RESUMO
This prospective single-center study enrolled 50 women with 51 contrast-enhanced mammography (CEM)-enhancing lesions that lacked a sonographic or mammographic correlate. Trial participants underwent CEM-guided biopsy. Biopsy was technically successful for 46 lesions and was not performed for five nonvisualized lesions (all nonmass enhancement), yielding a cancellation rate of 9.8%. Mean biopsy time was 16.6 minutes. All biopsies revealed concordant pathology (25 benign, 10 high-risk, 11 malignant). No non-visualized or benign lesion yielded malignancy at follow-up.
Assuntos
Neoplasias da Mama , Mama , Feminino , Humanos , Biópsia , Mama/patologia , Neoplasias da Mama/diagnóstico por imagem , Neoplasias da Mama/patologia , Biópsia Guiada por Imagem , Mamografia , Estudos Prospectivos , UltrassonografiaRESUMO
Automated quantitative measurement of the spine (i.e., multiple indices estimation of heights, widths, areas, and so on for the vertebral body and disc) plays a significant role in clinical spinal disease diagnoses and assessments, such as osteoporosis, intervertebral disc degeneration, and lumbar disc herniation, yet still an unprecedented challenge due to the variety of spine structure and the high dimensionality of indices to be estimated. In this paper, we propose a novel cascade amplifier regression network (CARN) with manifold regularization including local structure-preserved manifold regularization (LSPMR) and adaptive local shape-constrained manifold regularization (ALSCMR), to achieve accurate direct automated multiple indices estimation. The CARN architecture is composed of a cascade amplifier network (CAN) for expressive feature embedding and a linear regression model for multiple indices estimation. The CAN produces an expressive feature embedding by cascade amplifier units (AUs), which are used for selective feature reuse by stimulating effective feature and suppressing redundant feature during propagating feature map between adjacent layers. During training, the LSPMR is employed to obtain discriminative feature embedding by preserving the local geometric structure of the latent feature space similar to the target output manifold. The ALSCMR is utilized to alleviate overfitting and generate realistic estimation by learning the multiple indices distribution. Experiments on T1-weighted MR images of 215 subjects and T2-weighted MR images of 20 subjects show that the proposed approach achieves impressive performance with mean absolute errors of 1.22⯱â¯1.04â¯mm and 1.24⯱â¯1.07â¯mm for the 30 lumbar spinal indices estimation of the T1-weighted and T2-weighted spinal MR images respectively. The proposed method has great potential in clinical spinal disease diagnoses and assessments.
Assuntos
Processamento de Imagem Assistida por Computador/métodos , Imageamento por Ressonância Magnética/métodos , Reconhecimento Automatizado de Padrão/métodos , Doenças da Coluna Vertebral/diagnóstico por imagem , Coluna Vertebral/diagnóstico por imagem , Idoso , Aprendizado Profundo , Feminino , Humanos , Masculino , Pessoa de Meia-IdadeRESUMO
Pathogenesis-based diagnosis is a key step to prevent and control lumbar neural foraminal stenosis (LNFS). It conducts both early diagnosis and comprehensive assessment by drawing crucial pathological links between pathogenic factors and LNFS. Automated pathogenesis-based diagnosis would simultaneously localize and grade multiple spinal organs (neural foramina, vertebrae, intervertebral discs) to diagnose LNFS and discover pathogenic factors. The automated way facilitates planning optimal therapeutic schedules and relieving clinicians from laborious workloads. However, no successful work has been achieved yet due to its extreme challenges since 1) multiple targets: each lumbar spine has at least 17 target organs, 2) multiple scales: each type of target organ has structural complexity and various scales across subjects, and 3) multiple tasks, i.e., simultaneous localization and diagnosis of all lumbar organs, are extremely difficult than individual tasks. To address these huge challenges, we propose a deep multiscale multitask learning network (DMML-Net) integrating a multiscale multi-output learning and a multitask regression learning into a fully convolutional network. 1) DMML-Net merges semantic representations to reinforce the salience of numerous target organs. 2) DMML-Net extends multiscale convolutional layers as multiple output layers to boost the scale-invariance for various organs. 3) DMML-Net joins a multitask regression module and a multitask loss module to prompt the mutual benefit between tasks. Extensive experimental results demonstrate that DMML-Net achieves high performance (0.845 mean average precision) on T1/T2-weighted MRI scans from 200 subjects. This endows our method an efficient tool for clinical LNFS diagnosis.
Assuntos
Vértebras Lombares/diagnóstico por imagem , Aprendizado de Máquina , Comportamento Multitarefa , Redes Neurais de Computação , Raízes Nervosas Espinhais/diagnóstico por imagem , Estenose Espinal/diagnóstico por imagem , Idoso , Feminino , Humanos , Degeneração do Disco Intervertebral/diagnóstico por imagem , Masculino , Pessoa de Meia-IdadeRESUMO
Multitarget regression has recently generated intensive popularity due to its ability to simultaneously solve multiple regression tasks with improved performance, while great challenges stem from jointly exploring inter-target correlations and input-output relationships. In this paper, we propose multitarget sparse latent regression (MSLR) to simultaneously model intrinsic intertarget correlations and complex nonlinear input-output relationships in one single framework. By deploying a structure matrix, the MSLR accomplishes a latent variable model which is able to explicitly encode intertarget correlations via -norm-based sparse learning; the MSLR naturally admits a representer theorem for kernel extension, which enables it to flexibly handle highly complex nonlinear input-output relationships; the MSLR can be solved efficiently by an alternating optimization algorithm with guaranteed convergence, which ensures efficient multitarget regression. Extensive experimental evaluation on both synthetic data and six greatly diverse real-world data sets shows that the proposed MSLR consistently outperforms the state-of-the-art algorithms, which demonstrates its great effectiveness for multivariate prediction.
RESUMO
BACKGROUND: There are concerns about which lung to explant during single-lung transplantation (SLT). Traditionally, a quantitative lung perfusion scan (QLPS) is performed, and the better-perfused lung is retained. Occasionally, there is transplantation with graft "side-mismatching," where the less-well-perfused lung is retained. We performed a retrospective study of patients undergoing SLT at our institution to evaluate the effects of side-mismatching (according to the QLPS) on graft performance and outcome. METHODS: We defined graft side-mismatching with a prospectively designed formula using baseline QLPS, and defined patients as either side-matched or side-mismatched. Data on mortality, requirement for cardiopulmonary bypass, relative graft perfusion, lung function and exercise capacity were obtained from institutional databases and patients' files. RESULTS: In a cohort of 114 patients, we defined 97 as having received a side-matched SLT and 17 as having received a side-mismatched graft. After lung transplantation, forced expiratory volume in 1 second (FEV(1)) and exercise capacity improved in both groups (p < 0.001). Patients with mismatched lungs had significantly higher relative graft perfusion post-operatively (p = 0.0012). There was no significant difference between the two groups (matched vs mismatched) in mortality, physiologic parameters and need for cardiopulmonary bypass. CONCLUSIONS: There is no apparent risk to the patient when a side-mismatched lung graft is transplanted. We conclude that side-mismatched lung transplantation appears to be feasible when required.