1
|
Santoro-Fernandes V, Huff DT, Rivetti L, Deatsch A, Schott B, Perlman SB, Jeraj R. An automated methodology for whole-body, multimodality tracking of individual cancer lesions. Phys Med Biol 2024; 69:085012. [PMID: 38457838 DOI: 10.1088/1361-6560/ad31c6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2023] [Accepted: 03/08/2024] [Indexed: 03/10/2024]
Abstract
Objective. Manual analysis of individual cancer lesions to assess disease response is clinically impractical and requires automated lesion tracking methodologies. However, no methodology has been developed for whole-body individual lesion tracking, across an arbitrary number of scans, and acquired with various imaging modalities.Approach. This study introduces a lesion tracking methodology and benchmarked it using 2368Ga-DOTATATE PET/CT and PET/MR images of eight neuroendocrine tumor patients. The methodology consists of six steps: (1) alignment of multiple scans via image registration, (2) body-part labeling, (3) automatic lesion-wise dilation, (4) clustering of lesions based on local lesion shape metrics, (5) assignment of lesion tracks, and (6) output of a lesion graph. Registration performance was evaluated via landmark distance, lesion matching accuracy was evaluated between each image pair, and lesion tracking accuracy was evaluated via identical track ratio. Sensitivity studies were performed to evaluate the impact of lesion dilation (fixed versus automatic dilation), anatomic location, image modalities (inter- versus intra-modality), registration mode (direct versus indirect registration), and track size (number of time-points and lesions) on lesion matching and tracking performance.Main results. Manual contouring yielded 956 lesions, 1570 lesion-matching decisions, and 493 lesion tracks. The median residual registration error was 2.5 mm. The automatic lesion dilation led to 0.90 overall lesion matching accuracy, and an 88% identical track ratio. The methodology is robust regarding anatomic locations, image modalities, and registration modes. The number of scans had a moderate negative impact on the identical track ratio (94% for 2 scans, 91% for 3 scans, and 81% for 4 scans). The number of lesions substantially impacted the identical track ratio (93% for 2 nodes versus 54% for ≥5 nodes).Significance. The developed methodology resulted in high lesion-matching accuracy and enables automated lesion tracking in PET/CT and PET/MR.
Collapse
Affiliation(s)
- Victor Santoro-Fernandes
- School of Medicine and Public Health, Department of Medical Physics, University of Wisconsin, Madison, WI, United States of America
| | - Daniel T Huff
- School of Medicine and Public Health, Department of Medical Physics, University of Wisconsin, Madison, WI, United States of America
| | - Luciano Rivetti
- Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia
| | - Alison Deatsch
- School of Medicine and Public Health, Department of Medical Physics, University of Wisconsin, Madison, WI, United States of America
| | - Brayden Schott
- School of Medicine and Public Health, Department of Medical Physics, University of Wisconsin, Madison, WI, United States of America
| | - Scott B Perlman
- School of Medicine and Public Health, Department of Radiology, Section of Nuclear Medicine, University of Wisconsin, Madison, WI, United States of America
| | - Robert Jeraj
- School of Medicine and Public Health, Department of Medical Physics, University of Wisconsin, Madison, WI, United States of America
- Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia
| |
Collapse
|
2
|
Kandemirli SG, Kocak B, Naganawa S, Ozturk K, Yip SSF, Chopra S, Rivetti L, Aldine AS, Jones K, Cayci Z, Moritani T, Sato TS. Machine Learning-Based Multiparametric Magnetic Resonance Imaging Radiomics for Prediction of H3K27M Mutation in Midline Gliomas. World Neurosurg 2021; 151:e78-e85. [PMID: 33819703 DOI: 10.1016/j.wneu.2021.03.135] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2021] [Revised: 03/24/2021] [Accepted: 03/25/2021] [Indexed: 12/19/2022]
Abstract
OBJECTIVE H3K27M mutation in gliomas has prognostic implications. Previous magnetic resonance imaging (MRI) studies have reported variable rates of tumoral enhancement, necrotic changes, and peritumoral edema in H3K27M-mutant gliomas, with no distinguishing imaging features compared with wild-type gliomas. We aimed to construct an MRI machine learning (ML)-based radiomic model to predict H3K27M mutation in midline gliomas. METHODS A total of 109 patients from 3 academic centers were included in this study. Fifty patients had H3K27M mutation and 59 were wild-type. Conventional MRI sequences (T1-weighted, T2-weighted, T2-fluid-attenuated inversion recovery, postcontrast T1-weighted, and apparent diffusion coefficient maps) were used for feature extraction. A total of 651 radiomic features per each sequence were extracted. Patients were randomly selected with a 7:3 ratio to create training (n = 76) and test (n = 33) data sets. An extreme gradient boosting algorithm (XGBoost) was used in ML-based model development. Performance of the model was assessed by area under the receiver operating characteristic curve. RESULTS Pediatric patients accounted for a larger proportion of the study cohort (60 pediatric [55%] vs. 49 adult [45%] patients). XGBoost with additional feature selection had an area under the receiver operating characteristic curve of 0.791 and 0.737 in the training and test data sets, respectively. The model achieved accuracy, precision (positive predictive value), recall (sensitivity), and F1 (harmonic mean of precision and recall) measures of 72.7%, 76.5%, 72.2%, and 74.3%, respectively, in the test set. CONCLUSIONS Our multi-institutional study suggests that ML-based radiomic analysis of multiparametric MRI can be a promising noninvasive technique to predict H3K27M mutation status in midline gliomas.
Collapse
Affiliation(s)
| | - Burak Kocak
- Department of Radiology, Başakşehir Çam and Sakura City Hospital, Istanbul, Turkey
| | - Shotaro Naganawa
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA
| | - Kerem Ozturk
- Department of Radiology, University of Minnesota, Minneapolis, Minnesota, USA
| | - Stephen S F Yip
- Department of Medical Physics, University of Wisconsin, Madison, Wisconsin, USA; AIQ Solutions, Madison, Wisconsin, USA
| | - Saurav Chopra
- Department of Pathology, University of Iowa Hospital and Clinics, Iowa City, Iowa, USA
| | | | - Amro Saad Aldine
- Department of Radiology, Louisiana State University Health Sciences Center, Louisiana, Missouri, USA
| | - Karra Jones
- Department of Pathology, University of Iowa Hospital and Clinics, Iowa City, Iowa, USA
| | - Zuzan Cayci
- Department of Radiology, University of Minnesota, Minneapolis, Minnesota, USA
| | - Toshio Moritani
- Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA
| | - Takashi Shawn Sato
- Department of Radiology, University of Iowa Hospital and Clinics, Iowa City, Iowa, USA
| |
Collapse
|
3
|
Rivetti L, Sitta N, Allocca G, Coro' L, Forte C, Centa M, Mantovan R. P468High resolution micro-bipolar mapping for concealed accessory pathway ablation. Europace 2018. [DOI: 10.1093/europace/euy015.277] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Affiliation(s)
- L Rivetti
- Conegliano General Hospital, Cardiologia, Conegliano, Italy
| | - N Sitta
- Conegliano General Hospital, Cardiologia, Conegliano, Italy
| | - G Allocca
- Conegliano General Hospital, Cardiologia, Conegliano, Italy
| | - L Coro'
- Conegliano General Hospital, Cardiologia, Conegliano, Italy
| | - C Forte
- Conegliano General Hospital, Cardiologia, Conegliano, Italy
| | - M Centa
- Conegliano General Hospital, Cardiologia, Conegliano, Italy
| | - R Mantovan
- Conegliano General Hospital, Cardiologia, Conegliano, Italy
| |
Collapse
|
4
|
Spampinato RA, Kammerlander A, Ondrus T, Cho SW, Gillis K, Italia L, Zito C, Ancona F, Jahnke C, Paetsch I, Hilbert S, Schloma V, Dmitrieva Y, Strotdrees E, Hindricks G, Mohr FW, Wiesinger M, Duca F, Aschauer S, Zotter-Tufaro C, Schwaiger ML, Marzluf BA, Bartko PE, Bonderman D, Mascherbauer J, Mirica DC, Kotrc M, Kockova R, Van Camp G, Mo Y, Praveckova A, Penicka M, Park SJ, Kim SM, Hwang JW, Chang SA, Jeong DS, Lee SC, Park SW, Choe YH, Park PW, Bala G, Roosens B, Hernot S, Remory I, Droogmans S, Cosyns B, Geremia G, Stella S, Marini C, Rosa I, Ancona F, Latib A, Montorfano M, Colombo A, Margonato A, Agricola E, Bracco A, Baldi E, Di Bella G, Cusma Piccione M, Di Nunzio D, Donato R, Manganaro R, Terrizzi A, Pizzino F, Carerj ML, Rivetti L, Bitto R, Sergi M, Carerj S, Agricola E, Stella S, Rosa I, Marini C, Spartera M, Denti P, Margonato A, Hahn R, Alfieri O, Latib A, Colombo A. Rapid Fire Abstract: Multimodality imaging valvular heart disease742Quantification of aortic regurgitation by pulsed Doppler examination of the left subclavian artery velocity contour: a validation study with cardiac magnetic resonance imaging743Diastolic retrograde flow in the descending aorta by cardiovascular magnetic resonance imaging for the quantification of aortic regurgitation744Native T1 relaxation time can accurately identify limited left ventricular contractile reserve in patients with aortic stenosis745The validation and assessment of myocardial fibrosis by using cardiac magnetic resonance and speckle-tracking echocardiography in severe aortic stenosis746Clinical validation of a semi-automatic quantification score of aortic valve calcification with ultrasound747A comparison among conventional 3D-transesophageal echocardiography manual analysis, 3D automatic software analysis and computed tomography for the aortic annulus sizing in TAVI patients748New insights from a multimodality imaging evaluation of LV remodeling in patients with chronic ischemic mitral regurgitation: a combined magnetic resonance and speckle tracking analysis749Multimodality imaging monitoring during percutaneous tricuspid valve repair procedures. Eur Heart J Cardiovasc Imaging 2016. [DOI: 10.1093/ehjci/jew251] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
|
5
|
Campagnucci V, Silva A, Chamlian E, Gandra S, Rivetti L. Surgical removal of vena cava filter located on the right ventricle associated with bilateral pulmonary thromboendarterectomy case report. J Cardiothorac Surg 2013. [PMCID: PMC3846103 DOI: 10.1186/1749-8090-8-s1-p56] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022] Open
|
6
|
Campagnucci V, Silva A, Pereira W, Peroni A, Chamlian E, Gandra S, Scatolini A, Lourenço U, Silva F, Rivetti L. The use of implantable cardioverter defibrillators in pediatric patients. J Cardiothorac Surg 2013. [PMCID: PMC3844971 DOI: 10.1186/1749-8090-8-s1-o84] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022] Open
|
7
|
Guarini A, Amodio F, Rivetti L, Bonfiglio N. [Clinical experiences in the treatment of arrhythmias with bunaftine (Meregon)]. Minerva Cardioangiol 1975; 23:932-6. [PMID: 1232589] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
|