1
|
Jin Y, Liu J, Zhou Y, Chen R, Chen H, Duan W, Chen Y, Zhang XL. CRDet: A circle representation detector for lung granulomas based on multi-scale attention features with center point calibration. Comput Med Imaging Graph 2024; 113:102354. [PMID: 38341946 DOI: 10.1016/j.compmedimag.2024.102354] [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] [Received: 09/14/2023] [Revised: 02/04/2024] [Accepted: 02/04/2024] [Indexed: 02/13/2024]
Abstract
Lung granuloma is a very common lung disease, and its specific diagnosis is important for determining the exact cause of the disease as well as the prognosis of the patient. And, an effective lung granuloma detection model based on computer-aided diagnostics (CAD) can help pathologists to localize granulomas, thereby improving the efficiency of the specific diagnosis. However, for lung granuloma detection models based on CAD, the significant size differences between granulomas and how to better utilize the morphological features of granulomas are both critical challenges to be addressed. In this paper, we propose an automatic method CRDet to localize granulomas in histopathological images and deal with these challenges. We first introduce the multi-scale feature extraction network with self-attention to extract features at different scales at the same time. Then, the features will be converted to circle representations of granulomas by circle representation detection heads to achieve the alignment of features and ground truth. In this way, we can also more effectively use the circular morphological features of granulomas. Finally, we propose a center point calibration method at the inference stage to further optimize the circle representation. For model evaluation, we built a lung granuloma circle representation dataset named LGCR, including 288 images from 50 subjects. Our method yielded 0.316 mAP and 0.571 mAR, outperforming the state-of-the-art object detection methods on our proposed LGCR.
Collapse
Affiliation(s)
- Yu Jin
- Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan, China
| | - Juan Liu
- Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan, China.
| | - Yuanyuan Zhou
- Department of Immunology, TaiKang Medical School (School of Basic Medical Sciences), Wuhan University, Wuhan, China; Hubei Province Key Laboratory of Allergy and Immunology, Wuhan University, Wuhan, China
| | - Rong Chen
- Wuhan Jinyintan Hospital, Tongji Medical College of Huazhong University of Science and Technology, Wuhan, China
| | - Hua Chen
- Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan, China
| | - Wensi Duan
- Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan, China
| | - Yuqi Chen
- Institute of Artificial Intelligence, School of Computer Science, Wuhan University, Wuhan, China
| | - Xiao-Lian Zhang
- Department of Immunology, TaiKang Medical School (School of Basic Medical Sciences), Wuhan University, Wuhan, China; Hubei Province Key Laboratory of Allergy and Immunology, Wuhan University, Wuhan, China
| |
Collapse
|
2
|
Feng SL, Li JY, Dong CL. Primary biliary cholangitis presenting with granulomatous lung disease misdiagnosed as lung cancer: A case report. World J Clin Cases 2024; 12:354-360. [PMID: 38313637 PMCID: PMC10835678 DOI: 10.12998/wjcc.v12.i2.354] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Revised: 12/06/2023] [Accepted: 12/25/2023] [Indexed: 01/11/2024] Open
Abstract
BACKGROUND There are few cases of pulmonary granulomatous changes secondary to primary biliary cirrhosis (PBC). No case of granulomatous lung disease secondary to PBC misdiagnosed as lung cancer had been reported. CASE SUMMARY A middle-aged woman presented with lung nodules and was misdiagnosed with lung cancer by positron emission tomography/computed tomography. She underwent left lobectomy, and the pathology of the nodules showed granulomatous inflammation, which was then treated with antibiotics. However, a new nodule appeared. Further investigation with lung biopsy and liver serology led to the diagnosis of PBC, and chest computed tomography indicated significant reduction in the pulmonary nodule by treatment with methylprednisolone and ursodeoxycholic acid. CONCLUSION Diagnosis of pulmonary nodules requires integrating various clinical data to avoid unnecessary pulmonary lobectomy.
Collapse
Affiliation(s)
- Shan-Li Feng
- Department of Respiratory and Critical Care Medicine, The Second Hospital of Jilin University, Changchun 130041, Jilin Province, China
| | - Jun-Yao Li
- Department of Respiratory and Critical Care Medicine, The Second Hospital of Jilin University, Changchun 130041, Jilin Province, China
| | - Chun-Ling Dong
- Department of Respiratory and Critical Care Medicine, The Second Hospital of Jilin University, Changchun 130041, Jilin Province, China
| |
Collapse
|
3
|
Abstract
Rationale: The Sarcoidosis Diagnostic Score (SDS) has been established to quantitate the clinical features consistent with sarcoidosis in a monocentric study. Objectives: We aimed to confirm the diagnostic value of SDS in a large, multicontinental study and to assess the utility of SDS in differentiating sarcoidosis from alternative diagnoses, including infectious and noninfectious granulomatous diseases. Methods: We included patients with biopsy-confirmed sarcoidosis at nine centers across the world. Patients without sarcoidosis seen at the same sites served as control patients. Using a modified World Association of Sarcoidosis and Other Granulomatous Disorders organ assessment instrument, we scored all patients for the presence of granuloma on biopsy, highly probable symptoms, and least probable symptoms for each area. Two sarcoidosis scores were generated: SDS Biopsy (with biopsy) and SDS Clinical (without biopsy). SDS Clinical and Biopsy were calculated for all patients. We calculated and compared the area under the curve (AUC) for SDS Clinical and Biopsy according to different diagnosis scenarios. Results: A total of 1,041 patients with sarcoidosis and 1,035 without sarcoidosis were included. The results for SDS Clinical (AUC, 0.888; 95% confidence interval [CI], 0.874-0.902) and SDS Biopsy (AUC, 0.979; 95% CI, 0.973-0.985) according to AUC were good to excellent for differentiating sarcoidosis from alternative diagnosis. SDS Clinical was less discriminatory in males (P = 0.01) and in high tuberculosis prevalence centers (P < 0.001). However, SDS Clinical (AUC, 0.684; 95% CI, 0.602-0.766) and SDS Biopsy (AUC, 0.754; 95% CI, 0.673-0.835) were not sufficiently discriminative for noninfectious granulomatous diseases, but both SDSs could differentiate sarcoidosis from infectious granulomatous diseases. Algorithms were proposed for the SDS Clinical and SDS Biopsy to assist the clinician in the diagnostic process, and cutoff values were proposed for the SDS Clinical and SDS Biopsy, allowing the diagnosis of sarcoidosis to be safely confirmed or rejected in most cases except for noninfectious granulomatous disease. Conclusions: This multicontinental study confirms that both SDS Clinical and SDS Biopsy have good to excellent performance in discriminating sarcoidosis from alternative diagnoses. Differences in the AUC were seen for high tuberculosis prevalence versus low tuberculosis prevalence centers and for males versus females. Both SDSs had good discriminatory function for infectious granulomatous disease but failed in cases of noninfectious granulomatous disease such as berylliosis.
Collapse
|
4
|
The Risk of Sarcoidosis Misdiagnosis and the Harmful Effect of Corticosteroids When the Disease Picture Is Incomplete. Biomedicines 2023; 11:biomedicines11010175. [PMID: 36672683 PMCID: PMC9855435 DOI: 10.3390/biomedicines11010175] [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: 12/01/2022] [Revised: 01/05/2023] [Accepted: 01/09/2023] [Indexed: 01/12/2023] Open
Abstract
Sarcoidosis is a complex granulomatous disease of unknown etiology. Due to the heterogeneity of the disease, the diagnosis remains challenging in many cases, often at the physician's discretion, requiring a thorough and complex investigation. Many other granulomatous diseases have the potential to mimic sarcoidosis, whether infectious, occupational, or autoimmune diseases and starting an unnecessary corticosteroid treatment can worsen the patient's prognosis, leading to side effects that can be harder to treat than the actual disease.
Collapse
|
5
|
Sun W, Dong Z, Zhou Y, Xiong K, Liu H, Zhang Z, Fan L. Early Identification of Fungal and Mycobacterium Infections in Pulmonary Granulomas Using Metagenomic Next-Generation Sequencing on Formalin fixation and paraffin embedding tissue. Expert Rev Mol Diagn 2022; 22:461-468. [PMID: 35261303 DOI: 10.1080/14737159.2022.2052046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
Abstract
BACKGROUND The purpose of the study is to assess the etiology detection ability of Metagenomic Next-Generation Sequencing (mNGS) on formalin fixation and paraffin embedding (FFPE) tissue from postoperative biopsy specimen. METHODS We prospectively enrolled specimens from patients undergone surgery biopsy due to undefinite diagnosis and pathologically indicated granulomatous lesions. FFPE tissues were tested by mNGS and histopathology. The etiology detection rate of mNGS was calculated and compared with histopathology, using the clinical diagnosis as the reference criteria. RESULTS Among the 69 cases eventually included, 41 (59.42%) were diagnosed as infectious granuloma. The overall fungi and mycobacteria etiology detection rate of mNGS in granuloma lesions was 87.80 % (36/41) . The mNGS increased detection rate by 68.29 % (28/41) compared with histopathology, the difference was statistically significant (χ2= 28.97, P 0.00).The detection rates of mNGS in fungal infections (12/12,100%) and in mycobacterium infections (22/27, 81.48%) were significant higher than those of histopathology (8/12, 66.67% and 0/27,0.00 %;both P 0.00). 2 (2/2.100%) cases of co-infection were detected at one time by mNGS. All mNGS-based clinical decisions were made within 2 days. CONCLUSIONS The mNGS could accurately and quickly detect fungi and mycobacteria on FFPE specimens from postoperative granuloma specimens and identify the pathogens to the species level. CLINICAL TRIALS REGISTRATION China Clinical Trial Registry ChiCTR2000035464.
Collapse
Affiliation(s)
- Wenwen Sun
- Department of Tuberculosis and Shanghai Key Lab of Tuberculosis, Shanghai Pulmonary Hospital Affiliated to School of Medicine, Tongji University, Shanghai 200092, China
| | - Zhengwei Dong
- Department of Pathology, Shanghai Pulmonary Hospital Affiliated to School of Medicine, Tongji University, Shanghai, China
| | - Yiming Zhou
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital Affiliated to School of Medicine, Tongji University, Shanghai, China
| | - Kunlong Xiong
- Department of Tuberculosis and Shanghai Key Lab of Tuberculosis, Shanghai Pulmonary Hospital Affiliated to School of Medicine, Tongji University, Shanghai 200092, China
| | - Hongcheng Liu
- Department of Thoracic Surgery, Shanghai Pulmonary Hospital Affiliated to School of Medicine, Tongji University, Shanghai, China
| | | | - Lin Fan
- Department of Tuberculosis and Shanghai Key Lab of Tuberculosis, Shanghai Pulmonary Hospital Affiliated to School of Medicine, Tongji University, Shanghai 200092, China
| |
Collapse
|
6
|
Tissue Pathogens and Cancers: A Review of Commonly Seen Manifestations in Histo- and Cytopathology. Pathogens 2021; 10:pathogens10111410. [PMID: 34832566 PMCID: PMC8624235 DOI: 10.3390/pathogens10111410] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2021] [Revised: 10/26/2021] [Accepted: 10/28/2021] [Indexed: 02/07/2023] Open
Abstract
Tissue pathogens are commonly encountered in histopathology and cytology practice, where they can present as either benign mimickers of malignancy or true malignancies. The aim of this review is to provide a timely synthesis of our understanding of these tissue pathogens, with an emphasis on pertinent diagnostic conundrums associated with the benign mimickers of malignancy that can be seen with viral infections and those which manifest as granulomas. The oncogenic pathogens, including viruses, bacteria, and parasites, are then discussed with relationship to their associated malignancies. Although not exhaustive, the epidemiology, clinical manifestations, pathogenesis, and histological findings are included, along with a short review of emerging therapies.
Collapse
|
7
|
Judson MA. Granulomatous Sarcoidosis Mimics. Front Med (Lausanne) 2021; 8:680989. [PMID: 34307411 PMCID: PMC8295651 DOI: 10.3389/fmed.2021.680989] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2021] [Accepted: 06/10/2021] [Indexed: 12/19/2022] Open
Abstract
Many granulomatous diseases can mimic sarcoidosis histologically and in terms of their clinical features. These mimics include infectious granulomatous diseases, granulomatous reactions to occupational and environmental exposures, granulomatous drug reactions, vasculitides and idiopathic granulomatous conditions. It is important to distinguish sarcoidosis from these mimics, as a misdiagnosis of these diseases may have serious consequences. This manuscript reviews numerous sarcoidosis mimics and describes features of these diseases that may allow them to be differentiated from sarcoidosis. Distinguishing features between sarcoidosis and its mimics requires a careful review of the medical history, symptoms, demographics, radiographic findings, histologic features, and additional laboratory data. Understanding the clinical characteristics of sarcoidosis and its mimics should lead to more accurate diagnoses and treatment of granulomatous disorders that should improve the care of these patients. As the diagnostic criteria of sarcoidosis are not standardized, it is possible that some of these sarcoidosis mimics may represent varied clinical presentations of sarcoidosis itself.
Collapse
Affiliation(s)
- Marc A Judson
- Division of Pulmonary and Critical Care Medicine MC-91, Department of Medicine, Albany, NY, United States
| |
Collapse
|
8
|
Abstract
PURPOSE OF REVIEW Previous studies mainly described a role for organic agents as possible triggers for sarcoidosis. In this review, we address recent studies suggesting a possible role for inorganic elements, such as metals or silica in sarcoidosis pathogenesis. RECENT FINDINGS Several epidemiological papers suggest that inorganic agents, either by environmental exposures or occupational activities, could trigger sarcoidosis. Association between inorganics and sarcoidosis is also described in several recently published case reports and studies demonstrating immunological sensitization to inorganic agents in sarcoidosis patients.Studies comparing chronic beryllium disease (CBD) and sarcoidosis suggest that although antigenic triggers may differ, underlying processes may be comparable.Besides the fact that a growing number of studies show a possible role for inorganic triggers, it is also suggested that inorganic triggered sarcoidosis may result in a more severe phenotype, including pulmonary fibrosis. SUMMARY We can use the knowledge already gained on CBD pathogenesis to conduct further research into role of inorganics, such as metals and silica as antigens in sarcoidosis. Given the importance of a lymphocyte proliferation test (LPT) in diagnosing CBD, it seems obvious to also implement this test in the diagnostic work-up of sarcoidosis to identify patients with an inorganic antigenic trigger of their disease.
Collapse
|
9
|
Rojas‐Jaimes J, Hugo Rojas‐Figueroa V, Corcuera R, Arenas J, García‐Reynoso J. Wegener's granulomatosis and differential diagnosis of mucosal leishmaniasis. Clin Case Rep 2021; 9:e04280. [PMID: 34194788 PMCID: PMC8222648 DOI: 10.1002/ccr3.4280] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2020] [Revised: 04/11/2021] [Accepted: 04/26/2021] [Indexed: 11/06/2022] Open
Abstract
Granulomatosis with polyangiitis with nasal septal perforation can be confused with infectious diseases such as mucosal leishmaniasis, so these cases warrant an in-depth study in order to provide the correct treatment. Among the main characteristics to consider to define a Wegener's granulomatosis as opposed to an infectious disease are vasculitis, lymphadenopathy, and sinusopathy.
Collapse
Affiliation(s)
| | | | | | - José Arenas
- Surgical Pathology Service at Hospital Guillermo Almenara IrigoyenLimaPerú
| | | |
Collapse
|