Prof. Michael R. Savona Profile

Prof. Michael R. Savona

at Vanderbilt Univ Medical Ctr

SPIE Involvement:

Author

Publications (7)

SPIE Journal Paper | 19 February 2021

Validation and estimation of spleen volume via computer-assisted segmentation on clinically acquired CT scans

Yiyuan Yang, Yucheng Tang, Riqiang Gao, Shunxing Bao, Yuankai Huo, Matthew T. McKenna, Michael Savona, Richard Abramson, Bennett Landman

JMI, Vol. 8, Issue 01, 014004, (February 2021) https://doi.org/10.1117/12.10.1117/1.JMI.8.1.014004

KEYWORDS: Spleen, Image segmentation, Computed tomography, Evolutionary algorithms, Convolutional neural networks, Medicine, Image resolution, Image processing, 3D modeling, 3D metrology

Read Abstract +

SPIE Journal Paper | 30 July 2020

Learning from dispersed manual annotations with an optimized data weighting policy

Yucheng Tang, Riqiang Gao, Yunqiang Chen, Dashan Gao, Michael Savona, Richard Abramson, Shunxing Bao, Yuankai Huo, Bennett Landman

JMI, Vol. 7, Issue 04, 044002, (July 2020) https://doi.org/10.1117/12.10.1117/1.JMI.7.4.044002

KEYWORDS: Spleen, Data modeling, Liver, Image segmentation, Computed tomography, Machine learning, Stochastic processes, Kidney, Mining

Read Abstract +

Proceedings Article | 10 March 2020 Presentation + Paper

Contrast phase classification with a generative adversarial network

Yucheng Tang, Ho Hin Lee, Yuchen Xu, Olivia Tang, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Camilo Bermudez, Michael Savona, Richard Abramson, Yuankai Huo, Bennett Landman

Proceedings Volume 11313, 1131310 (2020) https://doi.org/10.1117/12.2549438

KEYWORDS: Image classification, Computed tomography, Gallium nitride, Image enhancement, Image contrast enhancement, Tissues, Heart, Kidney, Urinary system, Computer programming

Read Abstract +

Dynamic contrast enhanced computed tomography (CT) is an imaging technique that provides critical information on the relationship of vascular structure and dynamics in the context of underlying anatomy. A key challenge for image processing with contrast enhanced CT is that phase discrepancies are latent in different tissues due to contrast protocols, vascular dynamics, and metabolism variance. Previous studies with deep learning frameworks have been proposed for classifying contrast enhancement with networks inspired by computer vision. Here, we revisit the challenge in the context of whole abdomen contrast enhanced CTs. To capture and compensate for the complex contrast changes, we propose a novel discriminator in the form of a multi-domain disentangled representation learning network. The goal of this network is to learn an intermediate representation that separates contrast enhancement from anatomy and enables classification of images with varying contrast time. Briefly, our unpaired contrast disentangling GAN(CD-GAN) Discriminator follows the ResNet architecture to classify a CT scan from different enhancement phases. To evaluate the approach, we trained the enhancement phase classifier on 21060 slices from two clinical cohorts of 230 subjects. The scans were manually labeled with three independent enhancement phases (non-contrast, portal venous and delayed). Testing was performed on 9100 slices from 30 independent subjects who had been imaged with CT scans from all contrast phases. Performance was quantified in terms of the multi-class normalized confusion matrix. The proposed network significantly improved correspondence over baseline UNet, ResNet50 and StarGAN’s performance of accuracy scores 0.54. 0.55, 0.62 and 0.91, respectively (p-value<0.0001 paired t-test for ResNet versus CD-GAN). The proposed discriminator from the disentangled network presents a promising technique that may allow deeper modeling of dynamic imaging against patient specific anatomies.

Proceedings Article | 10 March 2020 Paper

Outlier guided optimization of abdominal segmentation

Yuchen Xu, Olivia Tang, Yucheng Tang, Ho Hin Lee, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael Savona, Richard Abramson, Yuankai Huo, Bennett Landman

Proceedings Volume 11313, 1131336 (2020) https://doi.org/10.1117/12.2549365

KEYWORDS: Data modeling, Image segmentation, Pancreas, 3D modeling, Image processing algorithms and systems, Computed tomography, Medical imaging, Abdomen, Visualization, Spleen

Read Abstract +

Proceedings Article | 10 March 2020 Presentation + Paper

Semi-supervised multi-organ segmentation through quality assurance supervision

Ho Hin Lee, Yucheng Tang, Olivia Tang, Yuchen Xu, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael Savona, Richard Abramson, Yuankai Huo, Bennett Landman

Proceedings Volume 11313, 113131I (2020) https://doi.org/10.1117/12.2549033

KEYWORDS: Image segmentation, Image quality, 3D modeling, Medical imaging, Data modeling, 3D image processing, Performance modeling, Image processing, Kidney, Spleen

Read Abstract +

Human in-the-loop quality assurance (QA) is typically performed after medical image segmentation to ensure that the systems are performing as intended, as well as identifying and excluding outliers. By performing QA on large-scale, previously unlabeled testing data, categorical QA scores (e.g. “successful” versus “unsuccessful”) can be generated. Unfortunately, the precious use of resources for human in-the-loop QA scores are not typically reused in medical image machine learning, especially to train a deep neural network for image segmentation. Herein, we perform a pilot study to investigate if the QA labels can be used as supplementary supervision to augment the training process in a semi-supervised fashion. In this paper, we propose a semi-supervised multi-organ segmentation deep neural network consisting of a traditional segmentation model generator and a QA involved discriminator. An existing 3-D abdominal segmentation network is employed, while the pre-trained ResNet-18 network is used as discriminator. A large-scale dataset of 2027 volumes are used to train the generator, whose 2-D montage images and segmentation mask with QA scores are used to train the discriminator. To generate the QA scores, the 2-D montage images were reviewed manually and coded 0 (success), 1 (errors consistent with published performance), and 2 (gross failure). Then, the ResNet-18 network was trained with 1623 montage images in equal distribution of all three code labels and achieved an accuracy 94% for classification predictions with 404 montage images withheld for the test cohort. To assess the performance of using the QA supervision, the discriminator was used as a loss function in a multi-organ segmentation pipeline. The inclusion of QA-loss function boosted performance on the unlabeled test dataset from 714 patients to 951 patients over the baseline model. Additionally, the number of failures decreased from 606 (29.90%) to 402 (19.83%). The contributions of the proposed method are threefold: We show that (1) the QA scores can be used as a loss function to perform semi-supervised learning for unlabeled data, (2) the well trained discriminator is learnt by QA score rather than traditional “true/false”, and (3) the performance of multi-organ segmentation on unlabeled datasets can be fine-tuned with more robust and higher accuracy than the original baseline method. The use of QA-inspired loss functions represents a promising area of future research and may permit tighter integration of supervised and semi-supervised learning.

Proceedings Article | 10 March 2020 Paper

Validation and optimization of multi-organ segmentation on clinical imaging archives

Olivia Tang, Yuchen Xu, Yucheng Tang, Ho Hin Lee, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael Savona, Richard Abramson, Yuankai Huo, Bennett Landman

Proceedings Volume 11313, 113132O (2020) https://doi.org/10.1117/12.2549035

KEYWORDS: Image segmentation, Liver, Gallbladder, 3D modeling, Computed tomography, Spleen, Data modeling, 3D image processing, Contamination, Abdomen

Read Abstract +

Proceedings Article | 15 March 2019 Presentation + Paper

Improving splenomegaly segmentation by learning from heterogeneous multi-source labels

Yucheng Tang, Yuankai Huo, Yunxi Xiong, Hyeonsoo Moon, Albert Assad, Tamara Moyo, Michael Savona, Richard Abramson, Bennett Landman

Proceedings Volume 10949, 1094908 (2019) https://doi.org/10.1117/12.2512842

KEYWORDS: Spleen, Image segmentation, Computed tomography, Connectors, Network architectures, Convolutional neural networks, Computer programming, Abdomen, Liver, Magnetic resonance imaging

Read Abstract +

Splenomegaly segmentation on computed tomography (CT) abdomen anatomical scans is essential for identifying spleen biomarkers and has applications for quantitative assessment in patients with liver and spleen disease. Deep convolutional neural network automated segmentation has shown promising performance for splenomegaly segmentation. However, manual labeling of abdominal structures is resource intensive, so the labeled abdominal imaging data are rare resources despite their essential role in algorithm training. Hence, the number of annotated labels (e.g., spleen only) are typically limited with a single study. However, with the development of data sharing techniques, more and more publicly available labeled cohorts are available from different resources. A key new challenging is to co-learn from the multi-source data, even with different numbers of labeled abdominal organs in each study. Thus, it is appealing to design a co-learning strategy to train a deep network from heterogeneously labeled scans. In this paper, we propose a new deep convolutional neural network (DCNN) based method that integrates heterogeneous multi-resource labeled cohorts for splenomegaly segmentation. To enable the proposed approach, a novel loss function is introduced based on the Dice similarity coefficient to adaptively learn multi-organ information from different resources. Three cohorts were employed in our experiments, the first cohort (98 CT scans) has only splenomegaly labels, while the second training cohort (100 CT scans) has 15 distinct anatomical labels with normal spleens. A separate, independent cohort consisting of 19 splenomegaly CT scans with labeled spleen was used as testing cohort. The proposed method achieved the highest median Dice similarity coefficient value (0.94), which is superior (p-value<0.01 against each other method) to the baselines of multi-atlas segmentation (0.86), SS-Net segmentation with only spleen labels (0.90) and U-Net segmentation with multi-organ training (0.91). Our approach for adapting the loss function and training structure is not specific to the abdominal context and may be beneficial in other situations where datasets with varied label sets are available.

Showing 5 of 7 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years