Imaging exams, such as chest radiography, will yield a small set of common findings and a much larger set of uncommon findings.
To circumvent this, a series of cylinders that are fitted along the course of the small bowel are used to guide the tracking to more reliable directions.
Our method can be one option for explicitly incorporating intensity distribution information of a target in network training.
The proposed method holds a high degree of usability in this problem by being able to utilize the scans with weak annotations, and thus by possibly reducing the required annotation cost.
no code implementations • 3 Jun 2022 • Lena Maier-Hein, Annika Reinke, Patrick Godau, Minu D. Tizabi, Evangelia Christodoulou, Ben Glocker, Fabian Isensee, Jens Kleesiek, Michal Kozubek, Mauricio Reyes, Michael A. Riegler, Manuel Wiesenfarth, Michael Baumgartner, Matthias Eisenmann, Doreen Heckmann-Nötzel, A. Emre Kavur, Tim Rädsch, Laura Acion, Michela Antonelli, Tal Arbel, Spyridon Bakas, Peter Bankhead, Arriel Benis, M. Jorge Cardoso, Veronika Cheplygina, Beth Cimini, Gary S. Collins, Keyvan Farahani, Luciana Ferrer, Adrian Galdran, Bram van Ginneken, Robert Haase, Daniel A. Hashimoto, Michael M. Hoffman, Merel Huisman, Pierre Jannin, Charles E. Kahn, Dagmar Kainmueller, Bernhard Kainz, Alexandros Karargyris, Alan Karthikesalingam, Hannes Kenngott, Florian Kofler, Annette Kopp-Schneider, Anna Kreshuk, Tahsin Kurc, Bennett A. Landman, Geert Litjens, Amin Madani, Klaus Maier-Hein, Anne L. Martel, Peter Mattson, Erik Meijering, Bjoern Menze, David Moher, Karel G. M. Moons, Henning Müller, Brennan Nichyporuk, Felix Nickel, Jens Petersen, Nasir Rajpoot, Nicola Rieke, Julio Saez-Rodriguez, Clarisa Sánchez Gutiérrez, Shravya Shetty, Maarten van Smeden, Carole H. Sudre, Ronald M. Summers, Abdel A. Taha, Sotirios A. Tsaftaris, Ben van Calster, Gaël Varoquaux, Paul F. Jäger
Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem.
Results: Experiments on 122 test T2 MRI volumes revealed that VFNet achieved a 51. 1% mAP and 78. 7% recall at 4 false positives (FP) per volume, while the one-stage model ensemble achieved a mAP of 52. 3% and sensitivity of 78. 7% at 4FP.
In clinical practice, radiologists are reliant on the lesion size when distinguishing metastatic from non-metastatic lesions.
Identification of lymph nodes (LN) in T2 Magnetic Resonance Imaging (MRI) is an important step performed by radiologists during the assessment of lymphoproliferative diseases.
It is formulated as finding the minimum cost path between given start and end nodes on a graph that is constructed based on the bowel wall detection.
We present a novel unsupervised domain adaptation method for small bowel segmentation based on feature disentanglement.
1 code implementation • 10 Jun 2021 • Michela Antonelli, Annika Reinke, Spyridon Bakas, Keyvan Farahani, AnnetteKopp-Schneider, Bennett A. Landman, Geert Litjens, Bjoern Menze, Olaf Ronneberger, Ronald M. Summers, Bram van Ginneken, Michel Bilello, Patrick Bilic, Patrick F. Christ, Richard K. G. Do, Marc J. Gollub, Stephan H. Heckers, William R. Jarnagin, Maureen K. McHugo, Sandy Napel, Jennifer S. Goli Pernicka, Kawal Rhode, Catalina Tobon-Gomez, Eugene Vorontsov, Henkjan Huisman, James A. Meakin, Sebastien Ourselin, Manuel Wiesenfarth, Pablo Arbelaez, Byeonguk Bae, Sihong Chen, Laura Daza, Jianjiang Feng, Baochun He, Fabian Isensee, Yuanfeng Ji, Fucang Jia, Namkug Kim, Ildoo Kim, Dorit Merhof, Akshay Pai, Beomhee Park, Mathias Perslev, Ramin Rezaiifar, Oliver Rippel, Ignacio Sarasua, Wei Shen, Jaemin Son, Christian Wachinger, Liansheng Wang, Yan Wang, Yingda Xia, Daguang Xu, Zhanwei Xu, Yefeng Zheng, Amber L. Simpson, Lena Maier-Hein, M. Jorge Cardoso
Segmentation is so far the most widely investigated medical image processing task, but the various segmentation challenges have typically been organized in isolation, such that algorithm development was driven by the need to tackle a single specific clinical problem.
1 code implementation • 12 Apr 2021 • Annika Reinke, Minu D. Tizabi, Carole H. Sudre, Matthias Eisenmann, Tim Rädsch, Michael Baumgartner, Laura Acion, Michela Antonelli, Tal Arbel, Spyridon Bakas, Peter Bankhead, Arriel Benis, M. Jorge Cardoso, Veronika Cheplygina, Evangelia Christodoulou, Beth Cimini, Gary S. Collins, Keyvan Farahani, Bram van Ginneken, Ben Glocker, Patrick Godau, Fred Hamprecht, Daniel A. Hashimoto, Doreen Heckmann-Nötzel, Michael M. Hoffman, Merel Huisman, Fabian Isensee, Pierre Jannin, Charles E. Kahn, Alexandros Karargyris, Alan Karthikesalingam, Bernhard Kainz, Emre Kavur, Hannes Kenngott, Jens Kleesiek, Thijs Kooi, Michal Kozubek, Anna Kreshuk, Tahsin Kurc, Bennett A. Landman, Geert Litjens, Amin Madani, Klaus Maier-Hein, Anne L. Martel, Peter Mattson, Erik Meijering, Bjoern Menze, David Moher, Karel G. M. Moons, Henning Müller, Brennan Nichyporuk, Felix Nickel, M. Alican Noyan, Jens Petersen, Gorkem Polat, Nasir Rajpoot, Mauricio Reyes, Nicola Rieke, Michael Riegler, Hassan Rivaz, Julio Saez-Rodriguez, Clarisa Sanchez Gutierrez, Julien Schroeter, Anindo Saha, Shravya Shetty, Maarten van Smeden, Bram Stieltjes, Ronald M. Summers, Abdel A. Taha, Sotirios A. Tsaftaris, Ben van Calster, Gaël Varoquaux, Manuel Wiesenfarth, Ziv R. Yaniv, Annette Kopp-Schneider, Paul Jäger, Lena Maier-Hein
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation.
In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues.
We introduce an edge prediction module in E$^2$Net and design an edge distance map between liver and tumor boundaries, which is used as an extra supervision signal to train the edge enhanced network.
Since the inner cylinder is free of the touching issue, a cylindrical shape constraint applied on this augmented branch guides the network to generate a topologically correct segmentation.
We expect the utility of our framework will extend to other problems beyond segmentation due to the improved quality of the generated images and enhanced ability to preserve small structures.
We present a deep network interpolation strategy for accelerated parallel MR image reconstruction.
(1) We show that COVID-19-CT-CXR, when used as additional training data, is able to contribute to improved DL performance for the classification of COVID-19 and non-COVID-19 CT. (2) We collected CT images of influenza and trained a DL baseline to distinguish a diagnosis of COVID-19, influenza, or normal or other types of diseases on CT. (3) We trained an unsupervised one-class classifier from non-COVID-19 CXR and performed anomaly detection to detect COVID-19 CXR.
In medical imaging applications, preserving small structures is important since these structures can carry information which is highly relevant for disease diagnosis.
no code implementations • 18 Mar 2020 • Nicola Rieke, Jonny Hancox, Wenqi Li, Fausto Milletari, Holger Roth, Shadi Albarqouni, Spyridon Bakas, Mathieu N. Galtier, Bennett Landman, Klaus Maier-Hein, Sebastien Ourselin, Micah Sheller, Ronald M. Summers, Andrew Trask, Daguang Xu, Maximilian Baust, M. Jorge Cardoso
Data-driven Machine Learning has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems.
Dual-energy (DE) chest radiography provides the capability of selectively imaging two clinically relevant materials, namely soft tissues, and osseous structures, to better characterize a wide variety of thoracic pathology and potentially improve diagnosis in posteroanterior (PA) chest radiographs.
We next developed an algorithm which performs iterative instance segmentation and classification of the entire spine with a 3D U-Net.
In medical imaging applications, preserving small structures is important since these structures can carry information which is highly relevant for disease diagnosis.
In this work, we propose a weakly-supervised co-segmentation model that first generates pseudo-masks from the RECIST slices and uses these as training labels for an attention-based convolutional neural network capable of segmenting common lesions from a pair of CT scans.
Lesion segmentation on computed tomography (CT) scans is an important step for precisely monitoring changes in lesion/tumor growth.
Purpose: To systematically investigate the influence of various data consistency layers, (semi-)supervised learning and ensembling strategies, defined in a $\Sigma$-net, for accelerated parallel MR image reconstruction using deep learning.
We explore an ensembled $\Sigma$-net for fast parallel MR imaging, including parallel coil networks, which perform implicit coil weighting, and sensitivity networks, involving explicit sensitivity maps.
In this work, we exploit the unsupervised domain adaptation problem for radiology image interpretation across domains.
When reading medical images such as a computed tomography (CT) scan, radiologists generally search across the image to find lesions, characterize and measure them, and then describe them in the radiological report.
Ranked #7 on Medical Object Detection on DeepLesion
In radiology, radiologists not only detect lesions from the medical image, but also describe them with various attributes such as their type, location, size, shape, and intensity.
To reduce the manual annotation burden and to train a robust lung segmentor that can be adapted to pathological lungs with hazy lung boundaries, an image-to-image translation module is employed to synthesize radiorealistic abnormal CXRs from the source of normal ones for data augmentation.
Ranked #1 on Lung Nodule Segmentation on NIH
In radiologists' routine work, one major task is to read a medical image, e. g., a CT scan, find significant lesions, and describe them in the radiology report.
Given a chest X-ray image in the testing phase, if it is normal, the learned architecture can well model and reconstruct the content; if it is abnormal, since the content is unseen in the training phase, the model would perform poorly in its reconstruction.
To address this problem, we define a set of 145 labels based on RadLex to describe a large variety of lesions in the DeepLesion dataset.
9 code implementations • 25 Feb 2019 • Amber L. Simpson, Michela Antonelli, Spyridon Bakas, Michel Bilello, Keyvan Farahani, Bram van Ginneken, Annette Kopp-Schneider, Bennett A. Landman, Geert Litjens, Bjoern Menze, Olaf Ronneberger, Ronald M. Summers, Patrick Bilic, Patrick F. Christ, Richard K. G. Do, Marc Gollub, Jennifer Golia-Pernicka, Stephan H. Heckers, William R. Jarnagin, Maureen K. McHugo, Sandy Napel, Eugene Vorontsov, Lena Maier-Hein, M. Jorge Cardoso
Semantic segmentation of medical images aims to associate a pixel with a label in a medical image without human initialization.
Results validate that the ST-ConvLSTM produces a Dice score of 83. 2%+-5. 1% and a RVD of 11. 2%+-10. 8%, both significantly outperforming (p<0. 05) other compared methods of linear model, ConvLSTM, and generative adversarial network (GAN) under the metric of predicting future tumor volumes.
To address this problem, this work constructs a pseudo mask for each lesion region that can be considered as a surrogate of the real mask, based on which the Mask R-CNN is employed for lesion detection.
In addition, highly confident samples (measured by classification probabilities) and their corresponding class-conditional heatmaps (generated by the CNN) are extracted and further fed into the AGCL framework to guide the learning of more distinctive convolutional features in the next iteration.
The first GAN reduces the noise in the CT image and the second GAN generates a higher resolution image with enhanced boundaries and high contrast.
Volumetric lesion segmentation from computed tomography (CT) images is a powerful means to precisely assess multiple time-point lesion/tumor changes.
3D context is known to be helpful in this differentiation task.
Ranked #10 on Medical Object Detection on DeepLesion
Response evaluation criteria in solid tumors (RECIST) is the standard measurement for tumor extent to evaluate treatment responses in cancer patients.
Toward this end, we introduce a convolutional neural network based weakly supervised self-paced segmentation (WSSS) method to 1) generate the initial lesion segmentation on the axial RECIST-slice; 2) learn the data distribution on RECIST-slices; 3) adapt to segment the whole volume slice by slice to finally obtain a volumetric segmentation.
In recent years, deep neural networks achieve impressive performances on many medical image segmentation tasks by supervised learning on large manually annotated data.
The cost for each node of the graph is determined by the UNet probability maps.
However, the success of most traditional classification methods relies on the presence of accurate cell segmentations.
Tumor growth is associated with cell invasion and mass-effect, which are traditionally formulated by mathematical models, namely reaction-diffusion equations and biomechanics.
Chest X-rays are one of the most common radiological examinations in daily clinical routines.
We categorize the collection of lesions using an unsupervised deep mining scheme to generate clustered pseudo lesion labels.
In this paper, we propose a convolutional neural network (CNN) based Unsupervised Body part Regression (UBR) algorithm to address this problem.
Pathological lung segmentation (PLS) is an important, yet challenging, medical image application due to the wide variability of pathological lung appearance and shape.
Our predictive model is pretrained on a group data set and personalized on the target patient data to estimate the future spatio-temporal progression of the patient's tumor.
The chest X-ray is one of the most commonly accessible radiological examinations for screening and diagnosis of many lung diseases.
Accurate and automatic organ segmentation from 3D radiological scans is an important yet challenging problem for medical image analysis.
Ranked #1 on 3D Medical Imaging Segmentation on TCIA Pancreas-CT
The recent rapid and tremendous success of deep convolutional neural networks (CNN) on many challenging computer vision tasks largely derives from the accessibility of the well-annotated ImageNet and PASCAL VOC datasets.
Accurately predicting and detecting interstitial lung disease (ILD) patterns given any computed tomography (CT) slice without any pre-processing prerequisites, such as manually delineated regions of interest (ROIs), is a clinically desirable, yet challenging goal.
Accurate automatic organ segmentation is an important yet challenging problem for medical image analysis.
Recurrent neural networks (RNNs) are then trained to describe the contexts of a detected disease, based on the deep CNN features.
Another effective method is transfer learning, i. e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks.
The use of joint vertebra-rib atlases produced a statistically significant increase in the Dice coefficient from 92. 5 $\pm$ 3. 1% to 93. 8 $\pm$ 2. 1% for the left and right transverse processes and a decrease in the mean and max surface distance from 0. 75 $\pm$ 0. 60mm and 8. 63 $\pm$ 4. 44mm to 0. 30 $\pm$ 0. 27mm and 3. 65 $\pm$ 2. 87mm, respectively.
In this work, we apply deep convolutional networks (ConvNets) for the automated detection of posterior element fractures of the spine.
Classification of vertebral compression fractures (VCF) having osteoporotic or neoplastic origin is fundamental to the planning of treatment.
The precise and accurate segmentation of the vertebral column is essential in the diagnosis and treatment of various orthopedic, neurological, and oncological traumas and pathologies.
We propose and evaluate several variations of deep ConvNets in the context of hierarchical, coarse-to-fine classification on image patches and regions, i. e. superpixels.
We present an interleaved text/image deep learning system to extract and mine the semantic interactions of radiology images and reports from a national research hospital's picture archiving and communication system.
We present a bottom-up approach for pancreas segmentation in abdominal CT scans that is based on a hierarchy of information propagation by classifying image patches at different resolutions; and cascading superpixels.
By leveraging existing CAD systems, coordinates of regions or volumes of interest (ROI or VOI) for lesion candidates are generated in this step and function as input for a second tier, which is our focus in this study.
We present an interleaved text/image deep learning system to extract and mine the semantic interactions of radiology images and reports from a national research hospital's Picture Archiving and Communication System.
We show that a data augmentation approach can help to enrich the data set and improve classification performance.
We evaluate our method on CT images of 82 patients (60 for training, 2 for validation, and 20 for testing).
In this paper, we propose a new algorithm representation of decomposing the LN detection problem into a set of 2D object detection subtasks on sampled CT slices, largely alleviating the curse of dimensionality issue.
Organ segmentation is a prerequisite for a computer-aided diagnosis (CAD) system to detect pathologies and perform quantitative analysis.
In testing, the CNN is employed to assign individual probabilities for a new set of N random views that are averaged at each ROI to compute a final per-candidate classification probability.
and 84%/90% at 6 FP/vol.