|
1
|
Zhu C, He X, Blumenfeld JD, Hu Z, Dev H, Sattar U, Bazojoo V, Sharbatdaran A, Aspal M, Romano D, Teichman K, Ng He HY, Wang Y, Soto Figueroa A, Weiss E, Prince AG, Chevalier JM, Shimonov D, Moghadam MC, Sabuncu M, Prince MR. A Primer for Utilizing Deep Learning and Abdominal MRI Imaging Features to Monitor Autosomal Dominant Polycystic Kidney Disease Progression. Biomedicines 2024; 12:1133. [PMID: 38791095 PMCID: PMC11118119 DOI: 10.3390/biomedicines12051133] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2024] [Revised: 05/06/2024] [Accepted: 05/13/2024] [Indexed: 05/26/2024] Open
Abstract
Abdominal imaging of autosomal dominant polycystic kidney disease (ADPKD) has historically focused on detecting complications such as cyst rupture, cyst infection, obstructing renal calculi, and pyelonephritis; discriminating complex cysts from renal cell carcinoma; and identifying sources of abdominal pain. Many imaging features of ADPKD are incompletely evaluated or not deemed to be clinically significant, and because of this, treatment options are limited. However, total kidney volume (TKV) measurement has become important for assessing the risk of disease progression (i.e., Mayo Imaging Classification) and predicting tolvaptan treatment's efficacy. Deep learning for segmenting the kidneys has improved these measurements' speed, accuracy, and reproducibility. Deep learning models can also segment other organs and tissues, extracting additional biomarkers to characterize the extent to which extrarenal manifestations complicate ADPKD. In this concept paper, we demonstrate how deep learning may be applied to measure the TKV and how it can be extended to measure additional features of this disease.
Collapse
Affiliation(s)
- Chenglin Zhu
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Xinzi He
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
- Meinig School of Biomedical Engineering, Cornell University, Ithaca, NY 14853, USA
- Cornell Tech, Cornell University, Ithaca, NY 10044, USA
| | - Jon D. Blumenfeld
- The Rogosin Institute, New York, NY 10021, USA; (J.D.B.); (J.M.C.); (D.S.)
- Department of Medicine, Weill Cornell Medicine, New York, NY 10065, USA
| | - Zhongxiu Hu
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Hreedi Dev
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Usama Sattar
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Vahid Bazojoo
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Arman Sharbatdaran
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Mohit Aspal
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Dominick Romano
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Kurt Teichman
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Hui Yi Ng He
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Yin Wang
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Andrea Soto Figueroa
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Erin Weiss
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Anna G. Prince
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - James M. Chevalier
- The Rogosin Institute, New York, NY 10021, USA; (J.D.B.); (J.M.C.); (D.S.)
- Department of Medicine, Weill Cornell Medicine, New York, NY 10065, USA
| | - Daniil Shimonov
- The Rogosin Institute, New York, NY 10021, USA; (J.D.B.); (J.M.C.); (D.S.)
- Department of Medicine, Weill Cornell Medicine, New York, NY 10065, USA
| | - Mina C. Moghadam
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
| | - Mert Sabuncu
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
- Cornell Tech, Cornell University, Ithaca, NY 10044, USA
- School of Electrical and Computer Engineering, Cornell University, Ithaca, NY 14853, USA
| | - Martin R. Prince
- Department of Radiology, Weill Cornell Medicine, New York, NY 10065, USA; (C.Z.); (X.H.); (Z.H.); (H.D.); (U.S.); (V.B.); (A.S.); (M.A.); (D.R.); (K.T.); (H.Y.N.H.); (Y.W.); (A.S.F.); (E.W.); (A.G.P.); (M.C.M.)
- Vagelos College of Physicians and Surgeons, Columbia University Irving Medical Center, New York, NY 10032, USA
| |
Collapse
|
|
2
|
He X, Hu Z, Dev H, Romano DJ, Sharbatdaran A, Raza SI, Wang SJ, Teichman K, Shih G, Chevalier JM, Shimonov D, Blumenfeld JD, Goel A, Sabuncu MR, Prince MR. Test Retest Reproducibility of Organ Volume Measurements in ADPKD Using 3D Multimodality Deep Learning. Acad Radiol 2024; 31:889-899. [PMID: 37798206 PMCID: PMC10957335 DOI: 10.1016/j.acra.2023.09.009] [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: 07/16/2023] [Revised: 08/28/2023] [Accepted: 09/05/2023] [Indexed: 10/07/2023]
Abstract
RATIONALE AND OBJECTIVES Following autosomal dominant polycystic kidney disease (ADPKD) progression by measuring organ volumes requires low measurement variability. The objective of this study is to reduce organ volume measurement variability on MRI of ADPKD patients by utilizing all pulse sequences to obtain multiple measurements which allows outlier analysis to find errors and averaging to reduce variability. MATERIALS AND METHODS In order to make measurements on multiple pulse sequences practical, a 3D multi-modality multi-class segmentation model based on nnU-net was trained/validated using T1, T2, SSFP, DWI and CT from 413 subjects. Reproducibility was assessed with test-re-test methodology on ADPKD subjects (n = 19) scanned twice within a 3-week interval correcting outliers and averaging the measurements across all sequences. Absolute percent differences in organ volumes were compared to paired students t-test. RESULTS Dice similarlity coefficient > 97%, Jaccard Index > 0.94, mean surface distance < 1 mm and mean Hausdorff Distance < 2 cm for all three organs and all five sequences were found on internal (n = 25), external (n = 37) and test-re-test reproducibility assessment (38 scans in 19 subjects). When averaging volumes measured from five MRI sequences, the model automatically segmented kidneys with test-re-test reproducibility (percent absolute difference between exam 1 and exam 2) of 1.3% which was better than all five expert observers. It reliably stratified ADPKD into Mayo Imaging Classification (area under the curve=100%) compared to radiologist. CONCLUSION 3D deep learning measures organ volumes on five MRI sequences leveraging the power of outlier analysis and averaging to achieve 1.3% total kidney test-re-test reproducibility.
Collapse
Affiliation(s)
- Xinzi He
- School of Electrical and Computer Engineering, Cornell University and Cornell Tech, New York, New York (X.H., R.S.); Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Zhongxiu Hu
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Hreedi Dev
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Dominick J Romano
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Arman Sharbatdaran
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Syed I Raza
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Sophie J Wang
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Kurt Teichman
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - George Shih
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - James M Chevalier
- Department of Medicine, Weill Cornell Medicine, New York, New York (J.M.C., D.S., J.D.B.); The Rogosin Institute, New York, New York (J.M.C., D.S., J.D.B.)
| | - Daniil Shimonov
- Department of Medicine, Weill Cornell Medicine, New York, New York (J.M.C., D.S., J.D.B.); The Rogosin Institute, New York, New York (J.M.C., D.S., J.D.B.)
| | - Jon D Blumenfeld
- Department of Medicine, Weill Cornell Medicine, New York, New York (J.M.C., D.S., J.D.B.); The Rogosin Institute, New York, New York (J.M.C., D.S., J.D.B.)
| | - Akshay Goel
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Mert R Sabuncu
- School of Electrical and Computer Engineering, Cornell University and Cornell Tech, New York, New York (X.H., R.S.); Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.)
| | - Martin R Prince
- Department of Radiology, Weill Cornell Medicine, New York, New York (X.H., Z.H., H.D., D.J.R., A.S., S.I.R., S.J.W., K.T., G.S., A.G., R.S., M.R.P.); Columbia University Vagelos College of Physicians and Surgeons, New York, New York (M.R.P.).
| |
Collapse
|
|
3
|
Schmidt EK, Krishnan C, Onuoha E, Gregory AV, Kline TL, Mrug M, Cardenas C, Kim H. Deep learning-based automated kidney and cyst segmentation of autosomal dominant polycystic kidney disease using single vs. multi-institutional data. Clin Imaging 2024; 106:110068. [PMID: 38101228 DOI: 10.1016/j.clinimag.2023.110068] [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: 08/27/2023] [Revised: 12/06/2023] [Accepted: 12/11/2023] [Indexed: 12/17/2023]
Abstract
PURPOSE This study aimed to investigate if a deep learning model trained with a single institution's data has comparable accuracy to that trained with multi-institutional data for segmenting kidney and cyst regions in magnetic resonance (MR) images of patients affected by autosomal dominant polycystic kidney disease (ADPKD). METHODS We used TensorFlow with a Keras custom UNet on 2D slices of 756 MRI images of kidneys with ADPKD obtained from four institutions in the Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) study. The ground truth was determined via a manual plus global thresholding method. Five models were trained with 80 % of all institutional data (n = 604) and each institutional data (n = 232, 172, 148, or 52), respectively, and validated with 10 % and tested on an unseen 10 % of the data. The model's performance was evaluated using the Dice Similarity Coefficient (DSC). RESULTS The DSCs by the model trained with all institutional data ranged from 0.92 to 0.95 for kidney image segmentation, only 1-2 % higher than those by the models trained with single institutional data (0.90-0.93).In cyst segmentation, however, the DSCs by the model trained with all institutional data ranged from 0.83 to 0.89, which were 2-20 % higher than those by the models trained with single institutional data (0.66-0.86). CONCLUSION The UNet performance, when trained with a single institutional dataset, exhibited similar accuracy to the model trained on a multi-institutional dataset. Segmentation accuracy increases with models trained on larger sample sizes, especially in more complex cyst segmentation.
Collapse
Affiliation(s)
- Emma K Schmidt
- Department of Biomedical Engineering, The University of Alabama at Birmingham, Birmingham, AL 35294, USA
| | - Chetana Krishnan
- Department of Biomedical Engineering, The University of Alabama at Birmingham, Birmingham, AL 35294, USA
| | - Ezinwanne Onuoha
- Department of Biomedical Engineering, The University of Alabama at Birmingham, Birmingham, AL 35294, USA
| | | | - Timothy L Kline
- Department of Radiology, Mayo Clinic, Rochester, MN 55902, USA
| | - Michal Mrug
- Department of Veterans Affairs Medical Center, Birmingham, AL 35233, USA; Department of Nephrology, The University of Alabama at Birmingham, Birmingham, AL 35294, USA
| | - Carlos Cardenas
- Department of Biomedical Engineering, The University of Alabama at Birmingham, Birmingham, AL 35294, USA; Department of Radiation Oncology, The University of Alabama at Birmingham, Birmingham, AL 35294, USA.
| | - Harrison Kim
- Department of Biomedical Engineering, The University of Alabama at Birmingham, Birmingham, AL 35294, USA; Department of Radiology, The University of Alabama at Birmingham, Birmingham, AL 35294, USA.
| |
Collapse
|