Abstract
Background[18F]-fluorodeoxyglucose (FDG) positron emission tomography with computed tomography (PET-CT) is a well-established modality in the work-up of patients with suspected or confirmed diagnosis of lung cancer. Recent research efforts have focused on extracting theragnostic and textural information from manually indicated lung lesions. Both semi-automatic and fully automatic use of artificial intelligence (AI) to localise and classify FDG-avid foci has been demonstrated. To fully harness AI’s usefulness, we have developed a method which both automatically detects abnormal lung lesions and calculates the total lesion glycolysis (TLG) on FDG PET-CT.MethodsOne hundred twelve patients (59 females and 53 males) who underwent FDG PET-CT due to suspected or for the management of known lung cancer were studied retrospectively. These patients were divided into a training group (59%; n = 66), a validation group (20.5%; n = 23) and a test group (20.5%; n = 23). A nuclear medicine physician manually segmented abnormal lung lesions with increased FDG-uptake in all PET-CT studies. The AI-based method was trained to segment the lesions based on the manual segmentations. TLG was then calculated from manual and AI-based measurements, respectively and analysed with Bland-Altman plots.ResultsThe AI-tool’s performance in detecting lesions had a sensitivity of 90%. One small lesion was missed in two patients, respectively, where both had a larger lesion which was correctly detected. The positive and negative predictive values were 88% and 100%, respectively. The correlation between manual and AI TLG measurements was strong (R2 = 0.74). Bias was 42 g and 95% limits of agreement ranged from − 736 to 819 g. Agreement was particularly high in smaller lesions.ConclusionsThe AI-based method is suitable for the detection of lung lesions and automatic calculation of TLG in small- to medium-sized tumours. In a clinical setting, it will have an added value due to its capability to sort out negative examinations resulting in prioritised and focused care on patients with potentially malignant lesions.
Highlights
Characterisation of lung lesions has become one of the main indications for [18F]-fluorodeoxyglucose (FDG) positron emission tomography with computed tomography (PET-CT) in recent years in nuclear medicine and radiology departments [1]
Our aim was to develop a completely automated method based on artificial intelligence (AI) for the analysis of FDG PET-CT in patients with known or suspected lung cancer and measure the total lesion glycolysis (TLG) compared to manual measurements
Material and methods The AI-based tool consists of two convolutional neural network (CNN), the Detection CNN trained to detect lung lesions and the Organ CNN trained to segment organs
Summary
Characterisation of lung lesions has become one of the main indications for [18F]-fluorodeoxyglucose (FDG) positron emission tomography with computed tomography (PET-CT) in recent years in nuclear medicine and radiology departments [1]. It has been reported that clinicians use PET-CT assertively to investigate nodules with low risk (< 5%) of malignancy even though guidelines do not recommend it [5]. A study has demonstrated that a critical number of patients with lung nodules and considered low risk had positive PET-CT findings and proven malignant histological diagnosis [6]. On the opposite side in the characterisation of larger lung lesions, PET-CT has become the tool of choice diminishing risks for patients from invasive techniques [7, 8] and providing valuable theragnostic tumour information [9] and tumour texture analysis [10]. For PET-CT studies, most of the research has been done in automatically obtained theragnostic [9] and radiomic features but always with manual tumour localisation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
