1
|
Galbusera F, Cina A. Image annotation and curation in radiology: an overview for machine learning practitioners. Eur Radiol Exp 2024; 8:11. [PMID: 38316659 PMCID: PMC10844188 DOI: 10.1186/s41747-023-00408-y] [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] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2023] [Accepted: 11/07/2023] [Indexed: 02/07/2024] Open
Abstract
"Garbage in, garbage out" summarises well the importance of high-quality data in machine learning and artificial intelligence. All data used to train and validate models should indeed be consistent, standardised, traceable, correctly annotated, and de-identified, considering local regulations. This narrative review presents a summary of the techniques that are used to ensure that all these requirements are fulfilled, with special emphasis on radiological imaging and freely available software solutions that can be directly employed by the interested researcher. Topics discussed include key imaging concepts, such as image resolution and pixel depth; file formats for medical image data storage; free software solutions for medical image processing; anonymisation and pseudonymisation to protect patient privacy, including compliance with regulations such as the Regulation (EU) 2016/679 "General Data Protection Regulation" (GDPR) and the 1996 United States Act of Congress "Health Insurance Portability and Accountability Act" (HIPAA); methods to eliminate patient-identifying features within images, like facial structures; free and commercial tools for image annotation; and techniques for data harmonisation and normalisation.Relevance statement This review provides an overview of the methods and tools that can be used to ensure high-quality data for machine learning and artificial intelligence applications in radiology.Key points• High-quality datasets are essential for reliable artificial intelligence algorithms in medical imaging.• Software tools like ImageJ and 3D Slicer aid in processing medical images for AI research.• Anonymisation techniques protect patient privacy during dataset preparation.• Machine learning models can accelerate image annotation, enhancing efficiency and accuracy.• Data curation ensures dataset integrity, compliance, and quality for artificial intelligence development.
Collapse
Affiliation(s)
- Fabio Galbusera
- Spine Center, Schulthess Clinic, Lengghalde 2, Zurich, 8008, Switzerland.
| | - Andrea Cina
- Spine Center, Schulthess Clinic, Lengghalde 2, Zurich, 8008, Switzerland
- ETH Zürich, Department of Health Sciences and Technologies, Zurich, Switzerland
| |
Collapse
|
2
|
Rubbert C, Wolf L, Vach M, Ivan VL, Hedderich DM, Gaser C, Dahnke R, Caspers J. Normal cohorts in automated brain atrophy estimation: how many healthy subjects to include? Eur Radiol 2024:10.1007/s00330-023-10522-5. [PMID: 38189981 DOI: 10.1007/s00330-023-10522-5] [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] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 11/17/2023] [Accepted: 11/25/2023] [Indexed: 01/09/2024]
Abstract
OBJECTIVES This study investigates the influence of normal cohort (NC) size and the impact of different NCs on automated MRI-based brain atrophy estimation. METHODS A pooled NC of 3945 subjects (NCpool) was retrospectively created from five publicly available cohorts. Voxel-wise gray matter volume atrophy maps were calculated for 48 Alzheimer's disease (AD) patients (55-82 years) using veganbagel and dynamic normal templates with an increasing number of healthy subjects randomly drawn from NCpool (initially three, and finally 100 subjects). Over 100 repeats of the process, the mean over a voxel-wise standard deviation of gray matter z-scores was established and plotted against the number of subjects in the templates. The knee point of these curves was defined as the minimum number of subjects required for consistent brain atrophy estimation. Atrophy maps were calculated using each NC for AD patients and matched healthy controls (HC). Two readers rated the extent of mesiotemporal atrophy to discriminate AD/HC. RESULTS The maximum knee point was at 15 subjects. For 21 AD/21 HC, a sufficient number of subjects were available in each NC for validation. Readers agreed on the AD diagnosis in all cases (Kappa for the extent of atrophy, 0.98). No differences in diagnoses between NCs were observed (intraclass correlation coefficient, 0.91; Cochran's Q, p = 0.19). CONCLUSION At least 15 subjects should be included in age- and sex-specific normal templates for consistent brain atrophy estimation. In the study's context, qualitative interpretation of regional atrophy allows reliable AD diagnosis with a high inter-reader agreement, irrespective of the NC used. CLINICAL RELEVANCE STATEMENT The influence of normal cohorts (NCs) on automated brain atrophy estimation, typically comparing individual scans to NCs, remains largely unexplored. Our study establishes the minimum number of NC-subjects needed and demonstrates minimal impact of different NCs on regional atrophy estimation. KEY POINTS • Software-based brain atrophy estimation often relies on normal cohorts for comparisons. • At least 15 subjects must be included in an age- and sex-specific normal cohort. • Using different normal cohorts does not influence regional atrophy estimation.
Collapse
Affiliation(s)
- Christian Rubbert
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University, Düsseldorf, Germany.
| | - Luisa Wolf
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University, Düsseldorf, Germany
| | - Marius Vach
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University, Düsseldorf, Germany
| | - Vivien L Ivan
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University, Düsseldorf, Germany
| | - Dennis M Hedderich
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Technical University of Munich, D-81675, Munich, Germany
| | - Christian Gaser
- Department of Psychiatry and Psychotherapy, Jena University Hospital, D-07745, Jena, Germany
- Department of Neurology, Jena University Hospital, D-07745, Jena, Germany
- German Center for Mental Health (DZPG), Jena, Germany
| | - Robert Dahnke
- Department of Psychiatry and Psychotherapy, Jena University Hospital, D-07745, Jena, Germany
- Department of Neurology, Jena University Hospital, D-07745, Jena, Germany
- German Center for Mental Health (DZPG), Jena, Germany
- Center of Functionally Integrative Neuroscience, Aarhus University, 8000, Aarhus, Denmark
| | - Julian Caspers
- Department of Diagnostic and Interventional Radiology, Medical Faculty and University Hospital Düsseldorf, Heinrich-Heine-University, Düsseldorf, Germany
| |
Collapse
|
3
|
Heiss R, Weber MA, Balbach EL, Hinsen M, Geissler F, Nagel AM, Ladd ME, Arkudas A, Horch RE, Gall C, Uder M, Roemer FW. Variation in cartilage T2 and T2* mapping of the wrist: a comparison between 3- and 7-T MRI. Eur Radiol Exp 2023; 7:80. [PMID: 38093075 PMCID: PMC10719234 DOI: 10.1186/s41747-023-00394-1] [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] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Accepted: 09/30/2023] [Indexed: 12/17/2023] Open
Abstract
BACKGROUND To analyze regional variations in T2 and T2* relaxation times in wrist joint cartilage and the triangular fibrocartilage complex (TFCC) at 3 and 7 T and to compare values between field strengths. METHODS Twenty-five healthy controls and 25 patients with chronic wrist pain were examined at 3 and 7 T on the same day using T2- and T2*-weighted sequences. Six different regions of interest (ROIs) were evaluated for cartilage and 3 ROIs were evaluated at the TFCC based on manual segmentation. Paired t-tests were used to compare T2 and T2* values between field strengths and between different ROIs. Spearman's rank correlation was calculated to assess correlations between T2 and T2* time values at 3 and 7 T. RESULTS T2 and T2* time values of the cartilage differed significantly between 3 and 7 T for all ROIs (p ≤ 0.045), with one exception: at the distal lunate, no significant differences in T2 values were observed between field strengths. T2* values differed significantly between 3 and 7 T for all ROIs of the TFCC (p ≤ 0.001). Spearman's rank correlation between 3 and 7 T ranged from 0.03 to 0.62 for T2 values and from 0.01 to 0.48 for T2* values. T2 and T2* values for cartilage varied across anatomic locations in healthy controls at both 3 and 7 T. CONCLUSION Quantitative results of T2 and T2* mapping at the wrist differ between field strengths, with poor correlation between 3 and 7 T. Local variations in cartilage T2 and T2* values are observed in healthy individuals. RELEVANCE STATEMENT T2 and T2* mapping are feasible for compositional imaging of the TFCC and the cartilage at the wrist at both 3 and 7 T, but the clinical interpretation remains challenging due to differences between field strengths and variations between anatomic locations. KEY POINTS •Field strength and anatomic locations influence T2 and T2* values at the wrist. •T2 and T2* values have a poor correlation between 3 and 7 T. •Local reference values are needed for each anatomic location for reliable interpretation.
Collapse
Affiliation(s)
- Rafael Heiss
- Department of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3, 91054, Erlangen, Germany.
| | - Marc-André Weber
- Institute of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology, University Medical Center Rostock, Schillingallee 35, 18057, Rostock, Germany
| | - Eva L Balbach
- Department of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3, 91054, Erlangen, Germany
| | - Maximilian Hinsen
- Department of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3, 91054, Erlangen, Germany
| | - Frederik Geissler
- Department of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3, 91054, Erlangen, Germany
| | - Armin M Nagel
- Department of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3, 91054, Erlangen, Germany
- Medical Physics in Radiology, German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, 69120, Heidelberg, Germany
| | - Mark E Ladd
- Medical Physics in Radiology, German Cancer Research Center (DKFZ), Im Neuenheimer Feld 280, 69120, Heidelberg, Germany
- Faculty of Medicine and Faculty of Physics and Astronomy, Heidelberg University, Im Neuenheimer Feld 226, 69120, Heidelberg, Germany
| | - Andreas Arkudas
- Department of Plastic and Hand Surgery and Laboratory for Tissue Engineering and Regenerative Medicine, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Krankenhausstraße 12, 91054, Erlangen, Germany
| | - Raymund E Horch
- Department of Plastic and Hand Surgery and Laboratory for Tissue Engineering and Regenerative Medicine, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Krankenhausstraße 12, 91054, Erlangen, Germany
| | - Christine Gall
- Institute for Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Waldstraße 6, 91054, Erlangen, Germany
| | - Michael Uder
- Department of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3, 91054, Erlangen, Germany
| | - Frank W Roemer
- Department of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Maximiliansplatz 3, 91054, Erlangen, Germany
- Boston University School of Medicine, 72 E Concord St, Boston, MA, 02118, USA
| |
Collapse
|
4
|
Gennaro G, Povolo L, Del Genio S, Ciampani L, Fasoli C, Carlevaris P, Petrioli M, Masiero T, Maggetto F, Caumo F. Using automated software evaluation to improve the performance of breast radiographers in tomosynthesis screening. Eur Radiol 2023:10.1007/s00330-023-10457-x. [PMID: 38019313 DOI: 10.1007/s00330-023-10457-x] [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] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2023] [Revised: 09/22/2023] [Accepted: 10/15/2023] [Indexed: 11/30/2023]
Abstract
OBJECTIVE To improve breast radiographers' individual performance by using automated software to assess the correctness of breast positioning and compression in tomosynthesis screening. MATERIALS AND METHODS In this retrospective longitudinal analysis of prospective cohorts, six breast radiographers with varying experience in the field were asked to use automated software to improve their performance in breast compression and positioning. The software tool automatically analyzes craniocaudal (CC) and mediolateral oblique (MLO) views for their positioning quality by scoring them according to PGMI classifications (perfect, good, moderate, inadequate) and checking whether the compression pressure is within the target range. The positioning and compression data from the studies acquired before the start of the project were used as individual baselines, while the data obtained after the training were used to test whether conscious use of the software could help the radiographers improve their performance. The percentage of views rated perfect or good and the percentage of views in target compression were used as overall metrics to assess changes in performance. RESULTS Following the use of the software, all radiographers significantly increased the percentage of images rated as perfect or good in both CCs and MLOs. Individual improvements ranged from 7 to 14% for CC and 10 to 16% for MLO views. Moreover, most radiographers exhibited improved compression performance in CCs, with improvements up to 16%. CONCLUSION Active use of a software tool to automatically assess the correctness of breast compression and positioning in breast cancer screening can improve the performance of radiographers. CLINICAL RELEVANCE STATEMENT This study suggests that the use of a software tool for automatically evaluating correctness of breast compression and positioning in breast cancer screening can improve the performance of radiographers on these metrics, which may ultimately lead to improved screening outcomes. KEY POINTS • Proper breast positioning and compression are critical in breast cancer screening to ensure accurate diagnosis. • Active use of the software increased the quality of craniocaudal and mediolateral oblique views acquired by all radiographers. • Improved performance of radiographers is expected to improve screening outcomes.
Collapse
Affiliation(s)
- Gisella Gennaro
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy.
| | - Letizia Povolo
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| | - Sara Del Genio
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| | - Lina Ciampani
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| | - Chiara Fasoli
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| | - Paolo Carlevaris
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| | - Maria Petrioli
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| | - Tiziana Masiero
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| | - Federico Maggetto
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| | - Francesca Caumo
- Unit of Breast Radiology, Department of Imaging and Radiotherapy, Veneto Institute of Oncology (IOV), IRCCS, via Gattamelata 64, 35128, Padua, Italy
| |
Collapse
|
5
|
Noordman CR, Yakar D, Bosma J, Simonis FFJ, Huisman H. Complexities of deep learning-based undersampled MR image reconstruction. Eur Radiol Exp 2023; 7:58. [PMID: 37789241 PMCID: PMC10547669 DOI: 10.1186/s41747-023-00372-7] [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] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Accepted: 08/01/2023] [Indexed: 10/05/2023] Open
Abstract
Artificial intelligence has opened a new path of innovation in magnetic resonance (MR) image reconstruction of undersampled k-space acquisitions. This review offers readers an analysis of the current deep learning-based MR image reconstruction methods. The literature in this field shows exponential growth, both in volume and complexity, as the capabilities of machine learning in solving inverse problems such as image reconstruction are explored. We review the latest developments, aiming to assist researchers and radiologists who are developing new methods or seeking to provide valuable feedback. We shed light on key concepts by exploring the technical intricacies of MR image reconstruction, highlighting the importance of raw datasets and the difficulty of evaluating diagnostic value using standard metrics.Relevance statement Increasingly complex algorithms output reconstructed images that are difficult to assess for robustness and diagnostic quality, necessitating high-quality datasets and collaboration with radiologists.Key points• Deep learning-based image reconstruction algorithms are increasing both in complexity and performance.• The evaluation of reconstructed images may mistake perceived image quality for diagnostic value.• Collaboration with radiologists is crucial for advancing deep learning technology.
Collapse
Affiliation(s)
- Constant Richard Noordman
- Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Nijmegen, 6525 GA, The Netherlands.
| | - Derya Yakar
- Medical Imaging Center, Departments of Radiology, Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, Groningen, 9700 RB, The Netherlands
| | - Joeran Bosma
- Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Nijmegen, 6525 GA, The Netherlands
| | | | - Henkjan Huisman
- Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Nijmegen, 6525 GA, The Netherlands
- Department of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, 7030, Norway
| |
Collapse
|
6
|
Midthun P, Kirkhus E, Østerås BH, Høiness PR, England A, Johansen S. Metal artifact reduction on musculoskeletal CT: a phantom and clinical study. Eur Radiol Exp 2023; 7:46. [PMID: 37524994 PMCID: PMC10390408 DOI: 10.1186/s41747-023-00354-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [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: 02/08/2023] [Accepted: 05/10/2023] [Indexed: 08/02/2023] Open
Abstract
BACKGROUND Artifacts caused by metal implants are challenging when undertaking computed tomography (CT). Dedicated algorithms have shown promising results although with limitations. Tin filtration (Sn) in combination with high tube voltage also shows promise but with limitations. There is a need to examine these limitations in more detail. The purpose of this study was to investigate the impact of different metal artefact reduction (MAR) algorithms, tin filtration, and ultra-high-resolution (UHR) scanning, alone or in different combinations in both phantom and clinical settings. METHODS An ethically approved clinical and phantom study was conducted. A modified Catphan® phantom with titanium and stainless-steel inserts was scanned with six different MAR protocols with tube voltage ranging from 80 to 150 kVp. Other scan parameters were kept identical. The differences (∆) in mean HU and standard deviation (SD) in images, with and without metal, were measured and compared. In the clinical study, three independent readers performed visual image quality assessments on eight different protocols using retrospectively acquired images. RESULTS Iterative MAR had the lowest ∆HU and ∆SD in the phantom study. For images of the forearm, the soft tissue noise for Sn-based 150-kVp UHR protocol with was significantly higher (p = 0.037) than for single-energy MAR protocols. All Sn-based 150-kVp protocols were rated significantly higher (p < 0.046 than the single-energy MAR protocols in the visual assessment. CONCLUSIONS All Sn-based 150-kVp UHR protocols showed similar objective MAR in the phantom study, and higher objective MAR and significantly improved visual image quality than single-energy MAR. RELEVANCE STATEMENT Images with less metal artifacts and higher visual image quality may be more clinically optimal in CT examination of musculoskeletal patients with metal implants. KEY POINTS • Metal artifact reduction algorithms and Sn filter combined with high kVp reduce artifacts. • Metal artifact reduction algorithms introduce new artifacts in certain metals. • Sn-based protocols alone may be considered as low metal artifact protocols.
Collapse
Affiliation(s)
- Petter Midthun
- Health Faculty, Oslo Metropolitan University, Pilestredet 48, 0130, Oslo, Norway
- Department of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway
| | - Eva Kirkhus
- Department of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway
| | - Bjørn Helge Østerås
- Department of Physics and Image Analysis, Oslo University Hospital, Oslo, Norway
| | | | - Andrew England
- School of Medicine, University College Cork, Cork, England
| | - Safora Johansen
- Health Faculty, Oslo Metropolitan University, Pilestredet 48, 0130, Oslo, Norway.
- Department of Cancer Treatment, Oslo University Hospital, Oslo, Norway.
| |
Collapse
|
7
|
Yamamoto S, Higaki A. Visual Turing test is not sufficient to evaluate the performance of medical generative models. Eur Radiol Exp 2023; 7:31. [PMID: 37423911 PMCID: PMC10329967 DOI: 10.1186/s41747-023-00347-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Accepted: 04/21/2023] [Indexed: 07/11/2023] Open
Affiliation(s)
- Shoichiro Yamamoto
- Department of Cardiology, Pulmonology, Hypertension and Nephrology, Ehime University Graduate School of Medicine, 454 Shitsukawa, Toon, Ehime, 791-0295, Japan
| | - Akinori Higaki
- Department of Cardiology, Pulmonology, Hypertension and Nephrology, Ehime University Graduate School of Medicine, 454 Shitsukawa, Toon, Ehime, 791-0295, Japan.
| |
Collapse
|
8
|
Breit HC, Vosshenrich J, Clauss M, Weikert TJ, Stieltjes B, Kovacs BK, Bach M, Harder D. Visual and quantitative assessment of hip implant-related metal artifacts at low field MRI: a phantom study comparing a 0.55-T system with 1.5-T and 3-T systems. Eur Radiol Exp 2023; 7:5. [PMID: 36750494 DOI: 10.1186/s41747-023-00320-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2022] [Accepted: 12/30/2022] [Indexed: 02/09/2023] Open
Abstract
BACKGROUND To investigate hip implant-related metal artifacts on a 0.55-T system compared with 1.5-T and 3-T systems. METHODS Total hip arthroplasty made of three different alloys were evaluated in a water phantom at 0.55, 1.5, and 3 T using routine protocols. Visually assessment (VA) was performed by three readers using a Likert scale from 0 (no artifacts) to 6 (extremely severe artifacts). Quantitative assessment (QA) was performed using the coefficient of variation (CoV) and the fraction of voxels within a threshold of the mean signal intensity compared to an automatically defined region of interest (FVwT). Agreement was evaluated using intra/inter-class correlation coefficient (ICC). RESULTS Interreader agreement of VA was strong-to-moderate (ICC 0.74-0.82). At all field strengths (0.55-T/1.5-T/3-T), artifacts were assigned a lower score for titanium (Ti) alloys (2.44/2.9/2.7) than for stainless steel (Fe-Cr) (4.1/3.9/5.1) and cobalt-chromium (Co-Cr) alloys (4.1/4.1/5.2) (p < 0.001 for both). Artifacts were lower for 0.55-T and 1.5-T than for 3-T systems, for all implants (p ≤ 0.049). A strong VA-to-QA correlation was found (r = 0.81; p < 0.001); CoV was lower for Ti alloys than for Fe-Cr and Co-Cr alloys at all field strengths. The FVwT showed a negative correlation with VA (-0.68 < r < -0.84; p < 0.001). CONCLUSIONS Artifact intensity was lowest for Ti alloys at 0.55 T. For other alloys, it was similar at 0.55 T and 1.5 T, higher at 3 T. Despite an inferior gradient system and a larger bore width, the 0.55-T system showed the same artifact intensity of the 1.5-T system.
Collapse
|
9
|
Hamdy E, Galeel AA, Ramadan I, Gaber D, Mustafa H, Mekky J. Iron deposition in multiple sclerosis: overall load or distribution alteration? Eur Radiol Exp 2022; 6:49. [PMID: 36074209 PMCID: PMC9458829 DOI: 10.1186/s41747-022-00279-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Accepted: 04/14/2022] [Indexed: 11/14/2022] Open
Abstract
Background Though abnormal iron deposition has been reported in specific brain regions in multiple sclerosis (MS), no data exist about whether the overall quantity of iron in the brain is altered or not. We aimed to determine whether the noted aberrant iron deposition in MS brains was a problem of overall load or regional distribution in a cohort of MS patients. Methods An experienced neuroradiologist, a radiology software engineer, and four neurologists analysed data from quantitative susceptibility maps reconstructed from 3-T magnetic resonance brain images of 30 MS patients and 15 age- and sex-matched healthy controls. Global brain iron load was calculated, and the regional iron concentrations were assessed in 1,000 regions of interest placed in MS lesions in different locations, normal appearing white matter, thalami, and basal ganglia. Results Global brain iron load was comparable between patients and controls after adjustment for volume (p = 0.660), whereas the regional iron concentrations were significantly different in patients than in control (p ≤ 0.031). There was no significant correlation between global iron load and clinical parameters, whereas regional iron concentrations correlated with patients’ age, disease duration, and disability grade (p ≤ 0.039). Conclusions The aberrant iron deposition noted in MS seems to be a problem of regional distribution rather than an altered global brain iron load. Supplementary Information The online version contains supplementary material available at 10.1186/s41747-022-00279-9.
Collapse
Affiliation(s)
- Eman Hamdy
- Department of Neurology, Faculty of Medicine, Alexandria University, Alexandria, Egypt.
| | - Aya Abdel Galeel
- Department of Radiology, Faculty of Medicine, Alexandria University, Alexandria, Egypt
| | - Ismail Ramadan
- Department of Neurology, Faculty of Medicine, Alexandria University, Alexandria, Egypt
| | - Dina Gaber
- Department of Neurology, Faculty of Medicine, Alexandria University, Alexandria, Egypt
| | | | - Jaidaa Mekky
- Department of Neurology, Faculty of Medicine, Alexandria University, Alexandria, Egypt
| |
Collapse
|
10
|
Sunoqrot MRS, Saha A, Hosseinzadeh M, Elschot M, Huisman H. Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges. Eur Radiol Exp 2022; 6:35. [PMID: 35909214 PMCID: PMC9339427 DOI: 10.1186/s41747-022-00288-8] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Accepted: 05/09/2022] [Indexed: 11/29/2022] Open
Abstract
Artificial intelligence (AI) for prostate magnetic resonance imaging (MRI) is starting to play a clinical role for prostate cancer (PCa) patients. AI-assisted reading is feasible, allowing workflow reduction. A total of 3,369 multi-vendor prostate MRI cases are available in open datasets, acquired from 2003 to 2021 in Europe or USA at 3 T (n = 3,018; 89.6%) or 1.5 T (n = 296; 8.8%), 346 cases scanned with endorectal coil (10.3%), 3,023 (89.7%) with phased-array surface coils; 412 collected for anatomical segmentation tasks, 3,096 for PCa detection/classification; for 2,240 cases lesions delineation is available and 56 cases have matching histopathologic images; for 2,620 cases the PSA level is provided; the total size of all open datasets amounts to approximately 253 GB. Of note, quality of annotations provided per dataset highly differ and attention must be paid when using these datasets (e.g., data overlap). Seven grand challenges and commercial applications from eleven vendors are here considered. Few small studies provided prospective validation. More work is needed, in particular validation on large-scale multi-institutional, well-curated public datasets to test general applicability. Moreover, AI needs to be explored for clinical stages other than detection/characterization (e.g., follow-up, prognosis, interventions, and focal treatment).
Collapse
Affiliation(s)
- Mohammed R S Sunoqrot
- Department of Circulation and Medical Imaging, NTNU-Norwegian University of Science and Technology, 7030, Trondheim, Norway. .,Department of Radiology and Nuclear Medicine, St. Olavs Hospital, Trondheim University Hospital, 7030, Trondheim, Norway.
| | - Anindo Saha
- Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Nijmegen, 6525 GA, The Netherlands
| | - Matin Hosseinzadeh
- Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Nijmegen, 6525 GA, The Netherlands
| | - Mattijs Elschot
- Department of Circulation and Medical Imaging, NTNU-Norwegian University of Science and Technology, 7030, Trondheim, Norway.,Department of Radiology and Nuclear Medicine, St. Olavs Hospital, Trondheim University Hospital, 7030, Trondheim, Norway
| | - Henkjan Huisman
- Department of Circulation and Medical Imaging, NTNU-Norwegian University of Science and Technology, 7030, Trondheim, Norway.,Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Nijmegen, 6525 GA, The Netherlands
| |
Collapse
|
11
|
Landsmann A, Ruppert C, Wieler J, Hejduk P, Ciritsis A, Borkowski K, Wurnig MC, Rossi C, Boss A. Radiomics in photon-counting dedicated breast CT: potential of texture analysis for breast density classification. Eur Radiol Exp 2022; 6:30. [PMID: 35854186 PMCID: PMC9296720 DOI: 10.1186/s41747-022-00285-x] [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] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2021] [Accepted: 05/12/2022] [Indexed: 11/10/2022] Open
Abstract
Background We investigated whether features derived from texture analysis (TA) can distinguish breast density (BD) in spiral photon-counting breast computed tomography (PC-BCT). Methods In this retrospective single-centre study, we analysed 10,000 images from 400 PC-BCT examinations of 200 patients. Images were categorised into four-level density scale (a–d) using Breast Imaging Reporting and Data System (BI-RADS)-like criteria. After manual definition of representative regions of interest, 19 texture features (TFs) were calculated to analyse the voxel grey-level distribution in the included image area. ANOVA, cluster analysis, and multinomial logistic regression statistics were used. A human readout then was performed on a subset of 60 images to evaluate the reliability of the proposed feature set. Results Of the 19 TFs, 4 first-order features and 7 second-order features showed significant correlation with BD and were selected for further analysis. Multinomial logistic regression revealed an overall accuracy of 80% for BD assessment. The majority of TFs systematically increased or decreased with BD. Skewness (rho -0.81), as a first-order feature, and grey-level nonuniformity (GLN, -0.59), as a second-order feature, showed the strongest correlation with BD, independently of other TFs. Mean skewness and GLN decreased linearly from density a to d. Run-length nonuniformity (RLN), as a second-order feature, showed moderate correlation with BD, but resulted in redundant being correlated with GLN. All other TFs showed only weak correlation with BD (range -0.49 to 0.49, p < 0.001) and were neglected. Conclusion TA of PC-BCT images might be a useful approach to assess BD and may serve as an observer-independent tool.
Collapse
Affiliation(s)
- Anna Landsmann
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland.
| | - Carlotta Ruppert
- Institute of Computational Physics, Zurich University of Applied Sciences, Zurich, Switzerland
| | - Jann Wieler
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland
| | - Patryk Hejduk
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland
| | - Alexander Ciritsis
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland
| | - Karol Borkowski
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland
| | - Moritz C Wurnig
- Institute of Diagnostic Radiology, Hospital Lachen AG, Lachen, Switzerland
| | - Cristina Rossi
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland
| | - Andreas Boss
- Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland
| |
Collapse
|
12
|
Rinaldi L, De Angelis SP, Raimondi S, Rizzo S, Fanciullo C, Rampinelli C, Mariani M, Lascialfari A, Cremonesi M, Orecchia R, Origgi D, Botta F. Reproducibility of radiomic features in CT images of NSCLC patients: an integrative analysis on the impact of acquisition and reconstruction parameters. Eur Radiol Exp 2022; 6:2. [PMID: 35075539 DOI: 10.1186/s41747-021-00258-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2021] [Accepted: 12/16/2021] [Indexed: 12/12/2022] Open
Abstract
BACKGROUND We investigated to what extent tube voltage, scanner model, and reconstruction algorithm affect radiomic feature reproducibility in a single-institution retrospective database of computed tomography images of non-small-cell lung cancer patients. METHODS This study was approved by the Institutional Review Board (UID 2412). Images of 103 patients were considered, being acquired on either among two scanners, at 100 or 120 kVp. For each patient, images were reconstructed with six iterative blending levels, and 1414 features were extracted from each reconstruction. At univariate analysis, Wilcoxon-Mann-Whitney test was applied to evaluate feature differences within scanners and voltages, whereas the impact of the reconstruction was established with the overall concordance correlation coefficient (OCCC). A multivariable mixed model was also applied to investigate the independent contribution of each acquisition/reconstruction parameter. Univariate and multivariable analyses were combined to analyse feature behaviour. RESULTS Scanner model and voltage did not affect features significantly. The reconstruction blending level showed a significant impact at both univariate analysis (154/1414 features yielding an OCCC < 0.85) and multivariable analysis, with most features (1042/1414) revealing a systematic trend with the blending level (multiple comparisons adjusted p < 0.05). Reproducibility increased in association to image processing with smooth filters, nonetheless specific investigation in relation to clinical endpoints should be performed to ensure that textural information is not removed. CONCLUSIONS Combining univariate and multivariable models is allowed to identify features for which corrections may be applied to reduce the trend with the algorithm and increase reproducibility. Subsequent clustering may be applied to eliminate residual redundancy.
Collapse
|
13
|
Dudurych I, Garcia-Uceda A, Saghir Z, Tiddens HAWM, Vliegenthart R, de Bruijne M. Creating a training set for artificial intelligence from initial segmentations of airways. Eur Radiol Exp 2021; 5:54. [PMID: 34841480 PMCID: PMC8627914 DOI: 10.1186/s41747-021-00247-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Accepted: 10/04/2021] [Indexed: 12/02/2022] Open
Abstract
Airways segmentation is important for research about pulmonary disease but require a large amount of time by trained specialists. We used an openly available software to improve airways segmentations obtained from an artificial intelligence (AI) tool and retrained the tool to get a better performance. Fifteen initial airway segmentations from low-dose chest computed tomography scans were obtained with a 3D-Unet AI tool previously trained on Danish Lung Cancer Screening Trial and Erasmus-MC Sophia datasets. Segmentations were manually corrected in 3D Slicer. The corrected airway segmentations were used to retrain the 3D-Unet. Airway measurements were automatically obtained and included count, airway length and luminal diameter per generation from the segmentations. Correcting segmentations required 2–4 h per scan. Manually corrected segmentations had more branches (p < 0.001), longer airways (p < 0.001) and smaller luminal diameters (p = 0.004) than initial segmentations. Segmentations from retrained 3D-Unets trended towards more branches and longer airways compared to the initial segmentations. The largest changes were seen in airways from 6th generation onwards. Manual correction results in significantly improved segmentations and is potentially a useful and time-efficient method to improve the AI tool performance on a specific hospital or research dataset.
Collapse
Affiliation(s)
- Ivan Dudurych
- Department of Radiology, University of Groningen, University Medical Centre Groningen, Groningen, Netherlands.
| | - Antonio Garcia-Uceda
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands.,Department of Paediatric Pulmonology and Allergology, Erasmus MC-Sophia Children Hospital, Rotterdam, Netherlands
| | - Zaigham Saghir
- Department of Medicine, Section of Pulmonary Medicine, Herlev-Gentofte Hospital, Hellerup, Denmark.,Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark
| | - Harm A W M Tiddens
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands.,Department of Paediatric Pulmonology and Allergology, Erasmus MC-Sophia Children Hospital, Rotterdam, Netherlands
| | - Rozemarijn Vliegenthart
- Department of Radiology, University of Groningen, University Medical Centre Groningen, Groningen, Netherlands
| | - Marleen de Bruijne
- Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands.,Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|
14
|
Aydin OU, Taha AA, Hilbert A, Khalil AA, Galinovic I, Fiebach JB, Frey D, Madai VI. An evaluation of performance measures for arterial brain vessel segmentation. BMC Med Imaging 2021; 21:113. [PMID: 34271876 PMCID: PMC8283850 DOI: 10.1186/s12880-021-00644-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2021] [Accepted: 07/07/2021] [Indexed: 01/03/2023] Open
Abstract
BACKGROUND Arterial brain vessel segmentation allows utilising clinically relevant information contained within the cerebral vascular tree. Currently, however, no standardised performance measure is available to evaluate the quality of cerebral vessel segmentations. Thus, we developed a performance measure selection framework based on manual visual scoring of simulated segmentation variations to find the most suitable measure for cerebral vessel segmentation. METHODS To simulate segmentation variations, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation. In 10 patients, we generated a set of approximately 300 simulated segmentation variations for each ground truth image. Each segmentation was visually scored based on a predefined scoring system and segmentations were ranked based on 22 performance measures common in the literature. The correlation of visual scores with performance measure rankings was calculated using the Spearman correlation coefficient. RESULTS The distance-based performance measures balanced average Hausdorff distance (rank = 1) and average Hausdorff distance (rank = 2) provided the segmentation rankings with the highest average correlation with manual rankings. They were followed by overlap-based measures such as Dice coefficient (rank = 7), a standard performance measure in medical image segmentation. CONCLUSIONS Average Hausdorff distance-based measures should be used as a standard performance measure in evaluating cerebral vessel segmentation quality. They can identify more relevant segmentation errors, especially in high-quality segmentations. Our findings have the potential to accelerate the validation and development of novel vessel segmentation approaches.
Collapse
Affiliation(s)
- Orhun Utku Aydin
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Abdel Aziz Taha
- Research Studio Data Science, Research Studios Austria, Salzburg, Austria
| | - Adam Hilbert
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Ahmed A. Khalil
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany
- Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany
- Mind, Brain, Body Institute, Berlin School of Mind and Brain, Humboldt-Universität Berlin, Berlin, Germany
| | - Ivana Galinovic
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Jochen B. Fiebach
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Dietmar Frey
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Vince Istvan Madai
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
- QUEST Center for Transforming Biomedical Research, Berlin Institute of Health (BIH), Charité - Universitätsmedizin Berlin, Berlin, Germany
- Faculty of Computing, Engineering and the Built Environment, School of Computing and Digital Technology, Birmingham City University, Birmingham, UK
| |
Collapse
|
15
|
Mangal U, Arum H, Huisoo K, Jung YH, Lee KJ, Yu HS, Hwang JJ, Choi SH. Tomographic similarity scan with a computed modified absolute mandibular midsagittal plane for precise and objective localization of mandibular asymmetry. Comput Biol Med 2021; 134:104465. [PMID: 33975208 DOI: 10.1016/j.compbiomed.2021.104465] [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] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2021] [Revised: 04/24/2021] [Accepted: 04/29/2021] [Indexed: 10/21/2022]
Abstract
The application of 3D imaging is at its cusp in craniofacial diagnosis and treatment planning. However, most applications are limited to simple subjective superimposition-based analysis. As the diagnostic accuracy dictates the precision in operability, we propose a novel method that enables objective clinical decision making for patients with mandibular asymmetry. We analyzed cone-beam computed tomography (CBCT) scans of 34 patients who underwent surgical correction for mandibular asymmetry using a high-throughput computing algorithm. Radiomic segmentation of quantitative features of surface and volume followed by exploration resulted in identification of a computed modified absolute mandibular midsagittal plane (cmAMP). Tomographic similarity scan (ToSS) curves were generated via bilateral equidistant scanning in an antero-posterior direction with cmAMP as the reference. ToSS comprised of a comprehensive similarity index (SI) score curve and a segment-wise volume curve. The SI score was computed using the Sørensen-Dice similarity coefficient ranging from 0 to 1. The volumetric analysis was represented as the non-overlapping volume (NOV) and overlapping volume (OV) for each segment, with two segmentation lines, at the mental foramen anteriorly and the intraoral vertical ramus osteotomy region posteriorly. Statistical analysis showed strong negative correlation between the NOV and SI scores for the anterior, middle, and total mandible (P < 0.001). Additionally, a significant correlation was observed between the change in the SI scores for anterior (P = 0.044) and middle segments (P < 0.001) to the total mandible when comparing the data before and after the surgery. This work demonstrated the potential of incorporating ToSS curves in surgical simulation software to improve precision in the clinical decision-making process.
Collapse
Affiliation(s)
- Utkarsh Mangal
- Department of Orthodontics, Institute of Craniofacial Deformity, Yonsei University College of Dentistry, Seoul, 03722, Republic of Korea.
| | - Han Arum
- Department of Orthodontics, Institute of Craniofacial Deformity, Yonsei University College of Dentistry, Seoul, 03722, Republic of Korea.
| | - Kim Huisoo
- Dental and Life Science Institute, Pusan National University, Yangsan, 50612, Republic of Korea.
| | - Yun-Hoa Jung
- Department of Oral and Maxillofacial Radiology, School of Dentistry, Pusan National University, Dental Research Institute, Yangsan, 50610, Republic of Korea.
| | - Kee-Joon Lee
- Department of Orthodontics, Institute of Craniofacial Deformity, Yonsei University College of Dentistry, Seoul, 03722, Republic of Korea.
| | - Hyung-Seog Yu
- Department of Orthodontics, Institute of Craniofacial Deformity, Yonsei University College of Dentistry, Seoul, 03722, Republic of Korea.
| | - Jae Joon Hwang
- Department of Oral and Maxillofacial Radiology, School of Dentistry, Pusan National University, Dental Research Institute, Yangsan, 50610, Republic of Korea.
| | - Sung-Hwan Choi
- Department of Orthodontics, Institute of Craniofacial Deformity, Yonsei University College of Dentistry, Seoul, 03722, Republic of Korea.
| |
Collapse
|
16
|
Aydin OU, Taha AA, Hilbert A, Khalil AA, Galinovic I, Fiebach JB, Frey D, Madai VI. On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking. Eur Radiol Exp 2021; 5:4. [PMID: 33474675 PMCID: PMC7817746 DOI: 10.1186/s41747-020-00200-2] [Citation(s) in RCA: 33] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2020] [Accepted: 12/03/2020] [Indexed: 02/07/2023] Open
Abstract
Average Hausdorff distance is a widely used performance measure to calculate the distance between two point sets. In medical image segmentation, it is used to compare ground truth images with segmentations allowing their ranking. We identified, however, ranking errors of average Hausdorff distance making it less suitable for applications in segmentation performance assessment. To mitigate this error, we present a modified calculation of this performance measure that we have coined “balanced average Hausdorff distance”. To simulate segmentations for ranking, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation as our use-case. Adding the created errors consecutively and randomly to the ground truth, we created sets of simulated segmentations with increasing number of errors. Each set of simulated segmentations was ranked using both performance measures. We calculated the Kendall rank correlation coefficient between the segmentation ranking and the number of errors in each simulated segmentation. The rankings produced by balanced average Hausdorff distance had a significantly higher median correlation (1.00) than those by average Hausdorff distance (0.89). In 200 total rankings, the former misranked 52 whilst the latter misranked 179 segmentations. Balanced average Hausdorff distance is more suitable for rankings and quality assessment of segmentations than average Hausdorff distance.
Collapse
Affiliation(s)
- Orhun Utku Aydin
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany.
| | - Abdel Aziz Taha
- Research Studio Data Science, Research Studios Austria, Salzburg, Austria
| | - Adam Hilbert
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Ahmed A Khalil
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany.,Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany.,Mind, Brain, Body Institute, Berlin School of Mind and Brain, Humboldt-Universität Berlin, Berlin, Germany
| | - Ivana Galinovic
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Jochen B Fiebach
- Centre for Stroke Research Berlin, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Dietmar Frey
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany
| | - Vince Istvan Madai
- CLAIM - Charité Lab for Artificial Intelligence in Medicine, Charité Universitätsmedizin Berlin, Berlin, Germany.,School of Computing and Digital Technology, Faculty of Computing, Engineering and the Built Environment, Birmingham City University, Birmingham, UK
| |
Collapse
|
17
|
Rizzetto F, Calderoni F, De Mattia C, Defeudis A, Giannini V, Mazzetti S, Vassallo L, Ghezzi S, Sartore-Bianchi A, Marsoni S, Siena S, Regge D, Torresin A, Vanzulli A. Impact of inter-reader contouring variability on textural radiomics of colorectal liver metastases. Eur Radiol Exp 2020; 4:62. [PMID: 33169295 PMCID: PMC7652946 DOI: 10.1186/s41747-020-00189-8] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2020] [Accepted: 10/13/2020] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Radiomics is expected to improve the management of metastatic colorectal cancer (CRC). We aimed at evaluating the impact of liver lesion contouring as a source of variability on radiomic features (RFs). METHODS After Ethics Committee approval, 70 liver metastases in 17 CRC patients were segmented on contrast-enhanced computed tomography scans by two residents and checked by experienced radiologists. RFs from grey level co-occurrence and run length matrices were extracted from three-dimensional (3D) regions of interest (ROIs) and the largest two-dimensional (2D) ROIs. Inter-reader variability was evaluated with Dice coefficient and Hausdorff distance, whilst its impact on RFs was assessed using mean relative change (MRC) and intraclass correlation coefficient (ICC). For the main lesion of each patient, one reader also segmented a circular ROI on the same image used for the 2D ROI. RESULTS The best inter-reader contouring agreement was observed for 2D ROIs according to both Dice coefficient (median 0.85, interquartile range 0.78-0.89) and Hausdorff distance (0.21 mm, 0.14-0.31 mm). Comparing RF values, MRC ranged 0-752% for 2D and 0-1567% for 3D. For 24/32 RFs (75%), MRC was lower for 2D than for 3D. An ICC > 0.90 was observed for more RFs for 2D (53%) than for 3D (34%). Only 2/32 RFs (6%) showed a variability between 2D and circular ROIs higher than inter-reader variability. CONCLUSIONS A 2D contouring approach may help mitigate overall inter-reader variability, albeit stable RFs can be extracted from both 3D and 2D segmentations of CRC liver metastases.
Collapse
Affiliation(s)
- Francesco Rizzetto
- Department of Radiology, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162, Milan, Italy
| | - Francesca Calderoni
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162, Milan, Italy
| | - Cristina De Mattia
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162, Milan, Italy
| | - Arianna Defeudis
- Department of Surgical Sciences, University of Turin, via Verdi 8, 10124, Turin, Italy
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale 142 km 3.95, 10060, Candiolo, Turin, Italy
| | - Valentina Giannini
- Department of Surgical Sciences, University of Turin, via Verdi 8, 10124, Turin, Italy
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale 142 km 3.95, 10060, Candiolo, Turin, Italy
| | - Simone Mazzetti
- Department of Surgical Sciences, University of Turin, via Verdi 8, 10124, Turin, Italy
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale 142 km 3.95, 10060, Candiolo, Turin, Italy
| | - Lorenzo Vassallo
- Radiology Unit, SS Annunziata Hospital ASLCN1 Cuneo, via Ospedali 14, 12038, Cuneo, Savigliano, Italy
| | - Silvia Ghezzi
- Niguarda Cancer Center, Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162, Milan, Italy
| | - Andrea Sartore-Bianchi
- Niguarda Cancer Center, Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162, Milan, Italy
- Department of Oncology and Hemato-Oncology, Università degli Studi di Milano, via Festa del Perdono 7, 20122, Milan, Italy
| | - Silvia Marsoni
- Precision Oncology, IFOM - The FIRC Institute of Molecular Oncology, via Adamello 16, 20139, Milan, Italy
| | - Salvatore Siena
- Niguarda Cancer Center, Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162, Milan, Italy
- Department of Oncology and Hemato-Oncology, Università degli Studi di Milano, via Festa del Perdono 7, 20122, Milan, Italy
| | - Daniele Regge
- Department of Surgical Sciences, University of Turin, via Verdi 8, 10124, Turin, Italy
- Radiology Unit, Candiolo Cancer Institute, FPO-IRCCS, Strada Provinciale 142 km 3.95, 10060, Candiolo, Turin, Italy
| | - Alberto Torresin
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162, Milan, Italy
- Department of Physics, Università degli Studi di Milano, via Giovanni Celoria 16, 20133, Milan, Italy
| | - Angelo Vanzulli
- Department of Radiology, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162, Milan, Italy.
- Department of Oncology and Hemato-Oncology, Università degli Studi di Milano, via Festa del Perdono 7, 20122, Milan, Italy.
| |
Collapse
|
18
|
Booz C, Yel I, Wichmann JL, Boettger S, Al Kamali A, Albrecht MH, Martin SS, Lenga L, Huizinga NA, D'Angelo T, Cavallaro M, Vogl TJ, Bodelle B. Artificial intelligence in bone age assessment: accuracy and efficiency of a novel fully automated algorithm compared to the Greulich-Pyle method. Eur Radiol Exp 2020; 4:6. [PMID: 31993795 PMCID: PMC6987270 DOI: 10.1186/s41747-019-0139-9] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2019] [Accepted: 11/22/2019] [Indexed: 11/10/2022] Open
Abstract
Background Bone age (BA) assessment performed by artificial intelligence (AI) is of growing interest due to improved accuracy, precision and time efficiency in daily routine. The aim of this study was to investigate the accuracy and efficiency of a novel AI software version for automated BA assessment in comparison to the Greulich-Pyle method. Methods Radiographs of 514 patients were analysed in this retrospective study. Total BA was assessed independently by three blinded radiologists applying the GP method and by the AI software. Overall and gender-specific BA assessment results, as well as reading times of both approaches, were compared, while the reference BA was defined by two blinded experienced paediatric radiologists in consensus by application of the Greulich-Pyle method. Results Mean absolute deviation (MAD) and root mean square deviation (RSMD) were significantly lower between AI-derived BA and reference BA (MAD 0.34 years, RSMD 0.38 years) than between reader-calculated BA and reference BA (MAD 0.79 years, RSMD 0.89 years; p < 0.001). The correlation between AI-derived BA and reference BA (r = 0.99) was significantly higher than between reader-calculated BA and reference BA (r = 0.90; p < 0.001). No statistical difference was found in reader agreement and correlation analyses regarding gender (p = 0.241). Mean reading times were reduced by 87% using the AI system. Conclusions A novel AI software enabled highly accurate automated BA assessment. It may improve efficiency in clinical routine by reducing reading times without compromising the accuracy compared with the Greulich-Pyle method.
Collapse
Affiliation(s)
- Christian Booz
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany.
| | - Ibrahim Yel
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Julian L Wichmann
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Sabine Boettger
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Ahmed Al Kamali
- Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Moritz H Albrecht
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Simon S Martin
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Lukas Lenga
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Nicole A Huizinga
- Interdisciplinary Center for Neuroscience, Goethe-University of Frankfurt, Frankfurt am Main, Germany
| | - Tommaso D'Angelo
- Department of Biomedical Sciences and Morphological and Functional Imaging, University of Messina, Messina, Italy
| | - Marco Cavallaro
- Department of Biomedical Sciences and Morphological and Functional Imaging, University of Messina, Messina, Italy
| | - Thomas J Vogl
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| | - Boris Bodelle
- Division of Experimental Imaging, Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Theodor-Stern-Kai 7, 60590, Frankfurt am Main, Germany
| |
Collapse
|
19
|
Rizzo S, Botta F, Raimondi S, Origgi D, Fanciullo C, Morganti AG, Bellomi M. Radiomics: the facts and the challenges of image analysis. Eur Radiol Exp 2018; 2:36. [PMID: 30426318 PMCID: PMC6234198 DOI: 10.1186/s41747-018-0068-z;] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022] Open
Abstract
Radiomics is an emerging translational field of research aiming to extract mineable high-dimensional data from clinical images. The radiomic process can be divided into distinct steps with definable inputs and outputs, such as image acquisition and reconstruction, image segmentation, features extraction and qualification, analysis, and model building. Each step needs careful evaluation for the construction of robust and reliable models to be transferred into clinical practice for the purposes of prognosis, non-invasive disease tracking, and evaluation of disease response to treatment. After the definition of texture parameters (shape features; first-, second-, and higher-order features), we briefly discuss the origin of the term radiomics and the methods for selecting the parameters useful for a radiomic approach, including cluster analysis, principal component analysis, random forest, neural network, linear/logistic regression, and other. Reproducibility and clinical value of parameters should be firstly tested with internal cross-validation and then validated on independent external cohorts. This article summarises the major issues regarding this multi-step process, focussing in particular on challenges of the extraction of radiomic features from data sets provided by computed tomography, positron emission tomography, and magnetic resonance imaging.
Collapse
Affiliation(s)
- Stefania Rizzo
- 0000 0004 1757 0843grid.15667.33Department of Radiology, IEO, European Institute of Oncology, IRCCS, Milan, IT Italy
| | - Francesca Botta
- 0000 0004 1757 0843grid.15667.33Medical Physics, European Institute of Oncology, Milan, Italy
| | - Sara Raimondi
- 0000 0004 1757 0843grid.15667.33Division of Epidemiology and Biostatistics, European Institute of Oncology, Milan, Italy
| | - Daniela Origgi
- 0000 0004 1757 0843grid.15667.33Medical Physics, European Institute of Oncology, Milan, Italy
| | - Cristiana Fanciullo
- 0000 0004 1757 2822grid.4708.bUniversità degli Studi di Milano, Postgraduate School in Radiodiagnostics, Milan, Italy
| | - Alessio Giuseppe Morganti
- 0000 0004 1757 1758grid.6292.fRadiation Oncology Center, School of Medicine, Department of Experimental, Diagnostic and Specialty Medicine – DIMES, University of Bologna, Bologna, Italy
| | - Massimo Bellomi
- 0000 0004 1757 2822grid.4708.bDepartment of Oncology and Hemato-Oncology, Università degli Studi di Milano, Milan, Italy
| |
Collapse
|
20
|
Ressel V, van Hedel HJA, Scheer I, O'Gorman Tuura R. Comparison of DTI analysis methods for clinical research: influence of pre-processing and tract selection methods. Eur Radiol Exp 2018; 2:33. [PMID: 30426317 PMCID: PMC6234200 DOI: 10.1186/s41747-018-0066-1] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2018] [Accepted: 08/28/2018] [Indexed: 12/28/2022] Open
Abstract
Background The primary aim was to compare fractional anisotropy (FA) values derived with different diffusion tensor imaging (DTI) analysis approaches (atlas-based, streamline tractography, and combined). A secondary aim was to compare FA values and number of tracts (NT) with the clinical motor outcome quantified by the functional independence measure for children (WeeFIM). Methods Thirty-nine DTI datasets of children with acquired brain injury were analysed. Regions of interest for the ipsilesional corticospinal tract were defined and mean FA and NT were calculated. We evaluated FA values with Spearman correlation, the Friedman and Wilcoxon tests, and Bland-Altman analysis. DTI values were compared to WeeFIM values by non-parametric partial correlation and accuracy was assessed by receiver operating characteristics analysis. Results The FA values from all approaches correlated significantly with each other (p < 0.001). However, the FA values from streamline tractography were significantly higher (mean ± standard deviation (SD), 0.52 ± 0.08) than those from the atlas-based (0.42 ± 0.11) or the combined approach (0.41 ± 0.11) (p < 0.001 for both). FA and NT values correlated significantly with WeeFIM values (atlas-based FA, partial correlation coefficient (ρ) = 0.545, p = 0.001; streamline FA, ρ = 0.505, p = 0.002; NT, ρ = 0.434, p = 0.008; combined FA, ρ = 0.611, p < 0.001). FA of the atlas-based approach (sensitivity 90%, specificity 67%, area under the curve 0.82) and the combined approach (87%, 67%, 0.82), provided the highest predictive accuracy for outcome compared to FA (70%, 67%, 0.67) and NT (50%, 100%, 0.79, respectively) of the streamline approach. Conclusion FA values from streamline tractography were higher than those from the atlas-based and combined approach. The atlas-based and combined approach offer the best predictive accuracy for motor outcome, although both atlas-based and streamline tractography approaches provide significant predictors of clinical outcome.
Collapse
Affiliation(s)
- Volker Ressel
- Centre MR-Research, University Children's Hospital, Zurich, Switzerland. .,Rehabilitation Centre, University Children's Hospital, Mühlebergstrasse 104, CH-8910, Affoltern am Albis, Switzerland. .,Children's Research Center, University Children's Hospital, Zurich, Switzerland.
| | - Hubertus J A van Hedel
- Rehabilitation Centre, University Children's Hospital, Mühlebergstrasse 104, CH-8910, Affoltern am Albis, Switzerland.,Children's Research Center, University Children's Hospital, Zurich, Switzerland
| | - Ianina Scheer
- Children's Research Center, University Children's Hospital, Zurich, Switzerland.,Diagnostic Imaging, University Children's Hospital, Zurich, Switzerland
| | - Ruth O'Gorman Tuura
- Centre MR-Research, University Children's Hospital, Zurich, Switzerland.,Children's Research Center, University Children's Hospital, Zurich, Switzerland
| |
Collapse
|
21
|
Rizzo S, Botta F, Raimondi S, Origgi D, Fanciullo C, Morganti AG, Bellomi M. Radiomics: the facts and the challenges of image analysis. Eur Radiol Exp 2018; 2:36. [PMID: 30426318 PMCID: PMC6234198 DOI: 10.1186/s41747-018-0068-z] [Citation(s) in RCA: 542] [Impact Index Per Article: 90.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2018] [Accepted: 10/09/2018] [Indexed: 12/13/2022] Open
Abstract
Radiomics is an emerging translational field of research aiming to extract mineable high-dimensional data from clinical images. The radiomic process can be divided into distinct steps with definable inputs and outputs, such as image acquisition and reconstruction, image segmentation, features extraction and qualification, analysis, and model building. Each step needs careful evaluation for the construction of robust and reliable models to be transferred into clinical practice for the purposes of prognosis, non-invasive disease tracking, and evaluation of disease response to treatment. After the definition of texture parameters (shape features; first-, second-, and higher-order features), we briefly discuss the origin of the term radiomics and the methods for selecting the parameters useful for a radiomic approach, including cluster analysis, principal component analysis, random forest, neural network, linear/logistic regression, and other. Reproducibility and clinical value of parameters should be firstly tested with internal cross-validation and then validated on independent external cohorts. This article summarises the major issues regarding this multi-step process, focussing in particular on challenges of the extraction of radiomic features from data sets provided by computed tomography, positron emission tomography, and magnetic resonance imaging.
Collapse
Affiliation(s)
- Stefania Rizzo
- Department of Radiology, IEO, European Institute of Oncology, IRCCS, Milan, IT, Italy.
| | - Francesca Botta
- Medical Physics, European Institute of Oncology, Milan, Italy
| | - Sara Raimondi
- Division of Epidemiology and Biostatistics, European Institute of Oncology, Milan, Italy
| | - Daniela Origgi
- Medical Physics, European Institute of Oncology, Milan, Italy
| | - Cristiana Fanciullo
- Università degli Studi di Milano, Postgraduate School in Radiodiagnostics, Milan, Italy
| | - Alessio Giuseppe Morganti
- Radiation Oncology Center, School of Medicine, Department of Experimental, Diagnostic and Specialty Medicine - DIMES, University of Bologna, Bologna, Italy
| | - Massimo Bellomi
- Department of Oncology and Hemato-Oncology, Università degli Studi di Milano, Milan, Italy
| |
Collapse
|