1
|
Azour L, Chandarana H, Maier C, Babb J, Moore W. Low Field MRI Surveillance 6-24 Months Post-acute COVID-19 Pneumonia: Factors Influencing Severity and Evolution of Lung Opacities. Acad Radiol 2024:S1076-6332(24)00092-8. [PMID: 38443207 DOI: 10.1016/j.acra.2024.02.021] [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: 12/23/2023] [Revised: 02/12/2024] [Accepted: 02/13/2024] [Indexed: 03/07/2024]
Abstract
RATIONALE AND OBJECTIVES To determine factors influencing low-field MRI lung opacity severity 6-24 months after acute Covid-19 pneumonia. MATERIALS AND METHODS 104 post-acute Covid-19 patients with 167 MRI exams were included. 32 patients had more than one exam, and 63 exams were serial exams. Pulmonary findings were graded on a scale of 0-4 by quadrant, total score ranging from 0 (no opacity) to 16 (opacity > 75%), and score >8 considered moderate and >12 severe opacity. Kruskal-Wallis, Mann-Whitney, and Spearman rank correlation was used to assess the association of clinical and demographic factors with MR opacity severity at time intervals from acute infection. Random coefficients regression was used to assess whether opacity score changed over time. RESULTS Severity of initial illness was associated with increased MR opacity score at timeframes up to 24 months (p < .05). Among the 167 exams, moderate to severe MR opacities (total opacity score >8) were identified in 33% of exams beyond 6 months: 37% at 6 - <12 months (n = 23/63); 31% at 12- < 18 months (n = 13/42); 25% at 18- < 24 months (n = 6/24); and 50% at > 24 months (n = 3/6). No significant change in total opacity score over time was identified by random coefficients regression. Among the 32 patients with serial exams, 11 demonstrated no change in opacity score from initial to final exam, 10 decrease in score (mean 2.3, stdev 1.25, range 1-4), and 11 increase in score (average 2.8, stdev 1.48, range 1-7). CONCLUSION Initial Covid-19 disease severity was associated with increased MRI total opacity score at time intervals up to 24 months, and moderate to severe opacities were commonly identified by low-field MRI beyond 6 months from acute illness.
Collapse
Affiliation(s)
- Lea Azour
- Department of Radiology, NYU Grossman School of Medicine, NYU Langone Health, New York, NY; Department of Radiological Sciences, David Geffen School of Medicine at UCLA, UCLA Health, Los Angeles, CA.
| | - Hersh Chandarana
- Department of Radiology, NYU Grossman School of Medicine, NYU Langone Health, New York, NY
| | - Christoph Maier
- Department of Radiology, NYU Grossman School of Medicine, NYU Langone Health, New York, NY
| | - James Babb
- Department of Radiology, NYU Grossman School of Medicine, NYU Langone Health, New York, NY
| | - William Moore
- Department of Radiology, NYU Grossman School of Medicine, NYU Langone Health, New York, NY
| |
Collapse
|
2
|
Feng Y, Ding Q, Meng C, Wang W, Zhang J, Lian H. Combining CT Images and Clinical Features of Four Periods to Predict Whether Patients Have Rectal Cancer. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2021; 2021:4662061. [PMID: 34917137 PMCID: PMC8670968 DOI: 10.1155/2021/4662061] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/15/2021] [Accepted: 11/19/2021] [Indexed: 01/30/2023]
Abstract
In this paper, we mainly use random forest and broad learning system (BLS) to predict rectal cancer. A total of 246 participants with computed tomography (CT) image records were enrolled. The total model in the training set (combined with imaging and clinical indicators) has the best prediction result, with the area under the curve (AUC) of 0.999 (95% confidence internal (CI): 0.996-1.000) and the accuracy of 0.990 (95%CI: 0.976-1.000). Model 3, the general model in the test set, has the best prediction result, with the AUC of 0.962 (95%CI: 0.915-1.000) and the accuracy of 0.920 (95%CI: 0.845-0.995). The results of the model using random forest prediction are compared with those using BLS prediction. It can be found that there is no statistical difference between the two results. Our prediction model combined with image features has a good prediction result, and this image feature is the most important among all features. Consequently, we can successfully predict rectal cancer through a combination of the clinical indicators and the comprehensive indicators of CT image characteristics in four different periods (plain scan, vein, artery, and excretion).
Collapse
Affiliation(s)
- Yingyin Feng
- Department of Radiology, Tianjin Fourth Central Hospital, Tianjin 300140, China
| | - Qi Ding
- Department of Radiology, Tianjin Fourth Central Hospital, Tianjin 300140, China
| | - Chen Meng
- Hemodialysis Room, Tianjin Fourth Central Hospital, Tianjin 300140, China
| | - Wenfeng Wang
- School of Science, Shanghai Institute of Technology, Shanghai 201418, China
| | - Jingjing Zhang
- School of Science, Shanghai Institute of Technology, Shanghai 201418, China
| | - Huixiu Lian
- Department of Medical Imaging, Yantai Affiliated Hospital of Binzhou Medical University, Yantai 264100, China
| |
Collapse
|
3
|
Lee C, Colletti PM, Chung JH, Ackman JB, Berry MF, Carter BW, de Groot PM, Hobbs SB, Johnson GB, Maldonado F, McComb BL, Tong BC, Walker CM, Kanne JP. ACR Appropriateness Criteria® Acute Respiratory Illness in Immunocompromised Patients. J Am Coll Radiol 2019; 16:S331-S339. [PMID: 31685101 DOI: 10.1016/j.jacr.2019.05.019] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2019] [Accepted: 05/14/2019] [Indexed: 02/08/2023]
Abstract
The immunocompromised patient with an acute respiratory illness (ARI) may present with fever, chills, weight loss, cough, shortness of breath, or chest pain. The number of immunocompromised patients continues to rise with medical advances including solid organ and stem cell transplantation, chemotherapy, and immunomodulatory therapy, along with the continued presence of human immunodeficiency virus and acquired immunodeficiency syndrome. Given the myriad of pathogens that can infect immunocompromised individuals, identifying the specific organism or organisms causing the lung disease can be elusive. Moreover, immunocompromised patients often receive prophylactic or empiric antimicrobial therapy, further complicating diagnostic evaluation. Noninfectious causes for ARI should also be considered, including pulmonary edema, drug-induced lung disease, atelectasis, malignancy, radiation-induced lung disease, pulmonary hemorrhage, diffuse alveolar damage, organizing pneumonia, lung transplant rejection, and pulmonary thromboembolic disease. As many immunocompromised patients with ARI progress along a rapid and potentially fatal course, timely selection of appropriate imaging is of great importance in this setting. 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)
| | - Christopher Lee
- Research Author, University of Southern California Keck School of Medicine, Los Angeles, California
| | | | | | - Jeanne B Ackman
- Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts
| | - Mark F Berry
- Stanford University Medical Center, Stanford, California, The Society of Thoracic Surgeons
| | - Brett W Carter
- The University of Texas MD Anderson Cancer Center, Houston, Texas
| | | | | | | | - Fabien Maldonado
- Vanderbilt University Medical Center, Nashville, Tennessee, American College of Chest Physicians
| | | | - Betty C Tong
- Duke University School of Medicine, Durham, North Carolina, The Society of Thoracic Surgeons
| | | | - Jeffrey P Kanne
- Specialty Chair, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin
| |
Collapse
|
4
|
Di Mango AL, Zanetti G, Penha D, Menna Barreto M, Marchiori E. Endemic pulmonary fungal diseases in immunocompetent patients: an emphasis on thoracic imaging. Expert Rev Respir Med 2019; 13:263-277. [PMID: 30668231 DOI: 10.1080/17476348.2019.1571914] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
INTRODUCTION Systemic endemic mycoses are prevalent in specific geographical areas of the world and are responsible for high rates of morbidity and mortality in these populations, and in immigrants and travelers returning from endemic regions. The most common fungal infections that can affect the lungs of immunocompetent patients include histoplasmosis, coccidioidomycosis, paracoccidioidomycosis, blastomycosis, sporotrichosis, aspergillosis, and cryptococcosis. Diagnosis and management of these diseases remain challenging, especially in non-endemic areas due to the lack of experience. Therefore, recognition of the various radiologic manifestations of pulmonary fungal infections associated with patients' clinical and epidemiologic history is imperative for narrowing the differential diagnosis. Areas covered: This review discusses the clinical and radiological findings of the main endemic fungal diseases affecting the lungs in immunocompetent patients. Specific topics discussed are their etiology, epidemiology, pathogenesis, clinical manifestations, methods of diagnosis, pathology and main imaging findings, especially in computed tomography. Expert commentary: Imaging plays an important role in the diagnosis and management of pulmonary fungal infection and may reveal useful signs. Although definitive diagnosis cannot be made based on imaging features alone, the use of a combination of epidemiologic, clinical and imaging findings may permit the formulation of an adequate differential diagnosis.
Collapse
Affiliation(s)
- Ana Luiza Di Mango
- a Department of Radiology , Universidade Federal do Rio de Janeiro , Rio de Janeiro , Brazil
| | - Gláucia Zanetti
- a Department of Radiology , Universidade Federal do Rio de Janeiro , Rio de Janeiro , Brazil
| | - Diana Penha
- b Cardiothoracic Consultant and Intervention , Liverpool Heart and Chest Hospital , Liverpool , UK
| | - Miriam Menna Barreto
- a Department of Radiology , Universidade Federal do Rio de Janeiro , Rio de Janeiro , Brazil
| | - Edson Marchiori
- a Department of Radiology , Universidade Federal do Rio de Janeiro , Rio de Janeiro , Brazil
| |
Collapse
|