RESUMEN
BACKGROUND: This study investigated alternative, non-invasive methods for human papillomavirus (HPV) detection in head and neck cancers (HNCs). We compared two approaches: analyzing computed tomography (CT) scans with a Deep Learning (DL) model and using radiomic features extracted from CT images with machine learning (ML) models. METHODS: Fifty patients with histologically confirmed HNC were included. We first trained a modified ResNet-18 DL model on CT data to predict HPV status. Next, radiomic features were extracted from manually segmented regions of interest near the oropharynx and used to train four ML models (K-Nearest Neighbors, logistic regression, decision tree, random forest) for the same purpose. RESULTS: The CT-based model achieved the highest accuracy (90%) in classifying HPV status. Among the ML models, K-Nearest Neighbors performed best (80% accuracy). Weighted Ensemble methods combining the CT-based model with each ML model resulted in moderate accuracy improvements (70-90%). CONCLUSIONS: Our findings suggest that CT scans analyzed by DL models hold promise for non-invasive HPV detection in HNC. Radiomic features, while less accurate in this study, offer a complementary approach. Future research should explore larger datasets and investigate the potential of combining DL and radiomic techniques.
RESUMEN
The study investigates the efficiency of integrating Machine Learning (ML) in clinical practice for diagnosing solitary pulmonary nodules' (SPN) malignancy. Patient data had been recorded in the Department of Nuclear Medicine, University Hospital of Patras, in Greece. A dataset comprising 456 SPN characteristics extracted from CT scans, the SUVmax score from the PET examination, and the ultimate outcome (benign/malignant), determined by patient follow-up or biopsy, was used to build the ML classifier. Two medical experts provided their malignancy likelihood scores, taking into account the patient's clinical condition and without prior knowledge of the true label of the SPN. Incorporating human assessments into ML model training improved diagnostic efficiency by approximately 3%, highlighting the synergistic role of human judgment alongside ML. Under the latter setup, the ML model had an accuracy score of 95.39% (CI 95%: 95.29-95.49%). While ML exhibited swings in probability scores, human readers excelled in discerning ambiguous cases. ML outperformed the best human reader in challenging instances, particularly in SPNs with ambiguous probability grades, showcasing its utility in diagnostic grey zones. The best human reader reached an accuracy of 80% in the grey zone, whilst ML exhibited 89%. The findings underline the collaborative potential of ML and human expertise in enhancing SPN characterization accuracy and confidence, especially in cases where diagnostic certainty is elusive. This study contributes to understanding how integrating ML and human judgement can optimize SPN diagnostic outcomes, ultimately advancing clinical decision-making in PET/CT screenings.
RESUMEN
OBJECTIVES: In this study, we aim to evaluate the long-term impact of thalassaemia on bone mineral density (BMD) through sequential analysis, compare changes in BMD values between male and female patients and find any correlation between BMD and biochemical markers in the adult thalassaemia group. BMD is a bone mineral density test using dual-energy X-ray to measure calcium hydroxyapatite per unit of bone, reflecting bone strength. METHODS: We conducted a longitudinal retrospective observational cohort study to determine the changes in BMD values and biochemical parameters in adult thalassaemia patients. BMD was assessed at the lumbar spine (L1-L4) and proximal femora using Hologic's bone dual-energy X-ray absorptiometry. Five serial BMD values were retrieved from electronic records. Biochemical parameters, including serum calcium, phosphorus and 25-hydroxyvitamin D levels, were also assessed. RESULTS: A total of 108 patients (47 males and 61 females; median age: 44 years) with thalassaemia major 71 patients, intermedia 20 patients, haemoglobin E disease 14 patients and thalassaemia-alpha three patients were included. The incidence of low BMD in patients with thalassaemia increased from 64 to 74% over three decades of analysis. Females and thalassaemia major patients had lower hip BMD values and corresponding Z -scores. CONCLUSION: There is a progressive decline in BMD values in adult thalassaemia, which was apparent in female thalassaemia major patients. No changes in biochemical parameters, however, were observed over long-term assessments.
Asunto(s)
Densidad Ósea , Talasemia , Humanos , Masculino , Femenino , Adulto , Estudios Retrospectivos , Estudios Longitudinales , Talasemia/sangre , Talasemia/diagnóstico por imagen , Talasemia/fisiopatología , Talasemia/complicaciones , Persona de Mediana Edad , Adulto Joven , Anciano , Absorciometría de FotónRESUMEN
OBJECTIVE: The objective of this study is to investigate the feasibility and potential advantages of 99m Tc-DTPA dynamic single photon emission computed tomography/computed tomography (SPECT/CT) renogram in adults. METHODS: Fifty-five patients aged 19-80â years (mean 56.3) were enrolled. The imaging protocol included: day 1: 99m Tc-DTPA planar renogram, followed by planar 99m Tc-DMSA scan. Day 3: attenuation-corrected dynamic 99m Tc-DTPA SPECT renogram [DSPECT(AC)] and Cr-51 ethylenediamine tetraacetic acid (EDTA) glomerular filtration rate (GFR) calculation. DSPECT(AC) included an initial CT scan followed by 12 consecutive SPECT sessions acquired via continuous-mode acquisition for a total of 24â min. Fast SPECT sequences (1-2â s/projection, 60 projections, every 6°) were obtained for the first 8â min, followed by slower acquisitions (3-4â s/projection) during the rest of the study. Renal activity was measured in the total kidney volume by regions of interest drawn on consecutive transaxial slices of the third SPECT, which were then copied on the whole 12-SPECT series. Corresponding time-activity curves were created. DSPECT(AC) parameters were compared with those of planar renogram. The reference method for split renal function was 99m Tc-DMSA (geometrical mean of anterior and posterior projection counts) and for GFR the Cr-51 EDTA 2-blood sample clearance method. RESULTS: DSPECT(AC) images were of good quality. There was good correlation between renogram parameters (time to peak activity and NORA20) comparing the two techniques ( r â =â 0.959 and 0.933, respectively). In 21 cases with >30% absolute difference between the two kidneys, spilt renal function calculation by DSPECT(AC) correlated perfectly ( r â =â 0.968) with the reference method, whereas planar renogram was less accurate ( r â =â 0.843). Anatomic information provided by nonenhanced CT offered an integrated structural-functional view valuable for final diagnosis. DSPECT(AC) early kidney uptake as a fraction of injected dose correlated better with reference GFR ( r â =â 0.789) than the Gates' method ( r â =â 0.642). CONCLUSION: 99m Tc-DTPA dynamic SPECT/CT renogram is feasible with conventional SPECT/CT systems. It allows accurate split renal function measurement, offers additional anatomical information and can be used for closer approximation of GFR compared with Gates' method.
Asunto(s)
Estudios de Factibilidad , Tomografía Computarizada por Tomografía Computarizada de Emisión de Fotón Único , Pentetato de Tecnecio Tc 99m , Humanos , Adulto , Persona de Mediana Edad , Anciano , Masculino , Femenino , Tomografía Computarizada por Tomografía Computarizada de Emisión de Fotón Único/métodos , Anciano de 80 o más Años , Adulto Joven , Renografía por Radioisótopo/métodos , Tasa de Filtración Glomerular , Riñón/diagnóstico por imagenRESUMEN
Parathyroidectomy for primary hyperparathyroidism (PHPT) could have poor outcomes, even with accurate preoperative localization of the adenomas, because their intraoperative localization can be challenging. Freehand single photon emission computed tomography (fhSPECT) is a new technique for radio-guided intraoperative navigation. Its use during parathyroidectomy could be useful and such data are limited. We herein present our experience on the feasibility of fhSPECT for intraoperative detection of abnormal parathyroid glands. We retrospectively reviewed the clinical data of 55 patients (30-77 years old) with PHPT due to parathyroid adenomas, that were subjected to parathyroidectomy from 12/2017 to 7/2022. In average, 111 ± 74 MBq of Tc-99 m Sestamibi were injected intravenously, approximately 2 h before the operation and fhSPECT was used to generate 3D images during parathyroidectomy. Measurements of PTH and calcium levels were performed preoperatively, postoperatively and 4-6 months after the procedure. FhSPECT successfully identified the parathyroid adenoma in all the patients. It took 3 min (median time) for fhSPECT to detect at least one radioactive spot in all patients. The mean duration of the operation was 66.6 ± 7.3 min. Forty-nine patients out of 55 had solitary and 6/55 had multiple adenomas, whereas 6/55 had ectopic abnormal parathyroid glands. None of the patients had persistent hyperparathyroidism during follow-up. To the best of our knowledge, this is the largest series of patients with PHPT that underwent fhSPECT assisted parathyroidectomy. Our data suggest that this navigation system is helpful in identifying parathyroid adenomas intraoperatively.
RESUMEN
Fuzzy Cognitive Maps (FCMs) have become an invaluable tool for healthcare providers because they can capture intricate associations among variables and generate precise predictions. FCMs have demonstrated their utility in diverse medical applications, from disease diagnosis to treatment planning and prognosis prediction. Their ability to model complex relationships between symptoms, biomarkers, risk factors, and treatments has enabled healthcare providers to make informed decisions, leading to better patient outcomes. This review article provides a thorough synopsis of using FCMs within the medical domain. A systematic examination of pertinent literature spanning the last two decades forms the basis of this overview, specifically delineating the diverse applications of FCMs in medical realms, including decision-making, diagnosis, prognosis, treatment optimisation, risk assessment, and pharmacovigilance. The limitations inherent in FCMs are also scrutinised, and avenues for potential future research and application are explored.
RESUMEN
OBJECTIVES: This prospective, multicenter, open-label, randomized, crossover trial study was to evaluate the diagnostic performance of 18F-PSMA-1007 (PSMA) vs. 18F-Choline PET/CT (FCH) in prostate cancer (PCa) patients (pts) with biochemical recurrence (BCR). METHODS: One hundred eighty-six pts, who have undergone primary definitive treatment for PCa with BCR, were recruited to this prospective study. All pts underwent one PSMA and one FCH PET/CT examination in randomized order within a time frame of 8 days and were followed up for at least 6 months (182â ±â 10 days). RESULTS: Recurrence of PCa was observed in 176 out of 186 pts. The overall correct detection rate (DR) was 84% (95% CI 0.7967-0.8830) for PSMA and 69% (95% CI 0.6191-0.7489) for FCH, yielding a difference in proportion of 16% ( P â <â 0.0001). PSMA had a sensitivity of 0.8464 and FCH 0.6857 with an odds ratio of 2.5259 ( P â <â 0.0001), with statistically significant greater sensitivity of PSMA (ORs, 2.7877 and 2.1283 respectively) ( P â <â 0.0001). PET/CT imaging led to a more accurate diagnosis in 166 (89.2%) pts, of which PSMA had contributed more than FCH in 91 (54.8%) of them. The DR for cutoff point PSAâ ≤â 1 ng/ml was higher for PSMA compared to FCH (61.8% vs. 39.5%). DR value of 51.6% for PSMA reached at PSAâ ≤â 0.3 ng/ml, while FCH reached that DR value with PSAâ ≤â 2.2 ng/ml. CONCLUSION: 18F-PSMA-1007 is more efficacious than 18F-Choline for the identification metastatic lesions both in patient and in regional level analysis in PCa patients with BCR.
Asunto(s)
Tomografía Computarizada por Tomografía de Emisión de Positrones , Neoplasias de la Próstata , Masculino , Humanos , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Estudios Prospectivos , Antígeno Prostático Específico , Neoplasias de la Próstata/patología , Colina , Recurrencia Local de Neoplasia/diagnóstico por imagen , Radioisótopos de GalioRESUMEN
BACKGROUND: Standardized patient-specific pretreatment dosimetry planning is mandatory in the modern era of nuclear molecular radiotherapy, which may eventually lead to improvements in the final therapeutic outcome. Only a comprehensive definition of a dosage therapeutic window encompassing the range of absorbed doses, that is, helpful without being detrimental can lead to therapy individualization and improved outcomes. As a result, setting absorbed dose safety limits for organs at risk (OARs) requires knowledge of the absorbed dose-effect relationship. Data sets of consistent and reliable inter-center dosimetry findings are required to characterize this relationship. PURPOSE: We developed and standardized a new pretreatment planning model consisting of a predictive dosimetry procedure for OARs in patients with neuroendocrine tumors (NETs) treated with 177 Lu-DOTATATE (Lutathera). In the retrospective study described herein, we used machine learning (ML) regression algorithms to predict absorbed doses in OARs by exploiting a combination of radiomic and dosiomic features extracted from patients' imaging data. METHODS: Pretreatment and posttreatment data for 20 patients with NETs treated with 177 Lu-DOTATATE were collected from two clinical centers. A total of 3412 radiomic and dosiomic features were extracted from the patients' computed tomography (CT) scans and dose maps, respectively. All dose maps were generated using Monte Carlo simulations. An ML regression model was designed based on ML algorithms for predicting the absorbed dose in every OAR (liver, left kidney, right kidney, and spleen) before and after the therapy and between each therapy session, thus predicting any possible radiotoxic effects. RESULTS: We evaluated nine ML regression algorithms. Our predictive model achieved a mean absolute dose error (MAE, in Gy) of 0.61 for the liver, 1.58 for the spleen, 1.30 for the left kidney, and 1.35 for the right kidney between pretherapy 68 Ga-DOTATOC positron emission tomography (PET)/CT and posttherapy 177 Lu-DOTATATE single photon emission (SPECT)/CT scans. Τhe best predictive performance observed was based on the gradient boost for the liver, the left kidney and the right kidney, and on the extra tree regressor for the spleen. Evaluation of the model's performance according to its ability to predict the absorbed dose in each OAR in every possible combination of pretherapy 68 Ga-DOTATOC PET/CT and any posttherapy 177 Lu-DOTATATE treatment cycle SPECT/CT scans as well as any 177 Lu-DOTATATE SPECT/CT treatment cycle and the consequent 177 Lu-DOTATATE SPECT/CT treatment cycle revealed mean absorbed dose differences ranges from -0.55 to 0.68 Gy. Incorporating radiodosiomics features from the 68 Ga-DOTATOC PET/CT and first 177 Lu-DOTATATE SPECT/CT treatment cycle scans further improved the precision and minimized the standard deviation of the predictions in nine out of 12 instances. An average improvement of 57.34% was observed (range: 17.53%-96.12%). However, it's important to note that in three instances (i.e., Ga,C.1 â C3 in spleen and left kidney, and Ga,C.1 â C2 in right kidney) we did not observe an improvement (absolute differences of 0.17, 0.08, and 0.05 Gy, respectively). Wavelet-based features proved to have high correlated predictive value, whereas non-linear-based ML regression algorithms proved to be more capable than the linear-based of producing precise prediction in our case. CONCLUSIONS: The combination of radiomics and dosiomics has potential utility for personalized molecular radiotherapy (PMR) response evaluation and OAR dose prediction. These radiodosiomic features can potentially provide information on any possible disease recurrence and may be highly useful in clinical decision-making, especially regarding dose escalation issues.
Asunto(s)
Tumores Neuroendocrinos , Compuestos Organometálicos , Humanos , Tomografía Computarizada por Tomografía de Emisión de Positrones , Estudios Retrospectivos , Recurrencia Local de Neoplasia/tratamiento farmacológico , Cintigrafía , Octreótido/efectos adversos , Compuestos Organometálicos/uso terapéutico , Tumores Neuroendocrinos/diagnóstico por imagen , Tumores Neuroendocrinos/radioterapiaRESUMEN
18F-FDG PET/CT is the imaging modality of choice for the accurate initial staging of most lymphomas. Hodgkin's, Diffuse Large B-cell and follicular lymphomas show avid FDG uptake, while a minority of Non-Hodgkin lymphoma subtypes namely MALT, marginal and small lymphocytic lymphoma demonstrate low or moderate avidity. As a rule of thumb, indolent lymphomas show lower FDG activity than aggressive ones. PET/CT has increased sensitivity in the detection of nodal involvement even in small or normal-sized nodes. It shows higher sensitivity than CT in the detection of extra-nodal disease, most often in the spleen and bone marrow. PET/CT leads to upstaging in up to 25% of Hodgkin lymphomas, paving the way to intensified therapy. It has excellent Negative Predictive Value (NPV>95%) in the detection of bone marrow involvement in Hodgkin's rendering bone marrow biopsy not absolutely necessary: a negative PET rules out bone marrow disease in Hodgkin's patients, yet this does not universally apply in Non-Hodgkin lymphomas. PET/CT is superior to other imaging modalities in the initial stating of aggressive Non-Hodgkin lymphomas detecting disease in previously not suspected or occult sites. 18F-FDG PET/CT is applied in the early therapeutic evaluation of Hodgkin's by means of interim PET performed after 2-3 initial cycles of chemotherapy. Patients with negative interim PET and no hypermetabolic disease identified may continue with the same effective treatment or switch to less aggressive therapy. On the other hand, patients who do not show PET response may be subjected to more intensified treatment to eradicate hypermetabolic active disease. Randomized controlled trials have proven that interim PET/CT shows high NPV for final treatment response and for increased progression free survival in Hodgkin's. The accuracy in reporting and interpretating interim and post-treatment PET/CT has increased by applying specific objective criteria: Deauville 5-score scale. Deauville's uptake scores of 4-5, more intense than liver activity, correspond to active lymphomatous disease. 18F-FDG uptake in lesions, equal or lower than mediastinal blood-pool, is interpreted as negative: Deauville scores of 1-2. Role of interim PET is also investigated in Non-Hodgkin Lymphomas, especially nowadays with more effective treatments being applied. PET/CT is highly recommended for post-treatment assessment of lymphomas with excellent NPV and superior diagnostic accuracy compared with CT. After treatment, a significant proportion of patients show residual anatomic lesions on CT f.e. residual mediastinal soft-tissue; yet, in the minority of cases, these lesions correspond to active disease. PET/CT has high diagnostic accuracy in the assessment of residual tissue and may distinguish between PET-negative fibrotic or necrotic tissue and PET-positive, active residual disease. The modality also has high NPV in the evaluation of megatherapy before stem cell transplantation: a favorable PET response is associated with better progression free survival and overall survival. To sum up, PET/CT has evolved as an established method in lymphoma patients being incorporated into clinical algorithms and guidelines altering therapeutic decisions.
Asunto(s)
Linfoma no Hodgkin , Linfoma , Humanos , Tomografía Computarizada por Tomografía de Emisión de Positrones/métodos , Fluorodesoxiglucosa F18 , Linfoma/diagnóstico por imagen , Linfoma/terapia , Tomografía de Emisión de Positrones/métodosRESUMEN
Deep learning (DL) is a well-established pipeline for feature extraction in medical and nonmedical imaging tasks, such as object detection, segmentation, and classification. However, DL faces the issue of explainability, which prohibits reliable utilisation in everyday clinical practice. This study evaluates DL methods for their efficiency in revealing and suggesting potential image biomarkers. Eleven biomedical image datasets of various modalities are utilised, including SPECT, CT, photographs, microscopy, and X-ray. Seven state-of-the-art CNNs are employed and tuned to perform image classification in tasks. The main conclusion of the research is that DL reveals potential biomarkers in several cases, especially when the models are trained from scratch in domains where low-level features such as shapes and edges are not enough to make decisions. Furthermore, in some cases, device acquisition variations slightly affect the performance of DL models.
RESUMEN
BACKGROUND: Parathyroid proliferative disorder encompasses a wide spectrum of diseases, including parathyroid adenoma (PTA), parathyroid hyperplasia, and parathyroid carcinoma. Imaging modalities that deliver their results preoperatively help in the localisation of parathyroid glands (PGs) and assist in surgery. Artificial intelligence and, more specifically, image detection methods, can assist medical experts and reduce the workload in their everyday routine. METHODS: The present study employs an innovative CNN topology called ParaNet, to analyse early MIBI, late MIBI, and TcO4 thyroid scan images simultaneously to perform first-level discrimination between patients with abnormal PGs (aPG) and patients with normal PGs (nPG). The study includes 632 parathyroid scans. RESULTS: ParaNet exhibits a top performance, reaching an accuracy of 96.56% in distinguishing between aPG and nPG scans. Its sensitivity and specificity are 96.38% and 97.02%, respectively. PPV and NPV values are 98.76% and 91.57%, respectively. CONCLUSIONS: The proposed network is the first to introduce the automatic discrimination of PG and nPG scans acquired by scintigraphy with 99mTc-sestamibi (MIBI). This methodology could be applied to the everyday routine of medics for real-time evaluation or educational purposes.
RESUMEN
Metastatic ureteral tumors arising from a primary breast carcinoma are extremely rare. They present with hematuria and radiological findings compatible with obstructive ureteral phenomena. We present a case of an 87-year-old woman with a history of lymphoma and triple negative breast cancer (TNBC), during an emergency admission for peptic ulcer, developed macroscopic hematuria. Radiologic and endoscopic investigations revealed a remarkable stenosis at the lower segment of the right ureter, attributed to metastases from her breast carcinoma. We report this case with the aim to make both oncologists and urologists aware of this rare condition.
Asunto(s)
Neoplasias de la Mama Triple Negativas , Uréter , Anciano de 80 o más Años , Femenino , Hematuria/patología , Humanos , Neoplasias de la Mama Triple Negativas/patología , Neoplasias de la Mama Triple Negativas/terapia , Uréter/patologíaRESUMEN
PURPOSE: This paper reviews recent applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging. Recent advances in Deep Learning (DL) and GANs catalysed the research of their applications in medical imaging modalities. As a result, several unique GAN topologies have emerged and been assessed in an experimental environment over the last two years. METHODS: The present work extensively describes GAN architectures and their applications in PET imaging. The identification of relevant publications was performed via approved publication indexing websites and repositories. Web of Science, Scopus, and Google Scholar were the major sources of information. RESULTS: The research identified a hundred articles that address PET imaging applications such as attenuation correction, de-noising, scatter correction, removal of artefacts, image fusion, high-dose image estimation, super-resolution, segmentation, and cross-modality synthesis. These applications are presented and accompanied by the corresponding research works. CONCLUSION: GANs are rapidly employed in PET imaging tasks. However, specific limitations must be eliminated to reach their full potential and gain the medical community's trust in everyday clinical practice.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Tomografía de Emisión de Positrones , Artefactos , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Tomografía de Emisión de Positrones/métodosRESUMEN
BACKGROUND: Radioembolization with 90 Y microspheres is a treatment approach for liver cancer. Currently, employed dosimetric calculations exhibit low accuracy, lacking consideration of individual patient, and tissue characteristics. PURPOSE: The purpose of the present study was to employ deep learning (DL) algorithms to differentiate patterns of pretreatment distribution of 99m Tc-macroaggregated albumin on SPECT/CT and post-treatment distribution of 90 Y microspheres on PET/CT and to accurately predict how the 90 Y-microspheres will be distributed in the liver tissue by radioembolization therapy. METHODS: Data for 19 patients with liver cancer (10 with hepatocellular carcinoma, 5 with intrahepatic cholangiocarcinoma, 4 with liver metastases) who underwent radioembolization with 90 Y microspheres were used for the DL training. We developed a 3D voxel-based variation of the Pix2Pix model, which is a special type of conditional GANs designed to perform image-to-image translation. SPECT and CT scans along with the clinical target volume for each patient were used as inputs, as were their corresponding post-treatment PET scans. The real and predicted absorbed PET doses for the tumor and the whole liver area were compared. Our model was evaluated using the leave-one-out method, and the dose calculations were measured using a tissue-specific dose voxel kernel. RESULTS: The comparison of the real and predicted PET/CT scans showed an average absorbed dose difference of 5.42% ± 19.31% and 0.44% ± 1.64% for the tumor and the liver area, respectively. The average absorbed dose differences were 7.98 ± 31.39 Gy and 0.03 ± 0.25 Gy for the tumor and the non-tumor liver parenchyma, respectively. Our model had a general tendency to underpredict the dosimetric results; the largest differences were noticed in one case, where the model underestimated the dose to the tumor area by 56.75% or 72.82 Gy. CONCLUSIONS: The proposed deep-learning-based pretreatment planning method for liver radioembolization accurately predicted 90 Y microsphere biodistribution. Its combination with a rapid and accurate 3D dosimetry method will render it clinically suitable and could improve patient-specific pretreatment planning.
Asunto(s)
Aprendizaje Profundo , Embolización Terapéutica , Neoplasias Hepáticas , Humanos , Hígado/diagnóstico por imagen , Neoplasias Hepáticas/diagnóstico por imagen , Neoplasias Hepáticas/radioterapia , Microesferas , Tomografía Computarizada por Tomografía de Emisión de Positrones , Agregado de Albúmina Marcado con Tecnecio Tc 99m , Distribución Tisular , Tomografía Computarizada de Emisión de Fotón Único , Radioisótopos de Itrio/uso terapéuticoRESUMEN
BACKGROUND Chronic posterior knee dislocation after total knee arthroplasty (TKA) is a rare but serious complication, especially when it coexists with septic implant loosening, flexion contracture, and extensive comorbidities. Although the severity is comparable to that in the native knee dislocation, there are few reports in the literature. When TKA dislocation is complicated with infection, bone defect, and patient's comorbidity, treatment becomes even more difficult. For these complex complications, in order to provide stable and mobile knees, constrained total knee prostheses are used. CASE REPORT We present the case of a 63-year-old, non-ambulatory man, with mental retardation and multiple comorbidities, who had a 9-year history of neglected posterior TKA dislocation, which later became complicated with septic loosening and productive fistula for 4 years. The patient required use of a wheel-chair for several years, was obese with a body mass index (BMI) of 34.3, and the affected knee was in a prolonged flexion contracture at 90°. The posterior TKA dislocation was later infected by Staphylococcus hominis and Staphylococcus epidermidis. He was successfully treated with two-stage revision surgery and managed to become ambulatory after 6 years of requiring use of a wheel-chair. CONCLUSIONS Neglected posterior dislocation of TKA is a rare and potentially limp-causing complication, especially when accompanied with chronic infection, implant loosening, severe bone loss, flexion contracture, and extensive comorbidities. A multidisciplinary approach with careful preoperative planning, exceptional surgical technique, and prolonged supervised physiotherapy are the keystones for a successful outcome.
Asunto(s)
Artroplastia de Reemplazo de Rodilla , Contractura , Prótesis de la Rodilla , Artroplastia de Reemplazo de Rodilla/efectos adversos , Contractura/etiología , Contractura/cirugía , Humanos , Articulación de la Rodilla , Prótesis de la Rodilla/efectos adversos , Masculino , Persona de Mediana Edad , Rango del Movimiento Articular , Resultado del TratamientoRESUMEN
Early and automatic diagnosis of Solitary Pulmonary Nodules (SPN) in Computed Tomography (CT) chest scans can provide early treatment for patients with lung cancer, as well as doctor liberation from time-consuming procedures. The purpose of this study is the automatic and reliable characterization of SPNs in CT scans extracted from Positron Emission Tomography and Computer Tomography (PET/CT) system. To achieve the aforementioned task, Deep Learning with Convolutional Neural Networks (CNN) is applied. The strategy of training specific CNN architectures from scratch and the strategy of transfer learning, by utilizing state-of-the-art pre-trained CNNs, are compared and evaluated. To enhance the training sets, data augmentation is performed. The publicly available database of CT scans, named as Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), is also utilized to further expand the training set and is added to the PET/CT dataset. The results highlight the effectiveness of transfer learning and data augmentation for the classification task of small datasets. The best accuracy obtained on the PET/CT dataset reached 94%, utilizing a modification proposal of a state-of-the-art CNN, called VGG16, and enhancing the training set with LIDC-IDRI dataset. Besides, the proposed modification outperforms in terms of sensitivity several similar researches, which exploit the benefits of transfer learning. Overview of the experiment setup. The two datasets containing nodule representations are combined to evaluate the effectiveness of transfer learning over the traditional approach of training Convolutional Neural Networks from scratch.
Asunto(s)
Neoplasias Pulmonares , Nódulo Pulmonar Solitario , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Aprendizaje Automático , Redes Neurales de la Computación , Tomografía Computarizada por Tomografía de Emisión de Positrones , Interpretación de Imagen Radiográfica Asistida por Computador , Nódulo Pulmonar Solitario/diagnóstico por imagen , Tomografía Computarizada por Rayos XRESUMEN
Renal cell carcinoma (RCC) is one of the most aggressive malignancies of the genito-urinary tract, having a poor prognosis especially in patients with metastasis. Surgical resection remains the gold standard for localized renal cancer disease, with radiotherapy (RT) receiving much skepticism during the last decades. However, many studies have evaluated the role of RT, and although renal cancer is traditionally considered radio-resistant, technological advances in the RT field with regards to modern linear accelerators, as well as advanced RT techniques have resulted in breakthrough therapeutic outcomes. Additionally, the combination of RT with immune checkpoint inhibitors and targeted agents may maximize the clinical benefit. This review article focuses on the role of RT in the therapeutic management of renal cell carcinoma.
Asunto(s)
Carcinoma de Células Renales , Neoplasias Renales , Carcinoma de Células Renales/radioterapia , Humanos , Neoplasias Renales/radioterapiaRESUMEN
PURPOSE: Accurate detection and treatment of Coronary Artery Disease is mainly based on invasive Coronary Angiography, which could be avoided provided that a robust, non-invasive detection methodology emerged. Despite the progress of computational systems, this remains a challenging issue. The present research investigates Machine Learning and Deep Learning methods in competing with the medical experts' diagnostic yield. Although the highly accurate detection of Coronary Artery Disease, even from the experts, is presently implausible, developing Artificial Intelligence models to compete with the human eye and expertise is the first step towards a state-of-the-art Computer-Aided Diagnostic system. METHODS: A set of 566 patient samples is analysed. The dataset contains Polar Maps derived from scintigraphic Myocardial Perfusion Imaging studies, clinical data, and Coronary Angiography results. The latter is considered as reference standard. For the classification of the medical images, the InceptionV3 Convolutional Neural Network is employed, while, for the categorical and continuous features, Neural Networks and Random Forest classifier are proposed. RESULTS: The research suggests that an optimal strategy competing with the medical expert's accuracy involves a hybrid multi-input network composed of InceptionV3 and a Random Forest. This method matches the expert's accuracy, which is 79.15% in the particular dataset. CONCLUSION: Image classification using deep learning methods can cooperate with clinical data classification methods to enhance the robustness of the predicting model, aiming to compete with the medical expert's ability to identify Coronary Artery Disease subjects, from a large scale patient dataset.