Manual or automatic delineation of the esophageal tumor in CT images is known to be very challenging. This is due to the low contrast between the tumor and adjacent tissues, the anatomical variation of the esophagus, as well as the occasional presence of foreign bodies (e.g. feeding tubes). Physicians therefore usually exploit additional knowledge such as endoscopic findings, clinical history, additional imaging modalities like PET scans. Achieving his additional information is time-consuming, while the results are error-prone and might lead to non-deterministic results. In this paper we aim to investigate if and to what extent a simplified clinical workflow based on CT alone, allows one to automatically segment the esophageal tumor with sufficient quality. For this purpose, we present a fully automatic end-to-end esophageal tumor segmentation method based on convolutional neural networks (CNNs). The proposed network, called Dilated Dense Attention Unet (DDAUnet), leverages spatial and channel attention gates in each dense block to selectively concentrate on determinant feature maps and regions. Dilated convolutional layers are used to manage GPU memory and increase the network receptive field. We collected a dataset of 792 scans from 288 distinct patients including varying anatomies with \mbox{air pockets}, feeding tubes and proximal tumors. Repeatability and reproducibility studies were conducted for three distinct splits of training and validation sets. The proposed network achieved a $\mathrm{DSC}$ value of $0.79 \pm 0.20$, a mean surface distance of $5.4 \pm 20.2mm$ and $95\%$ Hausdorff distance of $14.7 \pm 25.0mm$ for 287 test scans, demonstrating promising results with a simplified clinical workflow based on CT alone. Our code is publicly available via \url{this https URL}.
Manual or automatic delineation of the esophageal tumor in CT images is known to be very challenging. This is due to the low contrast between the tumor and adjacent tissues, the anatomical variation of the esophagus, as well as the occasional presence of foreign bodies (e.g. feeding tubes). Physicians therefore usually exploit additional knowledge such as endoscopic findings, clinical history, additional imaging modalities like PET scans. Achieving his additional information is time-consuming, while the results are error-prone and might lead to non-deterministic results. In this paper we aim to investigate if and to what extent a simplified clinical workflow based on CT alone, allows one to automatically segment the esophageal tumor with sufficient quality. For this purpose, we present a fully automatic end-to-end esophageal tumor segmentation method based on convolutional neural networks (CNNs). The proposed network, called Dilated Dense Attention Unet (DDAUnet), leverages spatial and channel attention gates in each dense block to selectively concentrate on determinant feature maps and regions. Dilated convolutional layers are used to manage GPU memory and increase the network receptive field. We collected a dataset of 792 scans from 288 distinct patients including varying anatomies with air pockets, feeding tubes and proximal tumors. Repeatability and reproducibility studies were conducted for three distinct splits of training and validation sets. The proposed network achieved a DSC value of 0.79 ± 0.20, a mean surface distance of 5.4 ± 20.2mm and 95% Hausdorff distance of 14.7 ± 25.0mm for 287 test scans, demonstrating promising results with a simplified clinical workflow based on CT alone. Our code is publicly available via https://github.com/yousefis/DenseUnet_Esophagus_Segmentation .
Positron Emission Tomography (PET) is an imaging method that can assess physiological function rather than structural disturbances by measuring cerebral perfusion or glucose consumption. However, this imaging technique relies on injection of radioactive tracers and is expensive. On the contrary, Arterial Spin Labeling (ASL) MRI is a non-invasive, non-radioactive, and relatively cheap imaging technique for brain hemodynamic measurements, which allows quantification to some extent. In this paper we propose a convolutional neural network (CNN) based model for translating ASL to PET images, which could benefit patients as well as the healthcare system in terms of expenses and adverse side effects. However, acquiring a sufficient number of paired ASL-PET scans for training a CNN is prohibitive for many reasons. To tackle this problem, we present a new semi-supervised multitask CNN which is trained on both paired data, i.e. ASL and PET scans, and unpaired data, i.e. only ASL scans, which alleviates the problem of training a network on limited paired data. Moreover, we present a new residual-based-attention guided mechanism to improve the contextual features during the training process. Also, we show that incorporating T1-weighted scans as an input, due to its high resolution and availability of anatomical information, improves the results. We performed a two-stage evaluation based on quantitative image metrics by conducting a 7-fold cross validation followed by a double-blind observer study. The proposed network achieved structural similarity index measure (SSIM), mean squared error (MSE) and peak signal-to-noise ratio (PSNR) values of $0.85\pm0.08$, $0.01\pm0.01$, and $21.8\pm4.5$ respectively, for translating from 2D ASL and T1-weighted images to PET data. The proposed model is publicly available via https://github.com/yousefis/ASL2PET.
Abstract We present a combination of a CNN-based encoder with an analytical forward map for solving inverse problems. We call it an encoder-analytic (EA) hybrid model. It does not require a dedicated training dataset and can train itself from the connected forward map in a direct learning fashion. A separate regularization term is not required either, since the forward map also acts as a regularizer. As it is not a generalization model it does not suffer from overfitting. We further show that the model can be customized to either find a specific target solution or one that follows a given heuristic. As an example, we apply this approach to the design of a multi-element surface magnet for low-field magnetic resonance imaging (MRI). We further show that the EA model can outperform the benchmark genetic algorithm model currently used for magnet design in MRI, obtaining almost 10 times better results.
This paper proposes a robust approach for face detection and gender classification in color images.Previous researches about gender recognition suppose an expensive computational and time-consuming pre-processing step in order to alignment in which face images are aligned so that facial landmarks like eyes, nose, lips, chin are placed in uniform locations in image.In this paper, a novel technique based on mathematical analysis is represented in three stages that eliminates alignment step.First, a new color based face detection method is represented with a better result and more robustness in complex backgrounds.Next, the features which are invariant to affine transformations are extracted from each face using scale invariant feature transform (SIFT) method.To evaluate the performance of the proposed algorithm, experiments have been conducted by employing a SVM classifier on a database of face images which contains 500 images from distinct people with equal ratio of male and female.
2 Abstract: In this paper we propose a novel hybrid multispectral MR images segmentation framework which combines Markov Random Field (MRF), stochastic relaxation (SR) scheme and an improved Genetic Algorithm (IGA). MRF models have by now been firmly established as a robust tool for de-noising and segmentation of medical images. Characterizing MRFs by their local properties (Markovianity), they are well suited to depict the spatial contextual constrains between voxels. Markovianity allows to achieve the global objective by concentrating on labeling of each site consider to its local neighbors. To determine these characteristics practically, Hammersley-Clifford theorem reduces the problem to the minimization of a non convex energy function. In order to optimize the solution, stochastic relaxation (SR) method has been employed widely. SR is very powerful for searching local regions of the solution space exhaustively via stochastic hill climbing and prevents from exploring the same diversity of solutions additionally has the solution refining capability, but imposes heavy overhead on the algorithm. In comparison, genetic algorithm (GA) has a good capability of global researching and converges quickly to a near-global optimum but is weak in hill climbing. By combining SR and GA for optimization, this paper puts forward a new 3D-MRF model for de-noising and segmentation of brain multispectral MR images. This conjunction allows us to keep the benefits of both SR and GA algorithms while simultaneously addressing their individual drawbacks. Ultimately, the performance of the novel method is investigated on the BrainWeb dataset. Experimental results demonstrate that the proposed method outperforms the traditional 2D-MRF in convergence speed and quality of the solution noticeably which is valuable in processing environment.
This paper proposes a novel combinational approach for statistical de-noising and segmentation of 3D magnetic resonance images (MRIs) of the brain. The proposed method is based on Markov Random Field (MRF), conjunction with simulated annealing (SA) and improved genetic algorithm (IGA). MRF methods have been widely studied for segmentation. Despite the Markovianity which depicts the local characteristic, which allows a global optimization problem to be solved locally, MRF still has a heavy computation burden, especially when it is used with stochastic relaxation schemes such as SA. Although, search procedure of SA is fairly localized and prevents from exploring the same diversity of solutions, it suffers from several limitations. In comparison, GA has a good capability of global researching but it is weak in hill climbing. Therefore, the combination of these two methods may have the advantages of both procedures while alleviating their individual shortcomings and high computation complexity. Evaluation of proposed approach shows that our algorithm outperforms the traditional MRF in both convergence speed and solution quality.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
