Nowadays, lung cancer assessment is a complex and tedious task mainly performed by radiological visual inspection of suspicious pulmonary nodules, using computed tomography (CT) scan images taken to patients over time.
Several computational tools relying on conventional artificial intelligence and computer vision algorithms have been proposed for supporting lung cancer detection and classification. These solutions mostly rely on the analysis of individual lung CT images of patients and on the use of hand-crafted image descriptors. Unfortunately, this makes them unable to cope with the complexity and variability of the problem. Recently, the advent of deep learning has led to a major break-through in the medical image domain, outperforming conventional approaches. Despite recent promising achievements in nodule detection, segmentation, and lung cancer classification, radiologists are still reluctant to use these solutions in their day-to-day clinical practice. One of the main reasons is that current solutions do not provide support to automatic analysis of the temporal evolution of lung tumours. The difficulty to collect and annotate longitudinal lung CT cases to train models may partially explain the lack of deep learning studies that address this issue. In this dissertation, we investigate how to automatically provide lung cancer assessment through deep learning algorithms and computer vision pipelines, especially taking into consideration the temporal evolution of the pulmonary nodules. To this end, our first goal consisted on obtaining accurate methods for lung cancer assessment (diagnostic ground truth) based on individual lung CT images. Since these types of labels are expensive and difficult to collect (e.g. usually after biopsy), we proposed to train different deep learning models, based on 3D convolutional neural networks (CNN), to predict nodule malignancy based on radiologist visual inspection annotations (which are reasonable to obtain). These classifiers were built based on ground truth consisting of the nodule malignancy, the position and the size of the nodules to classify. Next, we evaluated different ways of synthesizing the knowledge embedded by the nodule malignancy neural network, into an end-to-end pipeline aimed to detect pulmonary nodules and predict lung cancer at the patient level, given a lung CT image. The positive results confirmed the convenience of using CNNs for modelling nodule malignancy, according to radiologists, for the automatic prediction of lung cancer.
Next, we focused on the analysis of lung CT image series. Thus, we first faced the problem of automatically re-identifying pulmonary nodules from different lung CT scans of the same patient. To do this, we present a novel method based on a Siamese neural network (SNN) to rank similarity between nodules, overpassing the need for image registration. This change of paradigm avoided introducing potentially erroneous image deformations and provided computationally faster results. Different configurations of the SNN were examined, including the application of transfer learning, using different loss functions, and the combination of several feature maps of different network levels. This method obtained state-of-the-art performances for nodule matching, both in an isolated manner and embedded in an end-to-end nodule growth detection pipeline.
Afterwards, we moved to the core problem of supporting radiologists in the longitudinal management of lung cancer. For this purpose, we created a novel end-to-end deep learning pipeline, composed of four stages that completely automatize from the detection of nodules to the classification of cancer, through the detection of growth in the nodules. In addition, the pipeline integrated a novel approach for nodule growth detection, which relies on a recent hierarchical probabilistic segmentation network adapted to report uncertainty estimates. Also, a second novel method was introduced for lung cancer nodule classification, integrating into a two stream 3D-CNN the estimated nodule malignancy probabilities derived from a pre-trained nodule malignancy network. The pipeline was evaluated in a longitudinal cohort and the reported outcomes (i.e. nodule detection, re-identification, growth quantification, and malignancy prediction) were comparable with state-of-the-art work, focused on solving one or a few of the functionalities of our pipeline.
Thereafter, we also investigated how to help clinicians to prescribe more accurate tumour treatments and surgical planning. Thus, we created a novel method to forecast nodule growth given a single image of the nodule. Particularly, the method relied on a hierarchical, probabilistic and generative deep neural network able to produce multiple consistent future segmentations of the nodule at a given time. To do this, the network learned to model the multimodal posterior distribution of future lung tumour segmentations by using variational inference and injecting the posterior latent features. Eventually, by applying Monte-Carlo sampling on the outputs of the trained network, we estimated the expected tumour growth mean and the uncertainty associated with the prediction.
Although further evaluation in a larger cohort would be highly recommended, the proposed methods reported accurate results to adequately support the radiological workflow of pulmonary nodule follow-up. Beyond this specific application, the outlined innovations, such as the methods for integrating CNNs into computer vision pipelines, the re-identification of suspicious regions over time based on SNNs, without the need to warp the inherent image structure, or the proposed deep generative and probabilistic network to model tumour growth considering ambiguous images and label uncertainty, they could be easily applicable to other types of cancer (e.g. pancreas), clinical diseases (e.g. Covid-19) or medical applications (e.g. therapy follow-up).
© 2001-2024 Fundación Dialnet · Todos los derechos reservados