0.0009 and 95% confidence interval (0.9935, 0.9951); and the experimental Dice coefficient for bone tissue reports 0.7051 ± 0.1126 and 95% confidence interval (0.6125, 0.7977). The voxel-by-voxel correlation plot shows an excellent correlation between pseudo-CT and ground-truth CT Hounsfield Units (m = 0.87; adjusted R2 = 0.91; p < 0.001). The Bland–Altman plot shows that the average of the differences is low (−38.6471 ± 199.6100; 95% CI (−429.8827, 352.5884)). This work serves as a proof of concept to demonstrate the great potential of deep learning methods for pseudo-CT synthesis and their great potential using real clinical datasets.

Download Full-text

Automated Ground Truth Generation for Learning-Based Crack Detection on Concrete Surfaces

Applied Sciences ◽

10.3390/app112210966 ◽

2021 ◽

Vol 11 (22) ◽

pp. 10966

Author(s):

Hsiang-Chieh Chen ◽

Zheng-Ting Li

Keyword(s):

Deep Learning ◽

Crack Detection ◽

Ground Truth ◽

Experimental Results ◽

Training Data ◽

Generation Process ◽

Detection Model ◽

Ground Truth Generation ◽

Labeling Approach ◽

The Cost

This article introduces an automated data-labeling approach for generating crack ground truths (GTs) within concrete images. The main algorithm includes generating first-round GTs, pre-training a deep learning-based model, and generating second-round GTs. On the basis of the generated second-round GTs of the training data, a learning-based crack detection model can be trained in a self-supervised manner. The pre-trained deep learning-based model is effective for crack detection after it is re-trained using the second-round GTs. The main contribution of this study is the proposal of an automated GT generation process for training a crack detection model at the pixel level. Experimental results show that the second-round GTs are similar to manually marked labels. Accordingly, the cost of implementing learning-based methods is reduced significantly because data labeling by humans is not necessitated.

Download Full-text

GROUND TRUTH GENERATION AND DISPARITY ESTIMATION FOR OPTICAL SATELLITE IMAGERY

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b2-2020-127-2020 ◽

2020 ◽

Vol XLIII-B2-2020 ◽

pp. 127-134

Author(s):

M. Cournet ◽

E. Sarrazin ◽

L. Dumas ◽

J. Michel ◽

J. Guinet ◽

...

Keyword(s):

Deep Learning ◽

Satellite Imagery ◽

Learning Difficulties ◽

Ground Truth ◽

Disparity Estimation ◽

Learning Network ◽

Ground Truth Generation ◽

Global Matching ◽

Disparity Maps ◽

Deep Learning Network

Abstract. Several 3D reconstruction pipelines are being developed around the world for satellite imagery. Most of them implement their own versions of Semi-Global Matching, as an option for the matching step. However, deep learning based solutions already outperform every SGM derived algorithms on Kitti and Middlebury stereo datasets. But these deep learning based solutions need huge quantities of ground truths for training. This implies that the generation of ground truth stereo datasets, from satellite imagery and lidar, seems to be of great interest for the scientific community. It will aim at reducing the potential transfer learning difficulties, that could arise from a training done on datasets such as Middlebury or Kitti. In this work, we present a new ground truth generation pipeline. It produces stereo-rectified images and ground truth disparity maps, from satellite imagery and lidar. We also assess the rectification and the disparity accuracies of these outputs. We finally train a deep learning network on our preliminary ground truth dataset.

Download Full-text

PO-1718: Deep learning based auto-contouring of planning CT scans for rectal cancer

Radiotherapy and Oncology ◽

10.1016/s0167-8140(21)01736-9 ◽

2020 ◽

Vol 152 ◽

pp. S949

Author(s):

L. Bokhorst ◽

M.H.F. Savenije ◽

M.P.W. Intven ◽

C.A.T. Van den Berg

Keyword(s):

Rectal Cancer ◽

Deep Learning ◽

Ct Scans ◽

Planning Ct

Download Full-text

Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

Scientific Reports ◽

10.1038/s41598-021-88236-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Christian Crouzet ◽

Gwangjin Jeong ◽

Rachel H. Chae ◽

Krystal T. LoPresti ◽

Cody E. Dunn ◽

...

Keyword(s):

Deep Learning ◽

Prussian Blue ◽

Processing Speed ◽

Digital Pathology ◽

Ground Truth ◽

Individual Variability ◽

Rgb Images ◽

Cerebral Microhemorrhages ◽

Phasor Analysis ◽

Better Than

AbstractCerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

Download Full-text