RESUMO
Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead to less output pixel interdependence producing incomplete and unrealistic segmentation results. In this paper, we present a fully automatic deep learning method for robust medical image segmentation by formulating the segmentation problem as a recurrent framework using two systems. The first one is a forward system of an encoder-decoder CNN that predicts the segmentation result from the input image. The predicted probabilistic output of the forward system is then encoded by a fully convolutional network (FCN)-based context feedback system. The encoded feature space of the FCN is then integrated back into the forward system's feed-forward learning process. Using the FCN-based context feedback loop allows the forward system to learn and extract more high-level image features and fix previous mistakes, thereby improving prediction accuracy over time. Experimental results, performed on four different clinical datasets, demonstrate our method's potential application for single and multi-structure medical image segmentation by outperforming the state of the art methods. With the feedback loop, deep learning methods can now produce results that are both anatomically plausible and robust to low contrast images. Therefore, formulating image segmentation as a recurrent framework of two interconnected networks via context feedback loop can be a potential method for robust and efficient medical image analysis.
Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , RetroalimentaçãoRESUMO
Temporal bone CT-scan is a prerequisite in most surgical procedures concerning the ear such as cochlear implants. The 3D vision of inner ear structures is crucial for diagnostic and surgical preplanning purposes. Since clinical CT-scans are acquired at relatively low resolutions, improved performance can be achieved by registering patient-specific CT images to a high-resolution inner ear model built from accurate 3D segmentations based on micro-CT of human temporal bone specimens. This paper presents a framework based on convolutional neural network for human inner ear segmentation from micro-CT images which can be used to build such a model from an extensive database. The proposed approach employs an auto-context based cascaded 2D U-net architecture with 3D connected component refinement to segment the cochlear scalae, semicircular canals, and the vestibule. The system was formulated on a data set composed of 17 micro-CT from public Hear-EU dataset. A Dice coefficient of 0.90 and Hausdorff distance of 0.74 mm were obtained. The system yielded precise and fast automatic inner-ear segmentations.
Assuntos
Redes Neurais de Computação , Tomografia Computadorizada por Raios X/métodos , Orelha Interna/diagnóstico por imagem , Humanos , Osso Temporal/diagnóstico por imagemRESUMO
PURPOSE: This paper addresses the detection of the clinical target volume (CTV) in transrectal ultrasound (TRUS) image-guided intraoperative for permanent prostate brachytherapy. Developing a robust and automatic method to detect the CTV on intraoperative TRUS images is clinically important to have faster and reproducible interventions that can benefit both the clinical workflow and patient health. METHODS: We present a multi-task deep learning method for an automatic prostate CTV boundary detection in intraoperative TRUS images by leveraging both the low-level and high-level (prior shape) information. Our method includes a channel-wise feature calibration strategy for low-level feature extraction and learning-based prior knowledge modeling for prostate CTV shape reconstruction. It employs CTV shape reconstruction from automatically sampled boundary surface coordinates (pseudo-landmarks) to detect the low-contrast and noisy regions across the prostate boundary, while being less biased from shadowing, inherent speckles, and artifact signals from the needle and implanted radioactive seeds. RESULTS: The proposed method was evaluated on a clinical database of 145 patients who underwent permanent prostate brachytherapy under TRUS guidance. Our method achieved a mean accuracy of [Formula: see text] and a mean surface distance error of [Formula: see text]. Extensive ablation and comparison studies show that our method outperformed previous deep learning-based methods by more than 7% for the Dice similarity coefficient and 6.9 mm reduced 3D Hausdorff distance error. CONCLUSION: Our study demonstrates the potential of shape model-based deep learning methods for an efficient and accurate CTV segmentation in an ultrasound-guided intervention. Moreover, learning both low-level features and prior shape knowledge with channel-wise feature calibration can significantly improve the performance of deep learning methods in medical image segmentation.
Assuntos
Braquiterapia , Aprendizado Profundo , Diagnóstico por Computador/métodos , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/radioterapia , Ultrassonografia , Algoritmos , Artefatos , Humanos , Masculino , Modelos Estatísticos , Próstata/diagnóstico por imagem , Reprodutibilidade dos Testes , Fluxo de TrabalhoRESUMO
PURPOSE: To achieve accurate image segmentation, which is the first critical step in medical image analysis and interventions, using deep neural networks seems a promising approach provided sufficiently large and diverse annotated data from experts. However, annotated datasets are often limited because it is prone to variations in acquisition parameters and require high-level expert's knowledge, and manually labeling targets by tracing their contour is often laborious. Developing fast, interactive, and weakly supervised deep learning methods is thus highly desirable. METHODS: We propose a new efficient deep learning method to accurately segment targets from images while generating an annotated dataset for deep learning methods. It involves a generative neural network-based prior-knowledge prediction from pseudo-contour landmarks. The predicted prior knowledge (i.e., contour proposal) is then refined using a convolutional neural network that leverages the information from the predicted prior knowledge and the raw input image. Our method was evaluated on a clinical database of 145 intraoperative ultrasound and 78 postoperative CT images of image-guided prostate brachytherapy. It was also evaluated on a cardiac multi-structure segmentation from 450 2D echocardiographic images. RESULTS: Experimental results show that our model can segment the prostate clinical target volume in 0.499 s (i.e., 7.79 milliseconds per image) with an average Dice coefficient of 96.9 ± 0.9% and 95.4 ± 0.9%, 3D Hausdorff distance of 4.25 ± 4.58 and 5.17 ± 1.41 mm, and volumetric overlap ratio of 93.9 ± 1.80% and 91.3 ± 1.70 from TRUS and CT images, respectively. It also yielded an average Dice coefficient of 96.3 ± 1.3% on echocardiographic images. CONCLUSIONS: We proposed and evaluated a fast, interactive deep learning method for accurate medical image segmentation. Moreover, our approach has the potential to solve the bottleneck of deep learning methods in adapting to inter-clinical variations and speed up the annotation processes.
Assuntos
Aprendizado Profundo , Processamento de Imagem Assistida por Computador/métodos , Redes Neurais de Computação , Próstata/diagnóstico por imagem , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/radioterapia , Braquiterapia , Bases de Dados Factuais , Diagnóstico por Computador/métodos , Ecocardiografia , Humanos , Masculino , Variações Dependentes do Observador , Reconhecimento Automatizado de Padrão , Reprodutibilidade dos Testes , Tomografia Computadorizada por Raios X , UltrassonografiaRESUMO
PURPOSE: To evaluate the dose distribution of additional radioactive seeds implanted during salvage permanent prostate implant (sPPI) after a primary permanent prostate implant (pPPI). METHODS AND MATERIALS: Patients with localized prostate cancer were primarily implanted with iodine-125 seeds and had a dosimetric assessment based on day 30 postimplant CT (CT1). After an average of 6 years, these patients underwent sPPI followed by the same CT-based evaluation of dosimetry (CT2). Radioactive seeds on each CT were detected. The detected primary seeds on CT1 and CT2 were registered and then removed from CT2 referred as a modified CT2 (mCT2). Dosimetry evaluations (D90 and V100) of sPPI were performed with dedicated planning software on CT2 and mCT2. Indeed, prostate volume, D90, and V100 differences between CT2 and either CT1 or mCT2 were calculated, and values were expressed as mean (standard deviation). RESULTS: The mean prostate volume difference between sPPI and pPPI over the 6 patients was 9.85 (7.32) cm3. The average D90 and V100 assessed on CT2 were 486.5 Gy (58.9) and 100.0% (0.0), respectively, whereas it was 161.3 Gy (47.5) and 77.3% (25.2) on mCT2 (p = 0.031 each time). The average D90 the day of sPPI [145.4 Gy (11.2)] was not significantly different from that observed on mCT2 (p = 0.56). CONCLUSION: Postimplant D90 and V100 of sPPI after pPPI can be estimated on CT images after removing the primary seeds.