1
|
Hajjo R, Sabbah DA, Bardaweel SK, Tropsha A. Identification of Tumor-Specific MRI Biomarkers Using Machine Learning (ML). Diagnostics (Basel) 2021; 11:742. [PMID: 33919342 PMCID: PMC8143297 DOI: 10.3390/diagnostics11050742] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2021] [Revised: 04/09/2021] [Accepted: 04/12/2021] [Indexed: 02/06/2023] Open
Abstract
The identification of reliable and non-invasive oncology biomarkers remains a main priority in healthcare. There are only a few biomarkers that have been approved as diagnostic for cancer. The most frequently used cancer biomarkers are derived from either biological materials or imaging data. Most cancer biomarkers suffer from a lack of high specificity. However, the latest advancements in machine learning (ML) and artificial intelligence (AI) have enabled the identification of highly predictive, disease-specific biomarkers. Such biomarkers can be used to diagnose cancer patients, to predict cancer prognosis, or even to predict treatment efficacy. Herein, we provide a summary of the current status of developing and applying Magnetic resonance imaging (MRI) biomarkers in cancer care. We focus on all aspects of MRI biomarkers, starting from MRI data collection, preprocessing and machine learning methods, and ending with summarizing the types of existing biomarkers and their clinical applications in different cancer types.
Collapse
Affiliation(s)
- Rima Hajjo
- Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, P.O. Box 130, Amman 11733, Jordan;
- Laboratory for Molecular Modeling, Division of Chemical Biology and Medicinal Chemistry, Eshelman School of Pharmacy, The University of North Carlina at Chapel Hill, Chapel Hill, NC 27599, USA;
- National Center for Epidemics and Communicable Disease Control, Amman 11118, Jordan
| | - Dima A. Sabbah
- Department of Pharmacy, Faculty of Pharmacy, Al-Zaytoonah University of Jordan, P.O. Box 130, Amman 11733, Jordan;
| | - Sanaa K. Bardaweel
- Department of Pharmaceutical Sciences, School of Pharmacy, University of Jordan, Amman 11942, Jordan;
| | - Alexander Tropsha
- Laboratory for Molecular Modeling, Division of Chemical Biology and Medicinal Chemistry, Eshelman School of Pharmacy, The University of North Carlina at Chapel Hill, Chapel Hill, NC 27599, USA;
| |
Collapse
|
2
|
Liu LY, Liu LH. Imaging Strategies for Rectal Cancer Initial Staging: Does Pelvic Computed Tomography Provide Significantly Additional Findings when High-resolution Magnetic Resonance Imaging has Been Performed? Curr Med Imaging 2020; 16:1029-1033. [PMID: 33081663 DOI: 10.2174/1573405615666191019092606] [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: 05/25/2019] [Revised: 09/05/2019] [Accepted: 10/02/2019] [Indexed: 11/22/2022]
Abstract
BACKGROUND Initial staging of rectal cancer is done by high-resolution magnetic resonance imaging (MRI), however, pelvic computed tomography (CT) is also frequently used. The aim of this study was to evaluate the added clinical benefit of pelvic CT or whether it can alter the initial staging or not. METHODS The study was composed of 187 patients with rectal cancer. Firstly, imaging except pelvic CT was evaluated. Secondly, the pelvic CT was evaluated and the staging was adjusted according to the new findings. Subsequently, the two staging results were compared to investigate the added clinical benefit of pelvic CT. RESULTS Compared with the imaging data except pelvic CT, new findings revealed by the pelvic CT included metastases of the pelvic bone (n = 1) and pelvic peritoneum (n = 3). However, the new findings did not change the primary staging. Of the three patients with pelvic peritoneal metastasis, two were already determined with peritoneal involvement and ascites by abdominal CT, and the third patient was observed with liver and distant lymph node metastasis. Thus, none of their initial stagings needed to be changed. CONCLUSION The addition of pelvic CT to the pre-treatment imaging strategy cannot provide added clinical benefit for the primary evaluation of rectal cancer.
Collapse
Affiliation(s)
- Li-Yan Liu
- Department of Radiology, Tengzhou Maternal and Child Health Hospital, Tengzhou Children's Hospital, Tengzhou, China
| | - Li-Heng Liu
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China
| |
Collapse
|
3
|
deSouza NM, Achten E, Alberich-Bayarri A, Bamberg F, Boellaard R, Clément O, Fournier L, Gallagher F, Golay X, Heussel CP, Jackson EF, Manniesing R, Mayerhofer ME, Neri E, O'Connor J, Oguz KK, Persson A, Smits M, van Beek EJR, Zech CJ. Validated imaging biomarkers as decision-making tools in clinical trials and routine practice: current status and recommendations from the EIBALL* subcommittee of the European Society of Radiology (ESR). Insights Imaging 2019; 10:87. [PMID: 31468205 PMCID: PMC6715762 DOI: 10.1186/s13244-019-0764-0] [Citation(s) in RCA: 51] [Impact Index Per Article: 10.2] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2019] [Accepted: 06/28/2019] [Indexed: 12/12/2022] Open
Abstract
Observer-driven pattern recognition is the standard for interpretation of medical images. To achieve global parity in interpretation, semi-quantitative scoring systems have been developed based on observer assessments; these are widely used in scoring coronary artery disease, the arthritides and neurological conditions and for indicating the likelihood of malignancy. However, in an era of machine learning and artificial intelligence, it is increasingly desirable that we extract quantitative biomarkers from medical images that inform on disease detection, characterisation, monitoring and assessment of response to treatment. Quantitation has the potential to provide objective decision-support tools in the management pathway of patients. Despite this, the quantitative potential of imaging remains under-exploited because of variability of the measurement, lack of harmonised systems for data acquisition and analysis, and crucially, a paucity of evidence on how such quantitation potentially affects clinical decision-making and patient outcome. This article reviews the current evidence for the use of semi-quantitative and quantitative biomarkers in clinical settings at various stages of the disease pathway including diagnosis, staging and prognosis, as well as predicting and detecting treatment response. It critically appraises current practice and sets out recommendations for using imaging objectively to drive patient management decisions.
Collapse
Affiliation(s)
- Nandita M deSouza
- Cancer Research UK Imaging Centre, The Institute of Cancer Research and The Royal Marsden Hospital, Downs Road, Sutton, Surrey, SM2 5PT, UK.
| | | | | | - Fabian Bamberg
- Department of Radiology, University of Freiburg, Freiburg im Breisgau, Germany
| | | | | | | | | | | | - Claus Peter Heussel
- Universitätsklinik Heidelberg, Translational Lung Research Center (TLRC), German Center for Lung Research (DZL), University of Heidelberg, Im Neuenheimer Feld 156, 69120, Heidelberg, Germany
| | - Edward F Jackson
- University of Wisconsin School of Medicine and Public Health, Madison, WI, USA
| | - Rashindra Manniesing
- Department of Radiology and Nuclear Medicine, Radboud University Medical Center, Geert Grooteplein 10, 6525, GA, Nijmegen, The Netherlands
| | | | - Emanuele Neri
- Department of Translational Research, University of Pisa, Pisa, Italy
| | - James O'Connor
- Division of Cancer Sciences, University of Manchester, Manchester, UK
| | | | | | - Marion Smits
- Department of Radiology and Nuclear Medicine (Ne-515), Erasmus MC, PO Box 2040, 3000, CA, Rotterdam, The Netherlands
| | - Edwin J R van Beek
- Edinburgh Imaging, Queen's Medical Research Institute, Edinburgh Bioquarter, 47 Little France Crescent, Edinburgh, UK
| | - Christoph J Zech
- University Hospital Basel, Radiology and Nuclear Medicine, University of Basel, Petersgraben 4, CH-4031, Basel, Switzerland
| |
Collapse
|
4
|
Usefulness of diffusion-weighted MRI in the initial assessment of osseous sarcomas in children and adolescents. Pediatr Radiol 2019; 49:1201-1208. [PMID: 31203404 DOI: 10.1007/s00247-019-04436-y] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/20/2018] [Revised: 04/01/2019] [Accepted: 05/21/2019] [Indexed: 10/26/2022]
Abstract
BACKGROUND Concern regarding gadolinium deposition in the brain after repeated administration of intravenous gadolinium-based contrast agents has prompted evaluation of imaging alternatives. OBJECTIVE The study purpose was to determine if magnetic resonance imaging (MRI) using conventional sequences with diffusion-weighted imaging (DWI) instead of gadolinium-based contrast-enhanced MRI is valid for local staging and guiding biopsies in osseous sarcomas. MATERIALS AND METHODS Initial pretreatment MRI with DWI and gadolinium-based contrast-enhanced images in patients ≤ 18 years with histopathologically proven osseous sarcomas were included. Two radiologists blinded to collated demographic and clinical data, independently reviewed conventional/DWI and conventional/gadolinium-based contrast-enhanced MRI then conventional sequences alone, recording tumor size, skip lesions, necrosis, neurovascular invasion, enlarged lymph nodes and diffusion restriction. Discrepancies were resolved by a third reader. A single reader measured apparent diffusion coefficient (ADC) values in non-necrotic tumors, then correlated minimum ADC values -- with and without normalization to skeletal muscle -- with relative enhancement. RESULTS Twenty-one patients (mean age: 11.3±4.2 years, 15 [71%] females) had 14 osteosarcomas and 7 Ewing sarcomas, 50% centered in the femur. Conventional/DWI versus conventional/gadolinium-based contrast-enhanced MRI showed agreement for tumor size estimation with significant associations for necrosis (P=0.021), neurovascular involvement (P<0.001) and enlarged lymph nodes (P=0.005). Diagnostic accuracy of conventional/DWI is comparable to conventional/gadolinium-based contrast-enhanced MRI and superior to conventional sequences alone. Comparison between minimum ADC values and relative enhancement showed no correlation (P>0.05). CONCLUSION Significant associations of key imaging features in the initial assessment of osseous sarcomas support DWI as an alternative to gadolinium-based contrast-enhanced MRI. The lack of association between ADC values and relative enhancement suggests that they measure independent constructs, DWI dependent upon tumor cellularity and perfusion.
Collapse
|
5
|
Subtil JC, Alcázar JL, Betes MT, Mínguez JÁ, Zozaya FJ, Chacon E, Manzour N, Hidalgo A, Lozano MD, Muñoz-Navas M, Jurado M. Gastrointestinal Endoscopic Ultrasound-Guided Fine-Needle Aspiration for Assessing Suspected Deep Pelvic or Abdominal Recurrence in Gynecologic Cancer: A Feasibility Study. JOURNAL OF ULTRASOUND IN MEDICINE : OFFICIAL JOURNAL OF THE AMERICAN INSTITUTE OF ULTRASOUND IN MEDICINE 2019; 38:761-765. [PMID: 30171619 DOI: 10.1002/jum.14766] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/06/2018] [Revised: 06/26/2018] [Accepted: 06/29/2018] [Indexed: 06/08/2023]
Abstract
OBJECTIVES To assess the feasibility of gastrointestinal endoscopic ultrasound (EUS)-guided fine-needle aspiration (FNA) for histologic confirmation of cancer recurrence in women with gynecologic cancer. METHODS This work was a retrospective cohort study comprising 46 consecutive women treated for gynecologic cancer and suspected of having a deep pelvic or abdominal recurrence on ultrasound imaging, computed tomography, positron emission tomography-computed tomography, or magnetic resonance imaging, evaluated at our institution from January 2010 to December 2017. Primary cancer was ovarian (n = 22), cervical (n = 13), endometrial (n = 4), sarcoma (n = 4), and other (n = 3). All women underwent EUS examinations for locating the lesion and guiding FNA. The results of FNA (benign/malignant) were assessed. Procedure-related complications were recorded. RESULTS The patients' mean age was 57.8 years. A total of 66 procedures were performed. Eleven women underwent 2 procedures; 2 women underwent 3 procedures; and 1 woman underwent 6 procedures at different times during the study period. In 1 case, no lesion was detected on the EUS assessment, and in 2 cases, FNA was not successful. Most lesions were located in the retroperitoneum or involved the intestine. Fine-needle aspiration could be performed in 63 cases (94.5%). Cytologic samples were adequate in 62 of 63 (98.4%). Recurrence was confirmed in 56 cases (90.3%) and ruled out in 6 (9.7%). No patient had any complication related to the procedure. CONCLUSIONS Endoscopic ultrasound-guided FNA is a minimally invasive, feasible, and safe technique for confirming pelvic/abdominal recurrence of gynecologic cancer.
Collapse
Affiliation(s)
- José Carlos Subtil
- Department of Gastroenterology, Clinica Universidad de Navarra, Pamplona, Spain
| | - Juan Luis Alcázar
- Department of Obstetrics and Gynecology, Clinica Universidad de Navarra, Pamplona, Spain
| | - Maria Teresa Betes
- Department of Gastroenterology, Clinica Universidad de Navarra, Pamplona, Spain
| | - José Ángel Mínguez
- Department of Obstetrics and Gynecology, Clinica Universidad de Navarra, Pamplona, Spain
| | | | - Enrique Chacon
- Department of Obstetrics and Gynecology, Clinica Universidad de Navarra, Pamplona, Spain
| | - Nabil Manzour
- Department of Obstetrics and Gynecology, Clinica Universidad de Navarra, Pamplona, Spain
| | - Alberto Hidalgo
- Department of Obstetrics and Gynecology, Hospital Clinico San Cecilio, Granada, Spain
| | | | - Miguel Muñoz-Navas
- Department of Gastroenterology, Clinica Universidad de Navarra, Pamplona, Spain
| | - Matías Jurado
- Department of Obstetrics and Gynecology, Clinica Universidad de Navarra, Pamplona, Spain
| |
Collapse
|
6
|
Hybrid PET/MR: Updated Clinical Use and Potential Applications. CURRENT RADIOLOGY REPORTS 2016. [DOI: 10.1007/s40134-016-0191-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
7
|
Michielsen KLM, Vergote I, Dresen R, Op de Beeck K, Vanslembrouck R, Amant F, Leunen K, Moerman P, Fieuws S, De Keyzer F, Vandecaveye V. Whole-body diffusion-weighted magnetic resonance imaging in the diagnosis of recurrent ovarian cancer: a clinical feasibility study. Br J Radiol 2016; 89:20160468. [PMID: 27585490 DOI: 10.1259/bjr.20160468] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022] Open
Abstract
OBJECTIVE To assess the clinical feasibility of whole-body diffusion-weighted MRI (WB-DWI/MRI) for diagnosis and prediction of complete tumour resection in patients with suspected recurrent ovarian cancer. METHODS 51 females clinically suspected for ovarian cancer recurrence underwent 3-T WB-DWI/MRI in addition to contrast-enhanced CT. WB-DWI/MRI was assessed for detection of tumour recurrence, prediction of tumour extent and complete resection compared with CT. Tumour presence was confirmed by pathology obtained by surgery or biopsy, or by imaging follow-up. RESULTS WB-DWI/MRI showed 94% accuracy for detecting ovarian cancer recurrence, compared with 78% for CT (p = 0.008). WB-DWI/MRI showed better sensitivity [% (95% confidence interval)] than CT for detecting involvement of surgically critical tumour sites including mesenteric root infiltration [92 (62-100) vs 31 (10-61)], small bowel [93 (64-100) vs 21 (6-51)], colon carcinomatosis [91 (57-100) vs 27 (7-61)] and unresectable distant metastases [90 (54-99) vs 20 (4-56)]. WB-DWI/MRI correctly predicted complete resection in 33 of 35 (94%) patients eligible for salvage surgery compared with 17 of 35 (49%) for CT (p < 0.001). CONCLUSION WB-DWI/MRI allowed better detection of ovarian cancer recurrence and better prediction of complete resection than CT. Advances in knowledge: WB-DWI/MRI could assist in optimizing treatment planning for recurrent ovarian cancer, particularly by improving patient selection for salvage surgery, thus giving eligible patients the highest chance on prolonged survival and refraining patients who would not benefit from extensive surgery reducing related morbidity and mortality.
Collapse
Affiliation(s)
| | - Ignace Vergote
- 2 Department of Obstetrics and Gynaecology, Leuven Cancer Institute, University Hospitals Leuven, Leuven, Belgium
| | - Raphaëla Dresen
- 1 Department of Imaging and Pathology, University Hospitals Leuven, Leuven, Belgium
| | - Katya Op de Beeck
- 1 Department of Imaging and Pathology, University Hospitals Leuven, Leuven, Belgium
| | - Ragna Vanslembrouck
- 1 Department of Imaging and Pathology, University Hospitals Leuven, Leuven, Belgium
| | - Frédéric Amant
- 2 Department of Obstetrics and Gynaecology, Leuven Cancer Institute, University Hospitals Leuven, Leuven, Belgium.,3 Belgium and Center Gynaecological Oncology Amsterdam (CGOA), Antoni van Leeuwenhoek, Amsterdam, Netherlands
| | - Karin Leunen
- 2 Department of Obstetrics and Gynaecology, Leuven Cancer Institute, University Hospitals Leuven, Leuven, Belgium
| | - Philippe Moerman
- 1 Department of Imaging and Pathology, University Hospitals Leuven, Leuven, Belgium
| | - Steffen Fieuws
- 4 Department of Public Health and Primary Care, University Hospitals Leuven, Leuven, Belgium
| | - Frederik De Keyzer
- 1 Department of Imaging and Pathology, University Hospitals Leuven, Leuven, Belgium
| | - Vincent Vandecaveye
- 1 Department of Imaging and Pathology, University Hospitals Leuven, Leuven, Belgium
| |
Collapse
|
8
|
Liu LP, Cui LB, Zhang XX, Cao J, Chang N, Tang X, Qi S, Zhang XL, Yin H, Zhang J. Diagnostic Performance of Diffusion-weighted Magnetic Resonance Imaging in Bone Malignancy: Evidence From a Meta-Analysis. Medicine (Baltimore) 2015; 94:e1998. [PMID: 26559290 PMCID: PMC4912284 DOI: 10.1097/md.0000000000001998] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/26/2022] Open
Abstract
Current state-of-the-art nuclear medicine imaging methods (such as PET/CT or bone scintigraphy) may have insufficient sensitivity for predicting bone tumor, and substantial exposure to ionizing radiation is associated with the risk of secondary cancer development. Diffusion-weighted MRI (DW-MRI) is radiation free and requires no intravenous contrast media, and hence is more suitable for population groups that are vulnerable to ionizing radiation and/or impaired renal functions. This meta-analysis was conducted to investigate whether whole-body DW-MRI is a viable means in differentiating bone malignancy. Medline and Embase databases were searched from their inception to May 2015 without language restriction for studies evaluating DW-MRI for detection of bone lesions. Methodological quality was assessed by the quality assessment of diagnostic studies (QUADAS-2) instrument. Sensitivities, specificities, diagnostic odds ratio (DOR), and areas under the curve (AUC) were used as measures of the diagnostic accuracy. We combined the effects by using the random-effects mode. Potential threshold effects and publication bias were investigated. We included data from 32 studies with 1507 patients. The pooled sensitivity, specificity, and AUC were 0.95 (95% CI, 0.90-0.97), 0.92 (95% CI, 0.88-0.95), and 0.98 on a per-patient basis, and they were 0.91 (95% CI, 0.87-0.94), 0.94 (95% CI, 0.90-0.96), and 0.97 on a per-lesion basis. In subgroup analysis, there is no statistical significance found in the sensitivity and specificity of using DWI only and DWI combined with other morphological or functional imaging sequence in both basis (P > 0.05). A b value of 750 to 1000 s/mm enables higher AUC and DOR for whole-body imaging purpose when compared with other values in both basis either (P < 0.01). The ROC space did not show a curvilinear trend of points and a threshold effect was not observed. According to the Deek's plots, there was no publication bias on both basis. Our results support the use of DWI as an effective means for distinguishing malignant bone lesions; however, various imaging parameters need to be standardized prior to its broad use in clinical practice.
Collapse
Affiliation(s)
- Li-Peng Liu
- From the Department of Respiratory Medicine (L-PL, X-XZ, JC, NC, JZ); Department of Radiology, Xijing Hospital, Fourth Military Medical University, Xi'an, China (L-BC, XT, SQ, HY); and Department of Radiology, University of California, San Francisco, California (X-LZ)
| | | | | | | | | | | | | | | | | | | |
Collapse
|