Artificial intelligence-based algorithms in detection and 3D reconstruction of lung nodules on chest computed tomography scans

AbstractObjectiveConvolutional neural networks are a subclass of deep learning or artificial intelligence that are predominantly used for image analysis and classification. This proof-of-concept study attempts to train a convolutional neural network algorithm that can reliably determine if the middle turbinate is pneumatised (concha bullosa) on coronal sinus computed tomography images.MethodConsecutive high-resolution computed tomography scans of the paranasal sinuses were retrospectively collected between January 2016 and December 2018 at a tertiary rhinology hospital in Australia. The classification layer of Inception-V3 was retrained in Python using a transfer learning method to interpret the computed tomography images. Segmentation analysis was also performed in an attempt to increase diagnostic accuracy.ResultsThe trained convolutional neural network was found to have diagnostic accuracy of 81 per cent (95 per cent confidence interval: 73.0–89.0 per cent) with an area under the curve of 0.93.ConclusionA trained convolutional neural network algorithm appears to successfully identify pneumatisation of the middle turbinate with high accuracy. Further studies can be pursued to test its ability in other clinically important anatomical variants in otolaryngology and rhinology.

Download Full-text

An artificial intelligence algorithm that differentiates anterior ethmoidal artery location on sinus computed tomography scans

The Journal of Laryngology & Otology ◽

10.1017/s0022215119002536 ◽

2019 ◽

Vol 134 (1) ◽

pp. 52-55 ◽

Cited By ~ 3

Author(s):

J Huang ◽

A-R Habib ◽

D Mendis ◽

J Chong ◽

M Smith ◽

...

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Computed Tomography ◽

Neural Networks ◽

Convolutional Neural Network ◽

Convolutional Neural Networks ◽

Sinus Surgery ◽

Computed Tomography Scans ◽

Ethmoidal Artery ◽

Anterior Ethmoidal Artery

AbstractObjectiveDeep learning using convolutional neural networks represents a form of artificial intelligence where computers recognise patterns and make predictions based upon provided datasets. This study aimed to determine if a convolutional neural network could be trained to differentiate the location of the anterior ethmoidal artery as either adhered to the skull base or within a bone ‘mesentery’ on sinus computed tomography scans.MethodsCoronal sinus computed tomography scans were reviewed by two otolaryngology residents for anterior ethmoidal artery location and used as data for the Google Inception-V3 convolutional neural network base. The classification layer of Inception-V3 was retrained in Python (programming language software) using a transfer learning method to interpret the computed tomography images.ResultsA total of 675 images from 388 patients were used to train the convolutional neural network. A further 197 unique images were used to test the algorithm; this yielded a total accuracy of 82.7 per cent (95 per cent confidence interval = 77.7–87.8), kappa statistic of 0.62 and area under the curve of 0.86.ConclusionConvolutional neural networks demonstrate promise in identifying clinically important structures in functional endoscopic sinus surgery, such as anterior ethmoidal artery location on pre-operative sinus computed tomography.

Download Full-text

Indeterminate Pulmonary Nodules at Diagnosis in Rhabdomyosarcoma: Are They Clinically Significant? A Report From the European Paediatric Soft Tissue Sarcoma Study Group

Journal of Clinical Oncology ◽

10.1200/jco.18.01535 ◽

2019 ◽

Vol 37 (9) ◽

pp. 723-730 ◽

Cited By ~ 5

Author(s):

Bas Vaarwerk ◽

Gianni Bisogno ◽

Kieran McHugh ◽

Hervé J. Brisse ◽

Carlo Morosi ◽

...

Keyword(s):

Computed Tomography ◽

Overall Survival ◽

Soft Tissue ◽

Soft Tissue Sarcoma ◽

Pulmonary Nodules ◽

Study Group ◽

Event Free Survival ◽

Free Survival ◽

Chest Computed Tomography ◽

Computed Tomography Scans

Purpose To evaluate the clinical significance of indeterminate pulmonary nodules at diagnosis (defined as ≤ 4 pulmonary nodules < 5 mm or 1 nodule measuring ≥ 5 and < 10 mm) in patients with pediatric rhabdomyosarcoma (RMS). Patients and Methods We selected patients with supposed nonmetastatic RMS treated in large pediatric oncology centers in the United Kingdom, France, Italy, and the Netherlands, who were enrolled in the European Soft Tissue Sarcoma Study Group (E pSSG) RMS 2005 study. Patients included in the current study received a diagnosis between September 2005 and December 2013, and had chest computed tomography scans available for review that were done at time of diagnosis. Local radiologists were asked to review the chest computed tomography scans for the presence of pulmonary nodules and to record their findings on a standardized case report form. In the E pSSG RMS 2005 Study, patients with indeterminate pulmonary nodules were treated identically to patients without pulmonary nodules, enabling us to compare event-free survival and overall survival between groups by log-rank test. Results In total, 316 patients were included; 67 patients (21.2%) had indeterminate pulmonary nodules on imaging and 249 patients (78.8%) had no pulmonary nodules evident at diagnosis. Median follow-up for survivors (n = 258) was 75.1 months; respective 5-year event-free survival and overall survival rates (95% CI) were 77.0% (64.8% to 85.5%) and 82.0% (69.7% to 89.6%) for patients with indeterminate nodules and 73.2% (67.1% to 78.3%) and 80.8% (75.1% to 85.3%) for patients without nodules at diagnosis ( P = .68 and .76, respectively). Conclusion Our study demonstrated that indeterminate pulmonary nodules at diagnosis do not affect outcome in patients with otherwise localized RMS. There is no need to biopsy or upstage patients with RMS who have indeterminate pulmonary nodules at diagnosis.

Download Full-text