1
|
Alam T, Shia WC, Hsu FR, Hassan T. Improving Breast Cancer Detection and Diagnosis through Semantic Segmentation Using the Unet3+ Deep Learning Framework. Biomedicines 2023; 11:1536. [PMID: 37371631 DOI: 10.3390/biomedicines11061536] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2023] [Revised: 05/23/2023] [Accepted: 05/24/2023] [Indexed: 06/29/2023] Open
Abstract
We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide a more accurate and objective diagnosis of breast cancer, leading to improved patient outcomes.
Collapse
Affiliation(s)
- Taukir Alam
- Department of Information Engineering and Computer Science, Feng Chia University, Taichung 407, Taiwan
| | - Wei-Chung Shia
- Department of Information Engineering and Computer Science, Feng Chia University, Taichung 407, Taiwan
- Molecular Medicine Laboratory, Department of Research, Changhua Christian Hospital, Changhua 500, Taiwan
| | - Fang-Rong Hsu
- Department of Information Engineering and Computer Science, Feng Chia University, Taichung 407, Taiwan
| | - Taimoor Hassan
- Institute of Translational Medicine and New Drug Development, China Medical University, Taichung 404333, Taiwan
| |
Collapse
|
2
|
Czuczman GJ, Mandell JC, Wessell DE, Lenchik L, Ahlawat S, Baker JC, Cassidy RC, Demertzis JL, Garner HW, Klitzke A, Maynard JR, Pierce JL, Reitman C, Thiele R, Yost WJ, Beaman FD. ACR Appropriateness Criteria® Inflammatory Back Pain: Known or Suspected Axial Spondyloarthritis: 2021 Update. J Am Coll Radiol 2021; 18:S340-S360. [PMID: 34794593 DOI: 10.1016/j.jacr.2021.08.003] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2021] [Accepted: 08/26/2021] [Indexed: 02/07/2023]
Abstract
Inflammatory back pain is a hallmark feature of axial spondyloarthritis, a heterogeneous group of inflammatory disorders which affects the sacroiliac joints and spine. Imaging plays a key role in diagnosis of this disease and in facilitating appropriate treatment. This document provides evidence-based recommendations on the appropriate use of imaging studies during multiple stages of the clinical evaluation of patients with suspected or known axial spondyloarthritis. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.
Collapse
Affiliation(s)
| | - Jacob C Mandell
- Research Author, Brigham & Women's Hospital & Harvard Medical School, Boston, Massachusetts
| | | | - Leon Lenchik
- Panel Vice-Chair, Wake Forest University School of Medicine, Winston Salem, North Carolina
| | - Shivani Ahlawat
- Musculoskeletal Fellowship Director; and Chair, REiNS Whole Body MRI Committee, Johns Hopkins Hospital, Baltimore, Maryland
| | - Jonathan C Baker
- Mallinckrodt Institute of Radiology Washington University School of Medicine, Saint Louis, Missouri
| | - R Carter Cassidy
- UK Healthcare Spine and Total Joint Service, Lexington, Kentucky; Executive Board, Kentucky Orthopaedic Society; and American Academy of Orthopaedic Surgeons
| | | | | | - Alan Klitzke
- Roswell Park Comprehensive Cancer Center, Buffalo, New York; Board of Directors, American College of Nuclear Medicine; Board of Directors, SNMMI Correlative Imaging Council; and Delegate, American Medical Association House of Delegates
| | - Jennifer R Maynard
- Program Director Sports Medicine Fellowship, Mayo Clinic Florida, Jacksonville, Florida; Primary care physician; Medical Advisor Women's Tennis Association; Vice-Chair, Jacksonville Sports Medicine Program Executive Board; Chair, Florida High School Athletic Association Sports; and Medicine Advisory Committee
| | | | - Charles Reitman
- Medical University of South Carolina, Charleston, South Carolina; and Board of Directors, North American Spine Society
| | - Ralf Thiele
- University of Rochester School of Medicine and Dentistry, Rochester, New York, American College of Rheumatology
| | - William J Yost
- UnityPoint Health, Des Moines, Iowa, American College of Physicians
| | | |
Collapse
|
3
|
|
4
|
Jones A, Bray TJP, Mandl P, Hall-Craggs MA, Marzo-Ortega H, Machado PM. Performance of magnetic resonance imaging in the diagnosis of axial spondyloarthritis: a systematic literature review. Rheumatology (Oxford) 2020; 58:1955-1965. [PMID: 31046102 DOI: 10.1093/rheumatology/kez172] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2018] [Revised: 04/04/2019] [Indexed: 01/04/2023] Open
Abstract
OBJECTIVES To summarize the evidence on the performance of MRI for the diagnosis of axial SpA. METHODS This was a systematic literature review of all studies from January 2013 to March 2017 including adult patients with clinically suspected axial SpA undergoing MRI. Studies from a previously published systematic literature review up to January 2013 were also included. RESULTS Thirty-one studies were included. Six studies demonstrated good sensitivity and specificity for SI joint (SIJ) bone marrow oedema (BMO). Specificity was increased by the presence of other structural lesions alongside BMO, particularly erosions or fat infiltration. Four studies addressed the utility of SIJ fat infiltration, finding good sensitivity but poor specificity. SIJ erosions showed good specificity in five studies. Studies addressing high T1 signal in the SIJ, fluid signal in the SIJ, ankylosis, sclerosis, capsulitis, backfill and vacuum phenomenon reported limited diagnostic value. In the spine, four studies reported moderate sensitivity and specificity for corner inflammatory lesions, and four reported poor sensitivity and specificity for spinal fat infiltration. Five studies evaluated the added value of spinal MRI over SIJ MRI alone, with variable results depending on the cohort. Six studies addressed the effect of acquisition parameters on diagnostic accuracy: fat-saturated T2-weighted imaging and short tau inversion recovery (STIR) imaging showed comparable utility in identifying BMO. Three studies showed that gadolinium was of minimal added value in the detection of BMO. CONCLUSIONS These results confirmed the diagnostic utility of MRI in axial SpA. Performance varied according to the characteristics of the cohort and the number and combination of MRI lesions considered.
Collapse
Affiliation(s)
- Alexis Jones
- Department of Rheumatology, University College London Hospitals NHS Foundation Trust, London, UK
| | - Timothy J P Bray
- Centre for Medical Imaging, University College London, London, UK
| | - Peter Mandl
- Department of Rheumatology, Medical University of Vienna, Vienna, Austria
| | | | - Helena Marzo-Ortega
- NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds, London.,Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds, London
| | - Pedro M Machado
- Department of Rheumatology, University College London Hospitals NHS Foundation Trust, London, UK.,Department of Rheumatology, Northwick Park Hospital, London North West University Healthcare NHS Trust, London.,Centre for Rheumatology and MRC Centre for Neuromuscular Diseases, University College London, London, UK
| |
Collapse
|
5
|
Hamard A, Burns R, Miquel A, Sverzut JM, Chicheportiche V, Wybier M, Bousson V. Dactylitis: A pictorial review of key symptoms. Diagn Interv Imaging 2020; 101:193-207. [PMID: 32001209 DOI: 10.1016/j.diii.2020.01.005] [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: 09/13/2019] [Revised: 12/21/2019] [Accepted: 01/06/2020] [Indexed: 10/25/2022]
Abstract
Dactylitis refers to a global swelling of a finger or a toe giving it a clinical sausage-shape presentation. It is an extremely suggestive symptom as it guides the rheumatologist towards a shortlist of diagnoses. However, radiologists are less familiar with dactylitis. The aim of this review is to detail and illustrate the main causes of dactylitis using standard X-ray imaging, ultrasound, computed tomography and magnetic resonance imaging in order to make radiologists more familiar with this symptom by illustrating the various conditions that are associated with dactylitis including infection, peripheral spondyloarthritis, sarcoidosis, microcrystalline deposition, osteoid osteoma, and sickle cell disease.
Collapse
Affiliation(s)
- A Hamard
- Department of Radiology, Lariboisiere Hospital, AP-HP, 75010 Paris, France; Department of Radiology, EA 2415, Medical Imaging Group, Nimes University Hospital, 30029 Nîmes, France.
| | - R Burns
- Department of Radiology, Lariboisiere Hospital, AP-HP, 75010 Paris, France
| | - A Miquel
- Department of Radiology, Lariboisiere Hospital, AP-HP, 75010 Paris, France
| | - J M Sverzut
- Department of Radiology, Lariboisiere Hospital, AP-HP, 75010 Paris, France
| | - V Chicheportiche
- Department of Radiology, Lariboisiere Hospital, AP-HP, 75010 Paris, France
| | - M Wybier
- Department of Radiology, Lariboisiere Hospital, AP-HP, 75010 Paris, France
| | - V Bousson
- Department of Radiology, Lariboisiere Hospital, AP-HP, 75010 Paris, France; Université de Paris, Diderot Paris 7, B30A CNRS UMR 7052, 75010 Paris, France
| |
Collapse
|
6
|
Bray TJP, Jones A, Bennett AN, Conaghan PG, Grainger A, Hodgson R, Hutchinson C, Leandro M, Mandl P, McGonagle D, O’Connor P, Sengupta R, Thomas M, Toms A, Winn N, Hall-Craggs MA, Marzo-Ortega H, Machado PM. Recommendations for acquisition and interpretation of MRI of the spine and sacroiliac joints in the diagnosis of axial spondyloarthritis in the UK. Rheumatology (Oxford) 2019; 58:1831-1838. [DOI: 10.1093/rheumatology/kez173] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2018] [Revised: 04/04/2019] [Indexed: 11/12/2022] Open
Abstract
Abstract
Objectives
To develop evidence-based recommendations on the use of MRI in the diagnosis of axial SpA (axSpA).
Methods
A working group comprising nine rheumatologists and nine musculoskeletal radiologists with an interest in axSpA was established, with support from the British Society of Spondyloarthritis (BRITSpA). Two meetings were held. In the first meeting, research questions were formulated. In the second meeting, the results of a systematic literature review designed to inform the recommendations were reviewed. An anonymized Delphi process was used to formulate the final set of recommendations. For each recommendation, the level of evidence and strength of recommendation was determined. The level of agreement was assessed using a 0–10 numerical rating scale.
Results
Two overarching principles were formulated, as follows: The diagnosis of axSpA is based on clinical, laboratory and imaging features (overarching principle 1), and patients with axSpA can have isolated inflammation of either the sacroiliac joints or the spine (overarching principle 2). Seven recommendations addressing the use of MRI in the assessment of patients with suspected axSpA were formulated, covering topics including recommended sequences, anatomical coverage, acquisition parameters and interpretation of active and structural MRI lesions. The level of agreement for each recommendation was very high (range 8.8–9.8).
Conclusion
A joint rheumatology and radiology consensus on the acquisition and interpretation of MRI in axSpA diagnosis was achieved, and a research agenda formulated. This consensus should help standardize practice around MRI and ensure a more informed, consistent approach to the diagnosis of axSpA.
Collapse
Affiliation(s)
| | - Alexis Jones
- Department of Rheumatology, University College London Hospitals NHS Foundation Trust, London
| | - Alexander N Bennett
- Academic Department of Military Rehabilitation, Defence Medical Rehabilitation Centre, Stanford Hall, Nottinghamshire
- National Heart and Lung Institute, Faculty of Medicine, Imperial College London, London
| | - Philip G Conaghan
- NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds
- Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds
| | - Andrew Grainger
- NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds
| | - Richard Hodgson
- Arthritis Research UK Centre for Epidemiology, University of Manchester, Manchester
- NIHR Manchester Musculoskeletal Biomedical Research Unit, Manchester Academic Health Sciences Centre, Manchester
| | - Charles Hutchinson
- Department of Radiology, University Hospitals Coventry and Warwickshire NHS Trust, Coventry, UK
| | - Maria Leandro
- Department of Rheumatology, University College London Hospitals NHS Foundation Trust, London
| | - Peter Mandl
- Department of Rheumatology, Medical University of Vienna, Vienna, Austria
| | - Denis McGonagle
- NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds
- Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds
| | - Phill O’Connor
- NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds
| | - Raj Sengupta
- The Royal National Hospital for Rheumatic Diseases, Bath
| | | | - Andoni Toms
- Department of Radiology, Norfolk and Norwich University Hospitals NHS Foundation Trust, Norwich
| | - Naomi Winn
- Department of Radiology, Robert Jones and Agnes Hunt Orthopaedic Hospital NHS Foundation Trust, Oswestry
| | | | - Helena Marzo-Ortega
- NIHR Leeds Biomedical Research Centre, Leeds Teaching Hospitals NHS Trust, Leeds
- Leeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds
| | - Pedro M Machado
- Department of Rheumatology, University College London Hospitals NHS Foundation Trust, London
- Department of Rheumatology, Northwick Park Hospital, London North West University Healthcare NHS Trust, London
- Centre for Rheumatology and MRC Centre for Neuromuscular Diseases, University College London, London, UK
| | | |
Collapse
|
7
|
Krabbe S, Sørensen IJ, Jensen B, Møller JM, Balding L, Madsen OR, Lambert RGW, Maksymowych WP, Pedersen SJ, Østergaard M. Inflammatory and structural changes in vertebral bodies and posterior elements of the spine in axial spondyloarthritis: construct validity, responsiveness and discriminatory ability of the anatomy-based CANDEN scoring system in a randomised placebo-controlled trial. RMD Open 2018; 4:e000624. [PMID: 29556419 PMCID: PMC5856914 DOI: 10.1136/rmdopen-2017-000624] [Citation(s) in RCA: 23] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2017] [Revised: 01/29/2018] [Accepted: 02/15/2018] [Indexed: 12/22/2022] Open
Abstract
Background The Canada-Denmark (CANDEN) definitions of spinal MRI lesions allow a detailed anatomy-based evaluation of inflammatory and structural lesions in vertebral bodies and posterior elements of the spine in patients with axial spondyloarthritis (axSpA). The objective was to examine the reliability, responsiveness and discrimination of scores for spinal inflammation, fat, bone erosion and new bone formation based on the CANDEN system and to describe patterns of inflammatory and structural lesions and their temporal development. Methods 49 patients with axSpA from an investigator-initiated, randomised, placebo-controlled trial of adalimumab underwent spinal MRI at weeks 0/6/24/48. MR images were scored according to the CANDEN system and the Spondyloarthritis Research Consortium of Canada (SPARCC) method. Total scores, and various subscores, were created by summing individual lesion scores. Results The CANDEN spine inflammation score had high responsiveness, similar to the SPARCC MRI spine index (Guyatt’s responsiveness index 1.88 and 1.67, respectively), and discriminated between adalimumab and placebo treatment already at 6 weeks’ follow-up (P=0.03). Anterior/posterior corner inflammation subscores showed similar responsiveness. Inter-reader reliability for the CANDEN spine inflammation and fat scores was good to very good for status and change scores (intraclass correlation coefficient (ICC)=0.71–0.92). Reliability for CANDEN new bone formation and erosion scores was good to very good for status scores (ICC=0.61–0.75) but, due to minimal progression, poor for change scores (ICC≤0.40). Conclusions The CANDEN spine inflammation score showed good responsiveness, discrimination between active treatment and placebo and reliability. The CANDEN spine structural scores had good cross-sectional reliability, but longer studies are needed to investigate their sensitivity to change. Trial registration number NCT01029847; Results.
Collapse
Affiliation(s)
- Simon Krabbe
- Copenhagen Center for Arthritis Research, Center for Rheumatology and Spine Diseases, Rigshospitalet, Glostrup, Denmark.,Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Inge J Sørensen
- Copenhagen Center for Arthritis Research, Center for Rheumatology and Spine Diseases, Rigshospitalet, Glostrup, Denmark.,Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Bente Jensen
- Center for Rheumatology and Spine Diseases, Frederiksberg and Bispebjerg Hospitals, Copenhagen, Denmark
| | - Jakob M Møller
- Department of Radiology, Herlev and Gentofte Hospitals, Herlev, Denmark
| | - Lone Balding
- Department of Radiology, Herlev and Gentofte Hospitals, Herlev, Denmark
| | - Ole R Madsen
- Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark.,Center for Rheumatology and Spine Diseases, Herlev and Gentofte Hospitals, Herlev, Denmark
| | - Robert G W Lambert
- Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, Alberta, Canada
| | | | - Susanne J Pedersen
- Copenhagen Center for Arthritis Research, Center for Rheumatology and Spine Diseases, Rigshospitalet, Glostrup, Denmark.,Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark.,Center for Rheumatology and Spine Diseases, Herlev and Gentofte Hospitals, Herlev, Denmark
| | - Mikkel Østergaard
- Copenhagen Center for Arthritis Research, Center for Rheumatology and Spine Diseases, Rigshospitalet, Glostrup, Denmark.,Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| |
Collapse
|