1
|
Alves VM, dos Santos Cardoso J, Gama J. Classification of Pulmonary Nodules in 2-[ 18F]FDG PET/CT Images with a 3D Convolutional Neural Network. Nucl Med Mol Imaging 2024; 58:9-24. [PMID: 38261899 PMCID: PMC10796312 DOI: 10.1007/s13139-023-00821-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2022] [Revised: 05/17/2023] [Accepted: 08/08/2023] [Indexed: 01/25/2024] Open
Abstract
Purpose 2-[18F]FDG PET/CT plays an important role in the management of pulmonary nodules. Convolutional neural networks (CNNs) automatically learn features from images and have the potential to improve the discrimination between malignant and benign pulmonary nodules. The purpose of this study was to develop and validate a CNN model for classification of pulmonary nodules from 2-[18F]FDG PET images. Methods One hundred thirteen participants were retrospectively selected. One nodule per participant. The 2-[18F]FDG PET images were preprocessed and annotated with the reference standard. The deep learning experiment entailed random data splitting in five sets. A test set was held out for evaluation of the final model. Four-fold cross-validation was performed from the remaining sets for training and evaluating a set of candidate models and for selecting the final model. Models of three types of 3D CNNs architectures were trained from random weight initialization (Stacked 3D CNN, VGG-like and Inception-v2-like models) both in original and augmented datasets. Transfer learning, from ImageNet with ResNet-50, was also used. Results The final model (Stacked 3D CNN model) obtained an area under the ROC curve of 0.8385 (95% CI: 0.6455-1.0000) in the test set. The model had a sensibility of 80.00%, a specificity of 69.23% and an accuracy of 73.91%, in the test set, for an optimised decision threshold that assigns a higher cost to false negatives. Conclusion A 3D CNN model was effective at distinguishing benign from malignant pulmonary nodules in 2-[18F]FDG PET images. Supplementary Information The online version contains supplementary material available at 10.1007/s13139-023-00821-6.
Collapse
Affiliation(s)
- Victor Manuel Alves
- Faculty of Economics, University of Porto, Rua Dr. Roberto Frias, Porto, 4200-464 Porto, Portugal
- Department of Nuclear Medicine, University Hospital Center of São João, Alameda Prof. Hernâni Monteiro, 4200-319 Porto, Portugal
| | - Jaime dos Santos Cardoso
- Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
| | - João Gama
- Faculty of Economics, University of Porto, Rua Dr. Roberto Frias, Porto, 4200-464 Porto, Portugal
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
| |
Collapse
|
2
|
Radiomics and Artificial Intelligence Can Predict Malignancy of Solitary Pulmonary Nodules in the Elderly. Diagnostics (Basel) 2023; 13:diagnostics13030384. [PMID: 36766488 PMCID: PMC9914272 DOI: 10.3390/diagnostics13030384] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2022] [Revised: 01/16/2023] [Accepted: 01/18/2023] [Indexed: 01/22/2023] Open
Abstract
Solitary pulmonary nodules (SPNs) are a diagnostic and therapeutic challenge for thoracic surgeons. Although such lesions are usually benign, the risk of malignancy remains significant, particularly in elderly patients, who represent a large segment of the affected population. Surgical treatment in this subset, which usually presents several comorbidities, requires careful evaluation, especially when pre-operative biopsy is not feasible and comorbidities may jeopardize the outcome. Radiomics and artificial intelligence (AI) are progressively being applied in predicting malignancy in suspicious nodules and assisting the decision-making process. In this study, we analyzed features of the radiomic images of 71 patients with SPN aged more than 75 years (median 79, IQR 76-81) who had undergone upfront pulmonary resection based on CT and PET-CT findings. Three different machine learning algorithms were applied-functional tree, Rep Tree and J48. Histology was malignant in 64.8% of nodules and the best predictive value was achieved by the J48 model (AUC 0.9). The use of AI analysis of radiomic features may be applied to the decision-making process in elderly frail patients with suspicious SPNs to minimize the false positive rate and reduce the incidence of unnecessary surgery.
Collapse
|
3
|
Ishiwata T, Ujiie H, Gregor A, Inage T, Motooka Y, Kinoshita T, Aragaki M, Chen Z, Effat A, Bernards N, Yasufuku K. Pilot study using virtual 4-D tracking electromagnetic navigation bronchoscopy in the diagnosis of pulmonary nodules: a single center prospective study. J Thorac Dis 2021; 13:2885-2895. [PMID: 34164180 PMCID: PMC8182521 DOI: 10.21037/jtd-21-141] [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] [Indexed: 01/05/2023]
Abstract
Background Electromagnetic navigation bronchoscopy (ENB) is a navigation technology intended to improve the diagnostic yield of pulmonary nodules. However, nodule displacement due to respiratory motion may compromise the accuracy of the navigation guidance. The Veran SPiNDrive ENB system employs respiratory-gating (4D-tracking) to compensate for this motion. The aim of the present study was to evaluate the diagnostic performance and safety of the Veran SPiNDrive system for biopsy of pulmonary nodules. Methods Adult patients with pulmonary nodules of ≥1 cm were enrolled at a single center. Both conventional bronchoscopy and 4D-tracking ENB were performed in one procedure session under general anesthesia, with the procedure order being randomly assigned. Radial probe endobronchial ultrasound and fluoroscopy were used in both groups. The diagnostic performance, safety, total procedure time, and total fluoroscopy time of the ENB phase were compared to the corresponding conventional bronchoscopy phase. Results The study was terminated due to poor accrual; a total of eleven patients were enrolled. The mean size of pulmonary nodules was 2.1 cm. The sensitivity for malignancy was 67% (6/9) and 56% (5/9) with conventional bronchoscopy and with 4D-tracking ENB, respectively. Two cases developed minor bleeding after conventional bronchoscopy, while no complications were observed after 4D-tracking ENB. The mean procedure time was 16.1 and 21.7 min (P=0.090), and the mean duration time for fluoroscopy use was 77 and 44 sec (P=0.056) for the conventional bronchoscopy and the 4D-tracking ENB phases, respectively. Conclusions The diagnostic performance of the Veran SPiNDrive 4D-tracking ENB did not exceed that of conventional bronchoscopy for pulmonary nodules. No complications were seen during 4D-tracking ENB. A study with a larger number of participants is required for further assessment.
Collapse
Affiliation(s)
- Tsukasa Ishiwata
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Hideki Ujiie
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Alexander Gregor
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Terunaga Inage
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Yamato Motooka
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Tomonari Kinoshita
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Masato Aragaki
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Zhenchian Chen
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Andrew Effat
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Nicholas Bernards
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada
| | - Kazuhiro Yasufuku
- Division of Thoracic Surgery, Toronto General Hospital, University Health Network, Toronto, Ontario, Canada.,Princess Margaret Cancer Centre, University Health Network/University of Toronto, Toronto, Ontario, Canada.,TECHNA Institute for the Advancement of Technology for Health, University Health Network, Toronto, Ontario, Canada.,Institute of Biomedical Engineering, University of Toronto, Toronto, Ontario, Canada
| |
Collapse
|
4
|
Boo WH, Chan YC. Lo, the ever confounding nipple shadow! MALAYSIAN FAMILY PHYSICIAN : THE OFFICIAL JOURNAL OF THE ACADEMY OF FAMILY PHYSICIANS OF MALAYSIA 2020; 15:79-82. [PMID: 33329866 PMCID: PMC7735879] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
The discovery of a solitary pulmonary nodule (SPN) on chest imaging can be alarming for both the clinician and the patient. In the absence of a uniform guideline, managing SPN is nothing short of challenging for primary care physicians (PCPs). We present a case here of a patient presenting with prolonged cough who also displayed unilateral SPN on her chest radiograph. Through further examination, this presence was later shown to be a nipple shadow simulating SPN, and the patient was spared unnecessary testing and psychological distress.
Collapse
Affiliation(s)
- W H Boo
- MD, UTC Ipoh Health Clinic, LB 21-22, Bangunan UTC Ipoh, Jalan Dato Onn Jaafar, Ipoh, Perak, Malaysia,
| | - Y C Chan
- MD, Department of Family Medicine Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, Malaysia
| |
Collapse
|
5
|
Huang YS, Niisato E, Su MYM, Benkert T, Hsu HH, Shih JY, Chen JS, Chang YC. Detecting small pulmonary nodules with spiral ultrashort echo time sequences in 1.5 T MRI. MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE 2020; 34:399-409. [PMID: 32902778 DOI: 10.1007/s10334-020-00885-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Revised: 08/26/2020] [Accepted: 08/27/2020] [Indexed: 12/19/2022]
Abstract
OBJECTIVE This study investigated ultrashort echo time (UTE) sequences in 1.5 T magnetic resonance imaging (MRI) for small lung nodule detection. MATERIALS AND METHODS A total of 120 patients with 165 small lung nodules before video-associated thoracoscopic resection were enrolled. MRI sequences included conventional volumetric interpolated breath-hold examination (VIBE, scan time 16 s), spiral UTE (TE 0.05 ms) with free-breathing (scan time 3.5-5 min), and breath-hold sequences (scan time 20 s). Chest CT provided a standard reference for nodule size and morphology. Nodule detection sensitivity was evaluated on a lobe-by-lobe basis. RESULTS The nodule detection rate was significantly higher in spiral UTE free-breathing (> 78%, p < 0.05) and breath-hold sequences (> 75%, p < 0.05) compared with conventional VIBE (> 55%), reaching 100% when nodule size was > 16 mm, and reaching 95% when nodules were in solid morphology, regardless of size. The inter-sequence reliability between free-breathing and breath-hold spiral UTE was good (κ > 0.80). Inter-reader agreement was also high (κ > 0.77) for spiral UTE sequences. Nodule size measurements were consistent between CT and spiral UTE MRI, with a minimal bias up to 0.2 mm. DISCUSSION Spiral UTE sequences detect small lung nodules that warrant surgery, offers realistic scan times for clinical work, and could be implemented as part of routine lung MRI.
Collapse
Affiliation(s)
- Yu-Sen Huang
- Department of Medical Imaging, National Taiwan University Hospital, No.7, Chung-Shan South Road, Taipei, 100, Taiwan
- Department of Radiology, National Taiwan University College of Medicine, Taipei, Taiwan
| | | | - Mao-Yuan Marine Su
- Department of Medical Imaging, National Taiwan University Hospital, No.7, Chung-Shan South Road, Taipei, 100, Taiwan
- Department of Radiology, National Taiwan University College of Medicine, Taipei, Taiwan
| | | | - Hsao-Hsun Hsu
- Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
| | - Jin-Yuan Shih
- Department of Internal Medicine, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
| | - Jin-Shing Chen
- Department of Surgery, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
| | - Yeun-Chung Chang
- Department of Medical Imaging, National Taiwan University Hospital, No.7, Chung-Shan South Road, Taipei, 100, Taiwan.
- Department of Radiology, National Taiwan University College of Medicine, Taipei, Taiwan.
| |
Collapse
|
6
|
Honguero Martínez AF, Godoy Mayoral R, Genovés Crespo M, Sampedro Salinas CA, Andrés Pretel F, García Vicente A, López Miguel P, Callejas González J, Almonte García CE, Peyró Sánchez M, Núñez Ares AMDR, García Jiménez MD, Rodríguez Ortega CR, Lázaro Sahuquillo M, Jiménez López J, León Atance P, Morales Serrano ML. Analysis of solitary pulmonary nodule after surgical resection in patients with 18F-FDG positron emission tomography integrated computed tomography in the preoperative work-up. Med Clin (Barc) 2020; 156:535-540. [PMID: 32859401 DOI: 10.1016/j.medcli.2020.05.061] [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: 01/08/2020] [Revised: 05/18/2020] [Accepted: 05/20/2020] [Indexed: 11/28/2022]
Abstract
INTRODUCTION To analyse clinicopathological characteristics of patients operated for pulmonary solitary nodule (PSN) and 18F-FDG integrated PET-CT scan after surgical resection. METHODOLOGY Retrospective study on a prospective database of patients operated from January 2007 to October 2017 for PSN without preoperative diagnosis. Dependent variable was anatomopathological result (benign vs malignant) of PSN. Variables of the study were: age, sex, PET-CT uptake, SUVmax, smoking history, COPD, previous history of malignant disease, tumoral location, and tumour size on CT-scan. RESULTS A total of 305 patients were included in this study, 225 (73.8%) men, 80 (26.2%) women, mean age = 63.9 (range 29-86 years), mean size PSN = 1.68 (s.d. .65 cm), benign = 46 (15.1%), malignant = 258 (84.6%), type of resection: pulmonary wedge = 151 (49.5%), lobectomy = 141 (46.2%), segmentectomy = 12 (3.9%), exploratory intervention = 1 (0.3%). Postoperative mortality was 1.9%. COPD = 50.8% cases, previous cancer disease = 172 cases (56.4%), smoking history = 250 cases (82.0%), positive PET = 280 cases (91.8%), PSN in upper pulmonary fields = 204 cases (66.9%), median SUVmax = 3.4 (range 0-20.7). Backward stepwise binary logistic regression model showed that age, SUVmax, previous malignant disease and female sex were independent risk factors with statistical significance (p < .05). Sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy were 94.6%, 23.4%, 87.1%, 44.0%, and 83.6% respectively. There were 14 false negative cases (4.6%) and 36 false positive cases (11.8%). CONCLUSIONS Age, SUVmax, previous malignant disease, and female sex were independent risk factors in our study. Each case should be individually evaluated in a multidisciplinary committee, and the patient's preferences or concerns should be kept in mind in decision-making. Surgical resection of PSN is not exempt from morbidity and mortality, even in sublobar or pulmonary wedge resection.
Collapse
Affiliation(s)
| | - Raúl Godoy Mayoral
- Servicio de Neumología. Hospital General Universitario de Albacete, Albacete, España
| | - Marta Genovés Crespo
- Servicio de Cirugía Torácica. Hospital General Universitario de Albacete, Albacete, España
| | | | | | - Ana García Vicente
- Servicio de Medicina Nuclear. Hospital General Universitario de Ciudad Real, Ciudad Real, España
| | - Patricia López Miguel
- Servicio de Neumología. Hospital General Universitario de Albacete, Albacete, España
| | | | | | - María Peyró Sánchez
- Servicio de Cirugía Torácica. Hospital General Universitario de Albacete, Albacete, España
| | | | | | | | | | - Jesús Jiménez López
- Servicio de Neumología. Hospital General Universitario de Albacete, Albacete, España
| | - Pablo León Atance
- Servicio de Cirugía Torácica. Hospital General Universitario de Albacete, Albacete, España
| | | |
Collapse
|
7
|
Elia S, D’Angelo G, Palmieri F, Sorge R, Massoud R, Cortese C, Hardavella G, De Stefano A. A machine learning evolutionary algorithm-based formula to assess tumor markers and predict lung cancer in cytologically negative pleural effusions. Soft comput 2020. [DOI: 10.1007/s00500-019-04344-1] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
|
8
|
Dobler CC. Too much or too little medicine? Overdiagnosis, underdiagnosis, overtreatment and undertreatment in respiratory diseases. Breathe (Sheff) 2019; 15:2-3. [PMID: 30838052 PMCID: PMC6395983 DOI: 10.1183/20734735.0006-2019] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022] Open
Abstract
At a time when technical possibilities for medical investigations are plentiful and ever expanding, there is growing awareness that more is not always better and that “too much medicine” may be harmful. In recent years, the global Choosing Wisely educational campaign has aimed to bring attention to unnecessary healthcare. Unnecessary healthcare includes overtesting, overdiagnosis and overtreatment [1]. The March issue of Breathe aims to challenge us to rethink our clinical practice, to reflect on the evidence, and to identify potential cognitive biases that might influence us to provide “too much” or “too little” medicine [2]. The March issue of Breathe focuses on overdiagnosis, underdiagnosis, overtreatment and undertreatment in respiratory diseaseshttp://ow.ly/63OW30ntCeu
Collapse
Affiliation(s)
- Claudia C Dobler
- Dept of Respiratory Medicine, Liverpool Hospital, and University of New South Wales, Sydney, Australia
| |
Collapse
|