RESUMEN
BACKGROUND: Semiparametric survival analysis such as the Cox proportional hazards (CPH) regression model is commonly employed in endometrial cancer (EC) study. Although this method does not need to know the baseline hazard function, it cannot estimate event time ratio (ETR) which measures relative increase or decrease in survival time. To estimate ETR, the Weibull parametric model needs to be applied. The objective of this study is to develop and evaluate the Weibull parametric model for EC patients' survival analysis. METHODS: Training (n = 411) and testing (n = 80) datasets from EC patients were retrospectively collected to investigate this problem. To determine the optimal CPH model from the training dataset, a bi-level model selection with minimax concave penalty was applied to select clinical and radiomic features which were obtained from T2-weighted MRI images. After the CPH model was built, model diagnostic was carried out to evaluate the proportional hazard assumption with Schoenfeld test. Survival data were fitted into a Weibull model and hazard ratio (HR) and ETR were calculated from the model. Brier score and time-dependent area under the receiver operating characteristic curve (AUC) were compared between CPH and Weibull models. Goodness of the fit was measured with Kolmogorov-Smirnov (KS) statistic. RESULTS: Although the proportional hazard assumption holds for fitting EC survival data, the linearity of the model assumption is suspicious as there are trends in the age and cancer grade predictors. The result also showed that there was a significant relation between the EC survival data and the Weibull distribution. Finally, it showed that Weibull model has a larger AUC value than CPH model in general, and it also has smaller Brier score value for EC survival prediction using both training and testing datasets, suggesting that it is more accurate to use the Weibull model for EC survival analysis. CONCLUSIONS: The Weibull parametric model for EC survival analysis allows simultaneous characterization of the treatment effect in terms of the hazard ratio and the event time ratio (ETR), which is likely to be better understood. This method can be extended to study progression free survival and disease specific survival. TRIAL REGISTRATION: ClinicalTrials.gov NCT03543215, https://clinicaltrials.gov/ , date of registration: 30th June 2017.
Asunto(s)
Neoplasias Endometriales , Imagen por Resonancia Magnética , Modelos de Riesgos Proporcionales , Humanos , Femenino , Neoplasias Endometriales/mortalidad , Neoplasias Endometriales/diagnóstico por imagen , Persona de Mediana Edad , Imagen por Resonancia Magnética/métodos , Estudios Retrospectivos , Análisis de Supervivencia , Anciano , Curva ROC , Adulto , Modelos Estadísticos , RadiómicaRESUMEN
The rich chemical information from tissue metabolomics provides a powerful means to elaborate tissue physiology or tumor characteristics at cellular and tumor microenvironment levels. However, the process of obtaining such information requires invasive biopsies, is costly, and can delay clinical patient management. Conversely, computed tomography (CT) is a clinical standard of care but does not intuitively harbor histological or prognostic information. Furthermore, the ability to embed metabolome information into CT to subsequently use the learned representation for classification or prognosis has yet to be described. This study develops a deep learning-based framework -- tissue-metabolomic-radiomic-CT (TMR-CT) by combining 48 paired CT images and tumor/normal tissue metabolite intensities to generate ten image embeddings to infer metabolite-derived representation from CT alone. In clinical NSCLC settings, we ascertain whether TMR-CT results in an enhanced feature generation model solving histology classification/prognosis tasks in an unseen international CT dataset of 742 patients. TMR-CT non-invasively determines histological classes - adenocarcinoma/squamous cell carcinoma with an F1-score = 0.78 and further asserts patients' prognosis with a c-index = 0.72, surpassing the performance of radiomics models and deep learning on single modality CT feature extraction. Additionally, our work shows the potential to generate informative biology-inspired CT-led features to explore connections between hard-to-obtain tissue metabolic profiles and routine lesion-derived image data.
RESUMEN
There is a clinical need for 18F-labeled somatostatin analogs for the imaging of neuroendocrine tumors (NET), given the limitations of using [68Ga]Ga-DOTA-peptides, particularly with regard to widespread accessibility. We have shown that [18F]fluoroethyl-triazole-[Tyr3]-octreotate ([18F]FET-ßAG-TOCA) has favorable dosimetry and biodistribution. As a step toward clinical implementation, we conducted a prospective, noninferiority study of [18F]FET-ßAG-TOCA PET/CT compared with [68Ga]Ga-DOTA- peptide PET/CT in patients with NET. Methods: Forty-five patients with histologically confirmed NET, grades 1 and 2, underwent PET/CT imaging with both [18F]FET-ßAG-TOCA and [68Ga]Ga-peptide performed within a 6-mo window (median, 77 d; range, 6-180 d). Whole-body PET/CT was conducted 50 min after injection of 165 MBq of [18F]FET-ßAG-TOCA. Tracer uptake was evaluated by comparing SUVmax and tumor-to-background ratios at both lesion and regional levels by 2 unblinded, experienced readers. A randomized, blinded reading of both scans was also then undertaken by 3 experienced readers, and consensus was assessed at a regional level. The ability of both tracers to visualize liver metastases was also assessed. Results: A total of 285 lesions were detected on both imaging modalities. An additional 13 tumor deposits were seen in 8 patients on [18F]FET-ßAG-TOCA PET/CT, and [68Ga]Ga-DOTA-peptide PET/CT detected an additional 7 lesions in 5 patients. Excellent correlation in SUVmax was observed between both tracers (r = 0.91; P < 0.001). No difference was observed between median SUVmax across regions, except in the liver, where the median tumor-to-background ratio of [18F]FET-ßAG-TOCA was significantly lower than that of [68Ga]Ga-DOTA-peptide (2.5 ± 1.9 vs. 3.5 ± 2.3; P < 0.001). Conclusion: [18F]FET-ßAG-TOCA was not inferior to [68Ga]Ga-DOTA-peptide in visualizing NET and may be considered in routine clinical practice given the longer half-life and availability of the cyclotron-produced fluorine radioisotope.
RESUMEN
Ultrasound-based models exist to support the classification of adnexal masses but are subjective and rely upon ultrasound expertise. We aimed to develop an end-to-end machine learning (ML) model capable of automating the classification of adnexal masses. In this retrospective study, transvaginal ultrasound scan images with linked diagnoses (ultrasound subjective assessment or histology) were extracted and segmented from Imperial College Healthcare, UK (ICH development dataset; n = 577 masses; 1444 images) and Morgagni-Pierantoni Hospital, Italy (MPH external dataset; n = 184 masses; 476 images). A segmentation and classification model was developed using convolutional neural networks and traditional radiomics features. Dice surface coefficient (DICE) was used to measure segmentation performance and area under the ROC curve (AUC), F1-score and recall for classification performance. The ICH and MPH datasets had a median age of 45 (IQR 35-60) and 48 (IQR 38-57) years old and consisted of 23.1% and 31.5% malignant cases, respectively. The best segmentation model achieved a DICE score of 0.85 ± 0.01, 0.88 ± 0.01 and 0.85 ± 0.01 in the ICH training, ICH validation and MPH test sets. The best classification model achieved a recall of 1.00 and F1-score of 0.88 (AUC:0.93), 0.94 (AUC:0.89) and 0.83 (AUC:0.90) in the ICH training, ICH validation and MPH test sets, respectively. We have developed an end-to-end radiomics-based model capable of adnexal mass segmentation and classification, with a comparable predictive performance (AUC 0.90) to the published performance of expert subjective assessment (gold standard), and current risk models. Further prospective evaluation of the classification performance of this ML model against existing methods is required.
RESUMEN
Malignant transformation is characterised by aberrant phospholipid metabolism of cancers, associated with the upregulation of choline kinase alpha (CHKα). Due to the metabolic instability of choline radiotracers and the increasing use of late-imaging protocols, we developed a more stable choline radiotracer, [18F]fluoromethyl-[1,2-2H4]choline ([18F]D4-FCH). [18F]D4-FCH has improved protection against choline oxidase, the key choline catabolic enzyme, via a 1H/2D isotope effect, together with fluorine substitution. Due to the promising mechanistic and safety profiles of [18F]D4-FCH in vitro and preclinically, the radiotracer has transitioned to clinical development. [18F]D4-FCH is a safe positron emission tomography (PET) tracer, with a favourable radiation dosimetry profile for clinical imaging. [18F]D4-FCH PET/CT in lung and prostate cancers has shown highly heterogeneous intratumoral distribution and large lesion variability. Treatment with abiraterone or enzalutamide in metastatic castrate-resistant prostate cancer patients elicited mixed responses on PET at 12-16 weeks despite predominantly stable radiological appearances. The sum of the weighted tumour-to-background ratios (TBRs-wsum) was associated with the duration of survival.
Asunto(s)
Colina , Neoplasias de la Próstata , Masculino , Humanos , Colina/metabolismo , Tomografía Computarizada por Tomografía de Emisión de Positrones , Tomografía de Emisión de Positrones/métodos , Neoplasias de la Próstata/patología , RadiometríaRESUMEN
BACKGROUND: Methods to improve stratification of small (≤15 mm) lung nodules are needed. We aimed to develop a radiomics model to assist lung cancer diagnosis. METHODS: Patients were retrospectively identified using health records from January 2007 to December 2018. The external test set was obtained from the national LIBRA study and a prospective Lung Cancer Screening programme. Radiomics features were extracted from multi-region CT segmentations using TexLab2.0. LASSO regression generated the 5-feature small nodule radiomics-predictive-vector (SN-RPV). K-means clustering was used to split patients into risk groups according to SN-RPV. Model performance was compared to 6 thoracic radiologists. SN-RPV and radiologist risk groups were combined to generate "Safety-Net" and "Early Diagnosis" decision-support tools. RESULTS: In total, 810 patients with 990 nodules were included. The AUC for malignancy prediction was 0.85 (95% CI: 0.82-0.87), 0.78 (95% CI: 0.70-0.85) and 0.78 (95% CI: 0.59-0.92) for the training, test and external test datasets, respectively. The test set accuracy was 73% (95% CI: 65-81%) and resulted in 66.67% improvements in potentially missed [8/12] or delayed [6/9] cancers, compared to the radiologist with performance closest to the mean of six readers. CONCLUSIONS: SN-RPV may provide net-benefit in terms of earlier cancer diagnosis.
Asunto(s)
Detección Precoz del Cáncer , Neoplasias Pulmonares , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Estudios Prospectivos , Estudios Retrospectivos , Radiólogos , PulmónRESUMEN
Sulfur-[18F]fluoride exchange radiochemistry is a rapid and convenient method for incorporating fluorine-18 into biologically active molecules. We report a fully automated radiolabelling procedure for the synthesis of a [18F]SO3F-bearing prostate specific membrane antigen (PSMA) targeted ligand ([18F]5) using the GE FASTLab™ cassette-based platform in a 25.0 ± 2.6% radiochemical yield (decay corrected). Uptake in vitro and in vivo correlated with PSMA expression, and the radioligand exhibited favourable biodistribution and pharmacokinetic profiles.
RESUMEN
In recent years, molecularly imprinted polymer nanoparticles (nanoMIPs) have proven to be an attractive alternative to antibodies in diagnostic and therapeutic applications. However, several key questions remain: how suitable are intracellular epitopes as targets for nanoMIP binding? And to what extent can protein function be modulated via targeting specific epitopes? To investigate this, three extracellular and three intracellular epitopes of epidermal growth factor receptor (EGFR) were used as templates for the synthesis of nanoMIPs which were then used to treat cancer cells with different expression levels of EGFR. It was observed that nanoMIPs imprinted with epitopes from the intracellular kinase domain and the extracellular ligand binding domain of EGFR caused cells to form large foci of EGFR sequestered away from the cell surface, caused a reduction in autophosphorylation, and demonstrated effects on cell viability. Collectively, this suggests that intracellular domain-targeting nanoMIPs can be a potential new tool for cancer therapy.
Asunto(s)
Impresión Molecular , Nanopartículas , Polímeros Impresos Molecularmente , Epítopos , Polímeros/química , Nanopartículas/química , Receptores ErbB/metabolismoRESUMEN
Thymidylate synthase (TS) remains a major target for cancer therapy. TS inhibition elicits increases in DNA salvage pathway activity, detected as a transient compensatory "flare" in 3'-deoxy-3'-[18F]fluorothymidine positron emission tomography (18F-FLT PET). We determined the magnitude of the 18F-FLT flare in non-small cell lung cancer (NSCLC) patients treated with the antifolate pemetrexed in relation to clinical outcome. METHOD: Twenty-one patients with advanced/metastatic non-small cell lung cancer (NSCLC) scheduled to receive palliative pemetrexed ± platinum-based chemotherapy underwent 18F-FLT PET at baseline and 4 h after initiating single-agent pemetrexed. Plasma deoxyuridine (dUrd) levels and thymidine kinase 1 (TK1) activity were measured before each scan. Patients were then treated with the combination therapy. The 18F-FLT PET variables were compared to RECIST 1.1 and overall survival (OS). RESULTS: Nineteen patients had evaluable PET scans at both time points. A total of 32% (6/19) of patients showed 18F-FLT flares (>20% change in SUVmax-wsum). At the lesion level, only one patient had an FLT flare in all the lesions above (test-retest borders). The remaining had varied uptake. An 18F-FLT flare occurred in all lesions in 1 patient, while another patient had an 18F-FLT reduction in all lesions; 17 patients showed varied lesion uptake. All patients showed global TS inhibition reflected in plasma dUrd levels (p < 0.001) and 18F-FLT flares of TS-responsive normal tissues including small bowel and bone marrow (p = 0.004 each). Notably, 83% (5/6) of patients who exhibited 18F-FLT flares were also RECIST responders with a median OS of 31 m, unlike patients who did not exhibit 18F-FLT flares (15 m). Baseline plasma TK1 was prognostic of survival but its activity remained unchanged following treatment. CONCLUSIONS: The better radiological response and longer survival observed in patients with an 18F-FLT flare suggest the efficacy of the tracer as an indicator of the early therapeutic response to pemetrexed in NSCLC.
RESUMEN
OBJECTIVES: Accurate contouring of anatomical structures allows for high-precision radiotherapy planning, targeting the dose at treatment volumes and avoiding organs at risk. Manual contouring is time-consuming with significant user variability, whereas auto-segmentation (AS) has proven efficiency benefits but requires editing before treatment planning. This study investigated whether atlas-based AS (ABAS) accuracy improves with template atlas group size and character-specific atlas and test case selection. METHODS AND MATERIALS: One clinician retrospectively contoured the breast, nodes, lung, heart, and brachial plexus on 100 CT scans, adhering to peer-reviewed guidelines. Atlases were clustered in group sizes, treatment positions, chest wall separations, and ASs created with Mirada software. The similarity of ASs compared to reference contours was described by the Jaccard similarity coefficient (JSC) and centroid distance variance (CDV). RESULTS: Across group sizes, for all structures combined, the mean JSC was 0.6 (SD 0.3, p = .999). Across atlas-specific groups, 0.6 (SD 0.3, p = 1.000). The correlation between JSC and structure volume was weak in both scenarios (adjusted R2-0.007 and 0.185).Mean CDV was similar across groups but varied up to 1.2 cm for specific structures. CONCLUSIONS: Character-specific atlas groups and test case selection did not improve accuracy outcomes. High-quality ASs were obtained from groups containing as few as ten atlases, subsequently simplifying the application of ABAS. CDV measures indicating auto-segmentation variations on the x, y, and z axes can be utilised to decide on the clinical relevance of variations and reduce AS editing. ADVANCES IN KNOWLEDGE: High-quality ABASs can be obtained from as few as ten template atlases.Atlas and test case selection do not improve AS accuracy.Unlike well-known quantitative similarity indices, volume displacement metrics provide information on the location of segmentation variations, helping assessment of the clinical relevance of variations and reducing clinician editing. Volume displacement metrics combined with the qualitative measure of clinician assessment could reduce user variability.
Asunto(s)
Mama , Planificación de la Radioterapia Asistida por Computador , Humanos , Corazón , Órganos en Riesgo/diagnóstico por imagen , Planificación de la Radioterapia Asistida por Computador/métodos , Estudios RetrospectivosRESUMEN
C-Met is a receptor tyrosine kinase that is overexpressed in a range of different cancer types, and has been identified as a potential biomarker for cancer imaging and therapy. Previously, a 68Ga-labelled peptide, [68Ga]Ga-EMP-100, has shown promise for imaging c-Met in renal cell carcinoma in humans. Herein, we report the synthesis and preliminary biological evaluation of an [18F]AlF-labelled analogue, [18F]AlF-EMP-105, for c-Met imaging by positron emission tomography. EMP-105 was radiolabelled using the aluminium-[18F]fluoride method with 46 ± 2% RCY and >95% RCP in 35-40 min. In vitro evaluation showed that [18F]AlF-EMP-105 has a high specificity for c-Met-expressing cells. Radioactive metabolite analysis at 5 and 30 min post-injection revealed that [18F]AlF-EMP-105 has good blood stability, but undergoes transformation-transchelation, defluorination or demetallation-in the liver and kidneys. PET imaging in non-tumour-bearing mice showed high radioactive accumulation in the kidneys, bladder and urine, demonstrating that the tracer is cleared predominantly as [18F]fluoride by the renal system. With its high specificity for c-Met expressing cells, [18F]AlF-EMP-105 shows promise as a potential diagnostic tool for imaging cancer.
RESUMEN
PURPOSE: MRI and PET are used in neuro-oncology for the detection and characterisation of lesions for malignancy to target surgical biopsy and to plan surgical resections or stereotactic radiosurgery. The critical role of short-chain fatty acids (SCFAs) in brain tumour biology has come to the forefront. The non-metabolised SCFA radiotracer, [18F]fluoropivalate (FPIA), shows low background signal in most tissues except eliminating organs and has appropriate human dosimetry. Tumour uptake of the radiotracer is, however, unknown. We investigated the uptake characteristics of FPIA in this pilot PET/MRI study. METHODS: Ten adult glioma subjects were identified based on radiological features using standard-of-care MRI prior to any surgical intervention, with subsequent histopathological confirmation of glioma subtype and grade (lower-grade - LGG - and higher-grade - HGG - patients). FPIA was injected as an intravenous bolus injection (range 342-368 MBq), and dynamic PET and MRI data were acquired simultaneously over 66 min. RESULTS: All patients tolerated the PET/MRI protocol. Three patients were reclassified following resection and histology. Tumour maximum standardised uptake value (SUVmax,60) increased in the order LGG (WHO grade 2) < HGG (WHO grade 3) < HGG (WHO grade 4). The net irreversible solute transfer, Ki, and influx rate constant, K1, were significantly higher in HGG (p < 0.05). Of the MRI variables studied, DCE-MRI-derived extravascular-and-extracellular volume fraction (ve) was high in tumours of WHO grade 4 compared with other grades (p < 0.05). SLC25A20 protein expression was higher in HGG compared with LGG. CONCLUSION: Tumoural FPIA PET uptake is higher in HGG compared to LGG. This study supports further investigation of FPIA PET/MRI for brain tumour imaging in a larger patient population. CLINICAL TRIAL REGISTRATION: Clinicaltrials.gov, NCT04097535.
Asunto(s)
Neoplasias Encefálicas , Glioma , Adulto , Humanos , Proyectos Piloto , Estudios Prospectivos , Estudios de Factibilidad , Clasificación del Tumor , Glioma/metabolismo , Tomografía de Emisión de Positrones/métodos , Neoplasias Encefálicas/diagnóstico por imagen , Neoplasias Encefálicas/patología , Imagen por Resonancia Magnética , Proteínas de Transporte de MembranaRESUMEN
OBJECTIVES: Whole-body magnetic resonance imaging (WB-MRI) has been demonstrated to be efficient and cost-effective for cancer staging. The study aim was to develop a machine learning (ML) algorithm to improve radiologists' sensitivity and specificity for metastasis detection and reduce reading times. MATERIALS AND METHODS: A retrospective analysis of 438 prospectively collected WB-MRI scans from multicenter Streamline studies (February 2013-September 2016) was undertaken. Disease sites were manually labeled using Streamline reference standard. Whole-body MRI scans were randomly allocated to training and testing sets. A model for malignant lesion detection was developed based on convolutional neural networks and a 2-stage training strategy. The final algorithm generated lesion probability heat maps. Using a concurrent reader paradigm, 25 radiologists (18 experienced, 7 inexperienced in WB-/MRI) were randomly allocated WB-MRI scans with or without ML support to detect malignant lesions over 2 or 3 reading rounds. Reads were undertaken in the setting of a diagnostic radiology reading room between November 2019 and March 2020. Reading times were recorded by a scribe. Prespecified analysis included sensitivity, specificity, interobserver agreement, and reading time of radiology readers to detect metastases with or without ML support. Reader performance for detection of the primary tumor was also evaluated. RESULTS: Four hundred thirty-three evaluable WB-MRI scans were allocated to algorithm training (245) or radiology testing (50 patients with metastases, from primary 117 colon [n = 117] or lung [n = 71] cancer). Among a total 562 reads by experienced radiologists over 2 reading rounds, per-patient specificity was 86.2% (ML) and 87.7% (non-ML) (-1.5% difference; 95% confidence interval [CI], -6.4%, 3.5%; P = 0.39). Sensitivity was 66.0% (ML) and 70.0% (non-ML) (-4.0% difference; 95% CI, -13.5%, 5.5%; P = 0.344). Among 161 reads by inexperienced readers, per-patient specificity in both groups was 76.3% (0% difference; 95% CI, -15.0%, 15.0%; P = 0.613), with sensitivity of 73.3% (ML) and 60.0% (non-ML) (13.3% difference; 95% CI, -7.9%, 34.5%; P = 0.313). Per-site specificity was high (>90%) for all metastatic sites and experience levels. There was high sensitivity for the detection of primary tumors (lung cancer detection rate of 98.6% with and without ML [0.0% difference; 95% CI, -2.0%, 2.0%; P = 1.00], colon cancer detection rate of 89.0% with and 90.6% without ML [-1.7% difference; 95% CI, -5.6%, 2.2%; P = 0.65]). When combining all reads from rounds 1 and 2, reading times fell by 6.2% (95% CI, -22.8%, 10.0%) when using ML. Round 2 read-times fell by 32% (95% CI, 20.8%, 42.8%) compared with round 1. Within round 2, there was a significant decrease in read-time when using ML support, estimated as 286 seconds (or 11%) quicker ( P = 0.0281), using regression analysis to account for reader experience, read round, and tumor type. Interobserver variance suggests moderate agreement, Cohen κ = 0.64; 95% CI, 0.47, 0.81 (with ML), and Cohen κ = 0.66; 95% CI, 0.47, 0.81 (without ML). CONCLUSIONS: There was no evidence of a significant difference in per-patient sensitivity and specificity for detecting metastases or the primary tumor using concurrent ML compared with standard WB-MRI. Radiology read-times with or without ML support fell for round 2 reads compared with round 1, suggesting that readers familiarized themselves with the study reading method. During the second reading round, there was a significant reduction in reading time when using ML support.
Asunto(s)
Neoplasias del Colon , Neoplasias Pulmonares , Humanos , Imagen por Resonancia Magnética/métodos , Estudios Retrospectivos , Imagen de Cuerpo Entero/métodos , Pulmón , Neoplasias Pulmonares/diagnóstico por imagen , Neoplasias del Colon/diagnóstico por imagen , Sensibilidad y Especificidad , Pruebas Diagnósticas de RutinaRESUMEN
Tertiary lymphoid structure (TLS) is associated with prognosis in copy-number-driven tumors, including high-grade serous ovarian cancer (HGSOC), although the function of TLS and its interaction with copy-number alterations in HGSOC are not fully understood. In the current study, we confirm that TLS-high HGSOC patients show significantly better progression-free survival (PFS). We show that the presence of TLS in HGSOC tumors is associated with B cell maturation and cytotoxic tumor-specific T cell activation and proliferation. In addition, the copy-number loss of IL15 and CXCL10 may limit TLS formation in HGSOC; a list of genes that may dysregulate TLS function is also proposed. Last, a radiomics-based signature is developed to predict the presence of TLS, which independently predicts PFS in both HGSOC patients and immune checkpoint inhibitor (ICI)-treated non-small cell lung cancer (NSCLC) patients. Overall, we reveal that TLS coordinates intratumoral B cell and T cell response to HGSOC tumor, while the cancer genome evolves to counteract TLS formation and function.
Asunto(s)
Carcinoma de Pulmón de Células no Pequeñas , Cistadenocarcinoma Seroso , Neoplasias Pulmonares , Neoplasias Ováricas , Humanos , Femenino , Neoplasias Pulmonares/patología , Pronóstico , Tejido Linfoide , Neoplasias Ováricas/patologíaRESUMEN
Handcrafted and deep learning (DL) radiomics are popular techniques used to develop computed tomography (CT) imaging-based artificial intelligence models for COVID-19 research. However, contrast heterogeneity from real-world datasets may impair model performance. Contrast-homogenous datasets present a potential solution. We developed a 3D patch-based cycle-consistent generative adversarial network (cycle-GAN) to synthesize non-contrast images from contrast CTs, as a data homogenization tool. We used a multi-centre dataset of 2078 scans from 1,650 patients with COVID-19. Few studies have previously evaluated GAN-generated images with handcrafted radiomics, DL and human assessment tasks. We evaluated the performance of our cycle-GAN with these three approaches. In a modified Turing-test, human experts identified synthetic vs acquired images, with a false positive rate of 67% and Fleiss' Kappa 0.06, attesting to the photorealism of the synthetic images. However, on testing performance of machine learning classifiers with radiomic features, performance decreased with use of synthetic images. Marked percentage difference was noted in feature values between pre- and post-GAN non-contrast images. With DL classification, deterioration in performance was observed with synthetic images. Our results show that whilst GANs can produce images sufficient to pass human assessment, caution is advised before GAN-synthesized images are used in medical imaging applications.
Asunto(s)
COVID-19 , Aprendizaje Profundo , Humanos , Inteligencia Artificial , COVID-19/diagnóstico por imagen , Tomografía Computarizada por Rayos X , Aprendizaje AutomáticoRESUMEN
Lung cancer is the leading cause of cancer-related deaths worldwide. It exhibits, at the mesoscopic scale, phenotypic characteristics that are generally indiscernible to the human eye but can be captured non-invasively on medical imaging as radiomic features, which can form a high dimensional data space amenable to machine learning. Radiomic features can be harnessed and used in an artificial intelligence paradigm to risk stratify patients, and predict for histological and molecular findings, and clinical outcome measures, thereby facilitating precision medicine for improving patient care. Compared to tissue sampling-driven approaches, radiomics-based methods are superior for being non-invasive, reproducible, cheaper, and less susceptible to intra-tumoral heterogeneity. This review focuses on the application of radiomics, combined with artificial intelligence, for delivering precision medicine in lung cancer treatment, with discussion centered on pioneering and groundbreaking works, and future research directions in the area.
Asunto(s)
Inteligencia Artificial , Neoplasias Pulmonares , Humanos , Medicina de Precisión/métodos , Neoplasias Pulmonares/diagnóstico por imagen , Neoplasias Pulmonares/genética , Aprendizaje Automático , Diagnóstico por ImagenRESUMEN
PURPOSE: To predict deep myometrial infiltration (DMI), clinical risk category, histological type, and lymphovascular space invasion (LVSI) in women with endometrial cancer using machine learning classification methods based on clinical and image signatures from T2-weighted MR images. METHODS: A training dataset containing 413 patients and an independent testing dataset consisting of 82 cases were employed in this retrospective study. Manual segmentation of the whole tumor volume on sagittal T2-weighted MRI was performed. Clinical and radiomic features were extracted to predict: (i) DMI of endometrial cancer patients, (ii) endometrial cancer clinical high-risk level, (iii) histological subtype of tumor, and (iv) presence of LVSI. A classification model with different automatically selected hyperparameter values was created. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve, F1 score, average recall, and average precision were calculated to evaluate different models. RESULTS: Based on the independent external testing dataset, the AUCs for DMI, high-risk endometrial cancer, endometrial histological type, and LVSI classification were 0.79, 0.82, 0.91, and 0.85, respectively. The corresponding 95% confidence intervals (CI) of the AUCs were [0.69, 0.89], [0.75, 0.91], [0.83, 0.97], and [0.77, 0.93], respectively. CONCLUSION: It is possible to classify endometrial cancer DMI, risk, histology type, and LVSI using different machine learning methods.
RESUMEN
INTRODUCTION: Patient selection for checkpoint inhibitor immunotherapy is currently guided by programmed death-ligand 1 (PD-L1) expression obtained from immunohistochemical staining of tumor tissue samples. This approach is susceptible to limitations resulting from the dynamic and heterogeneous nature of cancer cells and the invasiveness of the tissue sampling procedure. To address these challenges, we developed a novel computed tomography (CT) radiomic-based signature for predicting disease response in patients with NSCLC undergoing programmed cell death protein 1 (PD-1) or PD-L1 checkpoint inhibitor immunotherapy. METHODS: This retrospective study comprises a total of 194 patients with suitable CT scans out of 340. Using the radiomic features computed from segmented tumors on a discovery set of 85 contrast-enhanced chest CTs of patients diagnosed with having NSCLC and their CD274 count, RNA expression of the protein-encoding gene for PD-L1, as the response vector, we developed a composite radiomic signature, lung cancer immunotherapy-radiomics prediction vector (LCI-RPV). This was validated in two independent testing cohorts of 66 and 43 patients with NSCLC treated with PD-1 or PD-L1 inhibition immunotherapy, respectively. RESULTS: LCI-RPV predicted PD-L1 positivity in both NSCLC testing cohorts (area under the curve [AUC] = 0.70, 95% confidence interval [CI]: 0.57-0.84 and AUC = 0.70, 95% CI: 0.46-0.94). In one cohort, it also demonstrated good prediction of cases with high PD-L1 expression exceeding key treatment thresholds (>50%: AUC = 0.72, 95% CI: 0.59-0.85 and >90%: AUC = 0.66, 95% CI: 0.45-0.88), the tumor's objective response to treatment at 3 months (AUC = 0.68, 95% CI: 0.52-0.85), and pneumonitis occurrence (AUC = 0.64, 95% CI: 0.48-0.80). LCI-RPV achieved statistically significant stratification of the patients into a high- and low-risk survival group (hazard ratio = 2.26, 95% CI: 1.21-4.24, p = 0.011 and hazard ratio = 2.45, 95% CI: 1.07-5.65, p = 0.035). CONCLUSIONS: A CT radiomics-based signature developed from response vector CD274 can aid in evaluating patients' suitability for PD-1 or PD-L1 checkpoint inhibitor immunotherapy in NSCLC.
Asunto(s)
Carcinoma de Pulmón de Células no Pequeñas , Neoplasias Pulmonares , Humanos , Neoplasias Pulmonares/tratamiento farmacológico , Neoplasias Pulmonares/genética , Antígeno B7-H1/genética , Antígeno B7-H1/metabolismo , Receptor de Muerte Celular Programada 1/metabolismo , Estudios Retrospectivos , Proteínas Reguladoras de la Apoptosis , Ligandos , Carcinoma de Pulmón de Células no Pequeñas/tratamiento farmacológico , Carcinoma de Pulmón de Células no Pequeñas/genética , Carcinoma de Pulmón de Células no Pequeñas/metabolismo , Biomarcadores , Inmunoterapia/métodosRESUMEN
High-grade serous ovarian carcinoma is a unique cancer characterised by universal TP53 mutations and widespread copy number alterations. These copy number alterations include deletion of tumour suppressors and amplification of driver oncogenes. Given their key oncogenic roles, amplified driver genes are often proposed as therapeutic targets. For example, development of anti-HER2 agents has been clinically successful in treatment of ERBB2-amplified tumours. A wide scope of preclinical work has since investigated numerous amplified genes as potential therapeutic targets in high-grade serous ovarian carcinoma. However, variable experimental procedures (e.g., choice of cell lines), ambiguous phenotypes or lack of validation hinders further clinical translation of many targets. In this review, we collate the genes proposed to be amplified therapeutic targets in high-grade serous ovarian carcinoma, and quantitatively appraise the evidence in support of each candidate gene. Forty-four genes are found to have evidence as amplified therapeutic targets; the five highest scoring genes are CCNE1, PAX8, URI1, PRKCI and FAL1. This review generates an up-to-date list of amplified therapeutic target candidates for further development and proposes comprehensive criteria to assist amplified therapeutic target discovery in the future.
Asunto(s)
Neoplasias Ováricas , Humanos , Femenino , Neoplasias Ováricas/tratamiento farmacológico , Neoplasias Ováricas/genética , Mutación , Oncogenes/genéticaRESUMEN
A quintessential setting for precision medicine, theranostics refers to a rapidly evolving field of medicine in which disease is diagnosed followed by treatment of disease-positive patients using tools for the therapy identical or similar to those used for the diagnosis. Against the backdrop of only-treat-when-visualized, the goal is a high therapeutic index with efficacy markedly surpassing toxicity. Oncology leads the way in theranostics innovation, where the approach has become possible with the identification of unique proteins and other factors selectively expressed in cancer versus healthy tissue, advances in imaging technology able to report these tissue factors, and major understanding of targeting chemicals and nanodevices together with methods to attach labels or warheads for imaging and therapy. Radiotheranostics-using radiopharmaceuticals-is becoming routine in patients with prostate cancer and neuroendocrine tumors who express the proteins PSMA (prostate-specific membrane antigen) and SSTR2 (somatostatin receptor 2), respectively, on their cancer. The palpable excitement in the field stems from the finding that a proportion of patients with large metastatic burden show complete and partial responses, and this outcome is catalyzing the search for more radiotheranostics approaches. Not every patient will benefit from radiotheranostics; but, for those who cross the target-detected line, the likelihood of response is very high.