Deep convolutional neural networks for the automated segmentation of malignant pleural mesothelioma on computed tomography scans

Convolutional Neural Networks for Segmentation of Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance)

The purpose of this study was to evaluate the impact of probability map threshold on pleural mesothelioma (PM) tumor delineations generated using a convolutional neural network (CNN). One hundred eighty-six CT scans from 48 PM patients were segmented by a VGG16/U-Net CNN. A radiologist modified the contours generated at a 0.5 probability threshold. Percent difference of tumor volume and overlap using the Dice Similarity Coefficient (DSC) were compared between the reference standard provided by the radiologist and CNN outputs for thresholds ranging from 0.001 to 0.9. CNN-derived contours consistently yielded smaller tumor volumes than radiologist contours. Reducing the probability threshold from 0.5 to 0.01 decreased the absolute percent volume difference, on average, from 42.93% to 26.60%. Median and mean DSC ranged from 0.57 to 0.59, with a peak at a threshold of 0.2; no distinct threshold was found for percent volume difference. The CNN exhibited deficiencies with specific disease presentations, such as severe pleural effusion or disease in the pleural fissure. No single output threshold in the CNN probability maps was optimal for both tumor volume and DSC. This study emphasized the importance of considering both figures of merit when evaluating deep learning-based tumor segmentations across probability thresholds. This work underscores the need to simultaneously assess tumor volume and spatial overlap when evaluating CNN performance. While automated segmentations may yield comparable tumor volumes to that of the reference standard, the spatial region delineated by the CNN at a specific threshold is equally important.

Convolutional Neural Networks for Segmentation of Malignant Pleural Mesothelioma: Analysis of Probability Map Thresholds (CALGB 30901, Alliance)

Malignant pleural mesothelioma (MPM) is the most common form of malignant mesothelioma, with exposure to asbestos being the primary cause of the disease. To assess response to treatment, tumor measurements are acquired and evaluated based on a patient's longitudinal computed tomography (CT) scans. Tumor volume, however, is the more accurate metric for assessing tumor burden and response. Automated segmentation methods using deep learning can be employed to acquire volume, which otherwise is a tedious task performed manually. The deep learning-based tumor volume and contours can then be compared with a standard reference to assess the robustness of the automated segmentations. The purpose of this study was to evaluate the impact of probability map threshold on MPM tumor delineations generated using a convolutional neural network (CNN). Eighty-eight CT scans from 21 MPM patients were segmented by a VGG16/U-Net CNN. A radiologist modified the contours generated at a 0.5 probability threshold. Percent difference of tumor volume and overlap using the Dice Similarity Coefficient (DSC) were compared between the standard reference provided by the radiologist and CNN outputs for thresholds ranging from 0.001 to 0.9. CNN annotations consistently yielded smaller tumor volumes than radiologist contours. Reducing the probability threshold from 0.5 to 0.1 decreased the absolute percent volume difference, on average, from 43.96% to 24.18%. Median and mean DSC ranged from 0.58 to 0.60, with a peak at a threshold of 0.5; no distinct threshold was found for percent volume difference. The CNN exhibited deficiencies with specific disease presentations, such as severe pleural effusion or disease in the pleural fissure. No single output threshold in the CNN probability maps was optimal for both tumor volume and DSC. This study emphasized the importance of considering both figures of merit when evaluating deep learning-based tumor segmentations across probability thresholds. This work underscores the need to simultaneously assess tumor volume and spatial overlap when evaluating CNN performance. While automated segmentations may yield comparable tumor volumes to that of the reference standard, the spatial region delineated by the CNN at a specific threshold is equally important.

ERS International Congress 2021: highlights from Assembly 8 Thoracic Surgery and Lung Transplantation

The thoracic surgery and lung transplantation assembly of the European Respiratory Society (ERS) is delighted to present the highlights from the 2021 International ERS Congress. We have selected four sessions that discussed recent advances across a wide range of topics: including digital health surveillance in thoracic surgery, emerging concepts in pulmonary metastasectomy, advances in mesothelioma care, and novel developments in lung graft allocation and monitoring. The sessions are summarised by early career members in close collaboration with the assembly faculty. We aim to give the reader an update on the highlights of the conference in the fields of thoracic surgery and lung transplantation.

New Updates of the Imaging Role in Diagnosis, Staging, and Response Treatment of Malignant Pleural Mesothelioma

Malignant pleural mesothelioma is a rare neoplasm with poor prognosis. CT is the first imaging technique used for diagnosis, staging, and assessment of therapy response. Although, CT has intrinsic limitations due to low soft tissue contrast and the current staging system as well as criteria for evaluating response, it does not consider the complex growth pattern of this tumor. Computer-based methods have proven their potentiality in diagnosis, staging, prognosis, and assessment of therapy response; moreover, computer-based methods can make feasible tasks like segmentation that would otherwise be impracticable. MRI, thanks to its high soft tissue contrast evaluation of contrast enhancement and through diffusion-weighted-images, could replace CT in many clinical settings.

A review of deep learning based methods for medical image multi-organ segmentation

Deep learning has revolutionized image processing and achieved the-state-of-art performance in many medical image segmentation tasks. Many deep learning-based methods have been published to segment different parts of the body for different medical applications. It is necessary to summarize the current state of development for deep learning in the field of medical image segmentation. In this paper, we aim to provide a comprehensive review with a focus on multi-organ image segmentation, which is crucial for radiotherapy where the tumor and organs-at-risk need to be contoured for treatment planning. We grouped the surveyed methods into two broad categories which are 'pixel-wise classification' and 'end-to-end segmentation'. Each category was divided into subgroups according to their network design. For each type, we listed the surveyed works, highlighted important contributions and identified specific challenges. Following the detailed review, we discussed the achievements, shortcomings and future potentials of each category. To enable direct comparison, we listed the performance of the surveyed works that used thoracic and head-and-neck benchmark datasets.

PleThora: Pleural effusion and thoracic cavity segmentations in diseased lungs for benchmarking chest CT processing pipelines

This manuscript describes a dataset of thoracic cavity segmentations and discrete pleural effusion segmentations we have annotated on 402 computed tomography (CT) scans acquired from patients with non-small cell lung cancer. The segmentation of these anatomic regions precedes fundamental tasks in image analysis pipelines such as lung structure segmentation, lesion detection, and radiomics feature extraction. Bilateral thoracic cavity volumes and pleural effusion volumes were manually segmented on CT scans acquired from The Cancer Imaging Archive "NSCLC Radiomics" data collection. Four hundred and two thoracic segmentations were first generated automatically by a U-Net based algorithm trained on chest CTs without cancer, manually corrected by a medical student to include the complete thoracic cavity (normal, pathologic, and atelectatic lung parenchyma, lung hilum, pleural effusion, fibrosis, nodules, tumor, and other anatomic anomalies), and revised by a radiation oncologist or a radiologist. Seventy-eight pleural effusions were manually segmented by a medical student and revised by a radiologist or radiation oncologist. Interobserver agreement between the radiation oncologist and radiologist corrections was acceptable. All expert-vetted segmentations are publicly available in NIfTI format through The Cancer Imaging Archive at https://doi.org/10.7937/tcia.2020.6c7y-gq39. Tabular data detailing clinical and technical metadata linked to segmentation cases are also available. Thoracic cavity segmentations will be valuable for developing image analysis pipelines on pathologic lungs - where current automated algorithms struggle most. In conjunction with gross tumor volume segmentations already available from "NSCLC Radiomics," pleural effusion segmentations may be valuable for investigating radiomics profile differences between effusion and primary tumor or training algorithms to discriminate between them.

Deep learning-based segmentation of malignant pleural mesothelioma tumor on computed tomography scans: application to scans demonstrating pleural effusion

Tumor volume is a topic of interest for the prognostic assessment, treatment response evaluation, and staging of malignant pleural mesothelioma. Many mesothelioma patients present with, or develop, pleural fluid, which may complicate the segmentation of this disease. Deep convolutional neural networks (CNNs) of the two-dimensional U-Net architecture were trained for segmentation of tumor in the left and right hemithoraces, with the networks initialized through layers pretrained on ImageNet. Networks were trained on a dataset of 5230 axial sections from 154 CT scans of 126 mesothelioma patients. A test set of 94 CT sections from 34 patients, who all presented with both tumor and pleural effusion, in addition to a more general test set of 130 CT sections from 43 patients, were used to evaluate segmentation performance of the deep CNNs. The Dice similarity coefficient (DSC), average Hausdorff distance, and bias in predicted tumor area were calculated through comparisons with radiologist-provided tumor segmentations on the test sets. The present method achieved a median DSC of 0.690 on the tumor and effusion test set and achieved significantly higher performance on both test sets when compared with a previous deep learning-based segmentation method for mesothelioma.

Imaging in pleural mesothelioma: A review of the 14th International Conference of the International Mesothelioma Interest Group

Mesothelioma patients rely on the information their clinical team obtains from medical imaging. Whether x-ray-based computed tomography (CT) or magnetic resonance imaging (MRI) based on local magnetic fields within a patient's tissues, different modalities generate images with uniquely different appearances and information content due to the physical differences of the image-acquisition process. Researchers are developing sophisticated ways to extract a greater amount of the information contained within these images. This paper summarizes the imaging-based research presented orally at the 2018 International Conference of the International Mesothelioma Interest Group (iMig) in Ottawa, Ontario, Canada, held May 2-5, 2018. Presented topics included advances in the imaging of preclinical mesothelioma models to inform clinical therapeutic strategies, optimization of the time delay between contrast administration and image acquisition for maximized enhancement of mesothelioma tumor on CT, an investigation of image-based criteria for clinical tumor and nodal staging of mesothelioma by contrast-enhanced CT, an investigation of methods for the extraction of mesothelioma tumor volume from MRI and the association of volume with patient survival, the use of deep learning for mesothelioma tumor segmentation in CT, and an evaluation of CT-based radiomics for the prognosis of mesothelioma patient survival.