Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 5 de 5
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
2.
J Vasc Interv Radiol ; 35(5): 780-789.e1, 2024 May.
Artigo em Inglês | MEDLINE | ID: mdl-38355040

RESUMO

PURPOSE: To validate the sensitivity and specificity of a 3-dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) software for lung lesion detection and to establish concordance between AI-generated needle paths and those used in actual biopsy procedures. MATERIALS AND METHODS: This was a retrospective study using computed tomography (CT) scans from 3 hospitals. Inclusion criteria were scans with 1-5 nodules of diameter ≥5 mm; exclusion criteria were poor-quality scans or those with nodules measuring <5mm in diameter. In the lesion detection phase, 2,147 nodules from 219 scans were used to develop and train the deep learning 3D-CNN to detect lesions. The 3D-CNN was validated with 235 scans (354 lesions) for sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. In the path planning phase, Bayesian optimization was used to propose possible needle trajectories for lesion biopsy while avoiding vital structures. Software-proposed needle trajectories were compared with actual biopsy path trajectories from intraprocedural CT scans in 150 patients, with a match defined as an angular deviation of <5° between the 2 trajectories. RESULTS: The model achieved an overall AUC of 97.4% (95% CI, 96.3%-98.2%) for lesion detection, with mean sensitivity of 93.5% and mean specificity of 93.2%. Among the software-proposed needle trajectories, 85.3% were feasible, with 82% matching actual paths and similar performance between supine and prone/oblique patient orientations (P = .311). The mean angular deviation between matching trajectories was 2.30° (SD ± 1.22); the mean path deviation was 2.94 mm (SD ± 1.60). CONCLUSIONS: Segmentation, lesion detection, and path planning for CT-guided lung biopsy using an AI-guided software showed promising results. Future integration with automated robotic systems may pave the way toward fully automated biopsy procedures.


Assuntos
Aprendizado Profundo , Biópsia Guiada por Imagem , Valor Preditivo dos Testes , Software , Tomografia Computadorizada por Raios X , Humanos , Estudos Retrospectivos , Reprodutibilidade dos Testes , Biópsia Guiada por Imagem/métodos , Feminino , Masculino , Pessoa de Meia-Idade , Neoplasias Pulmonares/patologia , Neoplasias Pulmonares/diagnóstico por imagem , Idoso , Interpretação de Imagem Radiográfica Assistida por Computador , Teorema de Bayes , Biópsia por Agulha , Pulmão/diagnóstico por imagem , Pulmão/patologia
3.
Eur J Radiol Open ; 11: 100529, 2023 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-37927530

RESUMO

Objectives: Multiparametric magnetic resonance imaging (mpMRI) surveillance post focal cryotherapy (FT) of prostate cancer is challenging as post treatment artefacts alter mpMRI findings. In this initial experience, we assessed diagnostic performance of mpMRI in detecting clinically significant prostate cancer (csPCa) after FT. Materials and methods: This single-centre phase II prospective clinical trial recruited 28 men with localized csPCa for FT between October 2019 and April 2021. 12-months post FT mpMRI were performed prior to biopsy and sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of all mpMRI positive subjects were analysed. Chi square goodness of fit test correlated biopsy positive PIRADS3 (P3) and PIRADS4/5 lesions with histology grade group. One way ANOVA test assessed performance of ADC values in differentiating csPCa, non csPCa and benign lesions. Results: Sensitivity, specificity, PPV and NPV of mpMRI were 100%, 14.28%, 53.84% and 100% for subjects with histologically proven cancer. Correlation of PIRADS v2.1 scores with histologically proven prostate cancer was statistically significant (p < 0.5). Correlation of P3 lesions with non-csPCa was statistically significant (p < 0.02535). Higher ADC value was associated with benign histology (adjusted odds ratio OR 0.97, 95% confidence interval: 0.94, 0.99) (p = 0.008). Among the malignant lesions, higher ADC value was associated with non-csPCa (adjusted OR: 0.97; 95% CI: 0.95, 0.99) (p = 0.032). Conclusion: mpMRI is highly sensitive in detecting residual cancer. ADC values and PIRADS scores may be of value in differentiating csPCa from non-csPCa with a potential for risk stratification of men requiring re-biopsy versus non-invasive surveillance of remnant prostate.

4.
J Exp Orthop ; 7(1): 77, 2020 Oct 06.
Artigo em Inglês | MEDLINE | ID: mdl-33025241

RESUMO

PURPOSE: The aim of this study was to (1) develop suture techniques in repairing radial meniscal tear; (2) to compare the biomechanical properties of the proposed repair techniques with the conventional double horizontal technique. METHODS: Thirty-six fresh-frozen porcine medial menisci were randomly assigned into four groups and a complete tear was made at the midline of each meniscus. The menisci were subsequently repaired using four different repair techniques: double vertical (DV), double vertical cross (DVX), hybrid composing one vertical and one horizontal stitch, and conventional double horizontal (DH) suture technique with suturing parallel to the tibia plateau. The conventional double horizontal group was the control. The repaired menisci were subjected to cyclic loading followed by the load to failure testing. Gap formation and strength were measured, stiffness was calculated, and mode of failure was recorded. RESULTS: Group differences in gap formation were not statistically significant at 100 cycles (p = .42), 300 cycles (p = .68), and 500 cycles (p = .70). A trend was found toward higher load to failure in DVX (276.8 N, p < .001), DV (241.5 N, p < .001), and Hybrid (237.6 N, p < .001) compared with DH (148.5 N). Stiffness was also higher in DVX (60.7 N/mm, p < .001), DV (55.3 N/mm, p < .01), and Hybrid (52.1 N/mm, p < .01), than DH group (30.5 N/mm). Tissue failure was the only failure mode observed in all specimens. CONCLUSION: Our two proposed vertical suture techniques, as well as the double vertical technique, had superior biomechanical properties than the conventional technique as demonstrated by higher stiffness and higher strength.

5.
J Orthop Surg (Hong Kong) ; 28(1): 2309499019894390, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-31916487

RESUMO

PURPOSE: Concerning the ongoing debate on the effects of continuing aspirin therapy on blood loss in knee arthroplasty, we conducted a retrospective investigation to test the hypothesis that continuation of aspirin prior total knee arthroplasty (TKA) will not cause more blood loss. METHODS: From a database of patients who underwent unilateral TKA between 2011 and 2016, we identified two groups: the aspirin group (patients continued aspirin during perioperative period) and the nonaspirin group (patients had no current or recent history of aspirin usage). We extracted and compared patient demographic information, comorbidity index, baseline serum hemoglobin (Hb), and creatinine level between the two groups. We also compared our primary outcomes, including the total blood loss, transfusion requirement, and length of hospitalization between the two groups. A multivariate logistic regression for analyzing the risk factors of requiring transfusion was performed. RESULTS: We found that apart from preoperative serum creatinine level, there was no difference in the baseline Hb level, perioperative change in Hb, total blood loss, or length of hospitalization between the two groups. The percentage of transfusion utilization was also comparable between the two groups. Our regression analysis shows that the risk of requiring transfusion after TKA is not significantly associated with patients taking aspirin therapy before operation. CONCLUSION: Patients who underwent TKA with continuation of low-dose aspirin did not result in more blood loss. Current blood loss management has provided sufficient reduction of blood loss to accommodate aspirin therapy perioperatively. We suggest that it is safe to continue aspirin prior to TKA.


Assuntos
Artroplastia do Joelho/métodos , Aspirina/efeitos adversos , Perda Sanguínea Cirúrgica/estatística & dados numéricos , Osteoartrite do Joelho/cirurgia , Hemorragia Pós-Operatória/epidemiologia , Idoso , Aspirina/administração & dosagem , Relação Dose-Resposta a Droga , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Inibidores da Agregação Plaquetária/administração & dosagem , Inibidores da Agregação Plaquetária/efeitos adversos , Estudos Retrospectivos , Fatores de Risco
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...