1
|
Yu F, Yang M, He C, Yang Y, Peng Y, Yang H, Lu H, Liu H. CT radiomics combined with clinical and radiological factors predict hematoma expansion in hypertensive intracerebral hemorrhage. Eur Radiol 2024:10.1007/s00330-024-10921-2. [PMID: 38990325 DOI: 10.1007/s00330-024-10921-2] [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: 11/27/2023] [Revised: 04/24/2024] [Accepted: 05/19/2024] [Indexed: 07/12/2024]
Abstract
OBJECTIVES This study aimed to establish a hematoma expansion (HE) prediction model for hypertensive intracerebral hemorrhage (HICH) patients by combining CT radiomics, clinical information, and conventional imaging signs. METHODS A retrospective continuous collection of HICH patients from three medical centers was divided into a training set (n = 555), a validation set (n = 239), and a test set (n = 77). Extract radiomics features from baseline CT plain scan images and combine them with clinical information and conventional imaging signs to construct radiomics models, clinical imaging sign models, and hybrid models, respectively. The models will be evaluated using the area under the curve (AUC), clinical decision curve analysis (DCA), net reclassification index (NRI), and integrated discrimination improvement (IDI). RESULTS In the training, validation, and testing sets, the radiomics model predicts an AUC of HE of 0.885, 0.827, and 0.894, respectively, while the clinical imaging sign model predicts an AUC of HE of 0.759, 0.725, and 0.765, respectively. Glasgow coma scale score at admission, first CT hematoma volume, irregular hematoma shape, and radiomics score were used to construct a hybrid model, with AUCs of 0.901, 0.838, and 0.917, respectively. The DCA shows that the hybrid model had the highest net profit rate. Compared with the radiomics model and the clinical imaging sign model, the hybrid model showed an increase in NRI and IDI. CONCLUSION The hybrid model based on CT radiomics combined with clinical and radiological factors can effectively individualize the evaluation of the risk of HE in patients with HICH. CLINICAL RELEVANCE STATEMENT CT radiomics combined with clinical information and conventional imaging signs can identify HICH patients with a high risk of HE and provide a basis for clinical-targeted treatment. KEY POINTS HE is an important prognostic factor in patients with HICH. The hybrid model predicted HE with training, validation, and test AUCs of 0.901, 0.838, and 0.917, respectively. This model provides a tool for a personalized clinical assessment of early HE risk.
Collapse
Affiliation(s)
- Fei Yu
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Engineering Research Center of Intelligent Medical Imaging in Guizhou Higher Education Institutions, Zunyi, China
- Department of Medical Imaging, Chongqing Emergency Medical Center, Chongqing University Central Hospital, The Fourth People's Hospital of Chongqing, Chongqing, China
| | - Mingguang Yang
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Engineering Research Center of Intelligent Medical Imaging in Guizhou Higher Education Institutions, Zunyi, China
- Department of Medical Imaging, Chongqing Emergency Medical Center, Chongqing University Central Hospital, The Fourth People's Hospital of Chongqing, Chongqing, China
| | - Cheng He
- Department of Medical Imaging, Chongqing Emergency Medical Center, Chongqing University Central Hospital, The Fourth People's Hospital of Chongqing, Chongqing, China
| | - Yanli Yang
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Engineering Research Center of Intelligent Medical Imaging in Guizhou Higher Education Institutions, Zunyi, China
| | - Ying Peng
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Engineering Research Center of Intelligent Medical Imaging in Guizhou Higher Education Institutions, Zunyi, China
| | - Hua Yang
- Department of Medical Imaging, Chongqing Traditional Chinese Medicine Hospital, Chongqing, China
| | - Hong Lu
- Department of Radiology, The Seventh People's Hospital of Chongqing, The Central Hospital Affiliated to Chongqing University of Technology, Chongqing, China
| | - Heng Liu
- Department of Radiology, Affiliated Hospital of Zunyi Medical University, Engineering Research Center of Intelligent Medical Imaging in Guizhou Higher Education Institutions, Zunyi, China.
| |
Collapse
|
2
|
Ju Y, Zheng L, Qi W, Tian G, Lu Y. Development of a joint prediction model based on both the radiomics and clinical factors for preoperative prediction of circumferential resection margin in middle-low rectal cancer using T2WI images. Med Phys 2024; 51:2563-2577. [PMID: 37987563 DOI: 10.1002/mp.16827] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2023] [Revised: 10/07/2023] [Accepted: 10/22/2023] [Indexed: 11/22/2023] Open
Abstract
OBJECTIVES A circumferential resection margin (CRM) is an independent risk factor for local recurrence, distant metastasis, and poor overall survival of rectal cancer. In this study, we developed and validated a radiomics prediction model to predict perioperative surgical margins in patients with middle and low rectal cancer following neoadjuvant treatment and for decisions about treatment plans for patients. METHODS This study retrospectively analyzed 275 patients from center 1(training cohort) and 120 patients from center 2(verification cohort) with rectal cancer diagnosed at two centers from July 2020 to July 2022 who underwent neoadjuvant therapy and had their CRM status confirmed by preoperative high-resolution magnetic resonance imaging (MRI) scans. Radiomics signatures were extracted and screened from MRI images and a radiomics signature was built by the least absolute shrinkage and selection operator (LASSO) logistic regression model, which was combined with clinical signatures to construct a nomogram. The receiver operating characteristic (ROC) curve and area under the curve (AUC) value, sensitivity, specificity, positive predictive value, negative predictive value, and calibration curve were used to evaluate the predictive performance of the model. RESULTS In our research, the combined model has the best performance. In the training group, the radiomics model based on high-spatial-resolution T2-weighted imaging (HR-T2WI), clinical model and combined model demonstrated an AUC of 0.819 (0.802-0.833), 0.843 (0.822-0.861), and 0.910 (0.880-0.940), respectively. In the validation group, they demonstrated an AUC of 0.745 (0.715-0.788), 0.827 (0.798-0.850), and 0.848 (0.779-0.917), respectively. The calibration curve confirmed the clinical applicability of the model. CONCLUSIONS The individualized prediction model established by combining radiomics signatures and clinical signatures can efficiently and objectively predict perioperative margin invasion in patients with middle and low rectal cancer.
Collapse
Affiliation(s)
- Yiheng Ju
- Department of Gastrointestinal Surgery, Affiliated Hospital of Qingdao University, Qingdao, China
| | - Longbo Zheng
- Department of Gastrointestinal Surgery, Affiliated Hospital of Qingdao University, Qingdao, China
| | - Wei Qi
- Department of Gastrointestinal Surgery, The Second Affiliated Hospital of Shandong First Medical University, Shandong, China
| | - Guangye Tian
- College of Control Science and Technology, Shandong University, Shandong, China
| | - Yun Lu
- Department of Gastrointestinal Surgery, Affiliated Hospital of Qingdao University, Qingdao, China
- Department of Gastrointestinal Surgery, Shandong Key Laboratory of Digital Medicine and Computer Assisted Surgery, Affiliated Hospital of Qingdao University, Qingdao, China
| |
Collapse
|
3
|
Fletcher-Sandersjöö A, Svedung Wettervik T, Tatter C, Tjerkaski J, Nelson DW, Maegele M, Svensson M, Lewén A, Enblad P, Bellander BM, Thelin EP. Absolute Contusion Expansion Is Superior to Relative Expansion in Predicting Traumatic Brain Injury Outcomes: A Multi-Center Observational Cohort Study. J Neurotrauma 2024; 41:705-713. [PMID: 38062766 PMCID: PMC10902499 DOI: 10.1089/neu.2023.0274] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2023] Open
Abstract
Contusion expansion (CE) is a potentially treatable outcome predictor in traumatic brain injury (TBI), and a suitable end-point for hemostatic therapy trials. However, there is no consensus on the definition of clinically relevant CE, both in terms of measurement criteria (absolute vs. relative volume increase) and cutoff values. In light of this, the aim of this study was to assess the predictive abilities of different CE definitions on outcome. We performed a multi-center observational cohort study of adults with moderate-to-severe TBI treated in an intensive care unit. The exposure of interest was CE, defined as the absolute and relative volume change between the first and second computed tomography scan. The primary outcome was the Glasgow Outcome Scale (GOS) at 6-12 months post-injury, dichotomized into unfavorable (GOS ≤3) or favorable (GOS ≥4). The secondary outcome was all-cause mortality. In total, 798 patients were included, with a median duration of 7.0 h between the first and second CT scan. The median absolute and relative CE was 1.5 mL (interquartile range [IQR] 0.1-8.3 mL) and 100% (IQR 10-530%), respectively. Both CE forms were independently associated with unfavorable GOS. Absolute CE outperformed relative CE in predicting both unfavorable GOS (area under the curve [AUC]: 0.65 vs. 0.60, p = 0.002) and all-cause mortality (AUC: 0.66 vs. 0.60, p = 0.003). For dichotomized CE, absolute cutoffs of 1-10 mL yielded the best results. We conclude that absolute CE demonstrates stronger outcome correlation than relative CE. In studies focusing on lesion progression in TBI, it may be advantageous to use absolute CE as the primary outcome metric. For dichotomized outcomes, cutoffs between 1 and 10 mL are suggested, depending on the desired sensitivity-specificity balance.
Collapse
Affiliation(s)
- Alexander Fletcher-Sandersjöö
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
- Department of Clinical Neuroscience, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
| | | | - Charles Tatter
- Department of Clinical Neuroscience, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
- Department of Radiology, Stockholm Southern Hospital, Stockholm, Sweden
| | - Jonathan Tjerkaski
- Department of Clinical Neuroscience, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
| | - David W. Nelson
- Function Perioperative Care and Medicine, Karolinska University Hospital, Stockholm, Sweden
- Department of Physiology and Pharmacology, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
| | - Marc Maegele
- Department for Trauma and Orthopedic Surgery, Cologne-Merheim Medical Center, University Witten/Herdecke, Cologne, Germany
- Institute for Research in Operative Medicine, University Witten/Herdecke, Cologne, Germany
| | - Mikael Svensson
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
- Department of Clinical Neuroscience, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
| | - Anders Lewén
- Department of Medical Sciences, Section of Neurosurgery, Uppsala University, Uppsala, Sweden
| | - Per Enblad
- Department of Medical Sciences, Section of Neurosurgery, Uppsala University, Uppsala, Sweden
| | - Bo-Michael Bellander
- Department of Neurosurgery, Karolinska University Hospital, Stockholm, Sweden
- Department of Clinical Neuroscience, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
| | - Eric Peter Thelin
- Department of Clinical Neuroscience, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
- Department of Neurology, Karolinska University Hospital, Stockholm, Sweden
| |
Collapse
|
4
|
Alanezi ST, Almutairi WM, Cronin M, Gobbo O, O'Mara SM, Sheppard D, O'Connor WT, Gilchrist MD, Kleefeld C, Colgan N. Whole-brain traumatic controlled cortical impact to the left frontal lobe: Magnetic resonance image-based texture analysis. J Neuropathol Exp Neurol 2024; 83:94-106. [PMID: 38164986 DOI: 10.1093/jnen/nlad110] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/03/2024] Open
Abstract
This research assesses the capability of texture analysis (TA) derived from high-resolution (HR) T2-weighted magnetic resonance imaging to identify primary sequelae following 1-5 hours of controlled cortical impact mild or severe traumatic brain injury (TBI) to the left frontal cortex (focal impact) and secondary (diffuse) sequelae in the right frontal cortex, bilateral corpus callosum, and hippocampus in rats. The TA technique comprised first-order (histogram-based) and second-order statistics (including gray-level co-occurrence matrix, gray-level run length matrix, and neighborhood gray-level difference matrix). Edema in the left frontal impact region developed within 1 hour and continued throughout the 5-hour assessments. The TA features from HR images confirmed the focal injury. There was no significant difference among radiomics features between the left and right corpus callosum or hippocampus from 1 to 5 hours following a mild or severe impact. The adjacent corpus callosum region and the distal hippocampus region (s), showed no diffuse injury 1-5 hours after mild or severe TBI. These results suggest that combining HR images with TA may enhance detection of early primary and secondary sequelae following TBI.
Collapse
Affiliation(s)
- Saleh T Alanezi
- Physics Department, Faculty of Science, Northern Border University, ArAr, Saudi Arabia
- School of Natural Sciences, College of Science and Engineering, University of Galway, Galway, Ireland
| | - Waleed M Almutairi
- Medical Imaging Department, King Abdullah bin Abdulaziz University Hospital, Riyadh, Saudi Arabia
- Department of Physics, College of Science, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia
| | - Michelle Cronin
- Conway Institute, University College Dublin, Belfield, Dublin, Ireland
| | - Oliviero Gobbo
- School of Pharmacy and Pharmaceutical Sciences & Institute of Neuroscience, Trinity College, Dublin, Ireland
| | - Shane M O'Mara
- Institute of Neuroscience, Trinity College, Dublin, Ireland
| | - Declan Sheppard
- Department of Radiology, University Hospital Galway, Galway, Ireland
| | - William T O'Connor
- University of Limerick School of Medicine, Castletroy, Limerick, Ireland
| | - Michael D Gilchrist
- School of Mechanical & Materials Engineering, University College Dublin, Belfield, Dublin, Ireland
| | - Christoph Kleefeld
- School of Natural Sciences, College of Science and Engineering, University of Galway, Galway, Ireland
| | - Niall Colgan
- School of Natural Sciences, College of Science and Engineering, University of Galway, Galway, Ireland
- Department of Engineering, Technological University of the Shannon, Athlone, Ireland
| |
Collapse
|
5
|
Understanding Acquired Brain Injury: A Review. Biomedicines 2022; 10:biomedicines10092167. [PMID: 36140268 PMCID: PMC9496189 DOI: 10.3390/biomedicines10092167] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Revised: 08/02/2022] [Accepted: 08/26/2022] [Indexed: 01/19/2023] Open
Abstract
Any type of brain injury that transpires post-birth is referred to as Acquired Brain Injury (ABI). In general, ABI does not result from congenital disorders, degenerative diseases, or by brain trauma at birth. Although the human brain is protected from the external world by layers of tissues and bone, floating in nutrient-rich cerebrospinal fluid (CSF); it remains susceptible to harm and impairment. Brain damage resulting from ABI leads to changes in the normal neuronal tissue activity and/or structure in one or multiple areas of the brain, which can often affect normal brain functions. Impairment sustained from an ABI can last anywhere from days to a lifetime depending on the severity of the injury; however, many patients face trouble integrating themselves back into the community due to possible psychological and physiological outcomes. In this review, we discuss ABI pathologies, their types, and cellular mechanisms and summarize the therapeutic approaches for a better understanding of the subject and to create awareness among the public.
Collapse
|