Affinity Graph Based End-to-End Deep Convolutional Networks for CT Hemorrhage Segmentation

National DRLs for adult body CT scans based on body width

Intracranial hemorrhage (ICH) is a type of stroke with a high mortality rate and failing to localize even minor ICH can put a patient's life at risk. However, its patterns are diverse in shapes and sizes and, sometimes, even hard to recognize its existence. Therefore, it is challenging to accurately detect and localize diverse ICH patterns. In this article, we propose a novel Perihematomal Edema Guided Scale Adaptive R-CNN (PESA R-CNN) for accurate segmentation of various size hemorrhages with the goal of minimizing missed hemorrhage regions. In our approach, we design a Center Surround Difference U-Net (CSD U-Net) to incorporate Perihematomal Edema (PHE) for more accurate Region of Interest (RoI) generation. We trained CSD U-Net to predict PHE and hemorrhage regions as targets in a weakly supervised manner and utilized its prediction results to generate RoI. By including more informative features of PHE around hemorrhage, this enhanced RoI generation allows a model to reduce the false-negative rate. Furthermore, these expanded RoIs are aligned with the Scale Adaptive RoI Align (SARA) module based on their size to prevent the loss of fine-scale information and small hemorrhage patterns. Each scale adaptively aligned RoI is processed with the corresponding separate segmentation network of Multi-Scale Segmentation Network (MSSN), which integrates the results from each scale's segmentation network. In experiments, our model shows significant improvement on dice coefficient (0.697) and Hausdorff distance (12.918), compared to all other segmentation models. It also minimizes the number of missing small hemorrhage regions and enhances overall segmentation performance on diverse ICH patterns.

Lung cancer is the deadliest type of cancer and is one of the most frequently occurring cancers. It is primarily diagnosed in later stages when treatment becomes difficult. For better treatment and higher chances of survival, the treatment response of lung cancer patients needs to be analyzed to check whether the patients are responding to the treatment or not. This analysis can be done with the help of follow‐up computed tomography (CT) imaging before and after the treatment. However, manually analyzing the baseline and post‐treatment CT scan images of so many lung cancer patients is a tedious task. This study proposes an intuitive approach based on deep learning to analyze lung cancer through CT scan images before and after the treatment. In this approach, we utilized a segmentation network to segment the lung tumor in the follow‐up CT images. The segmented tumor is then analyzed to check the treatment effect, as suggested by the Response Evaluation Criteria in Solid Tumors (RECIST) guidelines. The segmentation network combines a vision transformer and a convolutional neural network. The segmentation network is first trained on a public dataset and then fine‐tuned on the local dataset to improve the segmentation performance. For this study, we have collected a lung cancer dataset from an Indian hospital. The dataset is divided into two parts dataset I and dataset II. Dataset I consists of 100 CT scans, which we use to fine‐tune the proposed segmentation network. Dataset II comprises 220 CT scans of 110 patients, consisting of baseline and post‐treatment scans. We use dataset II for testing. We achieved significant performance.

Segmentation ability map: Interpret deep features for medical image segmentation.

Prevalence of Aortic Intimal Defect in Surgically Treated Acute Type A Intramural Hematoma

ObjectiveTo compare the effect of arm positioning on radiation dose, scan length, and image noise in computed tomography (CT) scans of the medial clavicular epiphysis for forensic age estimation performed with the arms alongside the body (arms-down) versus elevated above the head (arms-up).MethodsTwenty consecutive CT scans were analysed, ten performed with arms-down and ten with arms-up. The scans were conducted at 120 kVp and 37 mAs reference tube current. Scan length extended from 10 mm above to 10 mm below the medial clavicular epiphysis. Dose-relevant parameters (effective CT tube current, volume CT dose index (CTDIvol), CT dose length product (DLP), and effective dose) as well as scan length and image noise were compared between arms-up and arms-down CT scans.ResultsPopulation characteristics: 19 males, 1 female; mean weight 65.8 ± 9.2 kg; height 174.6 ± 7.8 cm; and body mass index (BMI) 21.6 ± 2.5 kg/m². Dose-relevant parameters were significantly lower with arms-up compared to arms-down (effective tube current: 80.9 ± 21.7 mAs vs. 146.0 ± 47.5 mAs, p = 0.001; CTDIvol: 5.5 ± 1.5 mGy vs. 9.9 ± 3.2 mGy, p = 0.001; DLP: 40.2 ± 13.7 mGy*cm vs. 63.8 ± 21.9 mGy*cm, p = 0.010; effective dose: 0.6 ± 0.2 mSv vs. 0.9 ± 0.3 mSv, p = 0.010). No significant differences were found in scan length, image noise, or population characteristics.ConclusionsRemoving the arms from the CT beam path reduced radiation dose by 33% without affecting scan length or image noise. Given the importance of dose optimisation in non-medical examinations of potentially minor individuals, CT scans of the medial clavicular epiphysis should be performed with arms elevated above the head.

The liver is an important organ in human body with certain variations in its edges, color, shape and pixel intensity distribution. These uncertainties may be because of various liver pathologies, hereditary or both. Along with it, liver has close proximity to its nearby organs. Hence, identifying liver in scanned images is a challenging step in image processing. This task becomes more imprecise when liver diseases are present at the edges. The liver segmentation is prerequisite for liver volumetry, computer-based surgery planning, liver surgery modelling, surgery training, 3D view generation, etc. The proposed hybrid segmentation method overcomes the problems and identifies liver boundary in Computed-Tomography (CT) scan images accurately. In this paper, the first step is to study statistics of pixel intensity distribution within liver image, and novel methodology is designed to obtain thresholds. Then, threshold-based segmentation is applied which separates the liver from abdominal CT scan images. In the second step, liver edge is corrected using improved chain code and Bresenham pixel interconnection methods. This provides a precise liver image. The initial points are located inside the liver region without user interventions. These initial points evolve outwardly using Fast Marching Method (FMM), identifying the liver boundary accurately in CT abdominal scan images.

Intensity population based unsupervised hemorrhage segmentation from brain CT images

In computed tomography (CT) cardiovascular imaging, the numerous contrast injection protocols used to enhance structures make it difficult to gather training datasets for deep learning applications supporting diverse protocols. Moreover, creating annotations on noncontrast scans is extremely tedious. Recently, spectral CT's virtual-noncontrast images (VNC) have been used as data augmentation to train segmentation networks performing on enhanced and true-noncontrast (TNC) scans alike, while improving results on protocols absent of their training dataset. However, spectral data are not widely available, making it difficult to gather specific datasets for each task. As a solution, we present a data augmentation workflow based on a trained image translation network, to bring spectral-like augmentation to any conventional CT dataset. The conventional CT-to-spectral image translation network (HUSpectNet) was first trained to generate VNC from conventional housnfied units images (HU), using an unannotated spectral dataset of 1830 patients. It was then tested on a second dataset of 300 spectral CT scans by comparing VNC generated through deep learning (VNCDL ) to their true counterparts. To illustrate and compare our workflow's efficiency with true spectral augmentation, HUSpectNet was applied to a third dataset of 112 spectral scans to generate VNCDL along HU and VNC images. Three different three-dimensional (3D) networks (U-Net, X-Net, and U-Net++) were trained for multilabel heart segmentation, following four augmentation strategies. As baselines, trainings were performed on contrasted images without (HUonly) and with conventional gray-values augmentation (HUaug). Then, the same networks were trained using a proportion of contrasted and VNC/VNCDL images (TrueSpec/GenSpec). Each training strategy applied to each architecture was evaluated using Dice coefficients on a fourth multicentric multivendor single-energy CT dataset of 121 patients, including different contrast injection protocols and unenhanced scans. The U-Net++ results were further explored with distance metrics on every label. Tested on 300 full scans, our HUSpectNet translation network shows a mean absolute error of 6.70±2.83 HU between VNCDL and VNC, while peak signal-to-noise ratio reaches 43.89dB. GenSpec and TrueSpec show very close results regardless of the protocol and used architecture: mean Dice coefficients (DSCmean ) are equal with a margin of 0.006, ranging from 0.879 to 0.938. Their performances significantly increase on TNC scans (p-values<0.017 for all architectures) compared to HUonly and HUaug, with DSCmean of 0.448/0.770/0.879/0.885 for HUonly/HUaug/TrueSpec/GenSpec using the U-Net++ architecture. Significant improvements are also noted for all architectures on chest-abdominal-pelvic scans (p-values<0.007) compared to HUonly and for pulmonary embolism scans (p-values<0.039) compared to HUaug. Using U-Net++, DSCmean reaches 0.892/0.901/0.903 for HUonly/TrueSpec/GenSpec on pulmonary embolism scans and 0.872/0.896/0.896 for HUonly/TrueSpec/GenSpec on chest-abdominal-pelvic scans. Using the proposed workflow, we trained versatile heart segmentation networks on a dataset of conventional enhanced CT scans, providing robust predictions on both enhanced scans with different contrast injection protocols and TNC scans. The performances obtained were not significantly inferior to training the model on a genuine spectral CT dataset, regardless of the architecture implemented. Using a general-purpose conventional-to-spectral CT translation network as data augmentation could therefore contribute to reducing data collection and annotation requirements for machine learning-based CT studies, while extending their range of application.

Segmentation of intracerebral hemorrhage (ICH) helps improve the quality of diagnosis, draft the desired treatment methods, and clinically observe the variations with healthy patients. The clinical utilization of various ICH progression scoring systems has limitations due to the systems' modest predictive value. This paper proposes a single pipeline of a multi-task model for end-to-end hemorrhage segmentation and risk estimation. We introduce a 3D spatial attention unit and integrate it into the state-of-the-art segmentation architecture, UNet, to enhance the accuracy by bootstrapping the global spatial representation. We further extract the geometric features from the segmented hemorrhage volume and fuse them with clinical features such as CT angiography (CTA) spot, Glasgow Coma Scale (GCS), and age to predict the ICH stability. Several state-of-the-art machine learning techniques such as multilayer perceptron (MLP), support vector machine (SVM), gradient boosting, and random forests are applied to train stability estimation and to compare the performances. To align clinical intuition with model learning, we determine the shapely values (SHAP) and explain the most significant features for the ICH risk scoring system. A total of 79 patients are included, of which 20 are found in critical condition. Our proposed single pipeline model achieves a segmentation accuracy of 86.3%, stability prediction accuracy of 78.3%, and precision of 82.9%; the mean square error of exact expansion rate regression is observed to be 0.46. The SHAP analysis reveals that CTA spot sign, age, solidity, location, and length of the first axis of the ICH volume are the most critical characteristics that help define the stability of the stroke lesion. We also show that integrating significant geometric features with clinical features can improve the ICH progression scoring by predicting long-term outcomes. Graphical abstract Overview of our proposed method comprising of spatial attention and feature extraction mechanisms. The architecture is trained on the input CT images, and the first step output is the predicted segmentation of the hemorrhagic region. The output is fed into a geometric feature extractor and is fused with clinical features to estimate ICH stability using a multilayer perceptron (MLP).

The new coronavirus, which has become a global pandemic, has confirmed more than 88 million cases worldwide since the first case was recorded in December 2019, causing over 1.9 million deaths. Since COIVD-19 lesions have clear imaging features on CT images, it is suitable for the auxiliary diagnosis and treatment of COVID-19. Deep learning can be used to segment the lesions areas of COVID-19 in CT images to help monitor the epidemic situation. In this paper, we propose a multi-point supervision network (MPS-Net) for segmentation of COVID-19 lung infection CT image lesions to solve the problem of a variety of lesion shapes and areas. A multi-scale feature extraction structure, a sieve connection structure (SC), a multi-scale input structure and a multi-point supervised training structure were implemented into MPS-Net. In order to increase the ability to segment various lesion areas of different sizes, the multi-scale feature extraction structure and the sieve connection structure will use different sizes of receptive fields to extract feature maps of various scales. The multi-scale input structure is used to minimize the edge loss caused by the convolution process. In order to improve the accuracy of segmentation, we propose a multi-point supervision training structure to extract supervision signals from different up-sampling points on the network. Experimental results showed that the dice similarity coefficient (DSC), sensitivity, specificity and IOU of the segmentation results of our model are 0.8325, 0.8406, 09988 and 0.742, respectively. The experimental results demonstrated that the network proposed in this paper can effectively segment COVID-19 infection on CT images. It can be used to assist the diagnosis and treatment of new coronary pneumonia.

This paper presents a novel combined energy functional based on edge and region information for active contour model, which can be applied to segment textured images containing low contrast and high illumination variations. In the proposed method, the edge features are calculated based on the phase-based approaches derived from the monogenic signal, which are robust to illumination variations in the image. These feature values are used in an edge energy functional to assist the active contour evolving towards the true object boundaries. To extract the region features, at first, we compute the normalized accumulated short-term autocorrelation (NASTA) values for the image, which suppress background clutter and enhance dissimilarities between objects and background. Next, a local cumulative distribution function (LCDF) of NASTA is calculated for every pixel in a local window around it and is used as a region feature for that pixel. Then, the obtained features are employed to define a new localized region-based energy functional that can correctly segment regions with same intensity mean and variance. The proposed edge and region energy terms are integrated and a regularization term is added to them to form our combined active contour. Experimental results indicate remarkable advantages of proposed method comparing to existing combination models.

Purpose:The detection and treatment of abdominal aortic aneurysm (AAA), a vascular disorder with life-threatening consequences, is challenging due to its lack of symptoms until it reaches a critical size. Abdominal ultrasound (US) is utilized for diagnosis; however, its inherent low image quality and reliance on operator expertise make computed tomography (CT) the preferred choice for monitoring and treatment. Moreover, CT datasets have been effectively used for training deep neural networks for aorta segmentation. In this work, we demonstrate how leveraging CT labels can be used to improve segmentation in ultrasound and hence save manual annotations.Methods:We introduce CACTUSS: a common anatomical CT-US space that inherits properties from both CT and ultrasound modalities to produce an image in intermediate representation (IR) space. CACTUSS acts as a virtual third modality between CT and US to address the scarcity of annotated ultrasound training data. The generation of IR images is facilitated by re-parametrizing a physics-based US simulator. In CACTUSS we use IR images as training data for ultrasound segmentation, eliminating the need for manual labeling. In addition, an image-to-image translation network is employed for the model’s application on real B-modes.Results:The model’s performance is evaluated quantitatively for the task of aorta segmentation by comparison against a fully supervised method in terms of Dice Score and diagnostic metrics. CACTUSS outperforms the fully supervised network in segmentation and meets clinical requirements for AAA screening and diagnosis.Conclusion:CACTUSS provides a promising approach to improve US segmentation accuracy by leveraging CT labels, reducing the need for manual annotations. We generate IRs that inherit properties from both modalities while preserving the anatomical structure and are optimized for the task of aorta segmentation. Future work involves integrating CACTUSS into robotic ultrasound platforms for automated screening and conducting clinical feasibility studies.

Detection of Covid-19 and other pneumonia cases from CT and X-ray chest images using deep learning based on feature reuse residual block and depthwise dilated convolutions neural network

Adaptive four-dimensional (4D) spiral computed tomography (CT) scans facilitate the acquisition of volume perfusion data for organs or long-range vessels; however, optimizing image quality and reducing noise while minimizing radiation doses remains challenging. Thus, image-processing techniques such as temporal maximum intensity projection (MIP) and average intensity projection (AIP) are crucial in this context. This ex vivo study aimed to compare the image noise, spatial resolution, and measurements of temporal MIP and AIP images generated from low radiation dose 4D CT scans data with those of conventional CT images using phantoms. Three phantoms were scanned with equivalent radiation doses using single helical and adaptive 10-phase 4D spiral scans using a third-generation dual-source CT scanner. Temporal MIP and AIP images of 4D CT scans were generated by summing varying numbers of phases, incorporating automatic motion correction with non-rigid registration and noise reduction algorithm. The CT values and image noise of the temporal MIP and AIP images were compared to conventional CT images. The task transfer function (TTF) was calculated using static phantoms. Vessel diameters of the phantoms for each image dataset were evaluated using motion phantoms. Temporal AIP images showed comparable CT values with those of the reference image. In contrast, the CT values of the temporal MIP images were significantly higher than those of the reference images (p<0.01). The image noise of temporal AIP images with six or more phases was equal to or lower than that of the reference images. In contrast, temporal MIP images exhibited consistently high noise levels regardless of the number of summed phases. The TTF of temporal AIP images was comparable to that of the reference CT images. However, the TTF of temporal MIP images gradually decreased as the number of summed phases increased. No significant differences were observed in vessel diameter measurements among the three groups or with varying numbers of summed phases (p>0.05). In conclusion, temporal MIP and AIP images generated from low radiation dose 4D CT scans could effectively reduce noise while preserving measurement reliability in the motion phantom, achieving performance comparable to conventional CT images.