RESUMO
OBJECTIVE: Asthma is a common chronic respiratory diseases, and the relationship between pulmonary ventilation function and the prognosis of patients with suspected asthma is not well understood. This study aims to explore the impact of pulmonary ventilation functions on the prognosis of patients with suspected asthma. METHODS: This retrospective observational study included patients with suspected asthma who were diagnosed and treated at the Guangdong Provincial Hospital of Traditional Chinese Medicine between August 2015 and January 2020. The primary outcome of interest was improvement in asthma symptoms, as measured by bronchial provocation test (BPT) results within one year after diagnosis. The impact of pulmonary ventilation functions on prognosis was explored by multivariable logistic regression analysis. RESULTS: Seventy-two patients were included in the study. Patients with normal (OR = 0.123, p = .004) or generally normal (OR = 0.075, p = .039) pulmonary ventilation function were more likely to achieve improvement in asthma symptoms compared with patients with mild obstruction. There were no significant differences between the improvement and non-improvement groups in baseline characteristics. CONCLUSION: These results suggest that suspected asthma patients with normal or generally normal pulmonary ventilation function are more likely to achieve improvement in asthma symptoms within one year compared to patients with mild obstruction.
Assuntos
Asma , Humanos , Asma/diagnóstico , Asma/fisiopatologia , Asma/terapia , Estudos Retrospectivos , Masculino , Feminino , Pessoa de Meia-Idade , Adulto , Prognóstico , Ventilação Pulmonar/fisiologia , Testes de Provocação Brônquica/métodos , Testes de Função Respiratória , IdosoRESUMO
The rise in crime rates in many parts of the world, coupled with advancements in computer vision, has increased the need for automated crime detection services. To address this issue, we propose a new approach for detecting suspicious behavior as a means of preventing shoplifting. Existing methods are based on the use of convolutional neural networks that rely on extracting spatial features from pixel values. In contrast, our proposed method employs object detection based on YOLOv5 with Deep Sort to track people through a video, using the resulting bounding box coordinates as temporal features. The extracted temporal features are then modeled as a time-series classification problem. The proposed method was tested on the popular UCF Crime dataset, and benchmarked against the current state-of-the-art robust temporal feature magnitude (RTFM) method, which relies on the Inflated 3D ConvNet (I3D) preprocessing method. Our results demonstrate an impressive 8.45-fold increase in detection inference speed compared to the state-of-the-art RTFM, along with an F1 score of 92%,outperforming RTFM by 3%. Furthermore, our method achieved these results without requiring expensive data augmentation or image feature extraction.
Assuntos
Crime , Redes Neurais de Computação , Humanos , Crime/prevenção & controleRESUMO
This research study mainly focused on the dynamic malware detection. Malware progressively changes, leading to the use of dynamic malware detection techniques in this research study. Each day brings a new influx of malicious software programmes that pose a threat to online safety by exploiting vulnerabilities in the Internet. The proliferation of harmful software has rendered manual heuristic examination of malware analysis ineffective. Automatic behaviour-based malware detection using machine learning algorithms is thus considered a game-changing innovation. Threats are automatically evaluated based on their behaviours in a simulated environment, and reports are created. These records are converted into sparse vector models for use in further machine learning efforts. Classifiers used to synthesise the results of this study included kNN, DT, RF, AdaBoost, SGD, extra trees and the Gaussian NB classifier. After reviewing the test and experimental data for all five classifiers, we found that the RF, SGD, extra trees and Gaussian NB Classifier all achieved a 100% accuracy in the test, as well as a perfect precision (1.00), a good recall (1.00), and a good f1-score (1.00). Therefore, it is reasonable to assume that the proof-of-concept employing autonomous behaviour-based malware analysis and machine learning methodologies might identify malware effectively and rapidly.
Assuntos
Algoritmos , Segurança Computacional , Aprendizado de Máquina , SoftwareRESUMO
Choroidal nevi (CN) are commonly divided into non-suspicious (stable) and suscpicious (progressive). However, there are still no clear data on OCT patterns of nevi progression, their transformation into initial melanomas. PURPOSE: The study aims to determine the types of OCT patterns of CN and to evaluate their prognostic value. MATERIAL AND METHODS: The study included 50 patients with CN (53 nevi). The height of 19 nevi evaluated with ultrasonography was 1.33±0.43 mm, diameter - 5.47±1.68 mm. RESULTS: CN is an area of local increase in reflectivity of the choroid; its widening and elevation of the tomographic section were observed in 72% of nevi. In more than half of all cases a distinct hyperreflective border was revealed between the CN and adjacent choroid. In two thirds of all cases the choriocapillaris layer was preserved and visualized mainly along the edge of lesion. Analysis of OCT scans showed distinct differences, which allowed designation of four OCT types of CN: 1) nevi with typical OCT pattern; 2) nevi with changes in retinal pigment epithelium (RPE); 3) nevi with neuroepithelial detachment; 4) nevi with atypical OCT pattern. CONCLUSION: Based on the analysis of OCT images of the determined types of nevi, it can be assumed that all of them initially had typical OCT pattern. With enlargement of the nevi and increase in the duration of its presence in the choroid, dystrophic processes in the adjacent retina and changes in RPE begin to occur. Disturbed pumping ability of the damaged RPE results in disruption of the trophism of adjacent retina, which leads to development of atrophic changes. Nevi with atypical OCT pattern should be considered as a sign of long-term benign process in the choroid that will cause atrophic changes in the choroid and adjacent retina, while nevi with changes in RPE and with neuroepithelial detachment - as a risk factor for transition to choroidal melanoma.
Assuntos
Neoplasias da Coroide , Nevo Pigmentado , Neoplasias Cutâneas , Humanos , Tomografia de Coerência Óptica/métodos , Neoplasias da Coroide/diagnóstico por imagem , Neoplasias da Coroide/patologia , Corioide/diagnóstico por imagem , Corioide/patologia , Nevo Pigmentado/diagnóstico por imagem , Nevo Pigmentado/patologia , Angiofluoresceinografia , Estudos RetrospectivosRESUMO
OBJECTIVE: While there are a number of benefits to minimally invasive surgery (MIS) for women with ovarian cysts, there is an increased risk of ovarian capsule rupture during the procedure, which could potentially seed the abdominal cavity with malignant cells. We developed a decision model to compare the risks, benefits, effectiveness and cost of MIS versus laparotomy in women with ovarian masses. DESIGN: Cost-effectiveness study POPULATION: Hypothetical cohort of 10 000 women with ovarian masses who were undergoing surgical management. METHODS: The initial decision point in the model was performance of surgery via laparotomy or a MIS approach. Model probabilities, costs and utility values were derived from published literature and administrative data sources. Extensive sensitivity analyses were conducted to assess the robustness of the findings. MAIN OUTCOME MEASURES: The primary outcome was the cost-effectiveness of MIS versus laparotomy for women with a pelvic mass measured by incremental cost-effectiveness ratios (ICERs). RESULTS: MIS was the least costly strategy at $7,732 per women on average, compared with $17,899 for laparotomy. In our hypothetical cohort of 10 000 women, there were 64 cases of ovarian rupture in the MIS group and 53 in the laparotomy group, while there were 26 cancer-related deaths in the MIS group and 25 in the laparotomy group. MIS was more effective than laparotomy (188 462 QALYs for MIS versus 187 631 quality adjusted life years [QALYs] for laparotomy). Thus, MIS was a dominant strategy, being both less costly and more effective than laparotomy. These results were robust in a variety of sensitivity analyses. CONCLUSION: MIS constitutes a cost-effective management strategy for women with suspicious ovarian masses. TWEETABLE ABSTRACT: MIS is a cost-effective management strategy for women with suspicious ovarian masses.
Assuntos
Procedimentos Cirúrgicos Minimamente Invasivos , Neoplasias Ovarianas , Análise Custo-Benefício , Feminino , Humanos , Laparotomia/efeitos adversos , Laparotomia/métodos , Procedimentos Cirúrgicos Minimamente Invasivos/efeitos adversos , Procedimentos Cirúrgicos Minimamente Invasivos/métodos , Neoplasias Ovarianas/patologia , Anos de Vida Ajustados por Qualidade de VidaRESUMO
BACKGROUND AND OBJECTIVES: Suspicious peritoneal cytology refers to the result of peritoneal cytology testing that is insufficient in either quality or quantity for a definitive diagnosis of malignancy. This study examined characteristics and survival outcomes related to suspicious peritoneal cytology in endometrial cancer. METHODS: A population-based retrospective study by querying the National Cancer Institute's Surveillance, Epidemiology, and End Results Program was conducted. A total of 41,229 women with Stage I-III endometrial cancer who had peritoneal cytologic sampling at hysterectomy from 2010 to 2016 were examined. A Cox proportional hazard regression model and a competing risk analysis with Fine-Gray model were fitted to assess survival outcome related to suspicious peritoneal cytology. RESULTS: Suspicious peritoneal cytology was seen in 702 (1.7%) cases. In multivariable models, suspicious peritoneal cytology was associated with increased risk of endometrial cancer mortality (subdistribution-hazard ratio [HR] 1.69, 95% confidence interval [CI] 1.29-2.20, p < 0.001) and all-cause mortality (adjusted-HR: 1.55, 95% CI: 1.27-1.90, p < 0.001) compared with negative peritoneal cytology. Sensitivity analysis demonstrated that suspicious peritoneal cytology had discrete overall survival improvement compared with malignant peritoneal cytology in a propensity score weighting model (HR: 0.85, 95% CI: 0.72-0.99, p = 0.049). CONCLUSION: Our study suggests that suspicious peritoneal cytology may be a prognostic factor for decreased survival in endometrial cancer.
Assuntos
Carcinoma Endometrioide/patologia , Citodiagnóstico/métodos , Neoplasias do Endométrio/patologia , Histerectomia/métodos , Neoplasias Peritoneais/patologia , Idoso , Carcinoma Endometrioide/cirurgia , Neoplasias do Endométrio/cirurgia , Feminino , Seguimentos , Humanos , Pessoa de Meia-Idade , Neoplasias Peritoneais/cirurgia , Prognóstico , Estudos Retrospectivos , Fatores de Risco , Programa de SEER , Taxa de SobrevidaRESUMO
AIM: Management of the rectal defect after transanal endoscopic microsurgery (TEM) is a matter of debate. Data are lacking on long term outcomes and continence of patients with open or closed rectal defect. We sought to analyse these in a retrospective cohort study. METHODS: Patients undergoing TEM via the Specialist Early Rectal Cancer (SERC) MDT between 2012 and 2019 were included from a prospectively maintained database. These were divided into two groups - open and closed, based on management of rectal defect. Patient demographics and outcomes, including pre- and postoperative oncological staging, morbidity, mortality, length of stay and faecal incontinence severity score (FISI) scores were assessed. RESULTS: A total of 170 matched patients were included (70-open, 100-closed rectal defects). Short-term complications (bleeding, infection, urinary retention and infection, length of stay and pain) were 18.8% with no significant difference between the two groups (22% vs. 16%). Most of the defects were well healed upon endoscopic follow-up; more unhealed/sinus formation was noticed in the open group (p = 0.01); more strictures were encountered in the closed group (p = 0.04). Comparing the open and closed defect groups, there was no difference in the functional outcome of patients in those who developed sinus (p = 0.87) or stricture (p = 0.79) but a significant difference in post-TEMS FISI scores in those with healed scar, with those in closed rectal defect group with worsening function (p = 0.02). CONCLUSION: There are pros and cons associated with both rectal defect management approaches. Long-term complications should be expected and actively followed up. Patients should be thoroughly counselled about these and possible deterioration in continence post-TEM.
Assuntos
Neoplasias Retais , Microcirurgia Endoscópica Transanal , Cirurgia Endoscópica Transanal , Humanos , Neoplasias Retais/cirurgia , Reto/cirurgia , Estudos Retrospectivos , Microcirurgia Endoscópica Transanal/efeitos adversos , Cirurgia Endoscópica Transanal/efeitos adversos , Resultado do TratamentoRESUMO
OBJECTIVE: Our objective was to investigate the management of patients with asymptomatic suspicious thyroid nodules ≤1 cm. METHODS: We retrospectively reviewed medical records of patients with sonographically suspicious thyroid nodules ≤1 cm and without distant metastases, suspicious lymph node metastasis (LNM), or extrathyroidal extension (ETE). RESULTS: Of the 386 enrolled patients, 174 (45.1%) had immediate surgery (IS), while 212 (54.9%) underwent active surveillance (AS). In the IS group, 166 (95.4%) patients were confirmed as having papillary thyroid microcarcinoma. LNM and ETE were observed in 24.7% and 2.4% cases, respectively. In the AS group, nodule size increased by ≥3 mm in 11 (5.2%) patients and 39 (18.4%) had a >50% increase in nodule volume after a median follow-up of 12 months. Nodules with smaller volume at diagnosis were more likely to increase in volume later. Newly suspicious LNM was detected in 23 (10.8%) patients. Delayed surgery (DS) was performed in 101 patients, with 27 showing disease progression. ETE and LNM were detected in 3% and 36%, respectively, of patients with papillary thyroid microcarcinoma. Compared with IS, tumors in the DS group more frequently showed lateral LNM and capsular invasion (P < .05). No patient had recurrence or died of thyroid cancer during postoperative follow-up (median 26 [4-60] months). CONCLUSIONS: IS or DS of patients with asymptomatic suspicious thyroid nodules ≤1 cm was relatively high in China. The inertia of low-risk nodules and the effectiveness of DS for those that progressed make AS a feasible strategy.
Assuntos
Carcinoma Papilar , Neoplasias da Glândula Tireoide , Nódulo da Glândula Tireoide , Carcinoma Papilar/diagnóstico por imagem , Carcinoma Papilar/cirurgia , Humanos , Recidiva Local de Neoplasia , Estudos Retrospectivos , Neoplasias da Glândula Tireoide/diagnóstico por imagem , Neoplasias da Glândula Tireoide/epidemiologia , Neoplasias da Glândula Tireoide/cirurgia , Nódulo da Glândula Tireoide/diagnóstico por imagem , Nódulo da Glândula Tireoide/epidemiologia , Nódulo da Glândula Tireoide/cirurgia , Tireoidectomia , Conduta ExpectanteRESUMO
The continuous development of intelligent video surveillance systems has increased the demand for enhanced vision-based methods of automated detection of anomalies within various behaviors found in video scenes. Several methods have appeared in the literature that detect different anomalies by using the details of motion features associated with different actions. To enable the efficient detection of anomalies, alongside characterizing the specificities involved in features related to each behavior, the model complexity leading to computational expense must be reduced. This paper provides a lightweight framework (LightAnomalyNet) comprising a convolutional neural network (CNN) that is trained using input frames obtained by a computationally cost-effective method. The proposed framework effectively represents and differentiates between normal and abnormal events. In particular, this work defines human falls, some kinds of suspicious behavior, and violent acts as abnormal activities, and discriminates them from other (normal) activities in surveillance videos. Experiments on public datasets show that LightAnomalyNet yields better performance comparative to the existing methods in terms of classification accuracy and input frames generation.
Assuntos
Acidentes por Quedas , Redes Neurais de Computação , HumanosRESUMO
The risk of choroidal melanoma developing from choroidal nevus (CN) varies in range of 0.78-7%. Absence of a common terminology and distinct diagnostic criteria characterizing small melanoma de novo and unusual CN often complicates treatment choice and patient prognosis. PURPOSE: To study the clinical features and the role of visualization methods in the diagnosis of CN transformation into melanoma. MATERIAL AND METHODS: The study analyzes the clinical picture and visualization results of 11 patients with initial diagnosis of «choroidal nevus¼ (n=3) and «suspicious choroidal nevus¼ (n=8). RESULTS AND DISCUSSION: Examination and continued observation revealed 7 patients to have melanoma that had developed from CN (2 of them confirmed with histological studies). The time before CN transformed into melanoma varied between 4 and 13 years, with median 5 [4; 12] years. Two patients were diagnosed with primary melanoma (melanoma de novo), two other patients - with suspicious CN. In progressive CN transforming into melanoma, visual impairments occurred between 6 months and 13 years in 6 out of 7 patients. Initial prominence of suspicious CN at the first visit was 1.9±0.68 mm (0.9 mm to 2.67 mm). The characteristic features of suspicious CN transforming into initial melanoma are: 1) asymmetric shape of the edges of expanded choroidal complex; 2) presence of areas of damaged choriocapillaris layer, direct and indirect signs of loss of integrity of the Bruch's membrane; 3) areas of accumulation of moderately hyperreflective subretinal exudate; 4) presence of intraretinal hyperreflective inclusions. The signs distinguishing primary choroidal melanoma from melanoma that had developed from CN are: 1) absence of areas with tomography pattern characteristic of nevi; 2) more pronounced asymmetry of the shape of edges, compared to melanoma developed from CN; 3) presence of cysts in larger tumors, compared to melanoma developed from CN. CONCLUSION: All patients with CN should be regularly followed up by an ophthalmologist.
Assuntos
Neoplasias da Coroide , Melanoma , Nevo , Neoplasias Cutâneas , Neoplasias da Coroide/diagnóstico , Humanos , Melanoma/diagnóstico , Tomografia de Coerência ÓpticaRESUMO
BACKGROUND: Colonoscopy is the reference standard for the detection of colorectal cancer but it is an invasive technique and has the risk of bowel perforation and bleeding. Unlike colonoscopy, sedation is not required in computed tomography colonography and requires additional reassurance endoscopy. The objectives of the study were to compare the diagnostic performance of computed tomography colonography against colonoscopy for a diagnosis of colorectal cancer. METHODS: Data regarding any polyp ≥10 mm diameter (ø) and < 10 mm ø but suspicious polyps of computed tomography colonography (n = 318), colonoscopy (n = 318), and surgical pathology (n = 77) for symptomatic colorectal cancer patients were collected and analyzed. Lesion ulceration, extramural invasion, and/ or lesion shouldering was considered as a suspicious polyp. Beneficial scores for decision making of curative surgeries were evaluated for each modality. The cost of diagnosis of colorectal cancer was also evaluated. RESULTS: Either of diagnosis showed polyps ≥10 mm ø in 27 patients and polyps of 50 patients were < 10 mm ø but suspicious. Therefore, a total of 77 patients were subjected to surgery. With respect to surgical pathology, sensitivities for computed tomographic colonography and colonoscopy were 0.961 and 0.831. For detection of ≥10 mm ø polyp, benefit score for computed tomographic colonography and colonoscopy were 0-0.906 diagnostic confidence and 0.035-0.5 diagnostic confidence. For polyps, ≥ 10 mm ø but not too many large polyps, colonoscopy had the risk of underdiagnosis. For < 10 mm ø but suspicious polyps, < 0.6 mm ø and < 2.2 mm â polyps could not be detected by computed tomographic colonography and colonoscopy, respectively. The computed tomographic colonography had less cost than colonoscopy (1345 ± 135 ¥/ patient vs. 1715 ± 241 ¥/ patient, p < 0.0001) for diagnosis of colorectal cancer. CONCLUSION: Computed tomographic colonography would be a non-inferior alternative than colonoscopy for a diagnosis of colorectal cancer. LEVEL OF EVIDENCE: III.
Assuntos
Colonografia Tomográfica Computadorizada/métodos , Colonoscopia/instrumentação , Neoplasias Colorretais/diagnóstico , Idoso , Tomada de Decisão Clínica , Colonoscopia/métodos , Neoplasias Colorretais/cirurgia , Testes Diagnósticos de Rotina , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Retrospectivos , Sensibilidade e EspecificidadeRESUMO
BACKGROUND: Artificial intelligence (AI) is increasingly being used in medical practice. Especially in the image-based diagnosis of skin cancer, AI shows great potential. However, there is a significant discrepancy between expectations and true relevance of AI in current dermatological practice. OBJECTIVES: This article summarizes promising study results of skin cancer diagnosis by computer-based diagnostic systems and discusses their significance for daily practice. We hereby focus on the analysis of dermoscopic images of pigmented and unpigmented skin lesions. MATERIALS AND METHODS: A selective literature search for recent relevant trials was conducted. The included studies used machine learning, and in particular "convolutional neural networks", which have been shown to be particularly effective for the classification of image data. RESULTS AND CONCLUSIONS: In numerous studies, computer algorithms were able to detect pigmented and nonpigmented neoplasms of the skin with high precision, comparable to that of dermatologists. The combination of the physician's assessment and AI showed the best results. Computer-based diagnostic systems are widely accepted among patients and physicians. However, they are still not applicable in daily practice, since computer-based diagnostic systems have only been tested in an experimental environment. In addition, many digital diagnostic criteria that help AI to classify skin lesions remain unclear. This lack of transparency still needs to be addressed. Moreover, clinical studies on the use of AI-based assistance systems are needed in order to prove its applicability in daily dermatologic practice.
Assuntos
Inteligência Artificial , Diagnóstico por Computador/métodos , Programas de Rastreamento/métodos , Melanoma/diagnóstico , Redes Neurais de Computação , Neoplasias Cutâneas/diagnóstico , Algoritmos , Dermoscopia , Humanos , Processamento de Imagem Assistida por Computador/métodosRESUMO
OBJECTIVE: Introduction: Approximately 10% of fine needle aspiration biopsy (FNAB) of thyroid nodules may be verified as "suspicious for follicular neoplasm"; this category involves follicular adenoma, follicular carcinoma, follicular variants of papillary carcinoma and subclass "suspicious for Hurthle cell neoplasm". At present, there is no diagnostic tool to discriminate between follicular adenoma and cancer. Most patients are required surgery to exclude malignant process. The aim: To define factors correlating with risk of malignancy in patients with FNAB of thyroid focal lesions and nodules verified as Bethesda tier IV. PATIENTS AND METHODS: Materials and Methods: In this study 110 consecutive patients were included. All patients were operated because of FNAB result "suspicious for follicular neoplasm" of thyroid gland at a single institution from January 2016 until March 2020. From this set, six specific categories were defined and the clinical records for patients were collected: sex, age, presence of oxyphilic cells, diameter of the tumour, presence of Hashimoto disease, aggregate amount of clinical and ultrasonographic features of malignancy according to ATA. RESULTS: Results: In 18 patients (16,3%) thyroid cancer occurred. Most frequent subtype turned out to be papillary cancer (66,6%). In group of benign lesion (92 patients) predominance of follicular adenoma was disclosed - (49%). Age, gender, tumour diameter, aggregate amount of clinical and ultrasonografic factors, presence of Hashimoto disease and fine needle aspiration biopsy result suspicious for Hurthle cell neoplasm did not correspond to increased risk of malignancy. CONCLUSION: Conclusions: In patients with FNAB results classified as Bethesda tier IV there are no reliable clinical features associated with low risk of malignancy and surgery should be consider in every case as most appropriate manner to exclude thyroid cancer .
Assuntos
Adenocarcinoma Folicular , Neoplasias da Glândula Tireoide , Nódulo da Glândula Tireoide , Biópsia por Agulha Fina , Humanos , Fatores de RiscoRESUMO
BACKGROUND: Diffusion-weighted imaging (DWI) can increase breast MRI diagnostic specificity due to the tendency of malignancies to restrict diffusion. Diffusion tensor imaging (DTI) provides further information over conventional DWI regarding diffusion directionality and anisotropy. Our study evaluates DTI features of suspicious breast lesions detected on MRI to determine the added diagnostic value of DTI for breast imaging. METHODS: With IRB approval, we prospectively enrolled patients over a 3-year period who had suspicious (BI-RADS category 4 or 5) MRI-detected breast lesions with histopathological results. Patients underwent multiparametric 3 T MRI with dynamic contrast-enhanced (DCE) and DTI sequences. Clinical factors (age, menopausal status, breast density, clinical indication, background parenchymal enhancement) and DCE-MRI lesion parameters (size, type, presence of washout, BI-RADS category) were recorded prospectively by interpreting radiologists. DTI parameters (apparent diffusion coefficient [ADC], fractional anisotropy [FA], axial diffusivity [λ1], radial diffusivity [(λ2 + λ3)/2], and empirical difference [λ1 - λ3]) were measured retrospectively. Generalized estimating equations (GEE) and least absolute shrinkage and selection operator (LASSO) methods were used for univariate and multivariate logistic regression, respectively. Diagnostic performance was internally validated using the area under the curve (AUC) with bootstrap adjustment. RESULTS: The study included 238 suspicious breast lesions (95 malignant, 143 benign) in 194 women. In univariate analysis, lower ADC, axial diffusivity, and radial diffusivity were associated with malignancy (OR = 0.37-0.42 per 1-SD increase, p < 0.001 for each), as was higher FA (OR = 1.45, p = 0.007). In multivariate analysis, LASSO selected only ADC (OR = 0.41) as a predictor for a DTI-only model, while both ADC (OR = 0.41) and FA (OR = 0.88) were selected for a model combining clinical and imaging parameters. Post-hoc analysis revealed varying association of FA with malignancy depending on the lesion type. The combined model (AUC = 0.81) had a significantly better performance than Clinical/DCE-MRI-only (AUC = 0.76, p < 0.001) and DTI-only (AUC = 0.75, p = 0.002) models. CONCLUSIONS: DTI significantly improves diagnostic performance in multivariate modeling. ADC is the most important diffusion parameter for distinguishing benign and malignant breast lesions, while anisotropy measures may help further characterize tumor microstructure and microenvironment.
Assuntos
Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/patologia , Mama/diagnóstico por imagem , Imagem de Tensor de Difusão , Aumento da Imagem/métodos , Adulto , Idoso , Idoso de 80 Anos ou mais , Mama/patologia , Meios de Contraste , Diagnóstico Diferencial , Imagem de Difusão por Ressonância Magnética , Feminino , Humanos , Interpretação de Imagem Assistida por Computador , Pessoa de Meia-Idade , Estudos Prospectivos , Curva ROC , Microambiente Tumoral , Adulto JovemRESUMO
There is strong demand for real-time suspicious tracking across multiple cameras in intelligent video surveillance for public areas, such as universities, airports and factories. Most criminal events show that the nature of suspicious behavior are carried out by un-known people who try to hide themselves as much as possible. Previous learning-based studies collected a large volume data set to train a learning model to detect humans across multiple cameras but failed to recognize newcomers. There are also several feature-based studies aimed to identify humans within-camera tracking. It would be very difficult for those methods to get necessary feature information in multi-camera scenarios and scenes. It is the purpose of this study to design and implement a suspicious tracking mechanism across multiple cameras based on correlation filters, called suspicious tracking across multiple cameras based on correlation filters (STAM-CCF). By leveraging the geographical information of cameras and YOLO object detection framework, STAM-CCF adjusts human identification and prevents errors caused by information loss in case of object occlusion and overlapping for within-camera tracking cases. STAM-CCF also introduces a camera correlation model and a two-stage gait recognition strategy to deal with problems of re-identification across multiple cameras. Experimental results show that the proposed method performs well with highly acceptable accuracy. The evidences also show that the proposed STAM-CCF method can continuously recognize suspicious behavior within-camera tracking and re-identify it successfully across multiple cameras.
RESUMO
Learners preferentially interpret novel nouns at the basic level ('dog') rather than at a more narrow level ('Labrador'). This 'basic-level bias' is mitigated by statistics: children and adults are more likely to interpret a novel noun at a more narrow label if they witness 'a suspicious coincidence' - the word applied to three exemplars of the same narrow category. Independent work has found that exemplar typicality influences learners' inferences and category learning. We bring these lines of work together to investigate whether the content (typicality) of a single exemplar affects the level of interpretation of words and whether an atypicality effect interacts with input statistics. Results demonstrate that both four- to five-year-olds and adults tend to assign a narrower interpretation to a word if it is exemplified by an atypical category member. This atypicality effect is roughly as strong as, and independent of, the suspicious coincidence effect, which is replicated.
RESUMO
In most proteome mass spectrometry experiments, more than half of the mass spectra cannot be identified, mainly because of various modifications. The open search strategy allows for a larger precursor tolerance to utilize more spectra, especially those with post-translational modifications; however, thorough quality control based on independent information is lacking. Here, we used the "Suspicious Discovery Rate (SDR)" based on translatome sequencing (RNC-seq) as an independent source to reference the proteome open search results in steady-state cells. We found that the open search strategy increased the spectra utilization with the cost of increased suspicious identifications that lack translation evidence. We further found that restricting the peptide FDR below 0.1% efficiently controlled the suspicious identifications of open search methods and thus enhanced the confidence of the peptide identification with modifications comparable to the level of the traditional narrow window search. We then demonstrated the successful and validated identification of 27 single amino acid variations from the spectra of two cell lines using the open search strategy without a predefined database. These results validated the proper use of open search methods for higher-quality proteome identifications with information on post-translational modifications and single amino acid polymorphisms.
Assuntos
Algoritmos , Espectrometria de Massas/métodos , Peptídeos/química , Processamento de Proteína Pós-Traducional , Proteômica/métodos , Sequência de Aminoácidos , Aminoácidos , Linhagem Celular Tumoral , Células HeLa , Humanos , Peptídeos/classificação , Peptídeos/isolamento & purificação , Biossíntese de Proteínas , Proteólise , Proteoma/genética , Proteoma/isolamento & purificação , Proteoma/metabolismo , RNA Mensageiro/genética , RNA Mensageiro/metabolismo , SoftwareRESUMO
OBJECTIVE: The second edition Bethesda System for Reporting Thyroid Cytology estimates 6%-18% malignancy rate of category III (B3) and 10%-40% for category IV (B4) nodules; however, reported malignancy rates have considerable variability among institutions. Use of molecular classifiers (including Afirma Gene Expression Classifier, GEC) can be utilized in management of thyroid nodules. Our objective was to analyse malignancy rates of B3 and B4 nodules and determine clinical outcomes of GEC Benign nodules. METHODS: A retrospective analysis of 2019 thyroid FNAs was performed at the University of Colorado from 2011 to 2015, including molecular, surgical and clinical follow-up. RESULTS: Of 2019 FNAs analysed, 231 (11.4%) were diagnosed as B3 and 80 (4.0%) as B4. GEC was obtained in 54.1% of B3 cases, with nearly half (48.8%) having a Benign result. Surgery was performed in 40.7% B3 cases with a 24.5% malignancy rate, ranging 8%-38% by year. In the B4 group, 52.5% underwent molecular testing with 28.6% as GEC Benign. About 68.8% of B4 cases underwent surgery with a 20% malignancy rate, ranging 0%-42% by year. Seventy-three GEC Benign cases were reviewed: 5 (6.8%) underwent surgery, with none demonstrating malignancy in the target nodule. Size remained stable for most GEC Benign nodules: 75.9% (B3) and 71.4% (B4) with no malignancy on repeat FNA. CONCLUSIONS: Our 5-year review demonstrated that malignancy rates of B3 and B4 nodules showed year-to-year variability. We suggest that clinicians use a multi-year average of their institution's malignancy rates to optimally manage patients. Follow-up for GEC Benign cases thus far supports their indolent nature.
RESUMO
Multiple search engines based on various models have been developed to search MS/MS spectra against a reference database, providing different results for the same data set. How to integrate these results efficiently with minimal compromise on false discoveries is an open question due to the lack of an independent, reliable, and highly sensitive standard. We took the advantage of the translating mRNA sequencing (RNC-seq) result as a standard to evaluate the integration strategies of the protein identifications from various search engines. We used seven mainstream search engines (Andromeda, Mascot, OMSSA, X!Tandem, pFind, InsPecT, and ProVerB) to search the same label-free MS data sets of human cell lines Hep3B, MHCCLM3, and MHCC97H from the Chinese C-HPP Consortium for Chromosomes 1, 8, and 20. As expected, the union of seven engines resulted in a boosted false identification, whereas the intersection of seven engines remarkably decreased the identification power. We found that identifications of at least two out of seven engines resulted in maximizing the protein identification power while minimizing the ratio of suspicious/translation-supported identifications (STR), as monitored by our STR index, based on RNC-Seq. Furthermore, this strategy also significantly improves the peptides coverage of the protein amino acid sequence. In summary, we demonstrated a simple strategy to significantly improve the performance for shotgun mass spectrometry by protein-level integrating multiple search engines, maximizing the utilization of the current MS spectra without additional experimental work.