1
|
Helgesson S, Tarai S, Langner T, Ahlström H, Johansson L, Kullberg J, Lundström E. Spleen volume is independently associated with non-alcoholic fatty liver disease, liver volume and liver fibrosis. Heliyon 2024; 10:e28123. [PMID: 38665588 PMCID: PMC11043861 DOI: 10.1016/j.heliyon.2024.e28123] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2023] [Revised: 03/12/2024] [Accepted: 03/12/2024] [Indexed: 04/28/2024] Open
Abstract
Non-alcoholic fatty liver disease (NAFLD) can lead to irreversible liver damage manifesting in systemic effects (e.g., elevated portal vein pressure and splenomegaly) with increased risk of deadly outcomes. However, the association of spleen volume with NAFLD and related type 2-diabetes (T2D) is not fully understood. The UK Biobank contains comprehensive health-data of 500,000 participants, including clinical data and MR images of >40,000 individuals. The present study estimated the spleen volume of 37,066 participants through automated deep learning-based image segmentation of neck-to-knee MR images. The aim was to investigate the associations of spleen volume with NAFLD, T2D and liver fibrosis, while adjusting for natural confounders. The recent redefinition and new designation of NAFLD to metabolic dysfunction-associated steatotic liver disease (MASLD), promoted by major organisations of studies on liver disease, was not employed as introduced after the conduct of this study. The results showed that spleen volume decreased with age, correlated positively with body size and was smaller in females compared to males. Larger spleens were observed in subjects with NAFLD and T2D compared to controls. Spleen volume was also positively and independently associated with liver fat fraction, liver volume and the fibrosis-4 score, with notable volumetric increases already at low liver fat fractions and volumes, but not independently associated with T2D. These results suggest a link between spleen volume and NAFLD already at an early stage of the disease, potentially due to initial rise in portal vein pressure.
Collapse
Affiliation(s)
- Samuel Helgesson
- Radiology, Department of Surgical Sciences, Uppsala University, Sweden
| | - Sambit Tarai
- Radiology, Department of Surgical Sciences, Uppsala University, Sweden
- Antaros Medical AB, BioVenture Hub, Sweden
| | | | - Håkan Ahlström
- Radiology, Department of Surgical Sciences, Uppsala University, Sweden
- Antaros Medical AB, BioVenture Hub, Sweden
| | | | - Joel Kullberg
- Radiology, Department of Surgical Sciences, Uppsala University, Sweden
- Antaros Medical AB, BioVenture Hub, Sweden
| | - Elin Lundström
- Radiology, Department of Surgical Sciences, Uppsala University, Sweden
| |
Collapse
|
2
|
Eriksson JW, Pereira MJ, Kagios C, Kvernby S, Lundström E, Fanni G, Lundqvist MH, Carlsson BCL, Sundbom M, Tarai S, Lubberink M, Kullberg J, Risérus U, Ahlström H. Short-term effects of obesity surgery versus low-energy diet on body composition and tissue-specific glucose uptake: a randomised clinical study using whole-body integrated 18F-FDG-PET/MRI. Diabetologia 2024:10.1007/s00125-024-06150-3. [PMID: 38656372 DOI: 10.1007/s00125-024-06150-3] [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] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/26/2023] [Accepted: 03/01/2024] [Indexed: 04/26/2024]
Abstract
AIMS/HYPOTHESIS Obesity surgery (OS) and diet-induced weight loss rapidly improve insulin resistance. We aim to investigate the impact of either Roux-en-Y gastric bypass (RYGB) or sleeve gastrectomy (SG) surgery compared with a diet low in energy (low-calorie diet; LCD) on body composition, glucose control and insulin sensitivity, assessed both at the global and tissue-specific level in individuals with obesity but not diabetes. METHODS In this parallel group randomised controlled trial, patients on a waiting list for OS were randomised (no blinding, sealed envelopes) to either undergo surgery directly or undergo an LCD before surgery. At baseline and 4 weeks after surgery (n=15, 11 RYGB and 4 SG) or 4 weeks after the start of LCD (n=9), investigations were carried out, including an OGTT and hyperinsulinaemic-euglycaemic clamps during which concomitant simultaneous whole-body [18F]fluorodeoxyglucose-positron emission tomography (PET)/MRI was performed. The primary outcome was HOMA-IR change. RESULTS One month after bariatric surgery and initiation of LCD, both treatments induced similar reductions in body weight (mean ± SD: -7.7±1.4 kg and -7.4±2.2 kg, respectively), adipose tissue volume (7%) and liver fat content (2% units). HOMA-IR, a main endpoint, was significantly reduced following OS (-26.3% [95% CI -49.5, -3.0], p=0.009) and non-significantly following LCD (-20.9% [95% CI -58.2, 16.5). For both groups, there were similar reductions in triglycerides and LDL-cholesterol. Fasting plasma glucose and insulin were also significantly reduced only following OS. There was an increase in glucose AUC in response to an OGTT in the OS group (by 20%) but not in the LCD group. During hyperinsulinaemia, only the OS group showed a significantly increased PET-derived glucose uptake rate in skeletal muscle but a reduced uptake in the heart and abdominal adipose tissue. Both liver and brain glucose uptake rates were unchanged after surgery or LCD. Whole-body glucose disposal and endogenous glucose production were not significantly affected. CONCLUSIONS/INTERPRETATION The short-term metabolic effects seen 4 weeks after OS are not explained by loss of body fat alone. Thus OS, but not LCD, led to reductions in fasting plasma glucose and insulin resistance as well as to distinct changes in insulin-stimulated glucose fluxes to different tissues. Such effects may contribute to the prevention or reversal of type 2 diabetes following OS. Moreover, the full effects on whole-body insulin resistance and plasma glucose require a longer time than 4 weeks. TRIAL REGISTRATION ClinicalTrials.gov NCT02988011 FUNDING: This work was supported by AstraZeneca R&D, the Swedish Diabetes Foundation, the European Union's Horizon Europe Research project PAS GRAS, the European Commission via the Marie Sklodowska Curie Innovative Training Network TREATMENT, EXODIAB, the Family Ernfors Foundation, the P.O. Zetterling Foundation, Novo Nordisk Foundation, the Agnes and Mac Rudberg Foundation and the Uppsala University Hospital ALF grants.
Collapse
Affiliation(s)
- Jan W Eriksson
- Department of Medical Sciences, Clinical Diabetology and Metabolism, Uppsala University, Uppsala, Sweden.
| | - Maria J Pereira
- Department of Medical Sciences, Clinical Diabetology and Metabolism, Uppsala University, Uppsala, Sweden
| | - Christakis Kagios
- Department of Medical Sciences, Clinical Diabetology and Metabolism, Uppsala University, Uppsala, Sweden
| | - Sofia Kvernby
- Department of Surgical Sciences, Molecular Imaging and Medical Physics, Uppsala University, Uppsala, Sweden
| | - Elin Lundström
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
| | - Giovanni Fanni
- Department of Medical Sciences, Clinical Diabetology and Metabolism, Uppsala University, Uppsala, Sweden
| | - Martin H Lundqvist
- Department of Medical Sciences, Clinical Diabetology and Metabolism, Uppsala University, Uppsala, Sweden
| | - Björn C L Carlsson
- Research and Early Development, Cardiovascular, Renal and Metabolism, BioPharmaceuticals R&D, AstraZeneca, Gothenburg, Sweden
| | - Magnus Sundbom
- Department of Surgical Sciences, Surgery, Uppsala University, Uppsala, Sweden
| | - Sambit Tarai
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
| | - Mark Lubberink
- Department of Surgical Sciences, Molecular Imaging and Medical Physics, Uppsala University, Uppsala, Sweden
| | - Joel Kullberg
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
- Antaros Medical, Mölndal, Sweden
| | - Ulf Risérus
- Department of Public Health and Caring Sciences, Clinical Nutrition and Metabolism, Uppsala University, Uppsala, Sweden
| | - Håkan Ahlström
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden.
- Antaros Medical, Mölndal, Sweden.
| |
Collapse
|
3
|
Ahmad N, Dahlberg H, Jönsson H, Tarai S, Guggilla RK, Strand R, Lundström E, Bergström G, Ahlström H, Kullberg J. Voxel-wise body composition analysis using image registration of a three-slice CT imaging protocol: methodology and proof-of-concept studies. Biomed Eng Online 2024; 23:42. [PMID: 38614974 PMCID: PMC11015680 DOI: 10.1186/s12938-024-01235-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] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2023] [Accepted: 04/02/2024] [Indexed: 04/15/2024] Open
Abstract
BACKGROUND Computed tomography (CT) is an imaging modality commonly used for studies of internal body structures and very useful for detailed studies of body composition. The aim of this study was to develop and evaluate a fully automatic image registration framework for inter-subject CT slice registration. The aim was also to use the results, in a set of proof-of-concept studies, for voxel-wise statistical body composition analysis (Imiomics) of correlations between imaging and non-imaging data. METHODS The current study utilized three single-slice CT images of the liver, abdomen, and thigh from two large cohort studies, SCAPIS and IGT. The image registration method developed and evaluated used both CT images together with image-derived tissue and organ segmentation masks. To evaluate the performance of the registration method, a set of baseline 3-single-slice CT images (from 2780 subjects including 8285 slices) from the SCAPIS and IGT cohorts were registered. Vector magnitude and intensity magnitude error indicating inverse consistency were used for evaluation. Image registration results were further used for voxel-wise analysis of associations between the CT images (as represented by tissue volume from Hounsfield unit and Jacobian determinant) and various explicit measurements of various tissues, fat depots, and organs collected in both cohort studies. RESULTS Our findings demonstrated that the key organs and anatomical structures were registered appropriately. The evaluation parameters of inverse consistency, such as vector magnitude and intensity magnitude error, were on average less than 3 mm and 50 Hounsfield units. The registration followed by Imiomics analysis enabled the examination of associations between various explicit measurements (liver, spleen, abdominal muscle, visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), thigh SAT, intermuscular adipose tissue (IMAT), and thigh muscle) and the voxel-wise image information. CONCLUSION The developed and evaluated framework allows accurate image registrations of the collected three single-slice CT images and enables detailed voxel-wise studies of associations between body composition and associated diseases and risk factors.
Collapse
Affiliation(s)
- Nouman Ahmad
- Radiology, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden.
| | - Hugo Dahlberg
- Radiology, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Hanna Jönsson
- Radiology, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Sambit Tarai
- Radiology, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | | | - Robin Strand
- Radiology, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
- Department of Information Technology, Uppsala University, Uppsala, Sweden
| | - Elin Lundström
- Radiology, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Göran Bergström
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Clinical Physiology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden
| | - Håkan Ahlström
- Radiology, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
- Antaros Medical, Mölndal, Sweden
| | - Joel Kullberg
- Radiology, Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
- Antaros Medical, Mölndal, Sweden
| |
Collapse
|
4
|
Tarai S, Lundström E, Sjöholm T, Jönsson H, Korenyushkin A, Ahmad N, Pedersen MA, Molin D, Enblad G, Strand R, Ahlström H, Kullberg J. Improved automated tumor segmentation in whole-body 3D scans using multi-directional 2D projection-based priors. Heliyon 2024; 10:e26414. [PMID: 38390107 PMCID: PMC10882139 DOI: 10.1016/j.heliyon.2024.e26414] [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: 11/14/2023] [Revised: 02/09/2024] [Accepted: 02/13/2024] [Indexed: 02/24/2024] Open
Abstract
Early cancer detection, guided by whole-body imaging, is important for the overall survival and well-being of the patients. While various computer-assisted systems have been developed to expedite and enhance cancer diagnostics and longitudinal monitoring, the detection and segmentation of tumors, especially from whole-body scans, remain challenging. To address this, we propose a novel end-to-end automated framework that first generates a tumor probability distribution map (TPDM), incorporating prior information about the tumor characteristics (e.g. size, shape, location). Subsequently, the TPDM is integrated with a state-of-the-art 3D segmentation network along with the original PET/CT or PET/MR images. This aims to produce more meaningful tumor segmentation masks compared to using the baseline 3D segmentation network alone. The proposed method was evaluated on three independent cohorts (autoPET, CAR-T, cHL) of images containing different cancer forms, obtained with different imaging modalities, and acquisition parameters and lesions annotated by different experts. The evaluation demonstrated the superiority of our proposed method over the baseline model by significant margins in terms of Dice coefficient, and lesion-wise sensitivity and precision. Many of the extremely small tumor lesions (i.e. the most difficult to segment) were missed by the baseline model but detected by the proposed model without additional false positives, resulting in clinically more relevant assessments. On average, an improvement of 0.0251 (autoPET), 0.144 (CAR-T), and 0.0528 (cHL) in overall Dice was observed. In conclusion, the proposed TPDM-based approach can be integrated with any state-of-the-art 3D UNET with potentially more accurate and robust segmentation results.
Collapse
Affiliation(s)
- Sambit Tarai
- Department of Surgical Sciences, Uppsala University, SE-75185, Uppsala, Sweden
| | - Elin Lundström
- Department of Surgical Sciences, Uppsala University, SE-75185, Uppsala, Sweden
| | - Therese Sjöholm
- Department of Surgical Sciences, Uppsala University, SE-75185, Uppsala, Sweden
| | - Hanna Jönsson
- Department of Surgical Sciences, Uppsala University, SE-75185, Uppsala, Sweden
| | | | - Nouman Ahmad
- Department of Surgical Sciences, Uppsala University, SE-75185, Uppsala, Sweden
| | - Mette A Pedersen
- Department of Nuclear Medicine & PET-Centre, Aarhus University Hospital, 8200 Aarhus N, Denmark
- Department of Biomedicine, Aarhus University, 8000 Aarhus C, Denmark
- Steno Diabetes Center Aarhus, Aarhus University Hospital, 8200 Aarhus N, Denmark
| | - Daniel Molin
- Department of Immunology, Genetics and Pathology, Uppsala University, SE-75185 Uppsala, Sweden
| | - Gunilla Enblad
- Department of Immunology, Genetics and Pathology, Uppsala University, SE-75185 Uppsala, Sweden
| | - Robin Strand
- Department of Information Technology, Uppsala University, SE-75237, Uppsala, Sweden
| | - Håkan Ahlström
- Department of Surgical Sciences, Uppsala University, SE-75185, Uppsala, Sweden
- Antaros Medical AB, SE-43153, Mölndal, Sweden
| | - Joel Kullberg
- Department of Surgical Sciences, Uppsala University, SE-75185, Uppsala, Sweden
- Antaros Medical AB, SE-43153, Mölndal, Sweden
| |
Collapse
|
5
|
Ahmad N, Strand R, Sparresäter B, Tarai S, Lundström E, Bergström G, Ahlström H, Kullberg J. Automatic segmentation of large-scale CT image datasets for detailed body composition analysis. BMC Bioinformatics 2023; 24:346. [PMID: 37723444 PMCID: PMC10506248 DOI: 10.1186/s12859-023-05462-2] [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: 03/27/2023] [Accepted: 09/01/2023] [Indexed: 09/20/2023] Open
Abstract
BACKGROUND Body composition (BC) is an important factor in determining the risk of type 2-diabetes and cardiovascular disease. Computed tomography (CT) is a useful imaging technique for studying BC, however manual segmentation of CT images is time-consuming and subjective. The purpose of this study is to develop and evaluate fully automated segmentation techniques applicable to a 3-slice CT imaging protocol, consisting of single slices at the level of the liver, abdomen, and thigh, allowing detailed analysis of numerous tissues and organs. METHODS The study used more than 4000 CT subjects acquired from the large-scale SCAPIS and IGT cohort to train and evaluate four convolutional neural network based architectures: ResUNET, UNET++, Ghost-UNET, and the proposed Ghost-UNET++. The segmentation techniques were developed and evaluated for automated segmentation of the liver, spleen, skeletal muscle, bone marrow, cortical bone, and various adipose tissue depots, including visceral (VAT), intraperitoneal (IPAT), retroperitoneal (RPAT), subcutaneous (SAT), deep (DSAT), and superficial SAT (SSAT), as well as intermuscular adipose tissue (IMAT). The models were trained and validated for each target using tenfold cross-validation and test sets. RESULTS The Dice scores on cross validation in SCAPIS were: ResUNET 0.964 (0.909-0.996), UNET++ 0.981 (0.927-0.996), Ghost-UNET 0.961 (0.904-0.991), and Ghost-UNET++ 0.968 (0.910-0.994). All four models showed relatively strong results, however UNET++ had the best performance overall. Ghost-UNET++ performed competitively compared to UNET++ and showed a more computationally efficient approach. CONCLUSION Fully automated segmentation techniques can be successfully applied to a 3-slice CT imaging protocol to analyze multiple tissues and organs related to BC. The overall best performance was achieved by UNET++, against which Ghost-UNET++ showed competitive results based on a more computationally efficient approach. The use of fully automated segmentation methods can reduce analysis time and provide objective results in large-scale studies of BC.
Collapse
Affiliation(s)
- Nouman Ahmad
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden.
| | - Robin Strand
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
- Department of Information Technology, Uppsala University, Uppsala, Sweden
| | - Björn Sparresäter
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
| | - Sambit Tarai
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
| | - Elin Lundström
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
| | - Göran Bergström
- Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
- Department of Clinical Physiology, Sahlgrenska University Hospital, Region Västra Götaland, Gothenburg, Sweden
| | - Håkan Ahlström
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
- Antaros Medical, Mölndal, Sweden
| | - Joel Kullberg
- Department of Surgical Sciences, Radiology, Uppsala University, Uppsala, Sweden
- Antaros Medical, Mölndal, Sweden
| |
Collapse
|
6
|
Sjöholm T, Tarai S, Malmberg F, Strand R, Korenyushkin A, Enblad G, Ahlström H, Kullberg J. A whole-body diffusion MRI normal atlas: development, evaluation and initial use. Cancer Imaging 2023; 23:87. [PMID: 37710346 PMCID: PMC10503210 DOI: 10.1186/s40644-023-00603-5] [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] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 08/28/2023] [Indexed: 09/16/2023] Open
Abstract
BACKGROUND Statistical atlases can provide population-based descriptions of healthy volunteers and/or patients and can be used for region- and voxel-based analysis. This work aims to develop whole-body diffusion atlases of healthy volunteers scanned at 1.5T and 3T. Further aims include evaluating the atlases by establishing whole-body Apparent Diffusion Coefficient (ADC) values of healthy tissues and including healthy tissue deviations in an automated tumour segmentation task. METHODS Multi-station whole-body Diffusion Weighted Imaging (DWI) and water-fat Magnetic Resonance Imaging (MRI) of healthy volunteers (n = 45) were acquired at 1.5T (n = 38) and/or 3T (n = 29), with test-retest imaging for five subjects per scanner. Using deformable image registration, whole-body MRI data was registered and composed into normal atlases. Healthy tissue ADCmean was manually measured for ten tissues, with test-retest percentage Repeatability Coefficient (%RC), and effect of age, sex and scanner assessed. Voxel-wise whole-body analyses using the normal atlases were studied with ADC correlation analyses and an automated tumour segmentation task. For the latter, lymphoma patient MRI scans (n = 40) with and without information about healthy tissue deviations were entered into a 3D U-Net architecture. RESULTS Sex- and Body Mass Index (BMI)-stratified whole-body high b-value DWI and ADC normal atlases were created at 1.5T and 3T. %RC of healthy tissue ADCmean varied depending on tissue assessed (4-48% at 1.5T, 6-70% at 3T). Scanner differences in ADCmean were visualised in Bland-Altman analyses of dually scanned subjects. Sex differences were measurable for liver, muscle and bone at 1.5T, and muscle at 3T. Volume of Interest (VOI)-based multiple linear regression, and voxel-based correlations in normal atlas space, showed that age and ADC were negatively associated for liver and bone at 1.5T, and positively associated with brain tissue at 1.5T and 3T. Adding voxel-wise information about healthy tissue deviations in an automated tumour segmentation task gave numerical improvements in the segmentation metrics Dice score, sensitivity and precision. CONCLUSIONS Whole-body DWI and ADC normal atlases were created at 1.5T and 3T, and applied in whole-body voxel-wise analyses.
Collapse
Affiliation(s)
- Therese Sjöholm
- Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Sambit Tarai
- Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
| | - Filip Malmberg
- Department of Information Technology, Uppsala University, Uppsala, Sweden
| | - Robin Strand
- Department of Information Technology, Uppsala University, Uppsala, Sweden
| | | | - Gunilla Enblad
- Department of Immunology, Genetics and Pathology, Uppsala University, Uppsala, Sweden
| | - Håkan Ahlström
- Department of Surgical Sciences, Uppsala University, Uppsala, Sweden
- Antaros Medical AB, Mölndal, Sweden
| | - Joel Kullberg
- Department of Surgical Sciences, Uppsala University, Uppsala, Sweden.
- Antaros Medical AB, Mölndal, Sweden.
| |
Collapse
|
7
|
Pedrosa J, Aresta G, Ferreira C, Atwal G, Phoulady HA, Chen X, Chen R, Li J, Wang L, Galdran A, Bouchachia H, Kaluva KC, Vaidhya K, Chunduru A, Tarai S, Nadimpalli SPP, Vaidya S, Kim I, Rassadin A, Tian Z, Sun Z, Jia Y, Men X, Ramos I, Cunha A, Campilho A. LNDb challenge on automatic lung cancer patient management. Med Image Anal 2021; 70:102027. [PMID: 33740739 DOI: 10.1016/j.media.2021.102027] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2020] [Revised: 01/18/2021] [Accepted: 02/26/2021] [Indexed: 12/21/2022]
Abstract
Lung cancer is the deadliest type of cancer worldwide and late detection is the major factor for the low survival rate of patients. Low dose computed tomography has been suggested as a potential screening tool but manual screening is costly and time-consuming. This has fuelled the development of automatic methods for the detection, segmentation and characterisation of pulmonary nodules. In spite of promising results, the application of automatic methods to clinical routine is not straightforward and only a limited number of studies have addressed the problem in a holistic way. With the goal of advancing the state of the art, the Lung Nodule Database (LNDb) Challenge on automatic lung cancer patient management was organized. The LNDb Challenge addressed lung nodule detection, segmentation and characterization as well as prediction of patient follow-up according to the 2017 Fleischner society pulmonary nodule guidelines. 294 CT scans were thus collected retrospectively at the Centro Hospitalar e Universitrio de So Joo in Porto, Portugal and each CT was annotated by at least one radiologist. Annotations comprised nodule centroids, segmentations and subjective characterization. 58 CTs and the corresponding annotations were withheld as a separate test set. A total of 947 users registered for the challenge and 11 successful submissions for at least one of the sub-challenges were received. For patient follow-up prediction, a maximum quadratic weighted Cohen's kappa of 0.580 was obtained. In terms of nodule detection, a sensitivity below 0.4 (and 0.7) at 1 false positive per scan was obtained for nodules identified by at least one (and two) radiologist(s). For nodule segmentation, a maximum Jaccard score of 0.567 was obtained, surpassing the interobserver variability. In terms of nodule texture characterization, a maximum quadratic weighted Cohen's kappa of 0.733 was obtained, with part solid nodules being particularly challenging to classify correctly. Detailed analysis of the proposed methods and the differences in performance allow to identify the major challenges remaining and future directions - data collection, augmentation/generation and evaluation of under-represented classes, the incorporation of scan-level information for better decision-making and the development of tools and challenges with clinical-oriented goals. The LNDb Challenge and associated data remain publicly available so that future methods can be tested and benchmarked, promoting the development of new algorithms in lung cancer medical image analysis and patient follow-up recommendation.
Collapse
Affiliation(s)
- João Pedrosa
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, Portugal.
| | - Guilherme Aresta
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, Portugal; Faculty of Engineering of the University of Porto (FEUP), Porto, Portugal
| | - Carlos Ferreira
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, Portugal; Faculty of Engineering of the University of Porto (FEUP), Porto, Portugal
| | - Gurraj Atwal
- Department of Computer Science, California State University, Sacramento, USA
| | | | - Xiaoyu Chen
- Department of Computer Science, School of Informatics, Xiamen University, China
| | - Rongzhen Chen
- Department of Computer Science, School of Informatics, Xiamen University, China
| | - Jiaoliang Li
- Department of Computer Science, School of Informatics, Xiamen University, China
| | - Liansheng Wang
- Department of Computer Science, School of Informatics, Xiamen University, China
| | - Adrian Galdran
- Department of Computing and Informatics, Bournemouth University, UK
| | - Hamid Bouchachia
- Department of Computing and Informatics, Bournemouth University, UK
| | | | | | | | | | | | | | - Ildoo Kim
- Kakao Brain, Seongnam-si, South Korea
| | | | - Zhenhuan Tian
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Peking Union Medical College, Beijing, China
| | | | - Yizhuan Jia
- Mediclouds Medical Technology, Beijing, China
| | - Xuejun Men
- Mediclouds Medical Technology, Beijing, China
| | - Isabel Ramos
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, Portugal; Department of Radiology, Centro Hospitalar e Universitário de S. João, Porto, Portugal
| | - António Cunha
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, Portugal; University of Trás-os-Montes e Alto Douro (UTAD), Vila Real, Portugal
| | - Aurélio Campilho
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, Portugal; Faculty of Engineering of the University of Porto (FEUP), Porto, Portugal
| |
Collapse
|