Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 43
Filtrar
1.
Eur Radiol ; 33(11): 7618-7628, 2023 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-37338558

RESUMO

OBJECTIVES: To measure the performance and variability of a radiomics-based model for the prediction of microvascular invasion (MVI) and survival in patients with resected hepatocellular carcinoma (HCC), simulating its sequential development and application. METHODS: This study included 230 patients with 242 surgically resected HCCs who underwent preoperative CT, of which 73/230 (31.7%) were scanned in external centres. The study cohort was split into training set (158 patients, 165 HCCs) and held-out test set (72 patients, 77 HCCs), stratified by random partitioning, which was repeated 100 times, and by a temporal partitioning to simulate the sequential development and clinical use of the radiomics model. A machine learning model for the prediction of MVI was developed with least absolute shrinkage and selection operator (LASSO). The concordance index (C-index) was used to assess the value to predict the recurrence-free (RFS) and overall survivals (OS). RESULTS: In the 100-repetition random partitioning cohorts, the radiomics model demonstrated a mean AUC of 0.54 (range 0.44-0.68) for the prediction of MVI, mean C-index of 0.59 (range 0.44-0.73) for RFS, and 0.65 (range 0.46-0.86) for OS in the held-out test set. In the temporal partitioning cohort, the radiomics model yielded an AUC of 0.50 for the prediction of MVI, a C-index of 0.61 for RFS, and 0.61 for OS, in the held-out test set. CONCLUSIONS: The radiomics models had a poor performance for the prediction of MVI with a large variability in the model performance depending on the random partitioning. Radiomics models demonstrated good performance in the prediction of patient outcomes. CLINICAL RELEVANCE STATEMENT: Patient selection within the training set strongly influenced the performance of the radiomics models for predicting microvascular invasion; therefore, a random approach to partitioning a retrospective cohort into a training set and a held-out set seems inappropriate. KEY POINTS: • The performance of the radiomics models for the prediction of microvascular invasion and survival widely ranged (AUC range 0.44-0.68) in the randomly partitioned cohorts. • The radiomics model for the prediction of microvascular invasion was unsatisfying when trying to simulate its sequential development and clinical use in a temporal partitioned cohort imaged with a variety of CT scanners. • The performance of the radiomics models for the prediction of survival was good with similar performances in the 100-repetition random partitioning and temporal partitioning cohorts.


Assuntos
Carcinoma Hepatocelular , Neoplasias Hepáticas , Humanos , Carcinoma Hepatocelular/patologia , Neoplasias Hepáticas/patologia , Estudos Retrospectivos , Invasividade Neoplásica , Tomografia Computadorizada por Raios X/métodos
2.
Respirology ; 27(10): 818-833, 2022 10.
Artigo em Inglês | MEDLINE | ID: mdl-35965430

RESUMO

In recent years, pulmonary imaging has seen enormous progress, with the introduction, validation and implementation of new hardware and software. There is a general trend from mere visual evaluation of radiological images to quantification of abnormalities and biomarkers, and assessment of 'non visual' markers that contribute to establishing diagnosis or prognosis. Important catalysts to these developments in thoracic imaging include new indications (like computed tomography [CT] lung cancer screening) and the COVID-19 pandemic. This review focuses on developments in CT, radiomics, artificial intelligence (AI) and x-ray velocimetry for imaging of the lungs. Recent developments in CT include the potential for ultra-low-dose CT imaging for lung nodules, and the advent of a new generation of CT systems based on photon-counting detector technology. Radiomics has demonstrated potential towards predictive and prognostic tasks particularly in lung cancer, previously not achievable by visual inspection by radiologists, exploiting high dimensional patterns (mostly texture related) on medical imaging data. Deep learning technology has revolutionized the field of AI and as a result, performance of AI algorithms is approaching human performance for an increasing number of specific tasks. X-ray velocimetry integrates x-ray (fluoroscopic) imaging with unique image processing to produce quantitative four dimensional measurement of lung tissue motion, and accurate calculations of lung ventilation.


Assuntos
COVID-19 , Neoplasias Pulmonares , Inteligência Artificial , COVID-19/diagnóstico por imagem , Detecção Precoce de Câncer/métodos , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Pandemias , Reologia , Tomografia Computadorizada por Raios X/métodos , Raios X
3.
Eur Radiol ; 26(2): 390-7, 2016 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-26065396

RESUMO

PURPOSE: Single-slice magnetization transfer (MT) imaging has shown promising results for evaluating post-radiation fibrosis. The study aim was to evaluate the value of multislice MT imaging to assess tumour response after chemoradiotherapy by comparing magnetization transfer ratios (MTR) with histopathological tumour regression grade (TRG). MATERIALS AND METHODS: Thirty patients with locally advanced rectal cancer (cT3-4 and/or cN2) underwent routine restaging MRI 8 weeks post-chemoradiotherapy, including multislice MT-sequence, covering the entire tumour bed. Two independent readers delineated regions of interest on MTR maps, covering all potential remaining tumour and fibrotic areas. Mean MTR and histogram parameters (minimum, maximum, median, standard deviation, skewness, kurtosis, and 5-30-70-95th percentiles) were calculated. Reference standard was histological TRG1-2 (good response) and TRG3-5 (poor response). RESULTS: 24/30 patients were male; mean age was 67.7 ± 10.8 years. Mean MTR rendered AUCs of 0.65 (reader1) and 0.87 (reader2) to differentiate between TRG1-2 versus TRG3-5. Best results were obtained for 95(th) percentile (AUC 0.75- 0.88). Interobserver agreement was moderate (ICC 0.50) for mean MTR and good (ICC 0.80) for 95(th) percentile. CONCLUSIONS: MT imaging is a promising tool to assess tumour response post-chemoradiotherapy in rectal cancer. Particularly, 95(th) percentile results in AUCs up to 0.88 to discriminate a good tumour response. KEY POINTS: • The mean MTR can differentiate between good and poor responders after chemoradiation. • In addition to measurement of the mean value, histogram analyses can be beneficial. • The histogram parameter 95 (th) percentile can reach AUCs of 0.75-0.88.


Assuntos
Quimiorradioterapia/efeitos adversos , Imageamento por Ressonância Magnética/métodos , Pneumonite por Radiação/patologia , Neoplasias Retais/patologia , Neoplasias Retais/terapia , Idoso , Feminino , Humanos , Masculino , Reprodutibilidade dos Testes , Estudos Retrospectivos
4.
Neuroradiology ; 58(12): 1197-1208, 2016 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-27796446

RESUMO

INTRODUCTION: The prognostic value of the dynamic contrast-enhanced (DCE) MRI perfusion and its histogram analysis-derived metrics is not well established for high-grade glioma (HGG) patients. The aim of this prospective study was to investigate DCE perfusion transfer coefficient (Ktrans), vascular plasma volume fraction (vp), extracellular volume fraction (ve), reverse transfer constant (kep), and initial area under gadolinium concentration time curve (IAUGC) as predictors of progression-free (PFS) and overall survival (OS) in HGG patients. METHODS: Sixty-nine patients with suspected anaplastic astrocytoma or glioblastoma underwent preoperative DCE-MRI scans. DCE perfusion whole tumor region histogram parameters, clinical details, and PFS and OS data were obtained. Univariate, multivariate, and Kaplan-Meier survival analyses were conducted. Receiver operating characteristic (ROC) curve analysis was employed to identify perfusion parameters with the best differentiation performance. RESULTS: On univariate analysis, ve and skewness of vp had significant negative impacts, while kep had significant positive impact on OS (P < 0.05). ve was also a negative predictor of PFS (P < 0.05). Patients with lower ve and IAUGC had longer median PFS and OS on Kaplan-Meier analysis (P < 0.05). Ktrans and ve could also differentiate grade III from IV gliomas (area under the curve 0.819 and 0.791, respectively). CONCLUSIONS: High ve is a consistent predictor of worse PFS and OS in HGG glioma patients. vp skewness and kep are also predictive for OS. Ktrans and ve demonstrated the best diagnostic performance for differentiating grade III from IV gliomas.


Assuntos
Neoplasias Encefálicas/mortalidade , Neoplasias Encefálicas/patologia , Glioma/mortalidade , Glioma/patologia , Angiografia por Ressonância Magnética/métodos , Adulto , Neoplasias Encefálicas/diagnóstico por imagem , Meios de Contraste , Feminino , Glioma/diagnóstico por imagem , Humanos , Aumento da Imagem/métodos , Masculino , Pessoa de Meia-Idade , Modelos Biológicos , Gradação de Tumores , Cuidados Pré-Operatórios/métodos , Cuidados Pré-Operatórios/estatística & dados numéricos , Prevalência , Prognóstico , Reprodutibilidade dos Testes , Medição de Risco/métodos , Sensibilidade e Especificidade , Taxa de Sobrevida , Resultado do Tratamento
5.
Cancer Imaging ; 24(1): 24, 2024 Feb 08.
Artigo em Inglês | MEDLINE | ID: mdl-38331808

RESUMO

BACKGROUND: To build machine learning predictive models for surgical risk assessment of extracapsular extension (ECE) in patients with prostate cancer (PCa) before radical prostatectomy; and to compare the use of decision curve analysis (DCA) and receiver operating characteristic (ROC) metrics for selecting input feature combinations in models. METHODS: This retrospective observational study included two independent data sets: 139 participants from a single institution (training), and 55 from 15 other institutions (external validation), both treated with Robotic Assisted Radical Prostatectomy (RARP). Five ML models, based on different combinations of clinical, semantic (interpreted by a radiologist) and radiomics features computed from T2W-MRI images, were built to predict extracapsular extension in the prostatectomy specimen (pECE+). DCA plots were used to rank the models' net benefit when assigning patients to prostatectomy with non-nerve-sparing surgery (NNSS) or nerve-sparing surgery (NSS), depending on the predicted ECE status. DCA model rankings were compared with those drived from ROC area under the curve (AUC). RESULTS: In the training data, the model using clinical, semantic, and radiomics features gave the highest net benefit values across relevant threshold probabilities, and similar decision curve was observed in the external validation data. The model ranking using the AUC was different in the discovery group and favoured the model using clinical + semantic features only. CONCLUSIONS: The combined model based on clinical, semantic and radiomic features may be used to predict pECE + in patients with PCa and results in a positive net benefit when used to choose between prostatectomy with NNS or NNSS.


Assuntos
Extensão Extranodal , Neoplasias da Próstata , Masculino , Humanos , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/cirurgia , Prostatectomia/métodos , Estudos Retrospectivos , Aprendizado de Máquina
6.
J Imaging Inform Med ; 37(1): 31-44, 2024 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-38343254

RESUMO

Radiogenomics has shown potential to predict genomic phenotypes from medical images. The development of models using standard-of-care pre-operative MRI images, as opposed to advanced MRI images, enables a broader reach of such models. In this work, a radiogenomics model for IDH mutation status prediction from standard-of-care MRIs in patients with glioma was developed and validated using multicentric data. A cohort of 142 (wild-type: 32.4%) patients with glioma retrieved from the TCIA/TCGA was used to train a logistic regression model to predict the IDH mutation status. The model was evaluated using retrospective data collected in two distinct hospitals, comprising 36 (wild-type: 63.9%) and 53 (wild-type: 75.5%) patients. Model development utilized ROC analysis. Model discrimination and calibration were used for validation. The model yielded an AUC of 0.741 vs. 0.716 vs. 0.938, a sensitivity of 0.784 vs. 0.739 vs. 0.875, and a specificity of 0.657 vs. 0.692 vs. 1.000 on the training, test cohort 1, and test cohort 2, respectively. The assessment of model fairness suggested an unbiased model for age and sex, and calibration tests showed a p < 0.05. These results indicate that the developed model allows the prediction of the IDH mutation status in gliomas using standard-of-care MRI images and does not appear to hold sex and age biases.

7.
Insights Imaging ; 15(1): 217, 2024 Aug 26.
Artigo em Inglês | MEDLINE | ID: mdl-39186182

RESUMO

The objective of this review is to survey radiomics signatures for detecting pathological extracapsular extension (pECE) on magnetic resonance imaging (MRI) in patients with prostate cancer (PCa) who underwent prostatectomy. Scientific Literature databases were used to search studies published from January 2007 to October 2023. All studies related to PCa MRI staging and using radiomics signatures to detect pECE after prostatectomy were included. Systematic review was performed according to Preferred Reporting Items for Systematic Review and Meta-analyses (PRISMA). The risk of bias and certainty of the evidence was assessed using QUADAS-2 and the radiomics quality score. From 1247 article titles screened, 16 reports were assessed for eligibility, and 11 studies were included in this systematic review. All used a retrospective study design and most of them used 3 T MRI. Only two studies were performed in more than one institution. The highest AUC of a model using only radiomics features was 0.85, for the test validation. The AUC for best model performance (radiomics associated with clinical/semantic features) varied from 0.72-0.92 and 0.69-0.89 for the training and validation group, respectively. Combined models performed better than radiomics signatures alone for detecting ECE. Most of the studies showed a low to medium risk of bias. After thorough analysis, we found no strong evidence supporting the clinical use of radiomics signatures for identifying extracapsular extension (ECE) in pre-surgery PCa patients. Future studies should adopt prospective multicentre approaches using large public datasets and combined models for detecting ECE. CRITICAL RELEVANT STATEMENT: The use of radiomics algorithms, with clinical and AI integration, in predicting extracapsular extension, could lead to the development of more accurate predictive models, which could help improve surgical planning and lead to better outcomes for prostate cancer patients. PROTOCOL OF SYSTEMATIC REVIEW REGISTRATION: PROSPERO CRD42021272088. Published: https://doi.org/10.1136/bmjopen-2021-052342 . KEY POINTS: Radiomics can extract diagnostic features from MRI to enhance prostate cancer diagnosis performance. The combined models performed better than radiomics signatures alone for detecting extracapsular extension. Radiomics are not yet reliable for extracapsular detection in PCa patients.

8.
JCO Clin Cancer Inform ; 8: e2300180, 2024 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-39292984

RESUMO

PURPOSE: Emerging evidence suggests that the use of artificial intelligence can assist in the timely detection and optimization of therapeutic approach in patients with prostate cancer. The conventional perspective on radiomics encompassing segmentation and the extraction of radiomic features considers it as an independent and sequential process. However, it is not necessary to adhere to this viewpoint. In this study, we show that besides generating masks from which radiomic features can be extracted, prostate segmentation and reconstruction models provide valuable information in their feature space, which can improve the quality of radiomic signatures models for disease aggressiveness classification. MATERIALS AND METHODS: We perform 2,244 experiments with deep learning features extracted from 13 different models trained using different anatomic zones and characterize how modeling decisions, such as deep feature aggregation and dimensionality reduction, affect performance. RESULTS: While models using deep features from full gland and radiomic features consistently lead to improved disease aggressiveness prediction performance, others are detrimental. Our results suggest that the use of deep features can be beneficial, but an appropriate and comprehensive assessment is necessary to ensure that their inclusion does not harm predictive performance. CONCLUSION: The study findings reveal that incorporating deep features derived from autoencoder models trained to reconstruct the full prostate gland (both zonal models show worse performance than radiomics only models), combined with radiomic features, often lead to a statistically significant increase in model performance for disease aggressiveness classification. Additionally, the results also demonstrate that the choice of feature selection is key to achieving good performance, with principal component analysis (PCA) and PCA + relief being the best approaches and that there is no clear difference between the three proposed latent representation extraction techniques.


Assuntos
Aprendizado Profundo , Neoplasias da Próstata , Humanos , Masculino , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/patologia , Processamento de Imagem Assistida por Computador/métodos , Algoritmos , Prognóstico , Interpretação de Imagem Assistida por Computador/métodos , Radiômica
9.
Comput Biol Med ; 171: 108216, 2024 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-38442555

RESUMO

Despite being one of the most prevalent forms of cancer, prostate cancer (PCa) shows a significantly high survival rate, provided there is timely detection and treatment. Computational methods can help make this detection process considerably faster and more robust. However, some modern machine-learning approaches require accurate segmentation of the prostate gland and the index lesion. Since performing manual segmentations is a very time-consuming task, and highly prone to inter-observer variability, there is a need to develop robust semi-automatic segmentation models. In this work, we leverage the large and highly diverse ProstateNet dataset, which includes 638 whole gland and 461 lesion segmentation masks, from 3 different scanner manufacturers provided by 14 institutions, in addition to other 3 independent public datasets, to train accurate and robust segmentation models for the whole prostate gland, zones and lesions. We show that models trained on large amounts of diverse data are better at generalizing to data from other institutions and obtained with other manufacturers, outperforming models trained on single-institution single-manufacturer datasets in all segmentation tasks. Furthermore, we show that lesion segmentation models trained on ProstateNet can be reliably used as lesion detection models.


Assuntos
Próstata , Neoplasias da Próstata , Masculino , Humanos , Próstata/diagnóstico por imagem , Imageamento Tridimensional/métodos , Estudos Retrospectivos , Algoritmos , Neoplasias da Próstata/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos
10.
Cancers (Basel) ; 15(5)2023 Feb 25.
Artigo em Inglês | MEDLINE | ID: mdl-36900261

RESUMO

Prostate cancer is one of the most common forms of cancer globally, affecting roughly one in every eight men according to the American Cancer Society. Although the survival rate for prostate cancer is significantly high given the very high incidence rate, there is an urgent need to improve and develop new clinical aid systems to help detect and treat prostate cancer in a timely manner. In this retrospective study, our contributions are twofold: First, we perform a comparative unified study of different commonly used segmentation models for prostate gland and zone (peripheral and transition) segmentation. Second, we present and evaluate an additional research question regarding the effectiveness of using an object detector as a pre-processing step to aid in the segmentation process. We perform a thorough evaluation of the deep learning models on two public datasets, where one is used for cross-validation and the other as an external test set. Overall, the results reveal that the choice of model is relatively inconsequential, as the majority produce non-significantly different scores, apart from nnU-Net which consistently outperforms others, and that the models trained on data cropped by the object detector often generalize better, despite performing worse during cross-validation.

11.
Diagnostics (Basel) ; 13(4)2023 Feb 15.
Artigo em Inglês | MEDLINE | ID: mdl-36832225

RESUMO

Radiotranscriptomics is an emerging field that aims to investigate the relationships between the radiomic features extracted from medical images and gene expression profiles that contribute in the diagnosis, treatment planning, and prognosis of cancer. This study proposes a methodological framework for the investigation of these associations with application on non-small-cell lung cancer (NSCLC). Six publicly available NSCLC datasets with transcriptomics data were used to derive and validate a transcriptomic signature for its ability to differentiate between cancer and non-malignant lung tissue. A publicly available dataset of 24 NSCLC-diagnosed patients, with both transcriptomic and imaging data, was used for the joint radiotranscriptomic analysis. For each patient, 749 Computed Tomography (CT) radiomic features were extracted and the corresponding transcriptomics data were provided through DNA microarrays. The radiomic features were clustered using the iterative K-means algorithm resulting in 77 homogeneous clusters, represented by meta-radiomic features. The most significant differentially expressed genes (DEGs) were selected by performing Significance Analysis of Microarrays (SAM) and 2-fold change. The interactions among the CT imaging features and the selected DEGs were investigated using SAM and a Spearman rank correlation test with a False Discovery Rate (FDR) of 5%, leading to the extraction of 73 DEGs significantly correlated with radiomic features. These genes were used to produce predictive models of the meta-radiomics features, defined as p-metaomics features, by performing Lasso regression. Of the 77 meta-radiomic features, 51 can be modeled in terms of the transcriptomic signature. These significant radiotranscriptomics relationships form a reliable basis to biologically justify the radiomics features extracted from anatomic imaging modalities. Thus, the biological value of these radiomic features was justified via enrichment analysis on their transcriptomics-based regression models, revealing closely associated biological processes and pathways. Overall, the proposed methodological framework provides joint radiotranscriptomics markers and models to support the connection and complementarities between the transcriptome and the phenotype in cancer, as demonstrated in the case of NSCLC.

12.
Sci Rep ; 13(1): 6206, 2023 04 17.
Artigo em Inglês | MEDLINE | ID: mdl-37069257

RESUMO

There is a growing piece of evidence that artificial intelligence may be helpful in the entire prostate cancer disease continuum. However, building machine learning algorithms robust to inter- and intra-radiologist segmentation variability is still a challenge. With this goal in mind, several model training approaches were compared: removing unstable features according to the intraclass correlation coefficient (ICC); training independently with features extracted from each radiologist's mask; training with the feature average between both radiologists; extracting radiomic features from the intersection or union of masks; and creating a heterogeneous dataset by randomly selecting one of the radiologists' masks for each patient. The classifier trained with this last resampled dataset presented with the lowest generalization error, suggesting that training with heterogeneous data leads to the development of the most robust classifiers. On the contrary, removing features with low ICC resulted in the highest generalization error. The selected radiomics dataset, with the randomly chosen radiologists, was concatenated with deep features extracted from neural networks trained to segment the whole prostate. This new hybrid dataset was then used to train a classifier. The results revealed that, even though the hybrid classifier was less overfitted than the one trained with deep features, it still was unable to outperform the radiomics model.


Assuntos
Inteligência Artificial , Neoplasias da Próstata , Masculino , Humanos , Aprendizado de Máquina , Neoplasias da Próstata/diagnóstico por imagem , Algoritmos
13.
BMJ Open ; 12(5): e052342, 2022 05 06.
Artigo em Inglês | MEDLINE | ID: mdl-35523484

RESUMO

INTRODUCTION: In patients with prostate cancer (PCa), the detection of extracapsular extension (ECE) and seminal vesicle invasion is not only important for selecting the appropriate therapy but also for preoperative planning and patient prognosis. It is of paramount importance to stage PCa correctly before surgery, in order to achieve better surgical and outcome results. Over the last years, MRI has been incorporated in the classical prostate staging nomograms with clinical improvement accuracy in detecting ECE, but with variability between studies and radiologist's experience. METHODS AND ANALYSIS: The research question, based on patient, index test, comparator, outcome and study design criteria, was the following: what is the diagnostic performance of artificial intelligence algorithms for predicting ECE in PCa patients, when compared with that of histopathological results after radical prostatectomy. To answer this question, we will use databases (EMBASE, PUBMED, Web of Science and CENTRAL) to search for the different studies published in the literature and we use the QUADA tool to evaluate the quality of the research selection. ETHICS AND DISSEMINATION: This systematic review does not require ethical approval. The results will be disseminated through publication in a peer-review journal, as a chapter of a doctoral thesis and through presentations at national and international conferences. PROSPERO REGISTRATION NUMBER: CRD42020215671.


Assuntos
Extensão Extranodal , Neoplasias da Próstata , Inteligência Artificial , Humanos , Aprendizado de Máquina , Imageamento por Ressonância Magnética/métodos , Masculino , Invasividade Neoplásica/patologia , Estadiamento de Neoplasias , Prostatectomia/métodos , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/cirurgia , Estudos Retrospectivos , Revisões Sistemáticas como Assunto
14.
Commun Med (Lond) ; 2: 133, 2022.
Artigo em Inglês | MEDLINE | ID: mdl-36310650

RESUMO

An increasing array of tools is being developed using artificial intelligence (AI) and machine learning (ML) for cancer imaging. The development of an optimal tool requires multidisciplinary engagement to ensure that the appropriate use case is met, as well as to undertake robust development and testing prior to its adoption into healthcare systems. This multidisciplinary review highlights key developments in the field. We discuss the challenges and opportunities of AI and ML in cancer imaging; considerations for the development of algorithms into tools that can be widely used and disseminated; and the development of the ecosystem needed to promote growth of AI and ML in cancer imaging.

15.
Updates Surg ; 74(1): 235-243, 2022 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-34596836

RESUMO

Clinically relevant postoperative pancreatic fistula (CR-POPF) is a life-threatening complication following pancreaticoduodenectomy (PD). Individualized preoperative risk assessment could improve clinical management and prevent or mitigate adverse outcomes. The aim of this study is to develop a machine learning risk model to predict occurrence of CR-POPF after PD from preoperative computed tomography (CT) scans. A total of 100 preoperative high-quality CT scans of consecutive patients who underwent pancreaticoduodenectomy in our institution between 2011 and 2019 were analyzed. Radiomic and morphological features extracted from CT scans related to pancreatic anatomy and patient characteristics were included as variables. These data were then assessed by a machine learning classifier to assess the risk of developing CR-POPF. Among the 100 patients evaluated, 20 had CR-POPF. The predictive model based on logistic regression demonstrated specificity of 0.824 (0.133) and sensitivity of 0.571 (0.337), with an AUC of 0.807 (0.155), PPV of 0.468 (0.310) and NPV of 0.890 (0.084). The performance of the model minimally decreased utilizing a random forest approach, with specificity of 0.914 (0.106), sensitivity of 0.424 (0.346), AUC of 0.749 (0.209), PPV of 0.502 (0.414) and NPV of 0.869 (0.076). Interestingly, using the same data, the model was also able to predict postoperative overall complications and a postoperative length of stay over the median with AUCs of 0.690 (0.209) and 0.709 (0.160), respectively. These findings suggest that preoperative CT scans evaluated by machine learning may provide a novel set of information to help clinicians choose a tailored therapeutic pathway in patients candidated to pancreatoduodenectomy.


Assuntos
Fístula Pancreática , Pancreaticoduodenectomia , Humanos , Aprendizado de Máquina , Fístula Pancreática/diagnóstico por imagem , Fístula Pancreática/etiologia , Pancreaticoduodenectomia/efeitos adversos , Complicações Pós-Operatórias/diagnóstico por imagem , Curva ROC , Estudos Retrospectivos , Fatores de Risco , Tomografia Computadorizada por Raios X
16.
PLoS One ; 16(11): e0260609, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-34843603

RESUMO

Cell counting is a frequent task in medical research studies. However, it is often performed manually; thus, it is time-consuming and prone to human error. Even so, cell counting automation can be challenging to achieve, especially when dealing with crowded scenes and overlapping cells, assuming different shapes and sizes. In this paper, we introduce a deep learning-based cell detection and quantification methodology to automate the cell counting process in the zebrafish xenograft cancer model, an innovative technique for studying tumor biology and for personalizing medicine. First, we implemented a fine-tuned architecture based on the Faster R-CNN using the Inception ResNet V2 feature extractor. Second, we performed several adjustments to optimize the process, paying attention to constraints such as the presence of overlapped cells, the high number of objects to detect, the heterogeneity of the cells' size and shape, and the small size of the data set. This method resulted in a median error of approximately 1% of the total number of cell units. These results demonstrate the potential of our novel approach for quantifying cells in poorly labeled images. Compared to traditional Faster R-CNN, our method improved the average precision from 71% to 85% on the studied data set.


Assuntos
Contagem de Células/métodos , Aprendizado Profundo , Processamento de Imagem Assistida por Computador/métodos , Neoplasias Experimentais/diagnóstico , Animais , Xenoenxertos , Humanos , Transplante de Neoplasias , Neoplasias/diagnóstico , Neoplasias/patologia , Neoplasias Experimentais/patologia , Peixe-Zebra
17.
Cancers (Basel) ; 13(23)2021 Dec 01.
Artigo em Inglês | MEDLINE | ID: mdl-34885175

RESUMO

Prostate cancer is one of the most prevalent cancers in the male population. Its diagnosis and classification rely on unspecific measures such as PSA levels and DRE, followed by biopsy, where an aggressiveness level is assigned in the form of Gleason Score. Efforts have been made in the past to use radiomics coupled with machine learning to predict prostate cancer aggressiveness from clinical images, showing promising results. Thus, the main goal of this work was to develop supervised machine learning models exploiting radiomic features extracted from bpMRI examinations, to predict biological aggressiveness; 288 classifiers were developed, corresponding to different combinations of pipeline aspects, namely, type of input data, sampling strategy, feature selection method and machine learning algorithm. On a cohort of 281 lesions from 183 patients, it was found that (1) radiomic features extracted from the lesion volume of interest were less stable to segmentation than the equivalent extraction from the whole gland volume of interest; and (2) radiomic features extracted from the whole gland volume of interest produced higher performance and less overfitted classifiers than radiomic features extracted from the lesions volumes of interest. This result suggests that the areas surrounding the tumour lesions offer relevant information regarding the Gleason Score that is ultimately attributed to that lesion.

18.
Breast ; 56: 14-17, 2021 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-33548617

RESUMO

INTRODUCTION: Innovations in 3D spatial technology and augmented reality imaging driven by digital high-tech industrial science have accelerated experimental advances in breast cancer imaging and the development of medical procedures aimed to reduce invasiveness. PRESENTATION OF CASE: A 57-year-old post-menopausal woman presented with screen-detected left-sided breast cancer. After undergoing all staging and pre-operative studies the patient was proposed for conservative breast surgery with tumor localization. During surgery, an experimental digital and non-invasive intra-operative localization method with augmented reality was compared with the standard pre-operative localization with carbon tattooing (institutional protocol). The breast surgeon wearing an augmented reality headset (Hololens) was able to visualize the tumor location projection inside the patient's left breast in the usual supine position. DISCUSSION: This work describes, to our knowledge, the first experimental test with a digital non-invasive method for intra-operative breast cancer localization using augmented reality to guide breast conservative surgery. In this case, a successful overlap of the previous standard pre-operative marks with carbon tattooing and tumor visualization inside the patient's breast with augmented reality was obtained. CONCLUSION: Breast cancer conservative guided surgery with augmented reality can pave the way for a digital non-invasive method for intra-operative tumor localization.


Assuntos
Realidade Aumentada , Neoplasias da Mama/cirurgia , Imageamento Tridimensional , Mamoplastia , Cirurgia Assistida por Computador/métodos , Neoplasias da Mama/diagnóstico por imagem , Feminino , Humanos , Imageamento por Ressonância Magnética , Pessoa de Meia-Idade
19.
GE Port J Gastroenterol ; 26(4): 260-267, 2019 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-31328140

RESUMO

BACKGROUND: Sorafenib is the currently recommended therapy in patients with advanced hepatocellular carcinoma (HCC). Among the several biomarkers available for the evaluation of the therapeutic response and prognosis, there is perfusion magnetic resonance imaging (p-MRI) that, through measurement of the vascular permeability unit (ktrans), may retrieve useful information regarding the microvascular properties of focal liver lesions. The aim of this study was to evaluate the impact of sorafenib therapy in patients with advanced HCC using the p-MRI technique. MATERIALS AND METHODS: In this retrospective study, 27 patients with the diagnosis of advanced HCC were included for palliative therapy using sorafenib. MRI of the liver was performed before the beginning of the oral therapy (T0), after 3 (T3), and after 6 months (T6). Dynamic acquisitions of the tumor (n = 50, during the first 2 min after contrast injection) were obtained in the coronal plane and were used to compute the parametric perfusion maps, acquiring the ktrans value using the extended Tofts pharmacokinetic model. RESULTS: The value of ktrans obtained at T0 was significantly different from the value of ktrans obtained at T6 (p = 0.028). There were no significant differences between T0 and T3 (p = 0.115) or a correlation between ktrans at T0 and the size of the lesion (p = 0.376). The ktrans value at T0 in patients with progression-free survival (PFS) > 6 months was not significantly different from the ktrans value in patients with PFS ≤6 months (p = 0.113). The ktrans value at T0 was not significantly different between patients who were previously submitted to chemoembolization and those who were not submitted (p = 0.587). CONCLUSION: In this pilot study, the ktrans value may serve as a biomarker of tumor response to antiangiogenic therapy, but only 6 months after its initiation. Clinical outcomes such as PFS were not predicted before the initiation of treatment.


INTRODUÇÃO: O sorafenib é a terapêutica atualmente recomendada em doentes com carcinoma hepatocelular avançado. Entre os vários biomarcadores disponíveis para a avaliação da resposta terapêutica e do prognóstico, existe a perfusão por Ressonância Magnética na qual, através da unidade de permeabilidade vascular (ktrans), se obtém informação relativa às propriedades microvasculares das lesões tumorais. O objetivo deste estudo foi avaliar o impacto da terapêutica com sorafenib em doentes com carcinoma hepatocelular avançado, através da técnica de perfusão por Ressonância Magnética (p-RM). MATERIAIS E MÉTODOS: Neste estudo observacional retrospetivo, foram incluídos 27 doentes, com diagnóstico de carcinoma hepatocelular avançado com indicação para terapêutica paliativa com sorafenib. Foi realizado estudo de Ressonância Magnética hepática antes do início da terapêutica com sorafenib (T0), aos 3 (T3) e aos 6 meses (T6) após o seu início. As imagens adquiridas no plano coronal (n = 50, durante os primeiros 2 minutos após a injeção de contraste paramagnético) foram utilizadas para fusão dos mapas paramétricos de perfusão, obtendo-se o valor de ktrans, usando o modelo farmacocinético de Tofts. RESULTADOS: O valor de ktrans obtido em T0 foi significativamente diferente do valor de ktrans obtido em T6 (p = 0.028). Não existiram diferenças significativas entre T0 e T3 (p = 0.115) ou correlação entre o valor de ktrans em T0 e a dimensão da lesão (p = 0.376). Associadamente, o valor de ktrans em T0 nos doentes com sobrevivência livre de progressão superior a 6 meses não foi significativamente diferente do valor de ktrans nos doentes com sobrevivência livre de progressão inferior ou igual a 6 meses (p = 0.113). O valor de ktrans em doentes com ou sem tratamento prévio por quimioembolização não mostrou diferença estatisticamente significativa (p = 0.587). CONCLUSÃO: Neste estudo inicial, o valor de ktrans pode servir como biomarcador da perfusão tumoral na resposta à terapêutica anti-angiogénica, 6 meses após o seu início. O seu valor antes do inicio do tratamento não permitiu predizer o desfecho clinico em termos de sobrevivência livre de doença nos pacientes submetidos ou não a prévia quimioembolização.© 2019 Sociedade Portugueasa de Gastrenterologia.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA