1
|
Luo H, Li J, Huang H, Jiao L, Zheng S, Ying Y, Li Q. AI-based segmentation of renal enhanced CT images for quantitative evaluate of chronic kidney disease. Sci Rep 2024; 14:16890. [PMID: 39043766 PMCID: PMC11266695 DOI: 10.1038/s41598-024-67658-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2024] [Accepted: 07/15/2024] [Indexed: 07/25/2024] Open
Abstract
To quantitatively evaluate chronic kidney disease (CKD), a deep convolutional neural network-based segmentation model was applied to renal enhanced computed tomography (CT) images. A retrospective analysis was conducted on a cohort of 100 individuals diagnosed with CKD and 90 individuals with healthy kidneys, who underwent contrast-enhanced CT scans of the kidneys or abdomen. Demographic and clinical data were collected from all participants. The study consisted of two distinct stages: firstly, the development and validation of a three-dimensional (3D) nnU-Net model for segmenting the arterial phase of renal enhanced CT scans; secondly, the utilization of the 3D nnU-Net model for quantitative evaluation of CKD. The 3D nnU-Net model achieved a mean Dice Similarity Coefficient (DSC) of 93.53% for renal parenchyma and 81.48% for renal cortex. Statistically significant differences were observed among different stages of renal function for renal parenchyma volume (VRP), renal cortex volume (VRC), renal medulla volume (VRM), the CT values of renal parenchyma (HuRP), the CT values of renal cortex (HuRC), and the CT values of renal medulla (HuRM) (F = 93.476, 144.918, 9.637, 170.533, 216.616, and 94.283; p < 0.001). Pearson correlation analysis revealed significant positive associations between glomerular filtration rate (eGFR) and VRP, VRC, VRM, HuRP, HuRC, and HuRM (r = 0.749, 0.818, 0.321, 0.819, 0.820, and 0.747, respectively, all p < 0.001). Similarly, a negative correlation was observed between serum creatinine (Scr) levels and VRP, VRC, VRM, HuRP, HuRC, and HuRM (r = - 0.759, - 0.777, - 0.420, - 0.762, - 0.771, and - 0.726, respectively, all p < 0.001). For predicting CKD in males, VRP had an area under the curve (AUC) of 0.726, p < 0.001; VRC, AUC 0.765, p < 0.001; VRM, AUC 0.578, p = 0.018; HuRP, AUC 0.912, p < 0.001; HuRC, AUC 0.952, p < 0.001; and HuRM, AUC 0.772, p < 0.001 in males. In females, VRP had an AUC of 0.813, p < 0.001; VRC, AUC 0.851, p < 0.001; VRM, AUC 0.623, p = 0.060; HuRP, AUC 0.904, p < 0.001; HuRC, AUC 0.934, p < 0.001; and HuRM, AUC 0.840, p < 0.001. The optimal cutoff values for predicting CKD in HuRP are 99.9 Hu for males and 98.4 Hu for females, while in HuRC are 120.1 Hu for males and 111.8 Hu for females. The kidney was effectively segmented by our AI-based 3D nnU-Net model for enhanced renal CT images. In terms of mild kidney injury, the CT values exhibited higher sensitivity compared to kidney volume. The correlation analysis revealed a stronger association between VRC, HuRP, and HuRC with renal function, while the association between VRP and HuRM was weaker, and the association between VRM was the weakest. Particularly, HuRP and HuRC demonstrated significant potential in predicting renal function. For diagnosing CKD, it is recommended to set the threshold values as follows: HuRP < 99.9 Hu and HuRC < 120.1 Hu in males, and HuRP < 98.4 Hu and HuRC < 111.8 Hu in females.
Collapse
Affiliation(s)
- Hui Luo
- Department of Radiology, Ningbo Yinzhou Second Hospital, Ningbo, China
| | - Jingzhen Li
- Department of Nephrology, Ningbo Yinzhou Second Hospital, Ningbo, China
| | - Haiyang Huang
- Department of Radiology, Ningbo Yinzhou Second Hospital, Ningbo, China
| | - Lianghong Jiao
- Department of Radiology, Ningbo Yinzhou Second Hospital, Ningbo, China
| | - Siyuan Zheng
- Department of Radiology, Ningbo Yinzhou Second Hospital, Ningbo, China
| | - Yibo Ying
- Department of Radiology, Ningbo Yinzhou Second Hospital, Ningbo, China
| | - Qiang Li
- Department of Radiology, The Affiliated People's Hospital of Ningbo University, Ningbo, 315000, China.
| |
Collapse
|
2
|
Ha S, Park BS, Han S, Oh JS, Chae SY, Kim JS, Moon DH. Deep learning-based measurement of split glomerular filtration rate with 99mTc-diethylenetriamine pentaacetic acid renal scan. EJNMMI Phys 2024; 11:64. [PMID: 39017817 PMCID: PMC11254887 DOI: 10.1186/s40658-024-00664-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2024] [Accepted: 06/27/2024] [Indexed: 07/18/2024] Open
Abstract
PURPOSE To develop a deep learning (DL) model for generating automated regions of interest (ROIs) on 99mTc-diethylenetriamine pentaacetic acid (DTPA) renal scans for glomerular filtration rate (GFR) measurement. METHODS Manually-drawn ROIs retrieved from a Picture Archiving and Communications System were used as ground-truth (GT) labels. A two-dimensional U-Net convolutional neural network architecture with multichannel input was trained to generate DL ROIs. The agreement between GFR values from GT and DL ROIs was evaluated using Lin's concordance correlation coefficient (CCC) and slope coefficients for linear regression analyses. Bias and 95% limits of agreement (LOA) were assessed using Bland-Altman plots. RESULTS A total of 24,364 scans (12,822 patients) were included. Excellent concordance between GT and DL GFR was found for left (CCC 0.982, 95% confidence interval [CI] 0.981-0.982; slope 1.004, 95% CI 1.003-1.004), right (CCC 0.969, 95% CI 0.968-0.969; slope 0.954, 95% CI 0.953-0.955) and both kidneys (CCC 0.978, 95% CI 0.978-0.979; slope 0.979, 95% CI 0.978-0.979). Bland-Altman analysis revealed minimal bias between GT and DL GFR, with mean differences of - 0.2 (95% LOA - 4.4-4.0), 1.4 (95% LOA - 3.5-6.3) and 1.2 (95% LOA - 6.5-8.8) mL/min/1.73 m² for left, right and both kidneys, respectively. Notably, 19,960 scans (81.9%) showed an absolute difference in GFR of less than 5 mL/min/1.73 m². CONCLUSION Our DL model exhibited excellent performance in the generation of ROIs on 99mTc-DTPA renal scans. This automated approach could potentially reduce manual effort and enhance the precision of GFR measurement in clinical practice.
Collapse
Affiliation(s)
- Sejin Ha
- Department of Nuclear Medicine, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea
- Department of Nuclear Medicine, Korea University Anam Hospital, Korea University College of Medicine, Seongbuk-gu, Seoul, 02841, Republic of Korea
| | - Byung Soo Park
- Department of Nuclear Medicine, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea
| | - Sangwon Han
- Department of Nuclear Medicine, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea.
| | - Jungsu S Oh
- Department of Nuclear Medicine, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea.
| | - Sun Young Chae
- Department of Nuclear Medicine, Uijeongbu Eulji Medical Center, Eulji University School of Medicine, Uijeongbu, 05505, Republic of Korea
| | - Jae Seung Kim
- Department of Nuclear Medicine, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea
| | - Dae Hyuk Moon
- Department of Nuclear Medicine, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, 05505, Republic of Korea
| |
Collapse
|
3
|
Niendorf T, Gladytz T, Cantow K, Klein T, Tasbihi E, Velasquez Vides JR, Zhao K, Millward JM, Waiczies S, Seeliger E. MRI of kidney size matters. MAGMA (NEW YORK, N.Y.) 2024:10.1007/s10334-024-01168-5. [PMID: 38960988 DOI: 10.1007/s10334-024-01168-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/15/2024] [Revised: 05/06/2024] [Accepted: 05/15/2024] [Indexed: 07/05/2024]
Abstract
OBJECTIVE To highlight progress and opportunities of measuring kidney size with MRI, and to inspire research into resolving the remaining methodological gaps and unanswered questions relating to kidney size assessment. MATERIALS AND METHODS This work is not a comprehensive review of the literature but highlights valuable recent developments of MRI of kidney size. RESULTS The links between renal (patho)physiology and kidney size are outlined. Common methodological approaches for MRI of kidney size are reviewed. Techniques tailored for renal segmentation and quantification of kidney size are discussed. Frontier applications of kidney size monitoring in preclinical models and human studies are reviewed. Future directions of MRI of kidney size are explored. CONCLUSION MRI of kidney size matters. It will facilitate a growing range of (pre)clinical applications, and provide a springboard for new insights into renal (patho)physiology. As kidney size can be easily obtained from already established renal MRI protocols without the need for additional scans, this measurement should always accompany diagnostic MRI exams. Reconciling global kidney size changes with alterations in the size of specific renal layers is an important topic for further research. Acute kidney size measurements alone cannot distinguish between changes induced by alterations in the blood or the tubular volume fractions-this distinction requires further research into cartography of the renal blood and the tubular volumes.
Collapse
Affiliation(s)
- Thoralf Niendorf
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Robert-Rössle-Str. 10, 13125, Berlin, Germany.
- Experimental and Clinical Research Center, A Joint Cooperation Between the Charité Medical Faculty and the Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany.
| | - Thomas Gladytz
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Robert-Rössle-Str. 10, 13125, Berlin, Germany
| | - Kathleen Cantow
- Institute of Translational Physiology, Charité-Universitätsmedizin Berlin, Campus Mitte, Berlin, Germany
| | - Tobias Klein
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Robert-Rössle-Str. 10, 13125, Berlin, Germany
- Experimental and Clinical Research Center, A Joint Cooperation Between the Charité Medical Faculty and the Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
- Digital Health-Machine Learning Research Group, Hasso Plattner Institute for Digital Engineering, University of Potsdam, Potsdam, Germany
| | - Ehsan Tasbihi
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Robert-Rössle-Str. 10, 13125, Berlin, Germany
- Charité-Universitätsmedizin Berlin, Berlin, Germany
| | - Jose Raul Velasquez Vides
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Robert-Rössle-Str. 10, 13125, Berlin, Germany
- Institute for Medical Engineering, Otto Von Guericke University, Magdeburg, Germany
| | - Kaixuan Zhao
- Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Department of Radiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Southern Medical University, Guangzhou, China
- Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Jason M Millward
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Robert-Rössle-Str. 10, 13125, Berlin, Germany
- Experimental and Clinical Research Center, A Joint Cooperation Between the Charité Medical Faculty and the Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Sonia Waiczies
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Robert-Rössle-Str. 10, 13125, Berlin, Germany
- Experimental and Clinical Research Center, A Joint Cooperation Between the Charité Medical Faculty and the Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Erdmann Seeliger
- Institute of Translational Physiology, Charité-Universitätsmedizin Berlin, Campus Mitte, Berlin, Germany
| |
Collapse
|
4
|
Hild O, Berriet P, Nallet J, Salvi L, Lenoir M, Henriet J, Thiran JP, Auber F, Chaussy Y. Automation of Wilms' tumor segmentation by artificial intelligence. Cancer Imaging 2024; 24:83. [PMID: 38956718 PMCID: PMC11218149 DOI: 10.1186/s40644-024-00729-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2024] [Accepted: 06/20/2024] [Indexed: 07/04/2024] Open
Abstract
BACKGROUND 3D reconstruction of Wilms' tumor provides several advantages but are not systematically performed because manual segmentation is extremely time-consuming. The objective of our study was to develop an artificial intelligence tool to automate the segmentation of tumors and kidneys in children. METHODS A manual segmentation was carried out by two experts on 14 CT scans. Then, the segmentation of Wilms' tumor and neoplastic kidney was automatically performed using the CNN U-Net and the same CNN U-Net trained according to the OV2ASSION method. The time saving for the expert was estimated depending on the number of sections automatically segmented. RESULTS When segmentations were performed manually by two experts, the inter-individual variability resulted in a Dice index of 0.95 for tumor and 0.87 for kidney. Fully automatic segmentation with the CNN U-Net yielded a poor Dice index of 0.69 for Wilms' tumor and 0.27 for kidney. With the OV2ASSION method, the Dice index varied depending on the number of manually segmented sections. For the segmentation of the Wilms' tumor and neoplastic kidney, it varied respectively from 0.97 to 0.94 for a gap of 1 (2 out of 3 sections performed manually) to 0.94 and 0.86 for a gap of 10 (1 section out of 6 performed manually). CONCLUSION Fully automated segmentation remains a challenge in the field of medical image processing. Although it is possible to use already developed neural networks, such as U-Net, we found that the results obtained were not satisfactory for segmentation of neoplastic kidneys or Wilms' tumors in children. We developed an innovative CNN U-Net training method that makes it possible to segment the kidney and its tumor with the same precision as an expert while reducing their intervention time by 80%.
Collapse
Affiliation(s)
- Olivier Hild
- Department of Pediatric Surgery, CHU Besançon, 3 boulevard Fleming, Besançon, F-25000, France
| | - Pierre Berriet
- Université de Franche-Comté, FEMTO-ST Institute, DISC, Besançon, F-25000, France
| | - Jérémie Nallet
- Department of Pediatric Surgery, CHU Besançon, 3 boulevard Fleming, Besançon, F-25000, France
| | - Lorédane Salvi
- Department of Pediatric Surgery, CHU Besançon, 3 boulevard Fleming, Besançon, F-25000, France
| | - Marion Lenoir
- Department of Radiology, CHU Besançon, Besançon, F-25000, France
| | - Julien Henriet
- Université de Franche-Comté, FEMTO-ST Institute, DISC, Besançon, F-25000, France
| | - Jean-Philippe Thiran
- Signal Processing Laboratory 5 (LTS5), Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, 1015, Switzerland
- University Hospital Center (CHUV) and University of Lausanne (UNIL), Lausanne, 1011, Switzerland
| | - Frédéric Auber
- Department of Pediatric Surgery, CHU Besançon, 3 boulevard Fleming, Besançon, F-25000, France
- Université de Franche-Comté, SINERGIES, Besançon, F-25000, France
| | - Yann Chaussy
- Department of Pediatric Surgery, CHU Besançon, 3 boulevard Fleming, Besançon, F-25000, France.
- Université de Franche-Comté, SINERGIES, Besançon, F-25000, France.
| |
Collapse
|
5
|
Kim Y, Bu S, Tao C, Bae KT. Deep Learning-Based Automated Imaging Classification of ADPKD. Kidney Int Rep 2024; 9:1802-1809. [PMID: 38899202 PMCID: PMC11184252 DOI: 10.1016/j.ekir.2024.04.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2023] [Revised: 03/20/2024] [Accepted: 04/01/2024] [Indexed: 06/21/2024] Open
Abstract
Introduction The Mayo imaging classification model (MICM) requires a prestep qualitative assessment to determine whether a patient is in class 1 (typical) or class 2 (atypical), where patients assigned to class 2 are excluded from the MICM application. Methods We developed a deep learning-based method to automatically classify class 1 and 2 from magnetic resonance (MR) images and provide classification confidence utilizing abdominal T 2 -weighted MR images from 486 subjects, where transfer learning was applied. In addition, the explainable artificial intelligence (XAI) method was illustrated to enhance the explainability of the automated classification results. For performance evaluations, confusion matrices were generated, and receiver operating characteristic curves were drawn to measure the area under the curve. Results The proposed method showed excellent performance for the classification of class 1 (97.7%) and 2 (100%), where the combined test accuracy was 98.01%. The precision and recall for predicting class 1 were 1.00 and 0.98, respectively, with F 1 -score of 0.99; whereas those for predicting class 2 were 0.87 and 1.00, respectively, with F 1 -score of 0.93. The weighted averages of precision and recall were 0.98 and 0.98, respectively, showing the classification confidence scores whereas the XAI method well-highlighted contributing regions for the classification. Conclusion The proposed automated method can classify class 1 and 2 cases as accurately as the level of a human expert. This method may be a useful tool to facilitate clinical trials investigating different types of kidney morphology and for clinical management of patients with autosomal dominant polycystic kidney disease (ADPKD).
Collapse
Affiliation(s)
- Youngwoo Kim
- Department of Computer Software Engineering, Kumoh National Institute of Technology, Republic of Korea
| | - Seonah Bu
- Jeju Technology Application Division, Korea Institute of Industrial Technology, Republic of Korea
| | - Cheng Tao
- Department of Radiology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania, USA
| | - Kyongtae T. Bae
- Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Pok Fu Lam, Hong Kong
| |
Collapse
|
6
|
Kellner E, Sekula P, Lipovsek J, Russe M, Horbach H, Schlett CL, Nauck M, Völzke H, Kroencke T, Bette S, Kauczor HU, Keil T, Pischon T, Heid IM, Peters A, Niendorf T, Lieb W, Bamberg F, Büchert M, Reichardt W, Reisert M, Köttgen A. Imaging Markers Derived From MRI-Based Automated Kidney Segmentation. DEUTSCHES ARZTEBLATT INTERNATIONAL 2024; 121:284-290. [PMID: 38530931 DOI: 10.3238/arztebl.m2024.0040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/07/2023] [Revised: 02/19/2024] [Accepted: 02/19/2024] [Indexed: 03/28/2024]
Abstract
BACKGROUND Population-wide research on potential new imaging biomarkers of the kidney depends on accurate automated segmentation of the kidney and its compartments (cortex, medulla, and sinus). METHODS We developed a robust deep-learning framework for kidney (sub-)segmentation based on a hierarchical, three-dimensional convolutional neural network (CNN) that was optimized for multiscale problems of combined localization and segmentation. We applied the CNN to abdominal magnetic resonance images from the population-based German National Cohort (NAKO) study. RESULTS There was good to excellent agreement between the model predictions and manual segmentations. The median values for the body-surface normalized total kidney, cortex, medulla, and sinus volumes of 9934 persons were 158, 115, 43, and 24 mL/m2. Distributions of these markers are provided both for the overall study population and for a subgroup of persons without kidney disease or any associated conditions. Multivariable adjusted regression analyses revealed that diabetes, male sex, and a higher estimated glomerular filtration rate (eGFR) are important predictors of higher total and cortical volumes. Each increase of eGFR by one unit (i.e., 1 mL/min per 1.73 m2 body surface area) was associated with a 0.98 mL/m2 increase in total kidney volume, and this association was significant. Volumes were lower in persons with eGFR-defined chronic kidney disease. CONCLUSION The extraction of image-based biomarkers through CNN-based renal sub-segmentation using data from a population-based study yields reliable results, forming a solid foundation for future investigations.
Collapse
Affiliation(s)
- Elias Kellner
- Division of Medical Physics, Department of Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; Institute of Genetic Epidemiology, Faculty of Medicine and Medical Center - University of Freiburg, Freiburg, Germany; Division of Medical Physics, Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; Institute of Genetic Epidemiology, Faculty of Medicine and Medical Center - University of Freiburg, Freiburg, Germany; Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg, Faculty of Medicine, Albert-Ludwigs-University Freiburg, Germany; Institute of Clinical Chemistry and Laboratory Medicine, University Medicine Greifswald, Germany; DZHK (German Centre for Cardiovascular Research), Partner Site Greifswald, University Medicine Greifswald, Germany; Institute for Community Medicine, University Medicine Greifswald, Germany; Department of Diagnostic and Interventional Radiology, University Hospital Augsburg, Germany; Centre for Advanced Analytics and Predictive Sciences (CAAPS), University of Augsburg, Germany; Department of Diagnostical and Interventional Radiology, University Hospital Heidelberg, Germany; Institute of Social Medicine, Epidemiology and Health Economics, Charité - Universitätsmedizin Berlin, Institute of Clinical Epidemiology and Biometry, University of Würzburg, State Institute of Health I, Bavarian Health and Food Safety Authority, Erlangen, Germany; Max-Delbrueck-Center for Molecular Medicine in the Helmholtz Association (MDC), Molecular Epidemiology Research Group; Max-Delbrueck-Center for Molecular Medicine in the Helmholtz Association (MDC), Biobank Technology Platform, Berlin; Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Germany; Chair of Genetic Epidemiology, University of Regensburg, Germany; Institute of Epidemiology, Helmholtz Center Munich, German Research Center for Environmental Health, Neuherberg; Chair of Epidemiology, Institute for Medical Information Processing, Biometrics, and Epidemiology, Medical Faculty, Ludwig-Maximilians-University Munich; DZHK (German Centre for Cardiovascular Research), Partner Site Munich, Munich Heart Alliance, Munich; DZD (German Centre for Diabetes Research), Neuherberg; Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin; Institute of Epidemiology, Kiel University, Kiel, Germany; Department of Diagnostic and Interventional Radiology, Core Facility MRDAC, University Medical Center Freiburg, Faculty of Medicine, Albert-Ludwigs-University Freiburg, Germany
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
7
|
Jeon SK, Joo I, Park J, Kim JM, Park SJ, Yoon SH. Fully-automated multi-organ segmentation tool applicable to both non-contrast and post-contrast abdominal CT: deep learning algorithm developed using dual-energy CT images. Sci Rep 2024; 14:4378. [PMID: 38388824 PMCID: PMC10883917 DOI: 10.1038/s41598-024-55137-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Accepted: 02/20/2024] [Indexed: 02/24/2024] Open
Abstract
A novel 3D nnU-Net-based of algorithm was developed for fully-automated multi-organ segmentation in abdominal CT, applicable to both non-contrast and post-contrast images. The algorithm was trained using dual-energy CT (DECT)-obtained portal venous phase (PVP) and spatiotemporally-matched virtual non-contrast images, and tested using a single-energy (SE) CT dataset comprising PVP and true non-contrast (TNC) images. The algorithm showed robust accuracy in segmenting the liver, spleen, right kidney (RK), and left kidney (LK), with mean dice similarity coefficients (DSCs) exceeding 0.94 for each organ, regardless of contrast enhancement. However, pancreas segmentation demonstrated slightly lower performance with mean DSCs of around 0.8. In organ volume estimation, the algorithm demonstrated excellent agreement with ground-truth measurements for the liver, spleen, RK, and LK (intraclass correlation coefficients [ICCs] > 0.95); while the pancreas showed good agreements (ICC = 0.792 in SE-PVP, 0.840 in TNC). Accurate volume estimation within a 10% deviation from ground-truth was achieved in over 90% of cases involving the liver, spleen, RK, and LK. These findings indicate the efficacy of our 3D nnU-Net-based algorithm, developed using DECT images, which provides precise segmentation of the liver, spleen, and RK and LK in both non-contrast and post-contrast CT images, enabling reliable organ volumetry, albeit with relatively reduced performance for the pancreas.
Collapse
Affiliation(s)
- Sun Kyung Jeon
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| | - Ijin Joo
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Korea.
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea.
- Institute of Radiation Medicine, Seoul National University Medical Research Center Seoul National University Hospital, Seoul, Korea.
| | - Junghoan Park
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
| | | | | | - Soon Ho Yoon
- Department of Radiology, Seoul National University Hospital, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, Korea
- MEDICALIP. Co. Ltd., Seoul, Korea
| |
Collapse
|
8
|
R SSRM, T J. Multi-Scale and Spatial Information Extraction for Kidney Tumor Segmentation: A Contextual Deformable Attention and Edge-Enhanced U-Net. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:151-166. [PMID: 38343255 DOI: 10.1007/s10278-023-00900-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/23/2023] [Revised: 09/04/2023] [Accepted: 09/05/2023] [Indexed: 03/02/2024]
Abstract
Kidney tumor segmentation is a difficult task because of the complex spatial and volumetric information present in medical images. Recent advances in deep convolutional neural networks (DCNNs) have improved tumor segmentation accuracy. However, the practical usability of current CNN-based networks is constrained by their high computational complexity. Additionally, these techniques often struggle to make adaptive modifications based on the structure of the tumors, which can lead to blurred edges in segmentation results. A lightweight architecture called the contextual deformable attention and edge-enhanced U-Net (CDA2E-Net) for high-accuracy pixel-level kidney tumor segmentation is proposed to address these challenges. Rather than using complex deep encoders, the approach includes a lightweight depthwise dilated ShuffleNetV2 (LDS-Net) encoder integrated into the CDA2E-Net framework. The proposed method also contains a multiscale attention feature pyramid pooling (MAF2P) module that improves the ability of multiscale features to adapt to various tumor shapes. Finally, an edge-enhanced loss function is introduced to guide the CDA2E-Net to concentrate on tumor edge information. The CDA2E-Net is evaluated on the KiTS19 and KiTS21 datasets, and the results demonstrate its superiority over existing approaches in terms of Hausdorff distance (HD), intersection over union (IoU), and dice coefficient (DSC) metrics.
Collapse
Affiliation(s)
- Shamija Sherryl R M R
- Department of Electronics & Communication Engineering, Ponjesly College of Engineering, Nagercoil, Tamil Nadu, India.
| | - Jaya T
- Department of Electronics & Communication Engineering, Saveetha Engineering College, Thandalam, India
| |
Collapse
|
9
|
Müller L, Tibyampansha D, Mildenberger P, Panholzer T, Jungmann F, Halfmann MC. Convolutional neural network-based kidney volume estimation from low-dose unenhanced computed tomography scans. BMC Med Imaging 2023; 23:187. [PMID: 37968580 PMCID: PMC10648730 DOI: 10.1186/s12880-023-01142-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2022] [Accepted: 10/27/2023] [Indexed: 11/17/2023] Open
Abstract
PURPOSE Kidney volume is important in the management of renal diseases. Unfortunately, the currently available, semi-automated kidney volume determination is time-consuming and prone to errors. Recent advances in its automation are promising but mostly require contrast-enhanced computed tomography (CT) scans. This study aimed at establishing an automated estimation of kidney volume in non-contrast, low-dose CT scans of patients with suspected urolithiasis. METHODS The kidney segmentation process was automated with 2D Convolutional Neural Network (CNN) models trained on manually segmented 2D transverse images extracted from low-dose, unenhanced CT scans of 210 patients. The models' segmentation accuracy was assessed using Dice Similarity Coefficient (DSC), for the overlap with manually-generated masks on a set of images not used in the training. Next, the models were applied to 22 previously unseen cases to segment kidney regions. The volume of each kidney was calculated from the product of voxel number and their volume in each segmented mask. Kidney volume results were then validated against results semi-automatically obtained by radiologists. RESULTS The CNN-enabled kidney volume estimation took a mean of 32 s for both kidneys in a CT scan with an average of 1026 slices. The DSC was 0.91 and 0.86 and for left and right kidneys, respectively. Inter-rater variability had consistencies of ICC = 0.89 (right), 0.92 (left), and absolute agreements of ICC = 0.89 (right), 0.93 (left) between the CNN-enabled and semi-automated volume estimations. CONCLUSION In our work, we demonstrated that CNN-enabled kidney volume estimation is feasible and highly reproducible in low-dose, non-enhanced CT scans. Automatic segmentation can thereby quantitatively enhance radiological reports.
Collapse
Affiliation(s)
- Lukas Müller
- Department of Diagnostic and Interventional Radiology, University Medical Center of the Johannes Gutenberg University Mainz, Langenbeckst, 1, 55131, Mainz, Germany
| | - Dativa Tibyampansha
- Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Center of the Johannes Gutenberg University Mainz, Obere Zahlbacher Str. 69, 55131, Mainz, Germany
| | - Peter Mildenberger
- Department of Diagnostic and Interventional Radiology, University Medical Center of the Johannes Gutenberg University Mainz, Langenbeckst, 1, 55131, Mainz, Germany
| | - Torsten Panholzer
- Institute of Medical Biostatistics, Epidemiology and Informatics, University Medical Center of the Johannes Gutenberg University Mainz, Obere Zahlbacher Str. 69, 55131, Mainz, Germany
| | - Florian Jungmann
- Department of Diagnostic and Interventional Radiology, University Medical Center of the Johannes Gutenberg University Mainz, Langenbeckst, 1, 55131, Mainz, Germany
| | - Moritz C Halfmann
- Department of Diagnostic and Interventional Radiology, University Medical Center of the Johannes Gutenberg University Mainz, Langenbeckst, 1, 55131, Mainz, Germany.
| |
Collapse
|
10
|
Guo J, Goyal M, Xi Y, Hinojosa L, Haddad G, Albayrak E, Pedrosa I. Style Transfer-assisted Deep Learning Method for Kidney Segmentation at Multiphase MRI. Radiol Artif Intell 2023; 5:e230043. [PMID: 38074795 PMCID: PMC10698598 DOI: 10.1148/ryai.230043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2023] [Revised: 07/28/2023] [Accepted: 08/30/2023] [Indexed: 02/12/2024]
Abstract
Purpose To develop and validate a semisupervised style transfer-assisted deep learning method for automated segmentation of the kidneys using multiphase contrast-enhanced (MCE) MRI acquisitions. Materials and Methods This retrospective, Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included 125 patients (mean age, 57.3 years; 67 male, 58 female) with renal masses. Cohort 1 consisted of 102 coronal T2-weighted MRI acquisitions and 27 MCE MRI acquisitions during the corticomedullary phase. Cohort 2 comprised 92 MCE MRI acquisitions (23 acquisitions during four phases each, including precontrast, corticomedullary, early nephrographic, and nephrographic phases). The kidneys were manually segmented on T2-weighted images. A cycle-consistent generative adversarial network (CycleGAN) was trained to generate anatomically coregistered synthetic corticomedullary style images using T2-weighted images as input. Synthetic images for precontrast, early nephrographic, and nephrographic phases were then generated using the synthetic corticomedullary images as input. Mask region-based convolutional neural networks were trained on the four synthetic phase series for kidney segmentation using T2-weighted masks. Segmentation performance was evaluated in a different cohort of 20 originally acquired MCE MRI examinations by using Dice and Jaccard scores. Results The CycleGAN network successfully generated anatomically coregistered synthetic MCE MRI-like datasets from T2-weighted acquisitions. The proposed deep learning approach for kidney segmentation achieved high mean Dice scores in all four phases of the original MCE MRI acquisitions (0.91 for precontrast, 0.92 for corticomedullary, 0.91 for early nephrographic, and 0.93 for nephrographic). Conclusion The proposed deep learning approach achieved high performance in kidney segmentation on different MCE MRI acquisitions.Keywords: Kidney Segmentation, Generative Adversarial Network, CycleGAN, Convolutional Neural Network, Transfer Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.
Collapse
Affiliation(s)
| | | | - Yin Xi
- From the Department of Radiology (J.G., M.G., Y.X., L.H., G.H., E.A.,
I.P.), Department of Urology (I.P.), and Advanced Imaging Research Center
(I.P.), University of Texas Southwestern Medical Center, 2201 Inwood Rd, Suite
202, Dallas, TX 75390-9085
| | - Lauren Hinojosa
- From the Department of Radiology (J.G., M.G., Y.X., L.H., G.H., E.A.,
I.P.), Department of Urology (I.P.), and Advanced Imaging Research Center
(I.P.), University of Texas Southwestern Medical Center, 2201 Inwood Rd, Suite
202, Dallas, TX 75390-9085
| | - Gaelle Haddad
- From the Department of Radiology (J.G., M.G., Y.X., L.H., G.H., E.A.,
I.P.), Department of Urology (I.P.), and Advanced Imaging Research Center
(I.P.), University of Texas Southwestern Medical Center, 2201 Inwood Rd, Suite
202, Dallas, TX 75390-9085
| | - Emin Albayrak
- From the Department of Radiology (J.G., M.G., Y.X., L.H., G.H., E.A.,
I.P.), Department of Urology (I.P.), and Advanced Imaging Research Center
(I.P.), University of Texas Southwestern Medical Center, 2201 Inwood Rd, Suite
202, Dallas, TX 75390-9085
| | - Ivan Pedrosa
- From the Department of Radiology (J.G., M.G., Y.X., L.H., G.H., E.A.,
I.P.), Department of Urology (I.P.), and Advanced Imaging Research Center
(I.P.), University of Texas Southwestern Medical Center, 2201 Inwood Rd, Suite
202, Dallas, TX 75390-9085
| |
Collapse
|
11
|
Yoo J, Kim JU, Kim J, Jeon S, Song YJ, Choi KH, Kim SH, Yoon JW, Kim H. Non-contrast low-dose CT can be used for volumetry of ADPKD. BMC Nephrol 2023; 24:317. [PMID: 37884882 PMCID: PMC10604523 DOI: 10.1186/s12882-023-03359-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Accepted: 10/04/2023] [Indexed: 10/28/2023] Open
Abstract
BACKGROUND Kidney volume provides important information for the diagnosis and prognosis of autosomal dominant polycystic kidney disease (ADPKD), as well as for the evaluation of the effects of drugs such as tolvaptan. Non-contrast computed tomography (CT) is commonly used for volumetry, and this study examined the correspondence and correlation of kidney volume measured by standard-dose or low-dose CT. METHODS Axial standard-dose and low-dose CT images with 1-mm slices were obtained from 24 ADPKD patients. The kidney was segmented in the Synapse 3D software and the kidney volume was calculated using stereology. The kidney volume was compared between the two sets of images using R2, Bland-Altman plots, coefficient of variation, and intra-class correlation coefficients (ICCs). RESULTS The mean age of the 24 patients was 48.4 ± 10.9 years, and 45.8% were men (n = 11). The mean total kidney volume on standard-dose CT was 1501 ± 838.2 mL. The R2 of volume between standard-dose and low-dose CT was 0.995. In the Bland-Altman plot, except for one case with a large kidney volume, the two measurements were consistent, and the coefficient of variation and ICC were also good (0.02, 0.998). The CT radiation dose (dose-length product) was 229 ± 68 mGy·cm for standard-dose CT and 50 ± 19 mGy·cm for low-dose CT. A comparable volume was obtained with 20% of the radiation dose of standard-dose CT. CONCLUSIONS Standard-dose and low-dose CT showed comparable kidney volume in ADPKD. Therefore, low-dose CT can substitute for ADPKD volumetry while minimizing radiation exposure.
Collapse
Affiliation(s)
- Jaeyeong Yoo
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea
| | - Jin Up Kim
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea
| | - Jisu Kim
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea
| | - Sohyun Jeon
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea
| | - Young-Jin Song
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea
| | - Kwang-Ho Choi
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea
| | - Seok-Hyung Kim
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea
| | - Jong-Woo Yoon
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea
| | - Hyunsuk Kim
- Department of Internal Medicine, Hallym University Medical Center, Chuncheon Sacred Heart Hospital, Chuncheon-si, Gangwon-do, 24253, Republic of Korea.
| |
Collapse
|
12
|
Peng T, Gu Y, Ruan SJ, Wu QJ, Cai J. Novel Solution for Using Neural Networks for Kidney Boundary Extraction in 2D Ultrasound Data. Biomolecules 2023; 13:1548. [PMID: 37892229 PMCID: PMC10604927 DOI: 10.3390/biom13101548] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2023] [Revised: 09/30/2023] [Accepted: 10/16/2023] [Indexed: 10/29/2023] Open
Abstract
Background and Objective: Kidney ultrasound (US) imaging is a significant imaging modality for evaluating kidney health and is essential for diagnosis, treatment, surgical intervention planning, and follow-up assessments. Kidney US image segmentation consists of extracting useful objects or regions from the total image, which helps determine tissue organization and improve diagnosis. Thus, obtaining accurate kidney segmentation data is an important first step for precisely diagnosing kidney diseases. However, manual delineation of the kidney in US images is complex and tedious in clinical practice. To overcome these challenges, we developed a novel automatic method for US kidney segmentation. Methods: Our method comprises two cascaded steps for US kidney segmentation. The first step utilizes a coarse segmentation procedure based on a deep fusion learning network to roughly segment each input US kidney image. The second step utilizes a refinement procedure to fine-tune the result of the first step by combining an automatic searching polygon tracking method with a machine learning network. In the machine learning network, a suitable and explainable mathematical formula for kidney contours is denoted by basic parameters. Results: Our method is assessed using 1380 trans-abdominal US kidney images obtained from 115 patients. Based on comprehensive comparisons of different noise levels, our method achieves accurate and robust results for kidney segmentation. We use ablation experiments to assess the significance of each component of the method. Compared with state-of-the-art methods, the evaluation metrics of our method are significantly higher. The Dice similarity coefficient (DSC) of our method is 94.6 ± 3.4%, which is higher than those of recent deep learning and hybrid algorithms (89.4 ± 7.1% and 93.7 ± 3.8%, respectively). Conclusions: We develop a coarse-to-refined architecture for the accurate segmentation of US kidney images. It is important to precisely extract kidney contour features because segmentation errors can cause under-dosing of the target or over-dosing of neighboring normal tissues during US-guided brachytherapy. Hence, our method can be used to increase the rigor of kidney US segmentation.
Collapse
Affiliation(s)
- Tao Peng
- School of Future Science and Engineering, Soochow University, Suzhou 215006, China
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China
- Department of Radiation Oncology, UT Southwestern Medical Center, Dallas, TX 75390, USA
| | - Yidong Gu
- Department of Medical Ultrasound, Suzhou Municipal Hospital, Suzhou 215000, China;
| | - Shanq-Jang Ruan
- Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei City 10607, Taiwan;
| | - Qingrong Jackie Wu
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC 27710, USA;
| | - Jing Cai
- Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, China
| |
Collapse
|
13
|
Wang H, Lei C, Zhao D, Gao L, Gao J. DeepHipp: accurate segmentation of hippocampus using 3D dense-block based on attention mechanism. BMC Med Imaging 2023; 23:158. [PMID: 37833644 PMCID: PMC10576314 DOI: 10.1186/s12880-023-01103-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2022] [Accepted: 09/14/2023] [Indexed: 10/15/2023] Open
Abstract
BACKGROUND The hippocampus is a key area of the brain responsible for learning, memory, and other abilities. Accurately segmenting the hippocampus and precisely calculating the volume of the hippocampus is of great significance for predicting Alzheimer's disease and amnesia. Most of the segmentation algorithms currently involved are based on templates, such as the more popular FreeSufer. METHODS This study proposes Deephipp, a deep learning network based on a 3D dense block using an attention mechanism for accurate segmentation of the hippocampus. DeepHipp is based on the following novelties: (i) DeepHipp adopts powerful data augmentation schemes to enhance the segmentation ability. (ii) DeepHipp is designed to incorporate 3D dense-block to capture multiple-scale features of the hippocampus. (iii) DeepHipp creatively uses the attention mechanism in the field of hippocampal image segmentation, extracting useful hippocampus information in a massive feature map, and improving the accuracy and sensitivity of the model. CONCLUSIONS We describe the illustrative results and show extensive qualitative and quantitative comparisons with other methods. Our achievement demonstrates that the accuracy of DeepHipp can reach 83.63%, which is superior to most existing methods in terms of accuracy and efficiency of hippocampus segmentation. It is noticeable that deep learning can potentially lead to an effective segmentation of medical images.
Collapse
Affiliation(s)
- Han Wang
- Department of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China
| | - Cai Lei
- Department of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China
| | - Di Zhao
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
| | - Liwei Gao
- Department of Radiation Oncology China, Japan Friendship Hospital, Beijing, China
| | - Jingyang Gao
- Department of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China
| |
Collapse
|
14
|
Inoue K, Hara Y, Nagawa K, Koyama M, Shimizu H, Matsuura K, Takahashi M, Osawa I, Inoue T, Okada H, Ishikawa M, Kobayashi N, Kozawa E. The utility of automatic segmentation of kidney MRI in chronic kidney disease using a 3D convolutional neural network. Sci Rep 2023; 13:17361. [PMID: 37833438 PMCID: PMC10575938 DOI: 10.1038/s41598-023-44539-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2023] [Accepted: 10/10/2023] [Indexed: 10/15/2023] Open
Abstract
We developed a 3D convolutional neural network (CNN)-based automatic kidney segmentation method for patients with chronic kidney disease (CKD) using MRI Dixon-based T1-weighted in-phase (IP)/opposed-phase (OP)/water-only (WO) images. The dataset comprised 100 participants with renal dysfunction (RD; eGFR < 45 mL/min/1.73 m2) and 70 without (non-RD; eGFR ≥ 45 mL/min/1.73 m2). The model was applied to the right, left, and both kidneys; it was first evaluated on the non-RD group data and subsequently on the combined data of the RD and non-RD groups. For bilateral kidney segmentation of the non-RD group, the best performance was obtained when using IP image, with a Dice score of 0.902 ± 0.034, average surface distance of 1.46 ± 0.75 mm, and a difference of - 27 ± 21 mL between ground-truth and automatically computed volume. Slightly worse results were obtained for the combined data of the RD and non-RD groups and for unilateral kidney segmentation, particularly when segmenting the right kidney from the OP images. Our 3D CNN-assisted automatic segmentation tools can be utilized in future studies on total kidney volume measurements and various image analyses of a large number of patients with CKD.
Collapse
Affiliation(s)
- Kaiji Inoue
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Yuki Hara
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Keita Nagawa
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan.
| | - Masahiro Koyama
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Hirokazu Shimizu
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Koichiro Matsuura
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Masao Takahashi
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Iichiro Osawa
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Tsutomu Inoue
- Department of Nephrology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Hirokazu Okada
- Department of Nephrology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Masahiro Ishikawa
- Department of Electronic Engineering and Computer Science, Faculty of Engineering, Kindai University Hiroshima Campus, 1 Takaya Umenobe, Higashi-Hiroshima City, Hiroshima, Japan
| | - Naoki Kobayashi
- School of Biomedical Engineering, Faculty of Health and Medical Care, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| | - Eito Kozawa
- Department of Radiology, Saitama Medical University, 38 Morohongou, Moroyama-machi, Iruma-gun, Saitama, Japan
| |
Collapse
|
15
|
Martin WP, Docherty NG. A Systems Nephrology Approach to Diabetic Kidney Disease Research and Practice. Nephron Clin Pract 2023; 148:127-136. [PMID: 37696257 DOI: 10.1159/000531823] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2023] [Accepted: 06/05/2023] [Indexed: 09/13/2023] Open
Abstract
BACKGROUND Diagnosis and staging of diabetic kidney disease (DKD) via the serial assessment of routine laboratory indices lacks the granularity required to resolve the heterogeneous disease mechanisms driving progression in the individual patient. A systems nephrology approach may help resolve mechanisms underlying this clinically apparent heterogeneity, paving a way for targeted treatment of DKD. SUMMARY Given the limited access to kidney tissue in routine clinical care of patients with DKD, data derived from renal tissue in preclinical model systems, including animal and in vitro models, can play a central role in the development of a targeted systems-based approach to DKD. Multi-centre prospective cohort studies, including the Kidney Precision Medicine Project (KPMP) and the European Nephrectomy Biobank (ENBiBA) project, will improve access to human diabetic kidney tissue for research purposes. Integration of diverse data domains from such initiatives including clinical phenotypic data, renal and retinal imaging biomarkers, histopathological and ultrastructural data, and an array of molecular omics (transcriptomics, proteomics, etc.) alongside multi-dimensional data from preclinical modelling offers exciting opportunities to unravel individual-level mechanisms underlying progressive DKD. The application of machine and deep learning approaches may particularly enhance insights derived from imaging and histopathological/ultrastructural data domains. KEY MESSAGES Integration of data from multiple model systems (in vitro, animal models, and patients) and from diverse domains (clinical phenotypic, imaging, histopathological/ultrastructural, and molecular omics) offers potential to create a precision medicine approach to DKD care wherein the right treatments are offered to the right patients at the right time.
Collapse
Affiliation(s)
- William P Martin
- Diabetes Complications Research Centre, School of Medicine, Conway Institute of Biomolecular and Biomedical Research, University College Dublin, Dublin, Ireland
| | - Neil G Docherty
- Diabetes Complications Research Centre, School of Medicine, Conway Institute of Biomolecular and Biomedical Research, University College Dublin, Dublin, Ireland
| |
Collapse
|
16
|
Lanktree MB, Kline T, Pei Y. Assessing the Risk of Progression to Kidney Failure in Patients With Autosomal Dominant Polycystic Kidney Disease. ADVANCES IN KIDNEY DISEASE AND HEALTH 2023; 30:407-416. [PMID: 38097331 DOI: 10.1053/j.akdh.2023.06.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/16/2022] [Revised: 06/07/2023] [Accepted: 06/09/2023] [Indexed: 12/18/2023]
Abstract
While autosomal dominant polycystic kidney disease (ADPKD) is a dichotomous diagnosis, substantial variability in disease severity exists. Identification of inherited risk through family history, genetic testing, and environmental risk factors through clinical assessment are important components of risk assessment for optimal management of patients with ADPKD. Genetic testing is especially helpful in cases with diagnostic uncertainty, particularly in cases with no apparent family history, in young cases (age less than 25 years) where a definitive diagnosis is sought, or in atypical presentations with early, severe, or discordant findings. Currently, risk assessment in ADPKD may be performed with the use of age-adjusted estimated glomerular filtration rate thresholds, evidence of rapid estimated glomerular filtration rate decline on serial measurements, age- and height-adjusted total kidney volume by Mayo Clinic Imaging Classification, or evidence of early hypertension and urological complications combined with PKD1 or PKD2 mutation class; however, caveats exist with each of these approaches. Fine-tuning of risk stratification with advanced imaging features and biomarkers is the subject of research but is not yet ready for general clinical practice. While conservative treatment strategies will be advised for all patients, those with the greatest rate of disease progression will have the most benefit from aggressive disease-modifying therapy. In this narrative review, we will summarize the evidence behind the clinical assessment and risk stratification of patients with ADPKD.
Collapse
Affiliation(s)
- Matthew B Lanktree
- Division of Nephrology, Department of Medicine, St Joseph's Healthcare Hamilton, McMaster University, Hamilton, Ontario, Canada; Population Health Research Institute, Hamilton, Ontario, Canada
| | - Timothy Kline
- Mayo Clinic, Department of Radiology and Division of Nephrology and Hypertension, Rochester, MN
| | - York Pei
- Division of Nephrology, Toronto General Hospital, University Health Network, University of Toronto, Toronto, Ontario, Canada.
| |
Collapse
|
17
|
Caroli A, Kline TL. Abdominal Imaging in ADPKD: Beyond Total Kidney Volume. J Clin Med 2023; 12:5133. [PMID: 37568535 PMCID: PMC10420262 DOI: 10.3390/jcm12155133] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2023] [Revised: 08/02/2023] [Accepted: 08/03/2023] [Indexed: 08/13/2023] Open
Abstract
In the context of autosomal dominant polycystic kidney disease (ADPKD), measurement of the total kidney volume (TKV) is crucial. It acts as a marker for tracking disease progression, and evaluating the effectiveness of treatment strategies. The TKV has also been recognized as an enrichment biomarker and a possible surrogate endpoint in clinical trials. Several imaging modalities and methods are available to calculate the TKV, and the choice depends on the purpose of use. Technological advancements have made it possible to accurately assess the cyst burden, which can be crucial to assessing the disease state and helping to identify rapid progressors. Moreover, the development of automated algorithms has increased the efficiency of total kidney and cyst volume measurements. Beyond these measurements, the quantification and characterization of non-cystic kidney tissue shows potential for stratifying ADPKD patients early on, monitoring disease progression, and possibly predicting renal function loss. A broad spectrum of radiological imaging techniques are available to characterize the kidney tissue, showing promise when it comes to non-invasively picking up the early signs of ADPKD progression. Radiomics have been used to extract textural features from ADPKD images, providing valuable information about the heterogeneity of the cystic and non-cystic components. This review provides an overview of ADPKD imaging biomarkers, focusing on the quantification methods, potential, and necessary steps toward a successful translation to clinical practice.
Collapse
Affiliation(s)
- Anna Caroli
- Bioengineering Department, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 24020 Ranica, BG, Italy
| | | |
Collapse
|
18
|
Amiri S, Abdolali F, Neshastehriz A, Nikoofar A, Farahani S, Firoozabadi LA, Askarabad ZA, Cheraghi S. A machine learning approach for prediction of auditory brain stem response in patients after head-and-neck radiation therapy. J Cancer Res Ther 2023; 19:1219-1225. [PMID: 37787286 DOI: 10.4103/jcrt.jcrt_2298_21] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/04/2023]
Abstract
Objective The present study aimed to assess machine learning (ML) models according to radiomic features to predict ototoxicity using auditory brain stem responses (ABRs) in patients with radiation therapy (RT) for head-and-neck cancers. Materials and Methods The ABR test was performed on 50 patients having head-and-neck RT. Radiomic features were extracted from the brain stem in computed tomography images to generate a radiomic signature. Moreover, accuracy, sensitivity, specificity, the area under the curve, and mean cross-validation were used to evaluate six different ML models. Results Out of 50 patients, 21 participants experienced ototoxicity. Furthermore, 140 radiomic features were extracted from the segmented area. Among the six ML models, the Random Forest method with 77% accuracy provided the best result. Conclusion According to the ML approach, we showed the relatively high prediction power of the radiomic features in radiation-induced ototoxicity. To better predict the outcomes, future studies on a larger number of participants are recommended.
Collapse
Affiliation(s)
- Sepideh Amiri
- Department of Computer Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Fatemeh Abdolali
- Department of Radiology and Diagnostic Imaging, Faculty of Medicine and Dentistry, Alberta University, Edmonton, AB, Canada
| | - Ali Neshastehriz
- Radiation Biology Research Center; Department of Radiation Sciences, Faculty of Allied Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Alireza Nikoofar
- Department of Radiation Oncology, Faculty of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Saeid Farahani
- Department of Audiology, School of Rehabilitation, Tehran University of Medical Sciences, Tehran, Iran
| | - Leila Alipour Firoozabadi
- Department of Radiation Sciences, Faculty of Allied Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Zahra Alaei Askarabad
- Department of Radiation Sciences, Faculty of Allied Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Susan Cheraghi
- Radiation Biology Research Center; Department of Radiation Sciences, Faculty of Allied Medicine, Iran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
19
|
Zhao D, Wang W, Tang T, Zhang YY, Yu C. Current progress in artificial intelligence-assisted medical image analysis for chronic kidney disease: A literature review. Comput Struct Biotechnol J 2023; 21:3315-3326. [PMID: 37333860 PMCID: PMC10275698 DOI: 10.1016/j.csbj.2023.05.029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2022] [Revised: 05/28/2023] [Accepted: 05/28/2023] [Indexed: 06/20/2023] Open
Abstract
Chronic kidney disease (CKD) causes irreversible damage to kidney structure and function. Arising from various etiologies, risk factors for CKD include hypertension and diabetes. With a progressively increasing global prevalence, CKD is an important public health problem worldwide. Medical imaging has become an important diagnostic tool for CKD through the non-invasive identification of macroscopic renal structural abnormalities. Artificial intelligence (AI)-assisted medical imaging techniques aid clinicians in the analysis of characteristics that cannot be easily discriminated by the naked eye, providing valuable information for the identification and management of CKD. Recent studies have demonstrated the effectiveness of AI-assisted medical image analysis as a clinical support tool using radiomics- and deep learning-based AI algorithms for improving the early detection, pathological assessment, and prognostic evaluation of various forms of CKD, including autosomal dominant polycystic kidney disease. Herein, we provide an overview of the potential roles of AI-assisted medical image analysis for the diagnosis and management of CKD.
Collapse
Affiliation(s)
- Dan Zhao
- Department of Nephrology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Wei Wang
- Department of Radiology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Tian Tang
- Department of Nephrology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Ying-Ying Zhang
- Department of Nephrology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Chen Yu
- Department of Nephrology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| |
Collapse
|
20
|
Shin JH, Kim YH, Lee MK, Min HS, Cho H, Kim H, Kim YC, Lee YS, Shin TY. Feasibility of artificial intelligence-based decision supporting system in tolvaptan prescription for autosomal dominant polycystic kidney disease. Investig Clin Urol 2023; 64:255-264. [PMID: 37341005 DOI: 10.4111/icu.20220411] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2022] [Revised: 03/12/2023] [Accepted: 03/26/2023] [Indexed: 06/22/2023] Open
Abstract
PURPOSE Total kidney volume (TKV) measurement is crucial for selecting treatment candidates in autosomal dominant polycystic kidney disease (ADPKD). We developed and investigated the performance of fully-automated 3D-volumetry model and applied it to software as a service (SaaS) for clinical support on tolvaptan prescription in ADPKD patients. MATERIALS AND METHODS Computed tomography scans of ADPKD patients taken between January 2000 and June 2022 were acquired from seven institutions. The quality of the images was manually reviewed in advance. The acquired dataset was split into training, validation, and test datasets at a ratio of 8.5:1:0.5. Convolutional, neural network-based automatic segmentation model was trained to obtain 3D segment mask for TKV measurement. The algorithm consisted of three steps: data preprocessing, ADPKD area extraction, and post-processing. After performance validation with the Dice score, 3D-volumetry model was applied to SaaS which is based on Mayo imaging classification for ADPKD. RESULTS A total of 753 cases with 95,117 slices were included. The differences between the ground-truth ADPKD kidney mask and the predicted ADPKD kidney mask were negligible, with intersection over union >0.95. The post-process filter successfully removed false alarms. The test-set performance was homogeneously equal and the Dice score of the model was 0.971; after post-processing, it improved to 0.979. The SaaS calculated TKV from uploaded Digital Imaging and Communications in Medicine images and classified patients according to height-adjusted TKV for age. CONCLUSIONS Our artificial intelligence-3D volumetry model exhibited effective, feasible, and non-inferior performance compared with that of human experts and successfully predicted the rapid ADPKD progressor.
Collapse
Affiliation(s)
- Jung Hyun Shin
- Department of Urology, Ewha Womans University Mokdong Hospital, Seoul, Korea
| | | | | | | | | | - Hyunsuk Kim
- Department of Nephrology, Hallym University Chuncheon Sacred Hospital, Chuncheon, Korea
| | - Yong Chul Kim
- Department of Nephrology, Seoul National University Hospital, Seoul, Korea
| | - Yong Seong Lee
- Department of Urology, Chung-Ang University Gwangmyeong Hospital, Gwangmyeong, Korea.
| | - Tae Young Shin
- Department of Urology, Ewha Womans University Mokdong Hospital, Seoul, Korea
- Synergy A.I. Co., Ltd, Seoul, Korea.
| |
Collapse
|
21
|
Rathi N, Attawettayanon W, Yasuda Y, Lewis K, Roversi G, Shah S, Wood A, Munoz-Lopez C, Palacios DA, Li J, Abdallah N, Schober JP, Strother M, Kutikov A, Uzzo R, Weight CJ, Eltemamy M, Krishnamurthi V, Abouassaly R, Campbell SC. Point of care parenchymal volume analyses to estimate split renal function and predict functional outcomes after radical nephrectomy. Sci Rep 2023; 13:6225. [PMID: 37069196 PMCID: PMC10110585 DOI: 10.1038/s41598-023-33236-6] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Accepted: 04/10/2023] [Indexed: 04/19/2023] Open
Abstract
Accurate prediction of new baseline GFR (NBGFR) after radical nephrectomy (RN) can inform clinical management and patient counseling whenever RN is a strong consideration. Preoperative global GFR, split renal function (SRF), and renal functional compensation (RFC) are fundamentally important for the accurate prediction of NBGFR post-RN. While SRF has traditionally been obtained from nuclear renal scans (NRS), differential parenchymal volume analysis (PVA) via software analysis may be more accurate. A simplified approach to estimate parenchymal volumes and SRF based on length/width/height measurements (LWH) has also been proposed. We compare the accuracies of these three methods for determining SRF, and, by extension, predicting NBGFR after RN. All 235 renal cancer patients managed with RN (2006-2021) with available preoperative CT/MRI and NRS, and relevant functional data were analyzed. PVA was performed on CT/MRI using semi-automated software, and LWH measurements were obtained from CT/MRI images. RFC was presumed to be 25%, and thus: Predicted NBGFR = 1.25 × Global GFRPre-RN × SRFContralateral. Predictive accuracies were assessed by mean squared error (MSE) and correlation coefficients (r). The r values for the LWH/NRS/software-derived PVA approaches were 0.72/0.71/0.86, respectively (p < 0.05). The PVA-based approach also had the most favorable MSE, which were 120/126/65, respectively (p < 0.05). Our data show that software-derived PVA provides more accurate and precise SRF estimations and predictions of NBGFR post-RN than NRS/LWH methods. Furthermore, the LWH approach is equivalent to NRS, precluding the need for NRS in most patients.
Collapse
Affiliation(s)
- Nityam Rathi
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Worapat Attawettayanon
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
- Division of Urology, Department of Surgery, Faculty of Medicine, Songklanagarind Hospital, Prince of Songkla University, Songkhla, Thailand
| | - Yosuke Yasuda
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
- Department of Urology, Tokyo Medical and Dental University, Tokyo, Japan
| | - Kieran Lewis
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Gustavo Roversi
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Snehi Shah
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Andrew Wood
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Carlos Munoz-Lopez
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Diego A Palacios
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Jianbo Li
- Department of Quantitative Health Sciences, Cleveland Clinic, Cleveland, OH, USA
| | - Nour Abdallah
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Jared P Schober
- Department of Surgery, Division of Urologic Surgery, University of Nebraska Medical Center, Omaha, NE, USA
| | - Marshall Strother
- Department of Urology, Oregon Health Sciences University, Portland, OR, USA
| | - Alexander Kutikov
- Department of Urology, Fox Chase Cancer Center, Philadelphia, PA, USA
| | - Robert Uzzo
- Department of Urology, Fox Chase Cancer Center, Philadelphia, PA, USA
| | | | - Mohamed Eltemamy
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | | | - Robert Abouassaly
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Steven C Campbell
- Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA.
| |
Collapse
|
22
|
Les T, Markiewicz T, Dziekiewicz M, Gallego J, Swiderska-Chadaj Z, Lorent M. Localization of spleen and kidney organs from CT scans based on classification of slices in rotational views. Sci Rep 2023; 13:5709. [PMID: 37029169 PMCID: PMC10082200 DOI: 10.1038/s41598-023-32741-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2022] [Accepted: 03/31/2023] [Indexed: 04/09/2023] Open
Abstract
This article presents a novel multiple organ localization and tracking technique applied to spleen and kidney regions in computed tomography images. The proposed solution is based on a unique approach to classify regions in different spatial projections (e.g., side projection) using convolutional neural networks. Our procedure merges classification results from different projection resulting in a 3D segmentation. The proposed system is able to recognize the contour of the organ with an accuracy of 88-89% depending on the body organ. Research has shown that the use of a single method can be useful for the detection of different organs: kidney and spleen. Our solution can compete with U-Net based solutions in terms of hardware requirements, as it has significantly lower demands. Additionally, it gives better results in small data sets. Another advantage of our solution is a significantly lower training time on an equally sized data set and more capabilities to parallelize calculations. The proposed system enables visualization, localization and tracking of organs and is therefore a valuable tool in medical diagnostic problems.
Collapse
Affiliation(s)
- Tomasz Les
- University of Technology, Plac Politechniki 1, 00-661, Warsaw, Poland.
| | - Tomasz Markiewicz
- University of Technology, Plac Politechniki 1, 00-661, Warsaw, Poland
- Military Institute of Medicine, Szaserów 128, 04-141, Warsaw, Poland
| | | | - Jaime Gallego
- University of Barcelona, Gran Via de les Corts Catalanes, 08007, Barcelona, Spain
| | | | - Malgorzata Lorent
- Military Institute of Medicine, Szaserów 128, 04-141, Warsaw, Poland
| |
Collapse
|
23
|
Shan T, Ying Y, Song G. Automatic Kidney Segmentation Method Based on an Enhanced Generative Adversarial Network. Diagnostics (Basel) 2023; 13:diagnostics13071358. [PMID: 37046576 PMCID: PMC10093289 DOI: 10.3390/diagnostics13071358] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2022] [Revised: 02/17/2023] [Accepted: 02/20/2023] [Indexed: 04/14/2023] Open
Abstract
When deciding on a kidney tumor's diagnosis and treatment, it is critical to take its morphometry into account. It is challenging to undertake a quantitative analysis of the association between kidney tumor morphology and clinical outcomes due to a paucity of data and the need for the time-consuming manual measurement of imaging variables. To address this issue, an autonomous kidney segmentation technique, namely SegTGAN, is proposed in this paper, which is based on a conventional generative adversarial network model. Its core framework includes a discriminator network with multi-scale feature extraction and a fully convolutional generator network made up of densely linked blocks. For qualitative and quantitative comparisons with the SegTGAN technique, the widely used and related medical image segmentation networks U-Net, FCN, and SegAN are used. The experimental results show that the Dice similarity coefficient (DSC), volumetric overlap error (VOE), accuracy (ACC), and average surface distance (ASD) of SegTGAN on the Kits19 dataset reach 92.28%, 16.17%, 97.28%, and 0.61 mm, respectively. SegTGAN outscores all the other neural networks, which indicates that our proposed model has the potential to improve the accuracy of CT-based kidney segmentation.
Collapse
Affiliation(s)
- Tian Shan
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
- Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| | - Yuhan Ying
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
- Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
- University of Chinese Academy of Sciences, Beijing 100049, China
| | - Guoli Song
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
- Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
| |
Collapse
|
24
|
Zhang H, Botler M, Kooman JP. Deep Learning for Image Analysis in Kidney Care. ADVANCES IN KIDNEY DISEASE AND HEALTH 2023; 30:25-32. [PMID: 36723278 DOI: 10.1053/j.akdh.2022.11.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/15/2022] [Revised: 08/23/2022] [Accepted: 11/07/2022] [Indexed: 12/24/2022]
Abstract
Analysis of medical images, such as radiological or tissue specimens, is an indispensable part of medical diagnostics. Conventionally done manually, the process may sometimes be time-consuming and prone to interobserver variability. Image classification and segmentation by deep learning strategies, predominantly convolutional neural networks, may provide a significant advance in the diagnostic process. In renal medicine, most evidence has been generated around the radiological assessment of renal abnormalities and histological analysis of renal biopsy specimens' segmentation. In this article, the basic principles of image analysis by convolutional neural networks, brief descriptions of convolutional neural networks, and their system architecture for image analysis are discussed, in combination with examples regarding their use in image analysis in nephrology.
Collapse
Affiliation(s)
| | | | - Jeroen P Kooman
- Division of Nephrology, Department of Internal Medicine, Maastricht University Medical Center, Maastricht, The Netherlands
| |
Collapse
|
25
|
Woznicki P, Siedek F, van Gastel MD, dos Santos DP, Arjune S, Karner LA, Meyer F, Caldeira LL, Persigehl T, Gansevoort RT, Grundmann F, Baessler B, Müller RU. Automated Kidney and Liver Segmentation in MR Images in Patients with Autosomal Dominant Polycystic Kidney Disease: A Multicenter Study. KIDNEY360 2022; 3:2048-2058. [PMID: 36591351 PMCID: PMC9802567 DOI: 10.34067/kid.0003192022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/02/2022] [Accepted: 09/19/2022] [Indexed: 12/31/2022]
Abstract
Background Imaging-based total kidney volume (TKV) and total liver volume (TLV) are major prognostic factors in autosomal dominant polycystic kidney disease (ADPKD) and end points for clinical trials. However, volumetry is time consuming and reader dependent in clinical practice. Our aim was to develop a fully automated method for joint kidney and liver segmentation in magnetic resonance imaging (MRI) and to evaluate its performance in a multisequence, multicenter setting. Methods The convolutional neural network was trained on a large multicenter dataset consisting of 992 MRI scans of 327 patients. Manual segmentation delivered ground-truth labels. The model's performance was evaluated in a separate test dataset of 93 patients (350 MRI scans) as well as a heterogeneous external dataset of 831 MRI scans from 323 patients. Results The segmentation model yielded excellent performance, achieving a median per study Dice coefficient of 0.92-0.97 for the kidneys and 0.96 for the liver. Automatically computed TKV correlated highly with manual measurements (intraclass correlation coefficient [ICC]: 0.996-0.999) with low bias and high precision (-0.2%±4% for axial images and 0.5%±4% for coronal images). TLV estimation showed an ICC of 0.999 and bias/precision of -0.5%±3%. For the external dataset, the automated TKV demonstrated bias and precision of -1%±7%. Conclusions Our deep learning model enabled accurate segmentation of kidneys and liver and objective assessment of TKV and TLV. Importantly, this approach was validated with axial and coronal MRI scans from 40 different scanners, making implementation in clinical routine care feasible.Clinical Trial registry name and registration number: The German ADPKD Tolvaptan Treatment Registry (AD[H]PKD), NCT02497521.
Collapse
Affiliation(s)
- Piotr Woznicki
- Institute of Diagnostic and Interventional Radiology, University of Cologne, University Hospital Cologne, Cologne, Germany,Department of Diagnostic and Interventional Radiology, University Hospital Wuerzburg, Wuerzburg, Germany
| | - Florian Siedek
- Institute of Diagnostic and Interventional Radiology, University of Cologne, University Hospital Cologne, Cologne, Germany
| | - Maatje D.A. van Gastel
- Department of Nephrology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Daniel Pinto dos Santos
- Institute of Diagnostic and Interventional Radiology, University of Cologne, University Hospital Cologne, Cologne, Germany,Institute of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt, Germany
| | - Sita Arjune
- Department II of Internal Medicine and Center for Molecular Medicine Cologne, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany
| | - Larina A. Karner
- Department II of Internal Medicine and Center for Molecular Medicine Cologne, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany
| | - Franziska Meyer
- Institute of Diagnostic and Interventional Radiology, University of Cologne, University Hospital Cologne, Cologne, Germany
| | - Liliana Lourenco Caldeira
- Institute of Diagnostic and Interventional Radiology, University of Cologne, University Hospital Cologne, Cologne, Germany
| | - Thorsten Persigehl
- Institute of Diagnostic and Interventional Radiology, University of Cologne, University Hospital Cologne, Cologne, Germany
| | - Ron T. Gansevoort
- Department of Nephrology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands
| | - Franziska Grundmann
- Department II of Internal Medicine and Center for Molecular Medicine Cologne, University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany
| | - Bettina Baessler
- Institute of Diagnostic and Interventional Radiology, University of Cologne, University Hospital Cologne, Cologne, Germany,Department of Diagnostic and Interventional Radiology, University Hospital Wuerzburg, Wuerzburg, Germany
| | - Roman-Ulrich Müller
- Cologne Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases (CECAD) University of Cologne, Faculty of Medicine and University Hospital Cologne, Cologne, Germany
| |
Collapse
|
26
|
Ji Y, Cho H, Seon S, Lee K, Yoon H. A deep learning model for CT-based kidney volume determination in dogs and normal reference definition. Front Vet Sci 2022; 9:1011804. [PMID: 36387402 PMCID: PMC9649823 DOI: 10.3389/fvets.2022.1011804] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2022] [Accepted: 10/13/2022] [Indexed: 10/07/2023] Open
Abstract
Kidney volume is associated with renal function and the severity of renal diseases, thus accurate assessment of the kidney is important. Although the voxel count method is reported to be more accurate than several methods, its laborious and time-consuming process is considered as a main limitation. In need of a new technology that is fast and as accurate as the manual voxel count method, the aim of this study was to develop the first deep learning model for automatic kidney detection and volume estimation from computed tomography (CT) images of dogs. A total of 182,974 image slices from 386 CT scans of 211 dogs were used to develop this deep learning model. Owing to the variance of kidney size and location in dogs compared to humans, several processing methods and an architecture based on UNEt Transformers which is known to show promising results for various medical image segmentation tasks including this study. Combined loss function and data augmentation were applied to elevate the performance of the model. The Dice similarity coefficient (DSC) which shows the similarity between manual segmentation and automated segmentation by deep-learning model was 0.915 ± 0.054 (mean ± SD) with post-processing. Kidney volume agreement analysis assessing the similarity between the kidney volume estimated by manual voxel count method and the deep-learning model was r = 0.960 (p < 0.001), 0.95 from Lin's concordance correlation coefficient (CCC), and 0.975 from the intraclass correlation coefficient (ICC). Kidney volume was positively correlated with body weight (BW), and insignificantly correlated with body conditions score (BCS), age, and sex. The correlations between BW, BCS, and kidney volume were as follows: kidney volume = 3.701 × BW + 11.962 (R 2 = 0.74, p < 0.001) and kidney volume = 19.823 × BW/BCS index + 10.705 (R 2 = 0.72, p < 0.001). The deep learning model developed in this study is useful for the automatic estimation of kidney volume. Furthermore, a reference range established in this study for CT-based normal kidney volume considering BW and BCS can be helpful in assessment of kidney in dogs.
Collapse
Affiliation(s)
- Yewon Ji
- Department of Veterinary Medical Imaging, College of Veterinary Medicine, Jeonbuk National University, Iksan, South Korea
| | | | | | - Kichang Lee
- Department of Veterinary Medical Imaging, College of Veterinary Medicine, Jeonbuk National University, Iksan, South Korea
| | - Hakyoung Yoon
- Department of Veterinary Medical Imaging, College of Veterinary Medicine, Jeonbuk National University, Iksan, South Korea
| |
Collapse
|
27
|
Pandey M, Gupta A. Tumorous kidney segmentation in abdominal CT images using active contour and 3D-UNet. Ir J Med Sci 2022:10.1007/s11845-022-03113-8. [PMID: 35930139 DOI: 10.1007/s11845-022-03113-8] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2022] [Accepted: 07/20/2022] [Indexed: 11/29/2022]
Abstract
BACKGROUND AND PURPOSE The precise segmentation of the kidneys in computed tomography (CT) images is vital in urology for diagnosis, treatment, and surgical planning. Medical experts can get assistance through segmentation, as it provides information about kidney malformations in terms of shape and size. Manual segmentation is slow, tedious, and not reproducible. An automatic computer-aided system is a solution to this problem. This paper presents an automated kidney segmentation technique based on active contour and deep learning. MATERIALS AND METHODS In this work, 210 CTs from the KiTS 19 repository were used. The used dataset was divided into a train set (168 CTs), test set (21 CTs), and validation set (21 CTs). The suggested technique has broadly four phases: (1) extraction of kidney regions using active contours, (2) preprocessing, (3) kidney segmentation using 3D U-Net, and (4) reconstruction of the segmented CT images. RESULTS The proposed segmentation method has received the Dice score of 97.62%, Jaccard index of 95.74%, average sensitivity of 98.28%, specificity of 99.95%, and accuracy of 99.93% over the validation dataset. CONCLUSION The proposed method can efficiently solve the problem of tumorous kidney segmentation in CT images by using active contour and deep learning. The active contour was used to select kidney regions and 3D-UNet was used for precisely segmenting the tumorous kidney.
Collapse
Affiliation(s)
- Mohit Pandey
- School of Computer Science & Engineering, Shri Mata Vaishno Devi University, Kakryal, Katra-182320, Jammu & Kashmir, India
| | - Abhishek Gupta
- School of Computer Science & Engineering, Shri Mata Vaishno Devi University, Kakryal, Katra-182320, Jammu & Kashmir, India.
| |
Collapse
|
28
|
Kim Y, Tao C, Kim H, Oh GY, Ko J, Bae KT. A Deep Learning Approach for Automated Segmentation of Kidneys and Exophytic Cysts in Individuals with Autosomal Dominant Polycystic Kidney Disease. J Am Soc Nephrol 2022; 33:1581-1589. [PMID: 35768178 PMCID: PMC9342631 DOI: 10.1681/asn.2021111400] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2021] [Accepted: 05/06/2022] [Indexed: 11/03/2022] Open
Abstract
BACKGROUND Total kidney volume (TKV) is an important imaging biomarker in autosomal dominant polycystic kidney disease (ADPKD). Manual computation of TKV, particularly with the exclusion of exophytic cysts, is laborious and time consuming. METHODS We developed a fully automated segmentation method for TKV using a deep learning network to selectively segment kidney regions while excluding exophytic cysts. We used abdominal T2 -weighted magnetic resonance images from 210 individuals with ADPKD who were divided into two groups: one group of 157 to train the network and a second group of 53 to test it. With a 3D U-Net architecture using dataset fingerprints, the network was trained by K-fold cross-validation, in that 80% of 157 cases were for training and the remaining 20% were for validation. We used Dice similarity coefficient, intraclass correlation coefficient, and Bland-Altman analysis to assess the performance of the automated segmentation method compared with the manual method. RESULTS The automated and manual reference methods exhibited excellent geometric concordance (Dice similarity coefficient: mean±SD, 0.962±0.018) on the test datasets, with kidney volumes ranging from 178.9 to 2776.0 ml (mean±SD, 1058.5±706.8 ml) and exophytic cysts ranging from 113.4 to 2497.6 ml (mean±SD, 549.0±559.1 ml). The intraclass correlation coefficient was 0.9994 (95% confidence interval, 0.9991 to 0.9996; P<0.001) with a minimum bias of -2.424 ml (95% limits of agreement, -49.80 to 44.95). CONCLUSIONS We developed a fully automated segmentation method to measure TKV that excludes exophytic cysts and has an accuracy similar to that of a human expert. This technique may be useful in clinical studies that require automated computation of TKV to evaluate progression of ADPKD and response to treatment.
Collapse
Affiliation(s)
- Youngwoo Kim
- Sustainable Technology and Wellness R&D Group, Korea Institute of Industrial Technology, Cheonan, Republic of Korea
| | - Cheng Tao
- Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania
| | - Hyungchan Kim
- Sustainable Technology and Wellness R&D Group, Korea Institute of Industrial Technology, Cheonan, Republic of Korea
| | - Geum-Yoon Oh
- Sustainable Technology and Wellness R&D Group, Korea Institute of Industrial Technology, Cheonan, Republic of Korea
| | - Jeongbeom Ko
- Sustainable Technology and Wellness R&D Group, Korea Institute of Industrial Technology, Cheonan, Republic of Korea
| | - Kyongtae T Bae
- Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania .,Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Pok Fu Lam, Hong Kong
| |
Collapse
|
29
|
Xie Y, Xu M, Chen Y, Zhu X, Ju S, Li Y. The predictive value of renal parenchymal information for renal function impairment in patients with ADPKD: a multicenter prospective study. ABDOMINAL RADIOLOGY (NEW YORK) 2022; 47:2845-2857. [PMID: 35633387 DOI: 10.1007/s00261-022-03554-w] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/26/2022] [Revised: 05/06/2022] [Accepted: 05/09/2022] [Indexed: 01/18/2023]
Abstract
OBJECTIVE Although the guideline indicates that total kidney volume (TKV) is an important detection indicator in patients with autosomal dominant polycystic kidney disease (ADPKD), this study attempted to demonstrate that renal parenchymal information, combined with parenchymal volume and radiomics features, may have more valuable clinical guiding significance. METHODS A totals of 340 ADPKD patients with normal renal function were prospectively collected and followed-up for five years, with renal function tests and non-contrast computed tomography (CT) performed every six months. The relationship between renal function impairment and renal parenchymal volume (RPV) as along with radiomics features was explored using a multiple linear regression model and multiple logistic regression. Then, a combined model of RPV with radiomics features was constructed to comprehensively evaluate its predictive value. RESULTS Compared with TKV, decreased RPV presented a closer relationship with renal function impairment, namely, with the impairment rate (RPV: 82.3% vs. TVK: 67.1%) and eGFR (RPV: r = 0.614, p < 0.001 vs. TKV: r = -0.452, p < 0.001), and showed higher predictive power (RPV: AUC = 0.752 [95%CI 0.692-0.805], p < 0.001 vs. TKV: AUC = 0.711 [95%CI 0.649-0.768], p < 0.001). Correspondingly, the radiomics analysis that was derived from the renal parenchyma also showed a satisfactory result (AUC = 0.849 [95%Cl 0.797-0.892], p < 0.001). Importantly, the predictive power for renal function impairment was further improved in the combined model of RPV and radiomics features (AUC = 0.902 [95%Cl 0.857-0.937], p < 0.001). CONCLUSION Renal parenchyma information may be a sensitive biomarker of renal function impairment in ADPKD, which can provide a new approach for clinically monitoring renal function, and may greatly improve the pre-hospital prevention and treatment effects.
Collapse
Affiliation(s)
- Yuhang Xie
- Department of Radiology, Affiliated Hospital of Jiangsu University, No. 438, Jiefang Road, Zhenjiang, 212001, Jiangsu, China
| | - Mengmiao Xu
- Department of Radiology, Affiliated Hospital of Jiangsu University, No. 438, Jiefang Road, Zhenjiang, 212001, Jiangsu, China
| | - Yajie Chen
- Department of Radiology, Affiliated Hospital of Jiangsu University, No. 438, Jiefang Road, Zhenjiang, 212001, Jiangsu, China
| | - Xiaolan Zhu
- Department of Central Laboratory, The Fourth Affiliated Hospital of Jiangsu University, No. 20, Zhengdong Road, Zhenjiang, 212001, Jiangsu, China.
| | - Shenghong Ju
- Department of Radiology, Southeast University Affiliated Zhongda Hospital, No. 87, Dingjiaqiao Road, Nanjing, 210009, Jiangsu, China.
| | - Yuefeng Li
- Department of Radiology, Affiliated Hospital of Jiangsu University, No. 438, Jiefang Road, Zhenjiang, 212001, Jiangsu, China.
- Department of Central Laboratory, The Fourth Affiliated Hospital of Jiangsu University, No. 20, Zhengdong Road, Zhenjiang, 212001, Jiangsu, China.
| |
Collapse
|
30
|
Sharbatdaran A, Romano D, Teichman K, Dev H, Raza SI, Goel A, Moghadam MC, Blumenfeld JD, Chevalier JM, Shimonov D, Shih G, Wang Y, Prince MR. Deep Learning Automation of Kidney, Liver, and Spleen Segmentation for Organ Volume Measurements in Autosomal Dominant Polycystic Kidney Disease. Tomography 2022; 8:1804-1819. [PMID: 35894017 PMCID: PMC9326744 DOI: 10.3390/tomography8040152] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/21/2022] [Revised: 07/01/2022] [Accepted: 07/08/2022] [Indexed: 12/02/2022] Open
Abstract
Organ volume measurements are a key metric for managing ADPKD (the most common inherited renal disease). However, measuring organ volumes is tedious and involves manually contouring organ outlines on multiple cross-sectional MRI or CT images. The automation of kidney contouring using deep learning has been proposed, as it has small errors compared to manual contouring. Here, a deployed open-source deep learning ADPKD kidney segmentation pipeline is extended to also measure liver and spleen volumes, which are also important. This 2D U-net deep learning approach was developed with radiologist labeled T2-weighted images from 215 ADPKD subjects (70% training = 151, 30% validation = 64). Additional ADPKD subjects were utilized for prospective (n = 30) and external (n = 30) validations for a total of 275 subjects. Image cropping previously optimized for kidneys was included in training but removed for the validation and inference to accommodate the liver which is closer to the image border. An effective algorithm was developed to adjudicate overlap voxels that are labeled as more than one organ. Left kidney, right kidney, liver and spleen labels had average errors of 3%, 7%, 3%, and 1%, respectively, on external validation and 5%, 6%, 5%, and 1% on prospective validation. Dice scores also showed that the deep learning model was close to the radiologist contouring, measuring 0.98, 0.96, 0.97 and 0.96 on external validation and 0.96, 0.96, 0.96 and 0.95 on prospective validation for left kidney, right kidney, liver and spleen, respectively. The time required for manual correction of deep learning segmentation errors was only 19:17 min compared to 33:04 min for manual segmentations, a 42% time saving (p = 0.004). Standard deviation of model assisted segmentations was reduced to 7, 5, 11, 5 mL for right kidney, left kidney, liver and spleen respectively from 14, 10, 55 and 14 mL for manual segmentations. Thus, deep learning reduces the radiologist time required to perform multiorgan segmentations in ADPKD and reduces measurement variability.
Collapse
Affiliation(s)
- Arman Sharbatdaran
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
| | - Dominick Romano
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
| | - Kurt Teichman
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
| | - Hreedi Dev
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
| | - Syed I. Raza
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
| | - Akshay Goel
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
| | - Mina C. Moghadam
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
| | - Jon D. Blumenfeld
- The Rogosin Institute and Department of Medicine Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (J.D.B.); (J.M.C.); (D.S.)
| | - James M. Chevalier
- The Rogosin Institute and Department of Medicine Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (J.D.B.); (J.M.C.); (D.S.)
| | - Daniil Shimonov
- The Rogosin Institute and Department of Medicine Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (J.D.B.); (J.M.C.); (D.S.)
| | - George Shih
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
| | - Yi Wang
- Departments of Radiology at Weill Cornell Medicine and Biomedical Engineering, Cornell University, New York, NY 10065, USA;
| | - Martin R. Prince
- Department of Radiology, Weill Cornell Medicine, Cornell University, New York, NY 10065, USA; (A.S.); (D.R.); (K.T.); (H.D.); (S.I.R.); (A.G.); (M.C.M.); (G.S.)
- Columbia College of Physicians and Surgeons, Cornell University, New York, NY 10027, USA
| |
Collapse
|
31
|
Hsiao CH, Sun TL, Lin PC, Peng TY, Chen YH, Cheng CY, Yang FJ, Yang SY, Wu CH, Lin FYS, Huang Y. A deep learning-based precision volume calculation approach for kidney and tumor segmentation on computed tomography images. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 221:106861. [PMID: 35588664 DOI: 10.1016/j.cmpb.2022.106861] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Revised: 03/24/2022] [Accepted: 05/07/2022] [Indexed: 06/15/2023]
Abstract
Previously, doctors interpreted computed tomography (CT) images based on their experience in diagnosing kidney diseases. However, with the rapid increase in CT images, such interpretations were required considerable time and effort, producing inconsistent results. Several novel neural network models were proposed to automatically identify kidney or tumor areas in CT images for solving this problem. In most of these models, only the neural network structure was modified to improve accuracy. However, data pre-processing was also a crucial step in improving the results. This study systematically discussed the necessary pre-processing methods before processing medical images in a neural network model. The experimental results were shown that the proposed pre-processing methods or models significantly improve the accuracy rate compared with the case without data pre-processing. Specifically, the dice score was improved from 0.9436 to 0.9648 for kidney segmentation and 0.7294 for all types of tumor detections. The performance was suitable for clinical applications with lower computational resources based on the proposed medical image processing methods and deep learning models. The cost efficiency and effectiveness were also achieved for automatic kidney volume calculation and tumor detection accurately.
Collapse
Affiliation(s)
- Chiu-Han Hsiao
- Research Center for Information Technology Innovation, Academia Sinica, Taipei City, Taiwan, ROC
| | - Tzu-Lung Sun
- Department of Information Management, National Taiwan University, Taipei City, Taiwan, ROC
| | - Ping-Cherng Lin
- Research Center for Information Technology Innovation, Academia Sinica, Taipei City, Taiwan, ROC
| | - Tsung-Yu Peng
- Department of Information Management, National Taiwan University, Taipei City, Taiwan, ROC
| | - Yu-Hsin Chen
- Department of Information Management, National Taiwan University, Taipei City, Taiwan, ROC
| | - Chieh-Yun Cheng
- Department of Information Management, National Taiwan University, Taipei City, Taiwan, ROC
| | - Feng-Jung Yang
- Department of Internal Medicine, National Taiwan University Hospital Yunlin Branch, Douliu City, Yunlin County; School of Medicine, College of Medicine, National Taiwan University, Taipei, Taiwan, ROC.
| | - Shao-Yu Yang
- Department of Internal Medicine, National Taiwan University Hospital, Taipei City, Taiwan, ROC
| | - Chih-Horng Wu
- Department of Medical Imaging, National Taiwan University Hospital, Taipei City, Taiwan, ROC
| | - Frank Yeong-Sung Lin
- Department of Information Management, National Taiwan University, Taipei City, Taiwan, ROC
| | - Yennun Huang
- Research Center for Information Technology Innovation, Academia Sinica, Taipei City, Taiwan, ROC
| |
Collapse
|
32
|
Altini N, Prencipe B, Cascarano GD, Brunetti A, Brunetti G, Triggiani V, Carnimeo L, Marino F, Guerriero A, Villani L, Scardapane A, Bevilacqua V. Liver, kidney and spleen segmentation from CT scans and MRI with deep learning: A survey. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2021.08.157] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
|
33
|
Jagtap JM, Gregory AV, Homes HL, Wright DE, Edwards ME, Akkus Z, Erickson BJ, Kline TL. Automated measurement of total kidney volume from 3D ultrasound images of patients affected by polycystic kidney disease and comparison to MR measurements. Abdom Radiol (NY) 2022; 47:2408-2419. [PMID: 35476147 PMCID: PMC9226108 DOI: 10.1007/s00261-022-03521-5] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2022] [Revised: 04/01/2022] [Accepted: 04/04/2022] [Indexed: 11/01/2022]
Abstract
PURPOSE Total kidney volume (TKV) is the most important imaging biomarker for quantifying the severity of autosomal-dominant polycystic kidney disease (ADPKD). 3D ultrasound (US) can accurately measure kidney volume compared to 2D US; however, manual segmentation is tedious and requires expert annotators. We investigated a deep learning-based approach for automated segmentation of TKV from 3D US in ADPKD patients. METHOD We used axially acquired 3D US-kidney images in 22 ADPKD patients where each patient and each kidney were scanned three times, resulting in 132 scans that were manually segmented. We trained a convolutional neural network to segment the whole kidney and measure TKV. All patients were subsequently imaged with MRI for measurement comparison. RESULTS Our method automatically segmented polycystic kidneys in 3D US images obtaining an average Dice coefficient of 0.80 on the test dataset. The kidney volume measurement compared with linear regression coefficient and bias from human tracing were R2 = 0.81, and - 4.42%, and between AI and reference standard were R2 = 0.93, and - 4.12%, respectively. MRI and US measured kidney volumes had R2 = 0.84 and a bias of 7.47%. CONCLUSION This is the first study applying deep learning to 3D US in ADPKD. Our method shows promising performance for auto-segmentation of kidneys using 3D US to measure TKV, close to human tracing and MRI measurement. This imaging and analysis method may be useful in a number of settings, including pediatric imaging, clinical studies, and longitudinal tracking of patient disease progression.
Collapse
|
34
|
Nam S, Kim D, Jung W, Zhu Y. Understanding the Research Landscape of Deep Learning in Biomedical Science: Scientometric Analysis. J Med Internet Res 2022; 24:e28114. [PMID: 35451980 PMCID: PMC9077503 DOI: 10.2196/28114] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2021] [Revised: 05/30/2021] [Accepted: 02/20/2022] [Indexed: 11/13/2022] Open
Abstract
BACKGROUND Advances in biomedical research using deep learning techniques have generated a large volume of related literature. However, there is a lack of scientometric studies that provide a bird's-eye view of them. This absence has led to a partial and fragmented understanding of the field and its progress. OBJECTIVE This study aimed to gain a quantitative and qualitative understanding of the scientific domain by analyzing diverse bibliographic entities that represent the research landscape from multiple perspectives and levels of granularity. METHODS We searched and retrieved 978 deep learning studies in biomedicine from the PubMed database. A scientometric analysis was performed by analyzing the metadata, content of influential works, and cited references. RESULTS In the process, we identified the current leading fields, major research topics and techniques, knowledge diffusion, and research collaboration. There was a predominant focus on applying deep learning, especially convolutional neural networks, to radiology and medical imaging, whereas a few studies focused on protein or genome analysis. Radiology and medical imaging also appeared to be the most significant knowledge sources and an important field in knowledge diffusion, followed by computer science and electrical engineering. A coauthorship analysis revealed various collaborations among engineering-oriented and biomedicine-oriented clusters of disciplines. CONCLUSIONS This study investigated the landscape of deep learning research in biomedicine and confirmed its interdisciplinary nature. Although it has been successful, we believe that there is a need for diverse applications in certain areas to further boost the contributions of deep learning in addressing biomedical research problems. We expect the results of this study to help researchers and communities better align their present and future work.
Collapse
Affiliation(s)
- Seojin Nam
- Department of Library and Information Science, Sungkyunkwan University, Seoul, Republic of Korea
| | - Donghun Kim
- Department of Library and Information Science, Sungkyunkwan University, Seoul, Republic of Korea
| | - Woojin Jung
- Department of Library and Information Science, Sungkyunkwan University, Seoul, Republic of Korea
| | - Yongjun Zhu
- Department of Library and Information Science, Yonsei University, Seoul, Republic of Korea
| |
Collapse
|
35
|
Kittipongdaja P, Siriborvornratanakul T. Automatic kidney segmentation using 2.5D ResUNet and 2.5D DenseUNet for malignant potential analysis in complex renal cyst based on CT images. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING 2022; 2022:5. [PMID: 35340560 PMCID: PMC8938741 DOI: 10.1186/s13640-022-00581-x] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/07/2021] [Accepted: 02/23/2022] [Indexed: 05/26/2023]
Abstract
Bosniak renal cyst classification has been widely used in determining the complexity of a renal cyst. However, it turns out that about half of patients undergoing surgery for Bosniak category III, take surgical risks that reward them with no clinical benefit at all. This is because their pathological results reveal that the cysts are actually benign not malignant. This problem inspires us to use recently popular deep learning techniques and study alternative analytics methods for precise binary classification (benign or malignant tumor) on Computerized Tomography (CT) images. To achieve our goal, two consecutive steps are required-segmenting kidney organs or lesions from CT images then classifying the segmented kidneys. In this paper, we propose a study of kidney segmentation using 2.5D ResUNet and 2.5D DenseUNet for efficiently extracting intra-slice and inter-slice features. Our models are trained and validated on the public data set from Kidney Tumor Segmentation (KiTS19) challenge in two different training environments. As a result, all experimental models achieve high mean kidney Dice scores of at least 95% on the KiTS19 validation set consisting of 60 patients. Apart from the KiTS19 data set, we also conduct separate experiments on abdomen CT images of four Thai patients. Based on the four Thai patients, our experimental models show a drop in performance, where the best mean kidney Dice score is 87.60%.
Collapse
Affiliation(s)
- Parin Kittipongdaja
- Graduate School of Applied Statistics, National Institute of Development Administration, Bangkok, Thailand
| | | |
Collapse
|
36
|
Goel A, Shih G, Riyahi S, Jeph S, Dev H, Hu R, Romano D, Teichman K, Blumenfeld JD, Barash I, Chicos I, Rennert H, Prince MR. Deployed Deep Learning Kidney Segmentation for Polycystic Kidney Disease MRI. Radiol Artif Intell 2022; 4:e210205. [PMID: 35391774 PMCID: PMC8980881 DOI: 10.1148/ryai.210205] [Citation(s) in RCA: 21] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2021] [Revised: 01/20/2022] [Accepted: 01/25/2022] [Indexed: 12/18/2022]
Abstract
This study develops, validates, and deploys deep learning for automated total kidney volume (TKV) measurement (a marker of disease severity) on T2-weighted MRI studies of autosomal dominant polycystic kidney disease (ADPKD). The model was based on the U-Net architecture with an EfficientNet encoder, developed using 213 abdominal MRI studies in 129 patients with ADPKD. Patients were randomly divided into 70% training, 15% validation, and 15% test sets for model development. Model performance was assessed using Dice similarity coefficient (DSC) and Bland-Altman analysis. External validation in 20 patients from outside institutions demonstrated a DSC of 0.98 (IQR, 0.97-0.99) and a Bland-Altman difference of 2.6% (95% CI: 1.0%, 4.1%). Prospective validation in 53 patients demonstrated a DSC of 0.97 (IQR, 0.94-0.98) and a Bland-Altman difference of 3.6% (95% CI: 2.0%, 5.2%). Last, the efficiency of model-assisted annotation was evaluated on the first 50% of prospective cases (n = 28), with a 51% mean reduction in contouring time (P < .001), from 1724 seconds (95% CI: 1373, 2075) to 723 seconds (95% CI: 555, 892). In conclusion, our deployed artificial intelligence pipeline accurately performs automated segmentation for TKV estimation of polycystic kidneys and reduces expert contouring time. Keywords: Convolutional Neural Network (CNN), Segmentation, Kidney ClinicalTrials.gov identification no.: NCT00792155 Supplemental material is available for this article. © RSNA, 2022.
Collapse
Affiliation(s)
- Akshay Goel
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - George Shih
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Sadjad Riyahi
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Sunil Jeph
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Hreedi Dev
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Rejoice Hu
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Dominick Romano
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Kurt Teichman
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Jon D. Blumenfeld
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Irina Barash
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Ines Chicos
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Hanna Rennert
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| | - Martin R. Prince
- From the Departments of Radiology (A.G., G.S., S.R., S.J., H.D.,
R.H., D.R., K.T., M.R.P.), Internal Medicine (J.D.B., I.B., I.C.), and Pathology
and Laboratory Medicine (H.R.), Weill Cornell Medicine, 525 E 68th St, New York,
NY 10021
| |
Collapse
|
37
|
Satoh Y, Funayama S, Onishi H, Kirito K. Semi-automated histogram analysis of normal bone marrow using 18F-FDG PET/CT: correlation with clinical indicators. BMC Med Imaging 2022; 22:31. [PMID: 35197004 PMCID: PMC8867739 DOI: 10.1186/s12880-022-00757-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2021] [Accepted: 02/11/2022] [Indexed: 11/10/2022] Open
Abstract
Background 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) is increasingly applied to the diagnosis of bone marrow failure such as myeloproliferative neoplasm, aplastic anemia, and myelodysplastic syndrome, as well as malignant lymphoma and multiple myeloma. However, few studies have shown a normal FDG uptake pattern. This study aimed to establish a standard of bone marrow FDG uptake by a reproducible quantitative method with fewer steps using deep learning-based organ segmentation. Methods Bone marrow PET images were obtained using segmented whole-spine and pelvic bone marrow cavity CT as mask images using a commercially available imaging workstation that implemented an automatic organ segmentation algorithm based on deep learning. The correlation between clinical indicators and quantitative PET parameters, including histogram features, was evaluated. Results A total of 98 healthy adults were analyzed. The volume of bone marrow PET extracted in men was significantly higher than that in women (p < 0.0001). Univariate and multivariate regression analyses showed that mean of standardized uptake value corrected by lean body mass (SULmean) and entropy in both men and women were inversely correlated with age (all p < 0.0001), and SULmax in women were also inversely correlated with age (p = 0.011). Conclusion A normal FDG uptake pattern was demonstrated by simplified FDG PET/CT bone marrow quantification.
Collapse
Affiliation(s)
- Yoko Satoh
- Yamanashi PET Imaging Clinic, Shimokato 3046-2, Chuo City, Yamanashi Prefecture, 409-3821, Japan. .,Department of Radiology, University of Yamanashi, Shimokato 1110, Chuo City, Yamanashi Prefecture, 409-3898, Japan.
| | - Satoshi Funayama
- Department of Radiology, University of Yamanashi, Shimokato 1110, Chuo City, Yamanashi Prefecture, 409-3898, Japan
| | - Hiroshi Onishi
- Department of Radiology, University of Yamanashi, Shimokato 1110, Chuo City, Yamanashi Prefecture, 409-3898, Japan
| | - Keita Kirito
- Department of Hematology and Oncology, University of Yamanashi, Shimokato 1110, Chuo City, Yamanashi Prefecture, 409-3898, Japan
| |
Collapse
|
38
|
Cayot B, Milot L, Nempont O, Vlachomitrou AS, Langlois-Jacques C, Dumortier J, Boillot O, Arnaud K, Barten TRM, Drenth JPH, Valette PJ. Polycystic liver: automatic segmentation using deep learning on CT is faster and as accurate compared to manual segmentation. Eur Radiol 2022; 32:4780-4790. [PMID: 35142898 DOI: 10.1007/s00330-022-08549-1] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2021] [Revised: 12/18/2021] [Accepted: 12/20/2021] [Indexed: 11/29/2022]
Abstract
OBJECTIVE This study aimed to develop and investigate the performance of a deep learning model based on a convolutional neural network (CNN) for the automatic segmentation of polycystic livers at CT imaging. METHOD This retrospective study used CT images of polycystic livers. To develop the CNN, supervised training and validation phases were performed using 190 CT series. To assess performance, the test phase was performed using 41 CT series. Manual segmentation by an expert radiologist (Rad1a) served as reference for all comparisons. Intra-observer variability was determined by the same reader after 12 weeks (Rad1b), and inter-observer variability by a second reader (Rad2). The Dice similarity coefficient (DSC) evaluated overlap between segmentations. CNN performance was assessed using the concordance correlation coefficient (CCC) and the two-by-two difference between the CCCs; their confidence interval was estimated with bootstrap and Bland-Altman analyses. Liver segmentation time was automatically recorded for each method. RESULTS A total of 231 series from 129 CT examinations on 88 consecutive patients were collected. For the CNN, the DSC was 0.95 ± 0.03 and volume analyses yielded a CCC of 0.995 compared with reference. No statistical difference was observed in the CCC between CNN automatic segmentation and manual segmentations performed to evaluate inter-observer and intra-observer variability. While manual segmentation required 22.4 ± 10.4 min, central and graphics processing units took an average of 5.0 ± 2.1 s and 2.0 ± 1.4 s, respectively. CONCLUSION Compared with manual segmentation, automated segmentation of polycystic livers using a deep learning method achieved much faster segmentation with similar performance. KEY POINTS • Automatic volumetry of polycystic livers using artificial intelligence method allows much faster segmentation than expert manual segmentation with similar performance. • No statistical difference was observed between automatic segmentation, inter-observer variability, or intra-observer variability.
Collapse
Affiliation(s)
- Bénédicte Cayot
- Department of Medical Imaging, Hospices Civils de Lyon, University of Lyon, Lyon, France. .,Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.
| | - Laurent Milot
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Department of Medical Imaging, Edouard Herriot Hospital, Civil Hospices of Lyon, University of Lyon, Lyon, France
| | - Olivier Nempont
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Philips France, 33 rue de Verdun, CS 60 055, Cedex 92156, Suresnes, France
| | - Anna S Vlachomitrou
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Philips France, 33 rue de Verdun, CS 60 055, Cedex 92156, Suresnes, France
| | - Carole Langlois-Jacques
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Unit of Biostatistics, Civil Hospices of Lyon, Lyon ,CNRS UMR5558, Laboratory of Biometry and Evolutionary Biology, Biostatistics-Health Team, Lyon, France
| | - Jérôme Dumortier
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Department of Hepatology and Gastroenterology, Civil Hospices of Lyon, Edouard Herriot Hospital, Federation of Digestive Specialties, University of Lyon, Lyon, France.,University of Lyon, Lyon, France
| | - Olivier Boillot
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,University of Lyon, Lyon, France.,Department of Hepatobiliary-Pancreatic Surgery and Hepatology, Civil Hospices of Lyon, Edouard Herriot Hospital, University of Lyon, Lyon, France
| | - Karine Arnaud
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Edouard Herriot Hospital, Civil Hospices of Lyon, Lyon, France
| | - Thijs R M Barten
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Radboud University Medical Center, Nijmegen, the Netherlands
| | - Joost P H Drenth
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Department of Gastroenterology and Hepatology, Radboud University Medical Center, Nijmegen, the Netherlands
| | - Pierre-Jean Valette
- Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France.,Department of Medical Imaging, Edouard Herriot Hospital, Civil Hospices of Lyon, University of Lyon, Lyon, France
| |
Collapse
|
39
|
Rabbi F, Dabbagh SR, Angin P, Yetisen AK, Tasoglu S. Deep Learning-Enabled Technologies for Bioimage Analysis. MICROMACHINES 2022; 13:mi13020260. [PMID: 35208385 PMCID: PMC8880650 DOI: 10.3390/mi13020260] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Revised: 01/31/2022] [Accepted: 02/03/2022] [Indexed: 02/05/2023]
Abstract
Deep learning (DL) is a subfield of machine learning (ML), which has recently demonstrated its potency to significantly improve the quantification and classification workflows in biomedical and clinical applications. Among the end applications profoundly benefitting from DL, cellular morphology quantification is one of the pioneers. Here, we first briefly explain fundamental concepts in DL and then we review some of the emerging DL-enabled applications in cell morphology quantification in the fields of embryology, point-of-care ovulation testing, as a predictive tool for fetal heart pregnancy, cancer diagnostics via classification of cancer histology images, autosomal polycystic kidney disease, and chronic kidney diseases.
Collapse
Affiliation(s)
- Fazle Rabbi
- Department of Mechanical Engineering, Koç University, Sariyer, Istanbul 34450, Turkey; (F.R.); (S.R.D.)
| | - Sajjad Rahmani Dabbagh
- Department of Mechanical Engineering, Koç University, Sariyer, Istanbul 34450, Turkey; (F.R.); (S.R.D.)
- Koç University Arçelik Research Center for Creative Industries (KUAR), Koç University, Sariyer, Istanbul 34450, Turkey
- Koc University Is Bank Artificial Intelligence Lab (KUIS AILab), Koç University, Sariyer, Istanbul 34450, Turkey
| | - Pelin Angin
- Department of Computer Engineering, Middle East Technical University, Ankara 06800, Turkey;
| | - Ali Kemal Yetisen
- Department of Chemical Engineering, Imperial College London, London SW7 2AZ, UK;
| | - Savas Tasoglu
- Department of Mechanical Engineering, Koç University, Sariyer, Istanbul 34450, Turkey; (F.R.); (S.R.D.)
- Koç University Arçelik Research Center for Creative Industries (KUAR), Koç University, Sariyer, Istanbul 34450, Turkey
- Koc University Is Bank Artificial Intelligence Lab (KUIS AILab), Koç University, Sariyer, Istanbul 34450, Turkey
- Institute of Biomedical Engineering, Boğaziçi University, Çengelköy, Istanbul 34684, Turkey
- Physical Intelligence Department, Max Planck Institute for Intelligent Systems, 70569 Stuttgart, Germany
- Correspondence:
| |
Collapse
|
40
|
Korfiatis P, Denic A, Edwards ME, Gregory AV, Wright DE, Mullan A, Augustine J, Rule AD, Kline TL. Automated Segmentation of Kidney Cortex and Medulla in CT Images: A Multisite Evaluation Study. J Am Soc Nephrol 2022; 33:420-430. [PMID: 34876489 PMCID: PMC8819990 DOI: 10.1681/asn.2021030404] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2021] [Accepted: 11/21/2021] [Indexed: 02/03/2023] Open
Abstract
BACKGROUND In kidney transplantation, a contrast CT scan is obtained in the donor candidate to detect subclinical pathology in the kidney. Recent work from the Aging Kidney Anatomy study has characterized kidney, cortex, and medulla volumes using a manual image-processing tool. However, this technique is time consuming and impractical for clinical care, and thus, these measurements are not obtained during donor evaluations. This study proposes a fully automated segmentation approach for measuring kidney, cortex, and medulla volumes. METHODS A total of 1930 contrast-enhanced CT exams with reference standard manual segmentations from one institution were used to develop the algorithm. A convolutional neural network model was trained (n=1238) and validated (n=306), and then evaluated in a hold-out test set of reference standard segmentations (n=386). After the initial evaluation, the algorithm was further tested on datasets originating from two external sites (n=1226). RESULTS The automated model was found to perform on par with manual segmentation, with errors similar to interobserver variability with manual segmentation. Compared with the reference standard, the automated approach achieved a Dice similarity metric of 0.94 (right cortex), 0.90 (right medulla), 0.94 (left cortex), and 0.90 (left medulla) in the test set. Similar performance was observed when the algorithm was applied on the two external datasets. CONCLUSIONS A fully automated approach for measuring cortex and medullary volumes in CT images of the kidneys has been established. This method may prove useful for a wide range of clinical applications.
Collapse
Affiliation(s)
| | - Aleksandar Denic
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | | | - Adriana V. Gregory
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | | | - Aidan Mullan
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | | | - Andrew D. Rule
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| | - Timothy L. Kline
- Department of Radiology, Mayo Clinic, Rochester, Minnesota,Division of Nephrology and Hypertension, Mayo Clinic, Rochester, Minnesota
| |
Collapse
|
41
|
Klepaczko A, Majos M, Stefańczyk L, Ejkefjord E, Lundervold A. Whole kidney and renal cortex segmentation in contrast-enhanced MRI using a joint classification and segmentation convolutional neural network. Biocybern Biomed Eng 2022. [DOI: 10.1016/j.bbe.2022.02.002] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
|
42
|
Moore MM, Iyer RS, Sarwani NI, Sze RW. Artificial intelligence development in pediatric body magnetic resonance imaging: best ideas to adapt from adults. Pediatr Radiol 2022; 52:367-373. [PMID: 33851261 PMCID: PMC8043435 DOI: 10.1007/s00247-021-05072-1] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/25/2020] [Revised: 02/09/2021] [Accepted: 03/22/2021] [Indexed: 12/22/2022]
Abstract
Emerging manifestations of artificial intelligence (AI) have featured prominently in virtually all industries and facets of our lives. Within the radiology literature, AI has shown great promise in improving and augmenting radiologist workflow. In pediatric imaging, while greatest AI inroads have been made in musculoskeletal radiographs, there are certainly opportunities within thoracoabdominal MRI for AI to add significant value. In this paper, we briefly review non-interpretive and interpretive data science, with emphasis on potential avenues for advancement in pediatric body MRI based on similar work in adults. The discussion focuses on MRI image optimization, abdominal organ segmentation, and osseous lesion detection encountered during body MRI in children.
Collapse
Affiliation(s)
- Michael M Moore
- Department of Radiology, Penn State Children's Hospital, Penn State Health, 500 University Drive, H066, Hershey, PA, 17033, USA.
| | - Ramesh S Iyer
- Seattle Children's Hospital, University of Washington, Seattle, WA, USA
| | | | - Raymond W Sze
- Children's Hospital of Philadelphia, University of Pennsylvania, Philadelphia, PA, USA
| |
Collapse
|
43
|
Kahn C, Leichter I, Lederman R, Sosna J, Duvdevani M, Yeshua T. Quantitative assessment of renal obstruction in multi-phase CTU using automatic 3D segmentation of the renal parenchyma and renal pelvis: A proof of concept. Eur J Radiol Open 2022; 9:100458. [DOI: 10.1016/j.ejro.2022.100458] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Revised: 11/21/2022] [Accepted: 11/24/2022] [Indexed: 11/27/2022] Open
|
44
|
Chantaduly C, Troutt HR, Perez Reyes KA, Zuckerman JE, Chang PD, Lau WL. Artificial Intelligence Assessment of Renal Scarring (AIRS Study). KIDNEY360 2021; 3:83-90. [PMID: 35368566 PMCID: PMC8967621 DOI: 10.34067/kid.0003662021] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/02/2021] [Accepted: 11/11/2021] [Indexed: 01/10/2023]
Abstract
Background The goal of the Artificial Intelligence in Renal Scarring (AIRS) study is to develop machine learning tools for noninvasive quantification of kidney fibrosis from imaging scans. Methods We conducted a retrospective analysis of patients who had one or more abdominal computed tomography (CT) scans within 6 months of a kidney biopsy. The final cohort encompassed 152 CT scans from 92 patients, which included images of 300 native kidneys and 76 transplant kidneys. Two different convolutional neural networks (slice-level and voxel-level classifiers) were tested to differentiate severe versus mild/moderate kidney fibrosis (≥50% versus <50%). Interstitial fibrosis and tubular atrophy scores from kidney biopsy reports were used as ground-truth. Results The two machine learning models demonstrated similar positive predictive value (0.886 versus 0.935) and accuracy (0.831 versus 0.879). Conclusions In summary, machine learning algorithms are a promising noninvasive diagnostic tool to quantify kidney fibrosis from CT scans. The clinical utility of these prediction tools, in terms of avoiding renal biopsy and associated bleeding risks in patients with severe fibrosis, remains to be validated in prospective clinical trials.
Collapse
Affiliation(s)
- Chanon Chantaduly
- Department of Radiological Sciences and Center for Artificial Intelligence in Diagnostic Medicine, University of California Irvine, Orange, California
| | - Hayden R. Troutt
- Division of Nephrology, Department of Medicine, University of California Irvine, Orange, California
| | - Karla A. Perez Reyes
- Division of Nephrology, Department of Medicine, University of California Irvine, Orange, California
| | - Jonathan E. Zuckerman
- Department of Pathology and Laboratory Medicine, David Geffen School of Medicine at University of California Los Angeles, Los Angeles, California
| | - Peter D. Chang
- Department of Radiological Sciences and Center for Artificial Intelligence in Diagnostic Medicine, University of California Irvine, Orange, California
| | - Wei Ling Lau
- Division of Nephrology, Department of Medicine, University of California Irvine, Orange, California
| |
Collapse
|
45
|
Deep-Learning-Based CT Imaging in the Quantitative Evaluation of Chronic Kidney Diseases. JOURNAL OF HEALTHCARE ENGINEERING 2021; 2021:3774423. [PMID: 34745497 PMCID: PMC8568539 DOI: 10.1155/2021/3774423] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/24/2021] [Revised: 09/29/2021] [Accepted: 10/01/2021] [Indexed: 12/02/2022]
Abstract
This study focused on the application of deep learning algorithms in the segmentation of CT images, so as to diagnose chronic kidney diseases accurately and quantitatively. First, the residual dual-attention module (RDA module) was used for automatic segmentation of renal cysts in CT images. 79 patients with renal cysts were selected as research subjects, of whom 27 cases were defined as the test group and 52 cases were defined as the training group. The segmentation results of the test group were evaluated factoring into the Dice similarity coefficient (DSC), precision, and recall. The experimental results showed that the loss function value of the RDA-UNET model rapidly decayed and converged, and the segmentation results of the model in the study were roughly the same as those of manual labeling, indicating that the model had high accuracy in image segmentation, and the contour of the kidney can be segmented accurately. Next, the RDA-UNET model achieved 96.25% DSC, 96.34% precision, and 96.88% recall for the left kidney and 94.22% DSC, 95.34% precision, and 94.61% recall for the right kidney, which were better than other algorithms. The results showed that the algorithm model in this study was superior to other algorithms in each evaluation index. It explained the advantages of this model compared with other algorithm models. In conclusion, the RDA-UNET model can effectively improve the accuracy of CT image segmentation, and it is worth of promotion in the quantitative assessment of chronic kidney diseases through CT imaging.
Collapse
|
46
|
Gladytz T, Millward JM, Cantow K, Hummel L, Zhao K, Flemming B, Periquito JS, Pohlmann A, Waiczies S, Seeliger E, Niendorf T. Reliable kidney size determination by magnetic resonance imaging in pathophysiological settings. Acta Physiol (Oxf) 2021; 233:e13701. [PMID: 34089569 DOI: 10.1111/apha.13701] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2021] [Revised: 05/05/2021] [Accepted: 06/01/2021] [Indexed: 12/24/2022]
Abstract
AIM Kidney diseases constitute a major health challenge, which requires noninvasive imaging to complement conventional approaches to diagnosis and monitoring. Several renal pathologies are associated with changes in kidney size, offering an opportunity for magnetic resonance imaging (MRI) biomarkers of disease. This work uses dynamic MRI and an automated bean-shaped model (ABSM) for longitudinal quantification of pathophysiologically relevant changes in kidney size. METHODS A geometry-based ABSM was developed for kidney size measurements in rats using parametric MRI (T2 , T2 * mapping). The ABSM approach was applied to longitudinal renal size quantification using occlusion of the (a) suprarenal aorta or (b) the renal vein, (c) increase in renal pelvis and intratubular pressure and (d) injection of an X-ray contrast medium into the thoracic aorta to induce pathophysiologically relevant changes in kidney size. RESULTS The ABSM yielded renal size measurements with accuracy and precision equivalent to the manual segmentation, with >70-fold time savings. The automated method could detect a ~7% reduction (aortic occlusion) and a ~5%, a ~2% and a ~6% increase in kidney size (venous occlusion, pelvis and intratubular pressure increase and injection of X-ray contrast medium, respectively). These measurements were not affected by reduced image quality following administration of ferumoxytol. CONCLUSION Dynamic MRI in conjunction with renal segmentation using an ABSM supports longitudinal quantification of changes in kidney size in pathophysiologically relevant experimental setups mimicking realistic clinical scenarios. This can potentially be instrumental for developing MRI-based diagnostic tools for various kidney disorders and for gaining new insight into mechanisms of renal pathophysiology.
Collapse
Affiliation(s)
- Thomas Gladytz
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Jason M Millward
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Kathleen Cantow
- Institute of Physiology, Charité-Universitätsmedizin Berlin, Campus Mitte, Berlin, Germany
| | - Luis Hummel
- Institute of Physiology, Charité-Universitätsmedizin Berlin, Campus Mitte, Berlin, Germany
| | - Kaixuan Zhao
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Bert Flemming
- Institute of Physiology, Charité-Universitätsmedizin Berlin, Campus Mitte, Berlin, Germany
| | - Joāo S Periquito
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany.,Institute of Physiology, Charité-Universitätsmedizin Berlin, Campus Mitte, Berlin, Germany
| | - Andreas Pohlmann
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Sonia Waiczies
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| | - Erdmann Seeliger
- Institute of Physiology, Charité-Universitätsmedizin Berlin, Campus Mitte, Berlin, Germany
| | - Thoralf Niendorf
- Berlin Ultrahigh Field Facility (B.U.F.F.), Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany.,Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max Delbrück Center for Molecular Medicine in the Helmholtz Association, Berlin, Germany
| |
Collapse
|
47
|
Verma A, Chitalia VC, Waikar SS, Kolachalama VB. Machine Learning Applications in Nephrology: A Bibliometric Analysis Comparing Kidney Studies to Other Medicine Subspecialities. Kidney Med 2021; 3:762-767. [PMID: 34693256 PMCID: PMC8515072 DOI: 10.1016/j.xkme.2021.04.012] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022] Open
Abstract
RATIONALE & OBJECTIVES Artificial intelligence driven by machine learning algorithms is being increasingly employed for early detection, disease diagnosis, and clinical management. We explored the use of machine learning-driven advancements in kidney research compared with other organ-specific fields. STUDY DESIGN Cross-sectional bibliometric analysis. SETTING & PARTICIPANTS ISI Web of Science database was queried using specific Medical Subject Headings (MeSH) terms about the organ system, journal International Standard Serial Number, and research methodology. In parallel, we screened the National Institutes of Health (NIH) RePORTER website to explore funded grants that proposed the use of machine learning as a methodology. PREDICTORS Number of publications using machine learning as a research method. OUTCOME Articles were characterized by research methodology among 5 organ systems (brain, heart, kidney, liver, and lung). Grants funded by NIH for machine learning were characterized by study sections. ANALYTICAL APPROACH Percentages of articles using machine learning and other research methodologies were compared among 5 organ systems. RESULTS Machine learning-based articles that are focused on the kidney accounted for 3.2% of the total relevant articles from the 5 organ systems. Specifically, brain research published over 19-fold higher number of articles than kidney research. As compared with machine learning, conventional statistical approaches such as the Cox proportional hazard model were used 9-fold higher in articles related to kidney research. In general, a lower utilization of machine learning-based approaches was observed in organ-specific specialty journals than the broad interdisciplinary journals. The digestive disease, kidney, and urology study sections funded 122 applications proposing machine learning-based approaches compared to 265 applications from the neurology, neuropsychology, and neuropathology study sections. LIMITATIONS Observational study. CONCLUSIONS Our analysis suggests lowest use of machine learning as a research tool among kidney researchers compared with other organ-specific researchers, underscoring a need to better inform the kidney research community about this emerging data analytic tool.
Collapse
Affiliation(s)
- Ashish Verma
- Renal Division, Brigham and Women’s Hospital, Boston, MA
- Section of Nephrology, Boston University School of Medicine and Boston Medical Center, Boston, MA
| | - Vipul C. Chitalia
- Section of Nephrology, Boston University School of Medicine and Boston Medical Center, Boston, MA
- Boston Veterans Affairs Healthcare System, Boston, MA
| | - Sushrut S. Waikar
- Section of Nephrology, Boston University School of Medicine and Boston Medical Center, Boston, MA
| | - Vijaya B. Kolachalama
- Section of Computational Biomedicine, Department of Medicine, School of Medicine, Boston University, Boston, MA
- Department of Computer Science and Faculty of Computing & Data Sciences, Boston University, Boston, MA
| |
Collapse
|
48
|
Connor KL, O'Sullivan ED, Marson LP, Wigmore SJ, Harrison EM. The Future Role of Machine Learning in Clinical Transplantation. Transplantation 2021; 105:723-735. [PMID: 32826798 DOI: 10.1097/tp.0000000000003424] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
Abstract
The use of artificial intelligence and machine learning (ML) has revolutionized our daily lives and will soon be instrumental in healthcare delivery. The rise of ML is due to multiple factors: increasing access to massive datasets, exponential increases in processing power, and key algorithmic developments that allow ML models to tackle increasingly challenging questions. Progressively more transplantation research is exploring the potential utility of ML models throughout the patient journey, although this has not yet widely transitioned into the clinical domain. In this review, we explore common approaches used in ML in solid organ clinical transplantation and consider opportunities for ML to help clinicians and patients. We discuss ways in which ML can aid leverage of large complex datasets, generate cutting-edge prediction models, perform clinical image analysis, discover novel markers in molecular data, and fuse datasets to generate novel insights in modern transplantation practice. We focus on key areas in transplantation in which ML is driving progress, explore the future potential roles of ML, and discuss the challenges and limitations of these powerful tools.
Collapse
Affiliation(s)
- Katie L Connor
- Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, United Kingdom.,Edinburgh Transplant Unit, Royal Infirmary of Edinburgh, Edinburgh, United Kingdom.,Centre for Inflammation Research, University of Edinburgh, Edinburgh, United Kingdom
| | - Eoin D O'Sullivan
- Centre for Inflammation Research, University of Edinburgh, Edinburgh, United Kingdom
| | - Lorna P Marson
- Edinburgh Transplant Unit, Royal Infirmary of Edinburgh, Edinburgh, United Kingdom.,Centre for Inflammation Research, University of Edinburgh, Edinburgh, United Kingdom
| | - Stephen J Wigmore
- Edinburgh Transplant Unit, Royal Infirmary of Edinburgh, Edinburgh, United Kingdom.,Centre for Inflammation Research, University of Edinburgh, Edinburgh, United Kingdom
| | - Ewen M Harrison
- Centre for Medical Informatics, Usher Institute, University of Edinburgh, Edinburgh, United Kingdom
| |
Collapse
|
49
|
Nazari M, Jiménez-Franco LD, Schroeder M, Kluge A, Bronzel M, Kimiaei S. Automated and robust organ segmentation for 3D-based internal dose calculation. EJNMMI Res 2021; 11:53. [PMID: 34100117 PMCID: PMC8184901 DOI: 10.1186/s13550-021-00796-5] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2021] [Accepted: 05/26/2021] [Indexed: 12/29/2022] Open
Abstract
PURPOSE In this work, we address image segmentation in the scope of dosimetry using deep learning and make three main contributions: (a) to extend and optimize the architecture of an existing convolutional neural network (CNN) in order to obtain a fast, robust and accurate computed tomography (CT)-based organ segmentation method for kidneys and livers; (b) to train the CNN with an inhomogeneous set of CT scans and validate the CNN for daily dosimetry; and (c) to evaluate dosimetry results obtained using automated organ segmentation in comparison with manual segmentation done by two independent experts. METHODS We adapted a performant deep learning approach using CT-images to delineate organ boundaries with sufficiently high accuracy and adequate processing time. The segmented organs were consequently used as binary masks for further convolution with a point spread function to retrieve the activity values from quantitatively reconstructed SPECT images for "volumetric"/3D dosimetry. The resulting activities were used to perform dosimetry calculations with the kidneys as source organs. RESULTS The computational expense of the algorithm was sufficient for clinical daily routine, required minimum pre-processing and performed with acceptable accuracy a Dice coefficient of [Formula: see text] for liver segmentation and of [Formula: see text] for kidney segmentation, respectively. In addition, kidney self-absorbed doses calculated using automated segmentation differed by [Formula: see text] from dosimetry performed by two medical physicists in 8 patients. CONCLUSION The proposed approach may accelerate volumetric dosimetry of kidneys in molecular radiotherapy with 177Lu-labelled radiopharmaceuticals such as 177Lu-DOTATOC. However, even though a fully automated segmentation methodology based on CT images accelerates organ segmentation and performs with high accuracy, it does not remove the need for supervision and corrections by experts, mostly due to misalignments in the co-registration between SPECT and CT images. Trial registration EudraCT, 2016-001897-13. Registered 26.04.2016, www.clinicaltrialsregister.eu/ctr-search/search?query=2016-001897-13 .
Collapse
Affiliation(s)
- Mahmood Nazari
- Technische Universität Dresden, Dresden, TU Germany
- ABX - CRO advanced pharmaceutical services, Dresden, Germany
| | | | | | - Andreas Kluge
- ABX - CRO advanced pharmaceutical services, Dresden, Germany
| | - Marcus Bronzel
- ABX - CRO advanced pharmaceutical services, Dresden, Germany
| | - Sharok Kimiaei
- ABX - CRO advanced pharmaceutical services, Dresden, Germany
| |
Collapse
|
50
|
Shin TY, Kim H, Lee JH, Choi JS, Min HS, Cho H, Kim K, Kang G, Kim J, Yoon S, Park H, Hwang YU, Kim HJ, Han M, Bae E, Yoon JW, Rha KH, Lee YS. Expert-level segmentation using deep learning for volumetry of polycystic kidney and liver. Investig Clin Urol 2021; 61:555-564. [PMID: 33135401 PMCID: PMC7606119 DOI: 10.4111/icu.20200086] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2020] [Revised: 06/03/2020] [Accepted: 06/23/2020] [Indexed: 11/18/2022] Open
Abstract
Purpose Volumetry is used in polycystic kidney and liver diseases (PKLDs), including autosomal dominant polycystic kidney disease (ADPKD), to assess disease progression and drug efficiency. However, since no rapid and accurate method for volumetry has been developed, volumetry has not yet been established in clinical practice, hindering the development of therapies for PKLD. This study presents an artificial intelligence (AI)-based volumetry method for PKLD. Materials and Methods The performance of AI was first evaluated in comparison with ground-truth (GT). We trained a V-net-based convolutional neural network on 175 ADPKD computed tomography (CT) segmentations, which served as the GT and were agreed upon by 3 experts using images from 214 patients analyzed with volumetry. The dice similarity coefficient (DSC), interobserver correlation coefficient (ICC), and Bland–Altman plots of 39 GT and AI segmentations in the validation set were compared. Next, the performance of AI on the segmentation of 50 random CT images was compared with that of 11 PKLD specialists based on the resulting DSC and ICC. Results The DSC and ICC of the AI were 0.961 and 0.999729, respectively. The error rate was within 3% for approximately 95% of the CT scans (error<1%, 46.2%; 1%≤error<3%, 48.7%). Compared with the specialists, AI showed moderate performance. Furthermore, an outlier in our results confirmed that even PKLD specialists can make mistakes in volumetry. Conclusions PKLD volumetry using AI was fast and accurate. AI performed comparably to human specialists, suggesting its use may be practical in clinical settings.
Collapse
Affiliation(s)
- Tae Young Shin
- Synergy A.I. Co.Ltd., Chuncheon, Korea.,Department of Urology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
| | - Hyunsuk Kim
- Department of Internal Medicine, Division of Nephrology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
| | | | - Jong Suk Choi
- Department of Urology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
| | | | | | - Kyungwook Kim
- Schulich School of Medicine & Dentistry, The University of Western, Ontario, London, ON, Canada
| | - Geon Kang
- Department of Urology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
| | - Jungkyu Kim
- Department of Urology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
| | - Sieun Yoon
- Schulich School of Medicine & Dentistry, The University of Western, Ontario, London, ON, Canada
| | - Hyungyu Park
- Department of Urology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
| | - Yeong Uk Hwang
- Department of Radiology, Inje University Ilsan Paik Hospital, Goyang, Korea
| | - Hyo Jin Kim
- Department of Internal Medicine, Pusan National University Hospital, Busan, Korea
| | - Miyeun Han
- Department of Internal Medicine, Pusan National University Hospital, Busan, Korea
| | - Eunjin Bae
- Department of Internal Medicine, Gyeongsang National University Changwon Hospital, Gyeongsang National University College of Medicine, Changwon, Korea
| | - Jong Woo Yoon
- Department of Internal Medicine, Division of Nephrology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
| | - Koon Ho Rha
- Department of Urology, Urological Science Institute, Yonsei University College of Medicine, Seoul, Korea
| | - Yong Seong Lee
- Department of Urology, Hallym University Sacred Heart Hospital, Hallym University Collge of Medicine, Anyang, Korea.
| |
Collapse
|