Artificial intelligence (AI)-assisted chest computer tomography (CT) insights: a study on intensive care unit (ICU) admittance trends in 78 coronavirus disease 2019 (COVID-19) patients

Background

The global coronavirus disease 2019 (COVID-19) pandemic has posed substantial challenges for healthcare systems, notably the increased demand for chest computed tomography (CT) scans, which lack automated analysis. Our study addresses this by utilizing artificial intelligence-supported automated computer analysis to investigate lung involvement distribution and extent in COVID-19 patients. Additionally, we explore the association between lung involvement and intensive care unit (ICU) admission, while also comparing computer analysis performance with expert radiologists' assessments.

Methods

A total of 81 patients from an open-source COVID database with confirmed COVID-19 infection were included in the study. Three patients were excluded. Lung involvement was assessed in 78 patients using CT scans, and the extent of infiltration and collapse was quantified across various lung lobes and regions. The associations between lung involvement and ICU admission were analysed. Additionally, the computer analysis of COVID-19 involvement was compared against a human rating provided by radiological experts.

Results

The results showed a higher degree of infiltration and collapse in the lower lobes compared to the upper lobes (P<0.05). No significant difference was detected in the COVID-19-related involvement of the left and right lower lobes. The right middle lobe demonstrated lower involvement compared to the right lower lobes (P<0.05). When examining the regions, significantly more COVID-19 involvement was found when comparing the posterior vs. the anterior halves and the lower vs. the upper half of the lungs. Patients, who required ICU admission during their treatment exhibited significantly higher COVID-19 involvement in their lung parenchyma according to computer analysis, compared to patients who remained in general wards. Patients with more than 40% COVID-19 involvement were almost exclusively treated in intensive care. A high correlation was observed between computer detection of COVID-19 affections and the rating by radiological experts.

Conclusions

The findings suggest that the extent of lung involvement, particularly in the lower lobes, dorsal lungs, and lower half of the lungs, may be associated with the need for ICU admission in patients with COVID-19. Computer analysis showed a high correlation with expert rating, highlighting its potential utility in clinical settings for assessing lung involvement. This information may help guide clinical decision-making and resource allocation during ongoing or future pandemics. Further studies with larger sample sizes are warranted to validate these findings.

Design and Experimental Validation of a 3D-Printed Embedded-Sensing Continuum Robot for Neurosurgery

A minimally-invasive manipulator characterized by hyper-redundant kinematics and embedded sensing modules is presented in this work. The bending angles (tilt and pan) of the robot tip are controlled through tendon-driven actuation; the transmission of the actuation forces to the tip is based on a Bowden-cable solution integrating some channels for optical fibers. The viability of the real-time measurement of the feedback control variables, through optoelectronic acquisition, is evaluated for automated bending of the flexible endoscope and trajectory tracking of the tip angles. Indeed, unlike conventional catheters and cannulae adopted in neurosurgery, the proposed robot can extend the actuation and control of snake-like kinematic chains with embedded sensing solutions, enabling real-time measurement, robust and accurate control of curvature, and tip bending of continuum robots for the manipulation of cannulae and microsurgical instruments in neurosurgical procedures. A prototype of the manipulator with a length of 43 mm and a diameter of 5.5 mm has been realized via 3D printing. Moreover, a multiple regression model has been estimated through a novel experimental setup to predict the tip angles from measured outputs of the optoelectronic modules. The sensing and control performance has also been evaluated during tasks involving tip rotations.

From Voxels to Prognosis: AI-Driven Quantitative Chest CT Analysis Forecasts ICU Requirements in 78 COVID-19 Cases

Background

The aim of the current study was to investigate the distribution and extent of lung involvement in patients with COVID-19 with AI-supported, automated computer analysis and to assess the relationship between lung involvement and the need for intensive care unit (ICU) admission. A secondary aim was to compare the performance of computer analysis with the judgment of radiological experts.

Methods

A total of 81 patients from an open-source COVID database with confirmed COVID-19 infection were included in the study. Three patients were excluded. Lung involvement was assessed in 78 patients using computed tomography (CT) scans, and the extent of infiltration and collapse was quantified across various lung lobes and regions. The associations between lung involvement and ICU admission were analyzed. Additionally, the computer analysis of COVID-19 involvement was compared against a human rating provided by radiological experts.

Results

The results showed a higher degree of infiltration and collapse in the lower lobes compared to the upper lobes (p < 0.05) No significant difference was detected in the COVID-19-related involvement of the left and right lower lobes. The right middle lobe demonstrated lower involvement compared to the right lower lobes (p < 0.05). When examining the regions, significantly more COVID-19 involvement was found when comparing the posterior vs. the anterior halves of the lungs and the lower vs. the upper half of the lungs. Patients, who required ICU admission during their treatment exhibited significantly higher COVID-19 involvement in their lung parenchyma according to computer analysis, compared to patients who remained in general wards. Patients with more than 40% COVID-19 involvement were almost exclusively treated in intensive care. A high correlation was observed between computer detection of COVID-19 affections and expert rating by radiological experts.

Conclusion

The findings suggest that the extent of lung involvement, particularly in the lower lobes, dorsal lungs, and lower half of the lungs, may be associated with the need for ICU admission in patients with COVID-19. Computer analysis showed a high correlation with expert rating, highlighting its potential utility in clinical settings for assessing lung involvement. This information may help guide clinical decision-making and resource allocation during ongoing or future pandemics. Further studies with larger sample sizes are warranted to validate these findings.

Deep learning-based 4D-synthetic CTs from sparse-view CBCTs for dose calculations in adaptive proton therapy

BACKGROUND

Time-resolved 4D cone beam-computed tomography (4D-CBCT) allows a daily assessment of patient anatomy and respiratory motion. However, 4D-CBCTs suffer from imaging artifacts that affect the CT number accuracy and prevent accurate proton dose calculations. Deep learning can be used to correct CT numbers and generate synthetic CTs (sCTs) that can enable CBCT-based proton dose calculations.

PURPOSE

In this work, sparse view 4D-CBCTs were converted into 4D-sCT utilizing a deep convolutional neural network (DCNN). 4D-sCTs were evaluated in terms of image quality and dosimetric accuracy to determine if accurate proton dose calculations for adaptive proton therapy workflows of lung cancer patients are feasible.

METHODS

A dataset of 45 thoracic cancer patients was utilized to train and evaluate a DCNN to generate 4D-sCTs, based on sparse view 4D-CBCTs reconstructed from projections acquired with a 3D acquisition protocol. Mean absolute error (MAE) and mean error were used as metrics to evaluate the image quality of single phases and average 4D-sCTs against 4D-CTs acquired on the same day. The dosimetric accuracy was checked globally (gamma analysis) and locally for target volumes and organs-at-risk (OARs) (lung, heart, and esophagus). Furthermore, 4D-sCTs were also compared to 3D-sCTs. To evaluate CT number accuracy, proton radiography simulations in 4D-sCT and 4D-CTs were compared in terms of range errors. The clinical suitability of 4D-sCTs was demonstrated by performing a 4D dose reconstruction using patient specific treatment delivery log files and breathing signals.

RESULTS

4D-sCTs resulted in average MAEs of 48.1 ± 6.5 HU (single phase) and 37.7 ± 6.2 HU (average). The global dosimetric evaluation showed gamma pass ratios of 92.3% ± 3.2% (single phase) and 94.4% ± 2.1% (average). The clinical target volume showed high agreement in D₉₈ between 4D-CT and 4D-sCT, with differences below 2.4% for all patients. Larger dose differences were observed in mean doses of OARs (up to 8.4%). The comparison with 3D-sCTs showed no substantial image quality and dosimetric differences for the 4D-sCT average. Individual 4D-sCT phases showed slightly lower dosimetric accuracy. The range error evaluation revealed that lung tissues cause range errors about three times higher than the other tissues.

CONCLUSION

In this study, we have investigated the accuracy of deep learning-based 4D-sCTs for daily dose calculations in adaptive proton therapy. Despite image quality differences between 4D-sCTs and 3D-sCTs, comparable dosimetric accuracy was observed globally and locally. Further improvement of 3D and 4D lung sCTs could be achieved by increasing CT number accuracy in lung tissues.

CoroFinder: A New Tool for Real Time Detection and Tracking of Coronary Arteries in Contrast-Free Cine-Angiography

Coronary Angiography (CA) is the standard of reference to diagnose coronary artery disease. Yet, only a portion of the information it conveys is usually used. Quantitative Coronary Angiography (QCA) reliably contributes to improving the measurable assessment of CA. In this work, we developed a new software, CoroFinder, able to automatically identify epicardial coronary arteries and to dynamically track the vessel profile in dye-free frames. The coronary tree is automatically segmented by Frangi’s filter in the angiogram’s frames where vessels are contrasted (“template frames”). Afterward, the image similarity among each template frame and the dye-free images is scored by cross-correlation. Finally, each dye-free image is associated with the most similar template frame, resulting in an estimation of vessel contour. CoroFinder allows locating the position of coronary arteries in absence of contrast dye. The developed algorithm is robust to diverse vessel curvatures, variation of vessel widths, and the presence of stenoses. This article describes the newly developed CoroFinder algorithm and the associated software and provides an overview of its potential application in research and for translation to the clinic.

Algorithms to Preprocess Microarray Image Data

Microarray is a powerful technology that enables the monitoring of expression levels for thousands of genes simultaneously, providing scientists with a full overview about DNA and RNA investigation. The process is made of three main phases: interaction with biological samples, data extraction, and data analysis. In particular, the data extraction phase strongly relies on image processing algorithms, since the expression levels are revealed by the interaction of light with fluorescent markers. More in detail, in order to extract quantitative information from probes image, three steps are required: (1) gridding, (2) segmentation, and (3) intensity quantification. Errors in one of these steps can deeply affect the process outcome. In this chapter each of the above mentioned steps will be analyzed and discussed. Software platforms dedicated to this purpose will be reported as well.

Clinical suitability of deep learning based synthetic CTs for adaptive proton therapy of lung cancer

Purpose

Adaptive proton therapy (APT) of lung cancer patients requires frequent volumetric imaging of diagnostic quality. Cone‐beam CT (CBCT) can provide these daily images, but x‐ray scattering limits CBCT‐image quality and hampers dose calculation accuracy. The purpose of this study was to generate CBCT‐based synthetic CTs using a deep convolutional neural network (DCNN) and investigate image quality and clinical suitability for proton dose calculations in lung cancer patients.

Methods

A dataset of 33 thoracic cancer patients, containing CBCTs, same‐day repeat CTs (rCT), planning‐CTs (pCTs), and clinical proton treatment plans, was used to train and evaluate a DCNN with and without a pCT‐based correction method. Mean absolute error (MAE), mean error (ME), peak signal‐to‐noise ratio, and structural similarity were used to quantify image quality. The evaluation of clinical suitability was based on recalculation of clinical proton treatment plans. Gamma pass ratios, mean dose to target volumes and organs at risk, and normal tissue complication probabilities (NTCP) were calculated. Furthermore, proton radiography simulations were performed to assess the HU‐accuracy of sCTs in terms of range errors.

Results

On average, sCTs without correction resulted in a MAE of 34 ± 6 HU and ME of 4 ± 8 HU. The correction reduced the MAE to 31 ± 4HU (ME to 2 ± 4HU). Average 3%/3 mm gamma pass ratios increased from 93.7% to 96.8%, when the correction was applied. The patient specific correction reduced mean proton range errors from 1.5 to 1.1 mm. Relative mean target dose differences between sCTs and rCT were below ± 0.5% for all patients and both synthetic CTs (with/without correction). NTCP values showed high agreement between sCTs and rCT (<2%).

Conclusion

CBCT‐based sCTs can enable accurate proton dose calculations for APT of lung cancer patients. The patient specific correction method increased the image quality and dosimetric accuracy but had only a limited influence on clinically relevant parameters.

Deep learning based synthetic-CT generation in radiotherapy and PET: A review

Recently,deep learning (DL)-based methods for the generation of synthetic computed tomography (sCT) have received significant research attention as an alternative to classical ones. We present here a systematic review of these methods by grouping them into three categories, according to their clinical applications: (i) to replace computed tomography in magnetic resonance (MR) based treatment planning, (ii) facilitate cone-beam computed tomography based image-guided adaptive radiotherapy, and (iii) derive attenuation maps for the correction of positron emission tomography. Appropriate database searching was performed on journal articles published between January 2014 and December 2020. The DL methods' key characteristics were extracted from each eligible study, and a comprehensive comparison among network architectures and metrics was reported. A detailed review of each category was given, highlighting essential contributions, identifying specific challenges, and summarizing the achievements. Lastly, the statistics of all the cited works from various aspects were analyzed, revealing the popularity and future trends and the potential of DL-based sCT generation. The current status of DL-based sCT generation was evaluated, assessing the clinical readiness of the presented methods.

An Open-Source COVID-19 CT Dataset with Automatic Lung Tissue Classification for Radiomics

The coronavirus disease 19 (COVID-19) pandemic is having a dramatic impact on society and healthcare systems. In this complex scenario, lung computerized tomography (CT) may play an important prognostic role. However, datasets released so far present limitations that hamper the development of tools for quantitative analysis. In this paper, we present an open-source lung CT dataset comprising information on 50 COVID-19-positive patients. The CT volumes are provided along with (i) an automatic threshold-based annotation obtained with a Gaussian mixture model (GMM) and (ii) a scoring provided by an expert radiologist. This score was found to significantly correlate with the presence of ground glass opacities and the consolidation found with GMM. The dataset is freely available in an ITK-based file format under the CC BY-NC 4.0 license. The code for GMM fitting is publicly available, as well. We believe that our dataset will provide a unique opportunity for researchers working in the field of medical image analysis, and hope that its release will lay the foundations for the successfully implementation of algorithms to support clinicians in facing the COVID-19 pandemic.

Metacognition and emotion regulation as treatment targets in binge eating disorder: a network analysis study

BACKGROUND

This study aims to examine the underlying associations between eating, affective and metacognitive symptoms in patients with binge eating disorder (BED) through network analysis (NA) in order to identify key variables that may be considered the target for psychotherapeutic interventions.

METHODS

A total of 155 patients with BED completed measures of eating psychopathology, affective symptoms, emotion regulation and metacognition. A cross-sectional network was inferred by means of Gaussian Markov random field estimation using graphical LASSO and the extended Bayesian information criterion (EBIC-LASSO), and central symptoms of BED were identified by means of the strength centrality index.

RESULTS

Impaired self-monitoring metacognition and difficulties in impulse control emerged as the symptoms with the highest centrality. Conversely, eating and affective features were less central. The centrality stability coefficient of strength was above the recommended cut-off, thus indicating the stability of the network.

CONCLUSIONS

According to the present NA findings, impaired self-monitoring metacognition and difficulties in impulse control are the central nodes in the psychopathological network of BED whereas eating symptoms appear marginal. If further studies with larger samples replicate these results, metacognition and impulse control could represent new targets of psychotherapeutic interventions in the treatment of BED. In light of this, metacognitive interpersonal therapy could be a promising aid in clinical practice to develop an effective treatment for BED.

A Review on Advances in Intra-operative Imaging for Surgery and Therapy: Imagining the Operating Room of the Future

With the advent of Minimally Invasive Surgery (MIS), intra-operative imaging has become crucial for surgery and therapy guidance, allowing to partially compensate for the lack of information typical of MIS. This paper reviews the advancements in both classical (i.e. ultrasounds, X-ray, optical coherence tomography and magnetic resonance imaging) and more recent (i.e. multispectral, photoacoustic and Raman imaging) intra-operative imaging modalities. Each imaging modality was analyzed, focusing on benefits and disadvantages in terms of compatibility with the operating room, costs, acquisition time and image characteristics. Tables are included to summarize this information. New generation of hybrid surgical room and algorithms for real time/in room image processing were also investigated. Each imaging modality has its own (site- and procedure-specific) peculiarities in terms of spatial and temporal resolution, field of view and contrasted tissues. Besides the benefits that each technique offers for guidance, considerations about operators and patient risk, costs, and extra time required for surgical procedures have to be considered. The current trend is to equip surgical rooms with multimodal imaging systems, so as to integrate multiple information for real-time data extraction and computer-assisted processing. The future of surgery is to enhance surgeons eye to minimize intra- and after-surgery adverse events and provide surgeons with all possible support to objectify and optimize the care-delivery process.

Comparison of CBCT based synthetic CT methods suitable for proton dose calculations in adaptive proton therapy

In-room imaging is a prerequisite for adaptive proton therapy. The use of onboard cone-beam computed tomography (CBCT) imaging, which is routinely acquired for patient position verification, can enable daily dose reconstructions and plan adaptation decisions. Image quality deficiencies though, hamper dose calculation accuracy and make corrections of CBCTs a necessity. This study compared three methods to correct CBCTs and create synthetic CTs that are suitable for proton dose calculations. CBCTs, planning CTs and repeated CTs (rCT) from 33 H&N cancer patients were used to compare a deep convolutional neural network (DCNN), deformable image registration (DIR) and an analytical image-based correction method (AIC) for synthetic CT (sCT) generation. Image quality of sCTs was evaluated by comparison with a same-day rCT, using mean absolute error (MAE), mean error (ME), Dice similarity coefficient (DSC), structural non-uniformity (SNU) and signal/contrast-to-noise ratios (SNR/CNR) as metrics. Dosimetric accuracy was investigated in an intracranial setting by performing gamma analysis and calculating range shifts. Neural network-based sCTs resulted in the lowest MAE and ME (37/2 HU) and the highest DSC (0.96). While DIR and AIC generated images with a MAE of 44/77 HU, a ME of -8/1 HU and a DSC of 0.94/0.90. Gamma and range shift analysis showed almost no dosimetric difference between DCNN and DIR based sCTs. The lower image quality of AIC based sCTs affected dosimetric accuracy and resulted in lower pass ratios and higher range shifts. Patient-specific differences highlighted the advantages and disadvantages of each method. For the set of patients, the DCNN created synthetic CTs with the highest image quality. Accurate proton dose calculations were achieved by both DCNN and DIR based sCTs. The AIC method resulted in lower image quality and dose calculation accuracy was reduced compared to the other methods.

Does a polarization state exist for mast cells in cancer?

The data of literature are discordant about the role of mast cells in different types of neoplasms. In this paper the authors propose the hypothesis that tumor-associated mast cells may switch to different polarization states, conditioning the immunogenic capacities of the different neoplasms. Anti-inflammatory polarized mast cells should express cytokines such as interleukin-10 (IL-10) and then mast cells number should be inversely related to the intensity of inflammatory infiltrate. On the contrary, when mast cells do not express anti-inflammatory cytokines their number should be directly related to the intensity of the inflammatory infiltrate. In this paper we briefly argue around feasible approaches, based on the retrospective studies of tumor tissue samples from neoplasms considered "immunologically hot" and neoplasms considered "immunologically cold", through immunohistochemistry and immunofluorescence techniques (confocal microscopy). The establishment of the actual existence of a polarization interchange of mast cells, could lead to a new vision in prognostic terms, useful to contrive new approaches in immunotherapy of tumors.

Fully automatic catheter segmentation in MRI with 3D convolutional neural networks: application to MRI-guided gynecologic brachytherapy

External-beam radiotherapy followed by high dose rate (HDR) brachytherapy is the standard-of-care for treating gynecologic cancers. The enhanced soft-tissue contrast provided by magnetic resonance imaging (MRI) makes it a valuable imaging modality for diagnosing and treating these cancers. However, in contrast to computed tomography (CT) imaging, the appearance of the brachytherapy catheters, through which radiation sources are inserted to reach the cancerous tissue later on, is often variable across images. This paper reports, for the first time, a new deep-learning-based method for fully automatic segmentation of multiple closely spaced brachytherapy catheters in intraoperative MRI. Represented in the data are 50 gynecologic cancer patients treated by MRI-guided HDR brachytherapy. For each patient, a single intraoperative MRI was used. 826 catheters in the images were manually segmented by an expert radiation physicist who is also a trained radiation oncologist. The number of catheters in a patient ranged between 10 and 35. A deep 3D convolutional neural network (CNN) model was developed and trained. In order to make the learning process more robust, the network was trained 5 times, each time using a different combination of shown patients. Finally, each test case was processed by the five networks and the final segmentation was generated by voting on the obtained five candidate segmentations. 4-fold validation was executed and all the patients were segmented. An average distance error of 2.0  ±  3.4 mm was achieved. False positive and false negative catheters were 6.7% and 1.5% respectively. Average Dice score was equal to 0.60  ±  0.17. The algorithm is available for use in the open source software platform 3D Slicer allowing for wide scale testing and research discussion. In conclusion, to the best of our knowledge, fully automatic segmentation of multiple closely spaced catheters from intraoperative MR images was achieved for the first time in gynecological brachytherapy.

Multi-organ segmentation of the head and neck area: an efficient hierarchical neural networks approach

PURPOSE

In radiation therapy, a key step for a successful cancer treatment is image-based treatment planning. One objective of the planning phase is the fast and accurate segmentation of organs at risk and target structures from medical images. However, manual delineation of organs, which is still the gold standard in many clinical environments, is time-consuming and prone to inter-observer variations. Consequently, many automated segmentation methods have been developed.

METHODS

In this work, we train two hierarchical 3D neural networks to segment multiple organs at risk in the head and neck area. First, we train a coarse network on size-reduced medical images to locate the organs of interest. Second, a subsequent fine network on full-resolution images is trained for a final accurate segmentation. The proposed method is purely deep learning based; accordingly, no pre-registration or post-processing is required.

RESULTS

The approach has been applied on a publicly available computed tomography dataset, created for the MICCAI 2015 Auto-Segmentation challenge. In an extensive evaluation process, the best configurations for the trained networks have been determined. Compared to the existing methods, the presented approach shows state-of-the-art performance for the segmentation of seven different structures in the head and neck area.

CONCLUSION

We conclude that 3D neural networks outperform the most existing model- and atlas-based methods for the segmentation of organs at risk in the head and neck area. The ease of use, high accuracy and the test time efficiency of the method make it promising for image-based treatment planning in clinical practice.

Innate Immunity Cells and the Neurovascular Unit

Recent studies have clarified many still unknown aspects related to innate immunity and the blood-brain barrier relationship. They have also confirmed the close links between effector immune system cells, such as granulocytes, macrophages, microglia, natural killer cells and mast cells, and barrier functionality. The latter, in turn, is able to influence not only the entry of the cells of the immune system into the nervous tissue, but also their own activation. Interestingly, these two components and their interactions play a role of great importance not only in infectious diseases, but in almost all the pathologies of the central nervous system. In this paper, we review the main aspects in the field of vascular diseases (cerebral ischemia), of primitive and secondary neoplasms of Central Nervous System CNS, of CNS infectious diseases, of most common neurodegenerative diseases, in epilepsy and in demyelinating diseases (multiple sclerosis). Neuroinflammation phenomena are constantly present in all diseases; in every different pathological state, a variety of innate immunity cells responds to specific stimuli, differentiating their action, which can influence the blood-brain barrier permeability. This, in turn, undergoes anatomical and functional modifications, allowing the stabilization or the progression of the pathological processes.

Multi atlas based segmentation: should we prefer the best atlas group over the group of best atlases?

Multi atlas based segmentation (MABS) uses a database of atlas images, and an atlas selection process is used to choose an atlas subset for registration and voting. In the current state of the art, atlases are chosen according to a similarity criterion between the target subject and each atlas in the database. In this paper, we propose a new concept for atlas selection that relies on selecting the best performing group of atlases rather than the group of highest scoring individual atlases. Experiments were performed using CT images of 50 patients, with contours of brainstem and parotid glands. The dataset was randomly split into two groups: 20 volumes were used as an atlas database and 30 served as target subjects for testing. Classic oracle selection, where atlases are chosen by the highest dice similarity coefficient (DSC) with the target, was performed. This was compared to oracle group selection, where all the combinations of atlas subgroups were considered and scored by computing DSC with the target subject. Subsequently, convolutional neural networks were designed to predict the best group of atlases. The results were also compared with the selection strategy based on normalized mutual information (NMI). Oracle group was proven to be significantly better than classic oracle selection (p  <  10^-5). Atlas group selection led to a median  ±  interquartile DSC of 0.740  ±  0.084, 0.718  ±  0.086 and 0.670  ±  0.097 for brainstem and left/right parotid glands respectively, outperforming NMI selection 0.676  ±  0.113, 0.632  ±  0.104 and 0.606  ±  0.118 (p  <  0.001) as well as classic oracle selection. The implemented methodology is a proof of principle that selecting the atlases by considering the performance of the entire group of atlases instead of each single atlas leads to higher segmentation accuracy, being even better then current oracle strategy. This finding opens a new discussion about the most appropriate atlas selection criterion for MABS.

Evaluation of segmentation methods on head and neck CT: Auto-segmentation challenge 2015

PURPOSE

Automated delineation of structures and organs is a key step in medical imaging. However, due to the large number and diversity of structures and the large variety of segmentation algorithms, a consensus is lacking as to which automated segmentation method works best for certain applications. Segmentation challenges are a good approach for unbiased evaluation and comparison of segmentation algorithms.

METHODS

In this work, we describe and present the results of the Head and Neck Auto-Segmentation Challenge 2015, a satellite event at the Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015 conference. Six teams participated in a challenge to segment nine structures in the head and neck region of CT images: brainstem, mandible, chiasm, bilateral optic nerves, bilateral parotid glands, and bilateral submandibular glands.

RESULTS

This paper presents the quantitative results of this challenge using multiple established error metrics and a well-defined ranking system. The strengths and weaknesses of the different auto-segmentation approaches are analyzed and discussed.

CONCLUSIONS

The Head and Neck Auto-Segmentation Challenge 2015 was a good opportunity to assess the current state-of-the-art in segmentation of organs at risk for radiotherapy treatment. Participating teams had the possibility to compare their approaches to other methods under unbiased and standardized circumstances. The results demonstrate a clear tendency toward more general purpose and fewer structure-specific segmentation algorithms.

Radiotherapy of Hodgkin and Non-Hodgkin Lymphoma

Purpose:

To improve the contouring of clinical target volume for the radiotherapy of neck Hodgkin/non-Hodgkin lymphoma by localizing the prechemotherapy gross target volume onto the simulation computed tomography using [18F]-fluorodeoxyglucose positron emission tomography/computed tomography.

Material and Methods:

The gross target volume delineated on prechemotherapy [18F]-fluorodeoxyglucose positron emission tomography/computed tomography images was warped onto simulation computed tomography using deformable image registration. Fifteen patients with neck Hodgkin/non-Hodgkin lymphoma were analyzed. Quality of image registration was measured by computing the Dice similarity coefficient on warped organs at risk. Five radiation oncologists visually scored the localization of automatic gross target volume, ranking it from 1 (wrong) to 5 (excellent). Deformable registration was compared to rigid registration by computing the overlap index between the automatic gross target volume and the planned clinical target volume and quantifying the V95 coverage.

Results:

The Dice similarity coefficient was 0.80 ± 0.07 (median ± quartiles). The physicians’ survey had a median score equal to 4 (good). By comparing the rigid versus deformable registration, the overlap index increased from a factor of about 4 and the V95 (percentage of volume receiving the 95% of the prescribed dose) went from 0.84 ± 0.38 to 0.99 ± 0.10 (median ± quartiles).

Conclusion:

This study demonstrates the impact of using deformable registration between prechemotherapy [18F]-fluorodeoxyglucose positron emission tomography/computed tomography and simulation computed tomography, in order to automatically localize the gross target volume for radiotherapy treatment of patients with Hodgkin/non-Hodgkin lymphoma.

Automatic segmentation of head and neck CT images for radiotherapy treatment planning using multiple atlases, statistical appearance models, and geodesic active contours

PURPOSE

Accurate delineation of organs at risk (OARs) is a precondition for intensity modulated radiation therapy. However, manual delineation of OARs is time consuming and prone to high interobserver variability. Because of image artifacts and low image contrast between different structures, however, the number of available approaches for autosegmentation of structures in the head-neck area is still rather low. In this project, a new approach for automated segmentation of head-neck CT images that combine the robustness of multiatlas-based segmentation with the flexibility of geodesic active contours and the prior knowledge provided by statistical appearance models is presented.

METHODS

The presented approach is using an atlas-based segmentation approach in combination with label fusion in order to initialize a segmentation pipeline that is based on using statistical appearance models and geodesic active contours. An anatomically correct approximation of the segmentation result provided by atlas-based segmentation acts as a starting point for an iterative refinement of this approximation. The final segmentation result is based on using model to image registration and geodesic active contours, which are mutually influencing each other.

RESULTS

18 CT images in combination with manually segmented labels of parotid glands and brainstem were used in a leave-one-out cross validation scheme in order to evaluate the presented approach. For this purpose, 50 different statistical appearance models have been created and used for segmentation. Dice coefficient (DC), mean absolute distance and max. Hausdorff distance between the autosegmentation results and expert segmentations were calculated. An average Dice coefficient of DC = 0.81 (right parotid gland), DC = 0.84 (left parotid gland), and DC = 0.86 (brainstem) could be achieved.

CONCLUSIONS

The presented framework provides accurate segmentation results for three important structures in the head neck area. Compared to a segmentation approach based on using multiple atlases in combination with label fusion, the proposed hybrid approach provided more accurate results within a clinically acceptable amount of time.