Publications by Year: 2021

Wang D, Zhang T, Li M, Bueno R, Jayender J. 3D Deep Learning Based Classification of Pulmonary Ground Glass Opacity Nodules With Automatic Segmentation. Comput Med Imaging Graph. 2021;88 :101814.Abstract
Classifying ground-glass lung nodules (GGNs) into atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) on diagnostic CT images is important to evaluate the therapy options for lung cancer patients. In this paper, we propose a joint deep learning model where the segmentation can better facilitate the classification of pulmonary GGNs. Based on our observation that masking the nodule to train the model results in better lesion classification, we propose to build a cascade architecture with both segmentation and classification networks. The segmentation model works as a trainable preprocessing module to provide the classification-guided 'attention' weight map to the raw CT data to achieve better diagnosis performance. We evaluate our proposed model and compare with other baseline models for 4 clinically significant nodule classification tasks, defined by a combination of pathology types, using 4 classification metrics: Accuracy, Average F1 Score, Matthews Correlation Coefficient (MCC), and Area Under the Receiver Operating Characteristic Curve (AUC). Experimental results show that the proposed method outperforms other baseline models on all the diagnostic classification tasks.
Wang D, Li M, Ben-Shlomo N, Corrales EC, Cheng Y, Zhang T, Jayender J. A Novel Dual-Network Architecture for Mixed-Supervised Medical Image Segmentation. Comput Med Imaging Graph. 2021;89 :101841.Abstract
In medical image segmentation tasks, deep learning-based models usually require densely and precisely annotated datasets to train, which are time-consuming and expensive to prepare. One possible solution is to train with the mixed-supervised dataset, where only a part of data is densely annotated with segmentation map and the rest is annotated with some weak form, such as bounding box. In this paper, we propose a novel network architecture called Mixed-Supervised Dual-Network (MSDN), which consists of two separate networks for the segmentation and detection tasks respectively, and a series of connection modules between the layers of the two networks. These connection modules are used to extract and transfer useful information from the detection task to help the segmentation task. We exploit a variant of a recently designed technique called 'Squeeze and Excitation' in the connection module to boost the information transfer between the two tasks. Compared with existing model with shared backbone and multiple branches, our model has flexible and trainable feature sharing fashion and thus is more effective and stable. We conduct experiments on 4 medical image segmentation datasets, and experiment results show that the proposed MSDN model outperforms multiple baselines.
He J, Zhang F, Xie G, Yao S, Feng Y, Bastos DCA, Rathi Y, Makris N, Kikinis R, Golby AJ, et al. Comparison of Multiple Tractography Methods for Reconstruction of the Retinogeniculate Visual Pathway Using Diffusion MRI. Hum Brain Mapp. 2021;42 (12) :3887-904.Abstract
The retinogeniculate visual pathway (RGVP) conveys visual information from the retina to the lateral geniculate nucleus. The RGVP has four subdivisions, including two decussating and two nondecussating pathways that cannot be identified on conventional structural magnetic resonance imaging (MRI). Diffusion MRI tractography has the potential to trace these subdivisions and is increasingly used to study the RGVP. However, it is not yet known which fiber tracking strategy is most suitable for RGVP reconstruction. In this study, four tractography methods are compared, including constrained spherical deconvolution (CSD) based probabilistic (iFOD1) and deterministic (SD-Stream) methods, and multi-fiber (UKF-2T) and single-fiber (UKF-1T) unscented Kalman filter (UKF) methods. Experiments use diffusion MRI data from 57 subjects in the Human Connectome Project. The RGVP is identified using regions of interest created by two clinical experts. Quantitative anatomical measurements and expert anatomical judgment are used to assess the advantages and limitations of the four tractography methods. Overall, we conclude that UKF-2T and iFOD1 produce the best RGVP reconstruction results. The iFOD1 method can better quantitatively estimate the percentage of decussating fibers, while the UKF-2T method produces reconstructed RGVPs that are judged to better correspond to the known anatomy and have the highest spatial overlap across subjects. Overall, we find that it is challenging for current tractography methods to both accurately track RGVP fibers that correspond to known anatomy and produce an approximately correct percentage of decussating fibers. We suggest that future algorithm development for RGVP tractography should take consideration of both of these two points.
Zhang F, Breger A, Cho KIK, Ning L, Westin C-F, O'Donnell LJ, Pasternak O. Deep Learning Based Segmentation of Brain Tissue from Diffusion MRI. Neuroimage. 2021;233 :117934.Abstract
Segmentation of brain tissue types from diffusion MRI (dMRI) is an important task, required for quantification of brain microstructure and for improving tractography. Current dMRI segmentation is mostly based on anatomical MRI (e.g., T1- and T2-weighted) segmentation that is registered to the dMRI space. However, such inter-modality registration is challenging due to more image distortions and lower image resolution in dMRI as compared with anatomical MRI. In this study, we present a deep learning method for diffusion MRI segmentation, which we refer to as DDSeg. Our proposed method learns tissue segmentation from high-quality imaging data from the Human Connectome Project (HCP), where registration of anatomical MRI to dMRI is more precise. The method is then able to predict a tissue segmentation directly from new dMRI data, including data collected with different acquisition protocols, without requiring anatomical data and inter-modality registration. We train a convolutional neural network (CNN) to learn a tissue segmentation model using a novel augmented target loss function designed to improve accuracy in regions of tissue boundary. To further improve accuracy, our method adds diffusion kurtosis imaging (DKI) parameters that characterize non-Gaussian water molecule diffusion to the conventional diffusion tensor imaging parameters. The DKI parameters are calculated from the recently proposed mean-kurtosis-curve method that corrects implausible DKI parameter values and provides additional features that discriminate between tissue types. We demonstrate high tissue segmentation accuracy on HCP data, and also when applying the HCP-trained model on dMRI data from other acquisitions with lower resolution and fewer gradient directions.
Xu Z, Luo J, Yan J, Li X, Jayender J. F3RNet: Full-resolution Residual Registration Network for Deformable Image Registration. Int J Comput Assist Radiol Surg. 2021;16 (6) :923-32.Abstract
PURPOSE: Deformable image registration (DIR) is essential for many image-guided therapies. Recently, deep learning approaches have gained substantial popularity and success in DIR. Most deep learning approaches use the so-called mono-stream high-to-low, low-to-high network structure and can achieve satisfactory overall registration results. However, accurate alignments for some severely deformed local regions, which are crucial for pinpointing surgical targets, are often overlooked. Consequently, these approaches are not sensitive to some hard-to-align regions, e.g., intra-patient registration of deformed liver lobes. METHODS: We propose a novel unsupervised registration network, namely full-resolution residual registration network (F3RNet), for deformable registration of severely deformed organs. The proposed method combines two parallel processing streams in a residual learning fashion. One stream takes advantage of the full-resolution information that facilitates accurate voxel-level registration. The other stream learns the deep multi-scale residual representations to obtain robust recognition. We also factorize the 3D convolution to reduce the training parameters and enhance network efficiency. RESULTS: We validate the proposed method on a clinically acquired intra-patient abdominal CT-MRI dataset and a public inspiratory and expiratory thorax CT dataset. Experiments on both multimodal and unimodal registration demonstrate promising results compared to state-of-the-art approaches. CONCLUSION: By combining the high-resolution information and multi-scale representations in a highly interactive residual learning fashion, the proposed F3RNet can achieve accurate overall and local registration. The run time for registering a pair of images is less than 3 s using a GPU. In future works, we will investigate how to cost-effectively process high-resolution information and fuse multi-scale representations.
Moreira P, Grimble J, Iftimia N, Bay CP, Tuncali K, Park J, Tokuda J. In Vivo Evaluation of Angulated Needle-Guide Template for MRI-Guided Transperineal Prostate Biopsy. Med Phys. 2021;48 (5) :2553-65.Abstract
PURPOSE: Magnetic resonance imaging (MRI)-guided transperineal prostate biopsy has been practiced since the early 2000s. The technique often suffers from targeting error due to deviation of the needle as a result of physical interaction between the needle and inhomogeneous tissues. Existing needle guide devices, such as a grid template, do not allow choosing an alternative insertion path to mitigate the deviation because of their limited degree-of-freedom (DoF). This study evaluates how an angulated needle insertion path can reduce needle deviation and improve needle placement accuracy. METHODS: We extended a robotic needle-guidance device (Smart Template) for in-bore MRI-guided transperineal prostate biopsy. The new Smart Template has a 4-DoF needle-guiding mechanism allowing a translational range of motion of 65 and 58 mm along the vertical and horizontal axis, and a needle rotational motion around the vertical and horizontal axis and a vertical rotational range of , respectively. We defined a path planning strategy, which chooses between straight and angulated insertion paths depending on the anatomical structures on the potential insertion path. We performed (a) a set of experiments to evaluate the device positioning accuracy outside the MR-bore, and (b) an in vivo experiment to evaluate the improvement of targeting accuracy combining straight and angulated insertions in animal models (swine, ). RESULTS: We analyzed 46 in vivo insertions using either straight or angulated insertions paths. The experiment showed that the proposed strategy of selecting straight or angulated insertions based on the subject's anatomy outperformed the conventional approach of just straight insertions in terms of targeting accuracy (2.4 mm [1.3-3.7] vs 3.9 mm [2.4-5.0] {Median ); p = 0.041 after the bias correction). CONCLUSION: The in vivo experiment successfully demonstrated that an angulated needle insertion path could improve needle placement accuracy with a path planning strategy that takes account of the subject-specific anatomical structures.
Sedghi A, O'Donnell LJ, Kapur T, Learned-Miller E, Mousavi P, Wells WM. Image Registration: Maximum Likelihood, Minimum Entropy and Deep Learning. Med Image Anal. 2021;69 :101939.Abstract
In this work, we propose a theoretical framework based on maximum profile likelihood for pairwise and groupwise registration. By an asymptotic analysis, we demonstrate that maximum profile likelihood registration minimizes an upper bound on the joint entropy of the distribution that generates the joint image data. Further, we derive the congealing method for groupwise registration by optimizing the profile likelihood in closed form, and using coordinate ascent, or iterative model refinement. We also describe a method for feature based registration in the same framework and demonstrate it on groupwise tractographic registration. In the second part of the article, we propose an approach to deep metric registration that implements maximum likelihood registration using deep discriminative classifiers. We show further that this approach can be used for maximum profile likelihood registration to discharge the need for well-registered training data, using iterative model refinement. We demonstrate that the method succeeds on a challenging registration problem where the standard mutual information approach does not perform well.
Moreira P, Tuncali K, Tempany CM, Tokuda J. The Impact of Placement Errors on the Tumor Coverage in MRI-Guided Focal Cryoablation of Prostate Cancer. Acad Radiol. 2021;28 (6) :841-8.Abstract
RATIONALE AND OBJECTIVES: There have been multiple investigations defining and reporting the effectiveness of focal cryoablation as a treatment option for organ-confined prostate cancer. However, the impact of cryo-needle/probe placement accuracy within the tumor and gland has not been extensively studied. We analyzed how variations in the placement of the cryo-needles, specifically errors leading to incomplete ablation, may affect prostate cancer's resulting cryoablation. MATERIALS AND METHODS: We performed a study based on isothermal models using Monte Carlo simulations to analyze the impact of needle placement errors on tumor coverage and the probability of positive ablation margin. We modeled the placement error as a Gaussian noise on the cryo-needle position. The analysis used retrospective MRI data of 15 patients with biopsy-proven, unifocal, and MRI visible prostate cancer to calculate the impact of placement error on the volume of the tumor encompassed by the -40°C and -20°C isotherms using one to four cryo-needles. RESULTS: When the standard deviation of the placement error reached 3 mm, the tumor coverage was still above 97% with the -20°C isotherm, and above 81% with the -40°C isotherm using two cryo-needles or more. The probability of positive margin was significantly lower considering the -20°C isotherm (0.04 for three needles) than using the -40°C isotherm (0.66 for three needles). CONCLUSION: The results indicated that accurate cryo-needle placement is essential for the success of focal cryoablation of prostate cancer. The analysis shows that an admissible targeting error depends on the lethal temperature considered and the number of cryo-needles used.
Nitsch J, Sack J, Halle MW, Moltz JH, Wall A, Rutherford AE, Kikinis R, Meine H. MRI-Based Radiomic Feature Analysis of End-Stage Liver Disease for Severity Stratification. Int J Comput Assist Radiol Surg. 2021;16 (3) :457-66.Abstract
PURPOSE: We aimed to develop a predictive model of disease severity for cirrhosis using MRI-derived radiomic features of the liver and spleen and compared it to the existing disease severity metrics of MELD score and clinical decompensation. The MELD score is compiled solely by blood parameters, and so far, it was not investigated if extracted image-based features have the potential to reflect severity to potentially complement the calculated score. METHODS: This was a retrospective study of eligible patients with cirrhosis ([Formula: see text]) who underwent a contrast-enhanced MR screening protocol for hepatocellular carcinoma (HCC) screening at a tertiary academic center from 2015 to 2018. Radiomic feature analyses were used to train four prediction models for assessing the patient's condition at time of scan: MELD score, MELD score [Formula: see text] 9 (median score of the cohort), MELD score [Formula: see text] 15 (the inflection between the risk and benefit of transplant), and clinical decompensation. Liver and spleen segmentations were used for feature extraction, followed by cross-validated random forest classification. RESULTS: Radiomic features of the liver and spleen were most predictive of clinical decompensation (AUC 0.84), which the MELD score could predict with an AUC of 0.78. Using liver or spleen features alone had slightly lower discrimination ability (AUC of 0.82 for liver and AUC of 0.78 for spleen features only), although this was not statistically significant on our cohort. When radiomic prediction models were trained to predict continuous MELD scores, there was poor correlation. When stratifying risk by splitting our cohort at the median MELD 9 or at MELD 15, our models achieved AUCs of 0.78 or 0.66, respectively. CONCLUSIONS: We demonstrated that MRI-based radiomic features of the liver and spleen have the potential to predict the severity of liver cirrhosis, using decompensation or MELD status as imperfect surrogate measures for disease severity.
Tempany-Afdhal CMC. Focal Treatment of Prostate Cancer: MRI Helps Guide the Way Forward. Editorial. Radiology. 2021;298 (3) :704-6.
Noh T, Mustroph M, Golby AJ. Intraoperative Imaging for High-Grade Glioma Surgery. Neurosurg Clin N Am. 2021;32 (1) :47-54.Abstract
This article discusses intraoperative imaging techniques used during high-grade glioma surgery. Gliomas can be difficult to differentiate from surrounding tissue during surgery. Intraoperative imaging helps to alleviate problems encountered during glioma surgery, such as brain shift and residual tumor. There are a variety of modalities available all of which aim to give the surgeon more information, address brain shift, identify residual tumor, and increase the extent of surgical resection. The article starts with a brief introduction followed by a review of with the latest advances in intraoperative ultrasound, intraoperative MRI, and intraoperative computed tomography.