Detection Of Anatomical Structures Research Articles

Artificial Intelligence in the Management of Women with Endometriosis and Adenomyosis: Can Machines Ever Be Worse Than Humans?

Artificial intelligence (AI) is experiencing advances and integration in all medical specializations, and this creates excitement but also concerns. This narrative review aims to critically assess the state of the art of AI in the field of endometriosis and adenomyosis. By enabling automation, AI may speed up some routine tasks, decreasing gynecologists' risk of burnout, as well as enabling them to spend more time interacting with their patients, increasing their efficiency and patients' perception of being taken care of. Surgery may also benefit from AI, especially through its integration with robotic surgery systems. This may improve the detection of anatomical structures and enhance surgical outcomes by combining intra-operative findings with pre-operative imaging. Not only that, but AI promises to improve the quality of care by facilitating clinical research. Through the introduction of decision-support tools, it can enhance diagnostic assessment; it can also predict treatment effectiveness and side effects, as well as reproductive prognosis and cancer risk. However, concerns exist regarding the fact that good quality data used in tool development and compliance with data sharing guidelines are crucial. Also, professionals are worried AI may render certain specialists obsolete. This said, AI is more likely to become a well-liked team member rather than a usurper.

HFSCCD: A Hybrid Neural Network for Fetal Standard Cardiac Cycle Detection in Ultrasound Videos.

In the fetal cardiac ultrasound examination, standard cardiac cycle (SCC) recognition is the essential foundation for diagnosing congenital heart disease. Previous studies have mostly focused on the detection of adult CCs, which may not be applicable to the fetus. In clinical practice, localization of SCCs needs to recognize end-systole (ES) and end-diastole (ED) frames accurately, ensuring that every frame in the cycle is a standard view. Most existing methods are not based on the detection of key anatomical structures, which may not recognize irrelevant views and background frames, results containing non-standard frames, or even it does not work in clinical practice. We propose an end-to-end hybrid neural network based on an object detector to detect SCCs from fetal ultrasound videos efficiently, which consists of 3 modules, namely Anatomical Structure Detection (ASD), Cardiac Cycle Localization (CCL), and Standard Plane Recognition (SPR). Specifically, ASD uses an object detector to identify 9 key anatomical structures, 3 cardiac motion phases, and the corresponding confidence scores from fetal ultrasound videos. On this basis, we propose a joint probability method in the CCL to learn the cardiac motion cycle based on the 3 cardiac motion phases. In SPR, to reduce the impact of structure detection errors on the accuracy of the standard plane recognition, we use XGBoost algorithm to learn the relation knowledge of the detected anatomical structures. We evaluate our method on the test fetal ultrasound video datasets and clinical examination cases and achieve remarkable results. This study may pave the way for clinical practices.

Robust tracking of deformable anatomical structures with severe occlusions using deformable geometrical primitives

Background and objective:Surgical robotics tends to develop cognitive control architectures to provide certain degree of autonomy to improve patient safety and surgery outcomes, while decreasing the required surgeons’ cognitive load dedicated to low level decisions. Cognition needs workspace perception, which is an essential step towards automatic decision-making and task planning capabilities. Robust and accurate detection and tracking in minimally invasive surgery suffers from limited visibility, occlusions, anatomy deformations and camera movements. Method:This paper develops a robust methodology to detect and track anatomical structures in real time to be used in automatic control of robotic systems and augmented reality. The work focuses on the experimental validation in highly challenging surgery: fetoscopic repair of Open Spina Bifida. The proposed method is based on two sequential steps: first, selection of relevant points (contour) using a Convolutional Neural Network and, second, reconstruction of the anatomical shape by means of deformable geometric primitives. Results:The methodology performance was validated with different scenarios. Synthetic scenario tests, designed for extreme validation conditions, demonstrate the safety margin offered by the methodology with respect to the nominal conditions during surgery. Real scenario experiments have demonstrated the validity of the method in terms of accuracy, robustness and computational efficiency. Conclusions:This paper presents a robust anatomical structure detection in present of abrupt camera movements, severe occlusions and deformations. Even though the paper focuses on a case study, Open Spina Bifida, the methodology is applicable in all anatomies which contours can be approximated by geometric primitives. The methodology is designed to provide effective inputs to cognitive robotic control and augmented reality systems that require accurate tracking of sensitive anatomies.

Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms

Pulmonary Embolisms (PE) represent a leading cause of cardiovascular death. While medical imaging, through computed tomographic pulmonary angiography (CTPA), represents the gold standard for PE diagnosis, it is still susceptible to misdiagnosis or significant diagnosis delays, which may be fatal for critical cases. Despite the recently demonstrated power of deep learning to bring a significant boost in performance in a wide range of medical imaging tasks, there are still very few published researches on automatic pulmonary embolism detection. Herein we introduce a deep learning based approach, which efficiently combines computer vision and deep neural networks for pulmonary embolism detection in CTPA. Our method brings novel contributions along three orthogonal axes: (1) automatic detection of anatomical structures; (2) anatomical aware pretraining, and (3) a dual-hop deep neural net for PE detection. We obtain state-of-the-art results on the publicly available multicenter large-scale RSNA dataset.

Focused Decoding Enables 3D Anatomical Detection by Transformers

Detection Transformers represent end-to-end object detection approaches based on a Transformer encoder-decoder architecture, exploiting the attention mechanism for global relation modeling. Although Detection Transformers deliver results on par with or even superior to their highly optimized CNN-based counterparts operating on 2D natural images, their success is closely coupled to access to a vast amount of training data. This, however, restricts the feasibility of employing Detection Transformers in the medical domain, as access to annotated data is typically limited. To tackle this issue and facilitate the advent of medical Detection Transformers, we propose a novel Detection Transformer for 3D anatomical structure detection, dubbed Focused Decoder. Focused Decoder leverages information from an anatomical region atlas to simultaneously deploy query anchors and restrict the crossattention’s field of view to regions of interest, which allows for a precise focus on relevant anatomical structures. We evaluate our proposed approach on two publicly available CT datasets and demonstrate that Focused Decoder not only provides strong detection results and thus alleviates the need for a vast amount of annotated data but also exhibits exceptional and highly intuitive explainability of results via attention weights. Our code is available at <a href='https://github.com/bwittmann/transoar'>https://github.com/bwittmann/transoar</a>

Development of a Fully Automated Graf Standard Plane and Angle Evaluation Method for Infant Hip Ultrasound Scans.

Background: Graf’s method is currently the most commonly used ultrasound-based technique for the diagnosis of developmental dysplasia of the hip (DDH). However, the efficiency and accuracy of diagnosis are highly affected by the sonographers’ qualification and the time and effort expended, which has a significant intra- and inter-observer variability. Methods: Aiming to minimize the manual intervention in the diagnosis process, we developed a deep learning-based computer-aided framework for the DDH diagnosis, which can perform fully automated standard plane detection and angle measurement for Graf type I and type II hips. The proposed framework is composed of three modules: an anatomical structure detection module, a standard plane scoring module, and an angle measurement module. This framework can be applied to two common clinical scenarios. The first is the static mode, measurement and classification are performed directly based on the given standard plane. The second is the dynamic mode, where a standard plane from ultrasound video is first determined, and measurement and classification are then completed. To the best of our knowledge, our proposed framework is the first CAD method that can automatically perform the entire measurement process of Graf’s method. Results: In our experiments, 1051 US images and 289 US videos of Graf type I and type II hips were used to evaluate the performance of the proposed framework. In static mode, the mean absolute error of α, β angles are 1.71° and 2.40°, and the classification accuracy is 94.71%. In dynamic mode, the mean absolute error of α, β angles are 1.97° and 2.53°, the classification accuracy is 89.51%, and the running speed is 31 fps. Conclusions: Experimental results demonstrate that our fully automated framework can accurately perform standard plane detection and angle measurement of an infant’s hip at a fast speed, showing great potential for clinical application.

THE ROLE OF BLACK TEA AND PINEAPPLE JUICE AS NEGATIVE ORAL CONTRASTS ON MAGNETIC RESONANCE CHOLANGIOPANCREATOGRAPHY (MRCP) EXAMINATION

Background: Magnetic resonance cholangiopancreatography examination is a superior examination in the detection of anatomic structures or pathological abnormalities in the human pancreatobiliary system. This examination is recommended to use negative oral contrast which aims to eliminate gastrointestinal signals that are around the pancreatobiliary system which can be a barrier to the visualization of the pancreatobiliary tract. Materials that can be used as oral contrast contrast must be able to survive for a long time in the gastrointestinal tract and contain elements of iron (Fe) and Manganese (Mn). The high Mn content of black and pineapple juice and its abundance need to be explored as contrast oral negative. Purpose: To prove the role of pineapple juice and black tea which are natural ingredients of negative oral contrast in the visualization of the pancreatobiliary system on MRCP examination. Methods: Experimental quasy studies have been carried out on 9 samples prospectively. Each sample underwent MRCP examination with three treatments, namely given black tea, pineapple juice and plain water. The image results from the three treatments were assessed by Radiology Doctors to assess the quality of their image. Results: The results showed that black tea was more effective in providing optimal image results on MRCP examination than pineapple juice and without using oral contrast contrast. The metal content of negative oral contrast can cause magnetic susceptibility which is characterized by the presence of shortening at the time of T2 relaxation. Negative contrast agents affect signal intensity usually by shortening T2 or T2 *, as an effect, areas of concern, especially areas with negative contrast agents will experience darkening. Conclusion: Black tea is effectively used as a negative oral contrat on MRCP examination.

Semantic segmentation and detection of mediastinal lymph nodes and anatomical structures in CT data for lung cancer staging.

Accurate lung cancer diagnosis is crucial to select the best course of action for treating the patient. From a simple chest CT volume, it is necessary to identify whether the cancer has spread to nearby lymph nodes or not. It is equally important to know precisely where each malignant lymph node is with respect to the surrounding anatomical structures and the airways. In this paper, we introduce a new data-set containing annotations of fifteen different anatomical structures in the mediastinal area, including lymph nodes of varying sizes. We present a 2D pipeline for semantic segmentation and instance detection of anatomical structures and potentially malignant lymph nodes in the mediastinal area. We propose a 2D pipeline combining the strengths of U-Net for pixel-wise segmentation using a loss function dealing with data imbalance and Mask R-CNN providing instance detection and improved pixel-wise segmentation within bounding boxes. A final stage performs pixel-wise labels refinement and 3D instance detection using a tracking approach along the slicing dimension. Detected instances are represented by a 3D pixel-wise mask, bounding volume, and centroid position. We validated our approach following a fivefold cross-validation over our new data-set of fifteen lung cancer patients. For the semantic segmentation task, we reach an average Dice score of 76% over all fifteen anatomical structures. For the lymph node instance detection task, we reach 75% recall for 9 false positives per patient, with an average centroid position estimation error of 3 mm in each dimension. Fusing 2D networks' results increases pixel-wise segmentation results while enabling good instance detection. Better leveraging of the 3D information and station mapping for the detected lymph nodes are the next steps.

Towards intelligent robust detection of anatomical structures in incomplete volumetric data.

Robust and fast detection of anatomical structures represents an important component of medical image analysis technologies. Current solutions for anatomy detection are based on machine learning, and are generally driven by suboptimal and exhaustive search strategies. In particular, these techniques do not effectively address cases of incomplete data, i.e., scans acquired with a partial field-of-view. We address these challenges by following a new paradigm, which reformulates the detection task to teaching an intelligent artificial agent how to actively search for an anatomical structure. Using the principles of deep reinforcement learning with multi-scale image analysis, artificial agents are taught optimal navigation paths in the scale-space representation of an image, while accounting for structures that are missing from the field-of-view. The spatial coherence of the observed anatomical landmarks is ensured using elements from statistical shape modeling and robust estimation theory. Experiments show that our solution outperforms marginal space deep learning, a powerful deep learning method, at detecting different anatomical structures without any failure. The dataset contains 5043 3D-CT volumes from over 2000 patients, totaling over 2,500,000 image slices. In particular, our solution achieves 0% false-positive and 0% false-negative rates at detecting whether the landmarks are captured in the field-of-view of the scan (excluding all border cases), with an average detection accuracy of 2.78 mm. In terms of runtime, we reduce the detection-time of the marginal space deep learning method by 20-30 times to under 40ms, an unmatched performance for high resolution incomplete 3D-CT data.

Detection of Anatomical Structures in Chest X-ray Photographs by Deep Neural Networks

Detection of Anatomical Structures in Chest X-ray Photographs by Deep Neural Networks

Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans.

Robust and fast detection of anatomical structures is a prerequisite for both diagnostic and interventional medical image analysis. Current solutions for anatomy detection are typically based on machine learning techniques that exploit large annotated image databases in order to learn the appearance of the captured anatomy. These solutions are subject to several limitations, including the use of suboptimal feature engineering techniques and most importantly the use of computationally suboptimal search-schemes for anatomy detection. To address these issues, we propose a method that follows a new paradigm by reformulating the detection problem as a behavior learning task for an artificial agent. We couple the modeling of the anatomy appearance and the object search in a unified behavioral framework, using the capabilities of deep reinforcement learning and multi-scale image analysis. In other words, an artificial agent is trained not only to distinguish the target anatomical object from the rest of the body but also how to find the object by learning and following an optimal navigation path to the target object in the imaged volumetric space. We evaluated our approach on 1487 3D-CT volumes from 532 patients, totaling over 500,000 image slices and show that it significantly outperforms state-of-the-art solutions on detecting several anatomical structures with no failed cases from a clinical acceptance perspective, while also achieving a 20-30 percent higher detection accuracy. Most importantly, we improve the detection-speed of the reference methods by 2-3 orders of magnitude, achieving unmatched real-time performance on large 3D-CT scans.

Fast detection of the main anatomical structures in digital retinal images based on intra- and inter-structure relational knowledge

Background and objective: The anatomical structure detection in retinal images is an open problem. However, most of the works in the related literature are oriented to the detection of each structure individually or assume the previous detection of a structure which is used as a reference. The objective of this paper is to obtain simultaneous detection of the main retinal structures (optic disc, macula, network of vessels and vascular bundle) in a fast and robust way.Methods: We propose a new methodology oriented to accomplish the mentioned objective. It consists of two stages. In an initial stage, a set of operators is applied to the retinal image. Each operator uses intra-structure relational knowledge in order to produce a set of candidate blobs that belongs to the desired structure. In a second stage, a set of tuples is created, each of which contains a different combination of the candidate blobs. Next, filtering operators, using inter-structure relational knowledge, are used in order to find the winner tuple. A method using template matching and mathematical morphology is implemented following the proposed methodology.Results: A success is achieved if the distance between the automatically detected blob center and the actual structure center is less than or equal to one optic disc radius. The success rates obtained in the different public databases analyzed were: MESSIDOR (99.33%, 98.58%, 97.92%), DIARETDB1 (96.63%, 100%, 97.75%), DRIONS (100%, n/a, 100%) and ONHSD (100%, 98.85%, 97.70%) for optic disc (OD), macula (M) and vascular bundle (VB), respectively. Finally, the overall success rate obtained in this study for each structure was: 99.26% (OD), 98.69% (M) and 98.95% (VB). The average time of processing per image was 4.16 ± 0.72 s.Conclusions: The main advantage of the use of inter-structure relational knowledge was the reduction of the number of false positives in the detection process. The implemented method is able to simultaneously detect four structures. It is fast, robust and its detection results are competitive in relation to other methods of the recent literature.

Evaluation of reconstruction parameters of electrical impedance tomography on aorta detection during saline bolus injection

Abstract An accurate detection of anatomical structures in electrical impedance tomography (EIT) is still at an early stage. Aorta detection in EIT is of special interest, since it would favor non-invasive assessment of hemodynamic processes in the body. Here, diverse EIT reconstruction parameters of the GREIT algorithm were systematically evaluated to detect the aorta after saline bolus injection in apnea. True aorta position and size were taken from computed tomography (CT). A comparison with CT showed that the smallest error for aorta displacement was attained for noise figure nf = 0.7, weighting radius rw = 0.15, and target size ts = 0.01. The spatial extension of the aorta was most precise for nf = 0.7, rw = 0.25, and ts = 0.07. Detection accuracy (F1-score) was highest with nf = 0.6, rw = 0.15, and ts = 0.04. This work provides algorithm-related evidence for potentially accurate aorta detection in EIT after injection of a saline bolus.

Magnetic resonance imaging in the evaluation of idiopathic pulmonary fibrosis: a real possibility, or an attractive challenge?

Magnetic resonance imaging in the evaluation of idiopathic pulmonary fibrosis: a real possibility, or an attractive challenge?

A Review of Computer Aided Detection of Anatomical Structures and Lesions of DR from Color Retina Images

Ophthalmology is the study of structures, functions, treatment and disorders of eye. Computer aided analysis of retina images is still an open research area. Numerous efforts have been made to automate the analysis of retina images. This paper presents a review of various existing research in detection of anatomical structures in retina and lesions for the diagnosis of diabetic retinopathy (DR). The research in detection of anatomical structures is further divided into subcategories, namely, vessel segmentation and vessel centerline extraction, optic disc segmentation and localization, and fovea/ macula detection and extraction. Various research works in each of the categories are reviewed highlighting the techniques employed and comparing the performance figures obtained. The issues/ lacuna of various approaches are brought out. The following major observations are made: Most of the vessel detection algorithms fail to extract small thin vessels having low contrast. It is difficult to detect vessels at regions where close vessels are merged, at regions of missing of small vessels, at optic disc regions, and at regions of pathology. Machine learning based approaches for blood vessel tracing requires long processing time. It is difficult to detect optic disc radius or boundary with simple blood vessel tracing. Automatic detection of fovea and macular region extraction becomes complicated due to non- uniform illuminations while imaging and diseases of the eyes. Techniques requiring prior knowledge leads to complexity. Most lesion detection algorithms underperform due to wide variations in the color of fundus images arising out of variations in the degree of pigmentation and presence of choroid.

Granular computing in model based abdominal organs detection

Detection of region specific voxel is a true challenge in many segmentation procedures. In this study a concept of implementing granular computing in the detection of anatomical structures in abdominal computed tomography (CT) scans is introduced. After proving the usefulness of the information granules to identify voxels that mark certain organs, an automatic model-based approach has been developed. A three-parameter granule that combines the interval and density distribution of voxels has been introduced and employed to identify organ specific voxels of the liver, spleen and kidneys. The specificity of the information granules varies between 90 and 99% for the liver and spleen and over 85% for the kidneys.

Labeling of Lumbar Discs Using Both Pixel- and Object-Level Features With a Two-Level Probabilistic Model

Backbone anatomical structure detection and labeling is a necessary step for various analysis tasks of the vertebral column. Appearance, shape and geometry measurements are necessary for abnormality detection locally at each disc and vertebrae (such as herniation) as well as globally for the whole spine (such as spinal scoliosis). We propose a two-level probabilistic model for the localization of discs from clinical magnetic resonance imaging (MRI) data that captures both pixel- and object-level features. Using a Gibbs distribution, we model appearance and spatial information at the pixel level, and at the object level, we model the spatial distribution of the discs and the relative distances between them. We use generalized expectation-maximization for optimization, which achieves efficient convergence of disc labels. Our two-level model allows the assumption of conditional independence at the pixel-level to enhance efficiency while maintaining robustness. We use a dataset that contains 105 MRI clinical normal and abnormal cases for the lumbar area. We thoroughly test our model and achieve encouraging results on normal and abnormal cases.

Static MR Images for Diagnosis of Swallowing

Evaluation of swallowing has been made possible by cine-Magnetic resonance (MR) imaging with high time resolution. However, the spatial resolution in cine-MR imaging remains inadequate for the detection of anatomical structures. Therefore, it is necessary to refer to static MR images in conjunction with cine-MR imaging. The aim of this study was to determine which MR parameters were appropriate for static imaging of the anatomical structures involved in swallowing. MR imaging was carried out, and T1-weighted, T2-weighted and proton-density-weighted MR images were obtained in the sagittal plane in 5 healthy volunteers. Each image was evaluated for anatomic landmark clarity by 3 oral radiologists. The anatomic landmarks selected were the lip, tip of tongue, center of tongue, tongue base, soft palate and epiglottis. Differences in clarity among 3 imaging modalities were evaluated. A 3-point score rating system was used. The results showed that lower TE sequences, i.e., either T1-weighted or proton-density-weighted images, were the most suitable for use in conjunction with cine-MR imaging in diagnosing swallowing disorders.

Detection of Anatomic Structures in Human Retinal Imagery

The widespread availability of electronic imaging devices throughout the medical community is leading to a growing body of research on image processing and analysis to diagnose retinal disease such as diabetic retinopathy (DR). Productive computer-based screening of large, at-risk populations at low cost requires robust, automated image analysis. In this paper we present results for the automatic detection of the optic nerve and localization of the macula using digital red-free fundus photography. Our method relies on the accurate segmentation of the vasculature of the retina followed by the determination of spatial features describing the density, average thickness, and average orientation of the vasculature in relation to the position of the optic nerve. Localization of the macula follows using knowledge of the optic nerve location to detect the horizontal raphe of the retina using a geometric model of the vasculature. We report 90.4% detection performance for the optic nerve and 92.5% localization performance for the macula for red-free fundus images representing a population of 345 images corresponding to 269 patients with 18 different pathologies associated with DR and other common retinal diseases such as age-related macular degeneration.

Image Quality, lesion detection, and diagnostic efficacy in digital mammography: Full-field digital mammography versus computed radiography-based mammography using digital storage phosphor plates

Objective To compare image quality, the lesion detection, and the diagnostic efficacy of full-field digital mammography (FFDM) and computed radiography-based mammography using digital storage phosphor plates (DSPM) in the evaluation of breast lesions. Materials and methods In this prospective study, 150 patients with suspicious breast lesions underwent FFDM and DSPM. Nine aspects of image quality (brightness, contrast, sharpness, noise, artifacts, and the detection of anatomic structures, i.e., skin, retromamillary space, glandular tissue, and calcifications) were evaluated by five radiologists. In addition, the detection of breast lesions and the diagnostic efficacy, based on the BI-RADS classification, were evaluated with histologic and follow-up correlation. Results For contrast, sharpness, and the detection of all anatomic structures, FFDM was rated significantly better ( p < 0.05). Mass lesions were equally detected, whereas FFDM detected more lesions consisting of calcifications (85 versus 75). DSPM yielded two false-negative results. Both lesions were rated BI-RADS 4 with FFDM, but BI-RADS 2 with DSPM. Both were invasive carcinoma at histology. The sensitivity, specificity, PPV, NPV, and accuracy of FFDM were 1.0, 0.397, 0.636, 1.0, and 0.707, compared to 0.974, 0.397, 0.630, 0.935, and 0.693 of DSPM. Conclusion Based on image quality parameters, FFDM is, in part, significantly better than DSPM. Furthermore, the detection of breast lesions with calcifications is favorable with FFDM. However, the diagnostic efficacy of FFDM and DSPM was equal. The interpretation of the false-negative results suggests that the perception and characterization of breast lesions is not defined solely by the digital mammography system but is strongly influenced by the radiologist, who is one of the determinants in the interpretation of breast imaging.