Deep learning PET/CT-based radiomics integrates clinical data: A feasibility study to distinguish between tuberculosis nodules and lung cancer

BACKGROUND

Radiomic diagnosis models generally consider only a single dimension of information, leading to limitations in their diagnostic accuracy and reliability. The integration of multiple dimensions of information into the deep learning model have the potential to improve its diagnostic capabilities. The purpose of study was to evaluate the performance of deep learning model in distinguishing tuberculosis (TB) nodules and lung cancer (LC) based on deep learning features, radiomic features, and clinical information.

METHODS

Positron emission tomography (PET) and computed tomography (CT) image data from 97 patients with LC and 77 patients with TB nodules were collected. One hundred radiomic features were extracted from both PET and CT imaging using the pyradiomics platform, and 2048 deep learning features were obtained through a residual neural network approach. Four models included traditional machine learning model with radiomic features as input (traditional radiomics), a deep learning model with separate input of image features (deep convolutional neural networks [DCNN]), a deep learning model with two inputs of radiomic features and deep learning features (radiomics-DCNN) and a deep learning model with inputs of radiomic features and deep learning features and clinical information (integrated model). The models were evaluated using area under the curve (AUC), sensitivity, accuracy, specificity, and F1-score metrics.

RESULTS

The results of the classification of TB nodules and LC showed that the integrated model achieved an AUC of 0.84 (0.82-0.88), sensitivity of 0.85 (0.80-0.88), and specificity of 0.84 (0.83-0.87), performing better than the other models.

CONCLUSION

The integrated model was found to be the best classification model in the diagnosis of TB nodules and solid LC.

FDG PET Scan Durations via Effective Data Processing

BACKGROUND

Total-body dynamic PET (dPET) imaging using ¹⁸ F-fluorodeoxyglucose (¹⁸ F-FDG) has received widespread attention in clinical oncology. However, the conventionally required scan duration of approximately 1 hour seriously limits the application and promotion of this imaging technique. In this study, we investigated the possibility and feasibility of shortening the total-body dynamic scan duration to 30 min post-injection (PI) with the help of a novel Patlak data processing algorithm for accurate K_i estimations of tumor lesions.

METHODS

Total-body dPET images acquired by uEXPLORER (United Imaging Healthcare Inc.) using ¹⁸ F-FDG of 15 patients with different tumor types were analyzed in this study. Dynamic images were reconstructed into 25 frames with a specific temporal dividing protocol for the scan data acquired 1 hour PI. Patlak analysis-based K_i parametric imaging was conducted based on the imaging data corresponding to the first 30 min PI, during which a Patlak data processing method based on cubit Hermite interpolation (THI) was applied. The resultant K_i images acquired by 30-min dynamic PET data and the standard 1-hour K_i images were compared in terms of visual imaging effect, region signal-to-noise ratio (SNR), and K_i estimation accuracy to evaluate the performance of the proposed K_i imaging method with a shortened scan duration.

RESULTS

With the help of Patlak data processing, acceptable K_i parametric images were obtained from dynamic PET data acquired with a scan duration of 30 min PI. Compared with K_i images obtained from unprocessed Patlak data, the resulting images from the proposed method performed better in terms of noise reduction. Moreover, Bland-Altman (BA) plot and Person correlation coefficient (PPC) analysis showed that that 30-min K_i images obtained from the processed Patlak data had higher accuracy for tumor lesions.

CONCLUSION

Satisfactory K_i parametric images with high tumor accuracy can be acquired from dynamic imaging data corresponding to the first 30 min PI. Patlak data processing can help achieve higher K_i imaging quality and higher accuracy regarding tumor lesion K_i values. Clinically, it is possible to shorten the dynamic scan duration of ¹⁸ F-FDG PET to 30 min to acquire an accurate tumor K_i and further effective tumor detection with uEXPLORER scanners. This article is protected by copyright. All rights reserved.

Imaging Approaches for the Study of Metabolism in Real Time Using Genetically Encoded Reporters

Metabolism comprises of two axes in order to serve homeostasis: anabolism and catabolism. Both axes are interbranched with the so-called bioenergetics aspect of metabolism. There is a plethora of analytical biochemical methods to monitor metabolites and reactions in lysates, yet there is a rising need to monitor, quantify and elucidate in real time the spatiotemporal orchestration of complex biochemical reactions in living systems and furthermore to analyze the metabolic effect of chemical compounds that are destined for the clinic. The ongoing technological burst in the field of imaging creates opportunities to establish new tools that will allow investigators to monitor dynamics of biochemical reactions and kinetics of metabolites at a resolution that ranges from subcellular organelle to whole system for some key metabolites. This article provides a mini review of available toolkits to achieve this goal but also presents a perspective on the open space that can be exploited to develop novel methodologies that will merge classic biochemistry of metabolism with advanced imaging. In other words, a perspective of "watching metabolism in real time."

Sarcoidosis and neuroendocrine tumours: case report and literature review

Rare cases of co-existing sarcoidosis and carcinoid tumour have been previously reported in the literature. Both diseases may have vague and overlapping clinical presentations that can lead to delayed or missed diagnosis. To avoid this diagnostic pitfall, we discuss and compare the clinical presentations of all reported cases in the literature including our case. We also provide hypothesis to explain the relationship between the two diseases.

Importance of PET/CT examination in patients with malignant uveal melanoma

INTRODUCTION

Diagnostic and therapeutic management of the patient with malignant uveal melanoma (MMU) is subject to ongoing efforts to innovate. PET/CT (Positron Emission Tomography / Computed Tomography) examination is important in both diagnosis and metastases.

MATERIAL AND METHODS

Evaluation of the importance of PET/CT examination in the group of patients diagnosed with MMU in the period 12.1.2016 to 6.12.2018. All patients with a diagnosis of secondary retinal detachment, suspected uveal melanoma, underwent standard examinations to detect possible metastases (liver ultrasound, chest X-ray). Patients for whom a stereotactic radiosurgery solution was planned due to the stage of the disease this examination was to exclude metastasis in the liver or lungs. PET/CT examination is part of the protocol within the exclusion criteria for treatment with stereotactic radiosurgery in one day session surgery.

RESULTS

In the group of 84 patients, 47 women (56 %) and 37 men (44 %) were aged between 26 and 90 years. Their average age was 61.4 years. The median group was 64 years, modus 65 years. Of 84 patients, 79 (94 % of cases) had a diagnosis of C69.3 (choroidal melanoma) and 5 patients (6 % of cases) had a diagnosis of C69.4 (ciliary body melanoma). Subsequent PET/CT examination in many patients did not reveal hypermetabolic manifestations that could involve various pathological processes, in others the radiopharmaceutical was captured in the primary tumor area of the uveal tract. Hypermetabolism in eye globe was only found in melanomas with a volume of more than 0.5 cm3. PET/CT examinations were 85, with one patient undergoing examination twice. However, in 25 patients (26 examinations), the radiopharmaceutical was taken up in places that subsequently required closer attention. The initial aim of the examination was to locate possible metastases of MMU. In the others, 3 incidents have been reported: increased metabolism in the lung and liver, thyroid and mediastinal lymph nodes. Of the 85 examinations, 26 (30.6 %) resulted in a hypermetabolic manifestation of accumulation, which was not located in the eye tract, resp. right in the eye. Two malignancies (prostatic carcinoma and rectosigmal carcinoma) have occurred in two patients. Very important was the discovery of MMU metastasis in the liver, which confirmed the important role of PET/CT examination in the management of MMU patients. The metastasis was discovered after repeated PET/CT examination.

CONCLUSION

PET/CT examination is a technically demanding examination and is one of the possibilities of imaging intraocular melanoma in tumors with volume more than 0.5 cm3. It is important in determining the grading and staging of the disease before radiosurgical treatment and also in detecting possible metastases after MMU treatment in cases where ultrasound or MRI examinations do not give a definite result. However, our study confirmed the significance of this examination for randomly detected 2 duplex malignancies (2.4%) and 3 incidentalomas (3.6%) in patients whose ophthalmologist diagnosed uveal melanoma and sent patients for full-body PET/CT examination.

Metabolic Plasticity of Melanoma Cells and Their Crosstalk With Tumor Microenvironment

Cutaneous melanoma (CM) is a highly aggressive and drug resistant solid tumor, showing an impressive metabolic plasticity modulated by oncogenic activation. In particular, melanoma cells can generate adenosine triphosphate (ATP) during cancer progression by both cytosolic and mitochondrial compartments, although CM energetic request mostly relies on glycolysis. The upregulation of glycolysis is associated with constitutive activation of BRAF/MAPK signaling sustained by BRAFV600E kinase mutant. In this scenario, the growth and progression of CM are strongly affected by melanoma metabolic changes and interplay with tumor microenvironment (TME) that sustain tumor development and immune escape. Furthermore, CM metabolic plasticity can induce a metabolic adaptive response to BRAF/MEK inhibitors (BRAFi/MEKi), associated with the shift from glycolysis toward oxidative phosphorylation (OXPHOS). Therefore, in this review article we survey the metabolic alterations and plasticity of CM, its crosstalk with TME that regulates melanoma progression, drug resistance and immunosurveillance. Finally, we describe hallmarks of melanoma therapeutic strategies targeting the shift from glycolysis toward OXPHOS.

Synthesis and Automated Labeling of [18F]Darapladib, a Lp-PLA2 Ligand, as Potential PET Imaging Tool of Atherosclerosis

Atherosclerosis and its associated clinical complications are major health issues in industrialized countries. Lipoprotein-associated phospholipase A₂ (Lp-PLA₂) was demonstrated to play an important role in atherogenesis and to be a potential risk prediction factor of plaque rupture. Darapladib is one of the most potent Lp-PLA₂ inhibitors with an IC₅₀ of 0.25 nM. Using its affinity for Lp-PLA₂, we describe herein the total synthesis of darapladib radiolabeling precursor and the automated radiolabeling process for positron emission tomography (PET) imaging via an arylboronate moiety. The tracer thus obtained was tested in a mouse model of atherosclerosis (ApoE KO) and compared with the widely used [¹⁸F]fluorodeoxyglucose ([¹⁸F]FDG) PET tracer, known to label metabolically active cells. [¹⁸F]Darapladib showed a significant accumulation within mice aortic atheromatous plaques dissected out ex vivo compared to [¹⁸F]FDG. Incubation of the radiotracer with human carotid samples showed a strong accumulation within the atherosclerotic plaques and supports its potential for use in PET imaging.