Metrics reloaded: recommendations for image analysis validation.

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.

Reliable brain morphometry from contrast-enhanced T1w-MRI in patients with multiple sclerosis.

Brain morphometry is usually based on non-enhanced (pre-contrast) T1-weighted MRI. However, such dedicated protocols are sometimes missing in clinical examinations. Instead, an image with a contrast agent is often available. Existing tools such as FreeSurfer yield unreliable results when applied to contrast-enhanced (CE) images. Consequently, these acquisitions are excluded from retrospective morphometry studies, which reduces the sample size. We hypothesize that deep learning (DL)-based morphometry methods can extract morphometric measures also from contrast-enhanced MRI. We have extended DL+DiReCT to cope with contrast-enhanced MRI. Training data for our DL-based model were enriched with non-enhanced and CE image pairs from the same session. The segmentations were derived with FreeSurfer from the non-enhanced image and used as ground truth for the coregistered CE image. A longitudinal dataset of patients with multiple sclerosis (MS), comprising relapsing remitting (RRMS) and primary progressive (PPMS) subgroups, was used for the evaluation. Global and regional cortical thickness derived from non-enhanced and CE images were contrasted to results from FreeSurfer. Correlation coefficients of global mean cortical thickness between non-enhanced and CE images were significantly larger with DL+DiReCT (r = 0.92) than with FreeSurfer (r = 0.75). When comparing the longitudinal atrophy rates between the two MS subgroups, the effect sizes between PPMS and RRMS were higher with DL+DiReCT both for non-enhanced (d = -0.304) and CE images (d = -0.169) than for FreeSurfer (non-enhanced d = -0.111, CE d = 0.085). In conclusion, brain morphometry can be derived reliably from contrast-enhanced MRI using DL-based morphometry tools, making additional cases available for analysis and potential future diagnostic morphometry tools.

Quadruple term gestation of quadri-chorionic quadri-amniotic pregnancy after artificial insemination: a case report.

BACKGROUND: To solve infertility, modern science has promoted assisted reproduction techniques such as in vitro fertilization, ovulation induction, and artificial insemination. Quadruple-type multiple pregnancies occur in 1 of every 500,000 pregnancies, and it is estimated that 90% occur due to assisted reproductive techniques, which often lead to numerous complications. CASE PRESENTATION: Here we present a case of a 33-year-old woman, who desired pregnancy, but had a history of primary infertility diagnosed by hysterosalpingography, and endometriosis, which was treated by fulguration and medical management. Concomitantly, the patient was anovulatory. To fulfill her wish, she underwent homologous artificial insemination, after treatment, she successfully conceived quadri-chorionic quadri-amniotic infants, who were born at 37.2 weeks, without perinatal or maternal complications. CONCLUSION: This paper presented the parameters of prenatal care, appropriate management approach, and successful resolution without maternal-fetal complications despite the inherent risks of this type of pregnancy.

RESUMEN: INTRODUCCIóN: Para solucionar la infertilidad, la ciencia moderna ha promovido las técnicas de reproducción asistida, como la fecundación in vitro, la inducción de la ovulación y la inseminación artificial. Los embarazos múltiples de tipo cuádruple se producen en 1 de cada 500.000 embarazos, y se estima que el 90% ocurren debido a las técnicas de reproducción asistida, que a menudo conllevan numerosas complicaciones. PRESENTACIóN DEL CASO: Presentamos el caso de una mujer de 33 años, que deseaba un embarazo, pero tenía antecedentes de infertilidad primaria diagnosticada por histerosalpingografía, y endometriosis, que fue tratada mediante fulguración y manejo médico. Al mismo tiempo, la paciente era anovulatoria. Para cumplir su deseo, se sometió a una inseminación artificial homóloga y, tras el tratamiento, concibió con éxito niños cuadri-coriónicos cuadri-amnióticos, que nacieron a las 37,2 semanas, sin complicaciones perinatales ni maternas. CONCLUSIóN: Este trabajo presentó los parámetros de atención prenatal, el enfoque de manejo adecuado y la resolución exitosa sin complicaciones materno-fetales a pesar de los riesgos inherentes a este tipo de embarazo.

Predicting Infarct Core From Computed Tomography Perfusion in Acute Ischemia With Machine Learning: Lessons From the ISLES Challenge.

BACKGROUND AND PURPOSE: The ISLES challenge (Ischemic Stroke Lesion Segmentation) enables globally diverse teams to compete to develop advanced tools for stroke lesion analysis with machine learning. Detection of irreversibly damaged tissue on computed tomography perfusion (CTP) is often necessary to determine eligibility for late-time-window thrombectomy. Therefore, the aim of ISLES-2018 was to segment infarcted tissue on CTP based on diffusion-weighted imaging as a reference standard. METHODS: The data, from 4 centers, consisted of 103 cases of acute anterior circulation large artery occlusion stroke who underwent diffusion-weighted imaging rapidly after CTP. Diffusion-weighted imaging lesion segmentation was performed manually and acted as a reference standard. The data were separated into 63 cases for training and 40 for testing, upon which quality metrics (dice score coefficient, Hausdorff distance, absolute lesion volume difference, etc) were computed to rank methods based on their overall performance. RESULTS: Twenty-four different teams participated in the challenge. Median time to CTP was 185 minutes (interquartile range, 180-238), the time between CTP and magnetic resonance imaging was 36 minutes (interquartile range, 25-79), and the median infarct lesion size was 15.2 mL (interquartile range, 5.7-45). The best performance for Dice score coefficient and absolute volume difference were 0.51 and 10.1 mL, respectively, from different teams. Based on the ranking criteria, the top team's algorithm demonstrated for average Dice score coefficient and average absolute volume difference 0.51 and 10.2 mL, respectively, outperforming the conventional threshold-based method (dice score coefficient, 0.3; volume difference, 15.3). Diverse algorithms were used, almost all based on deep learning, with top-ranked approaches making use of the raw perfusion data as well as methods to synthetically generate complementary information to boost prediction performance. CONCLUSIONS: Machine learning methods may predict infarcted tissue from CTP with improved accuracy compared with threshold-based methods used in clinical routine. This dataset will remain public and can be used to test improvement in algorithms over time.

Direct cortical thickness estimation using deep learning-based anatomy segmentation and cortex parcellation.

Accurate and reliable measures of cortical thickness from magnetic resonance imaging are an important biomarker to study neurodegenerative and neurological disorders. Diffeomorphic registration-based cortical thickness (DiReCT) is a known technique to derive such measures from non-surface-based volumetric tissue maps. ANTs provides an open-source method for estimating cortical thickness, derived by applying DiReCT to an atlas-based segmentation. In this paper, we propose DL+DiReCT, a method using high-quality deep learning-based neuroanatomy segmentations followed by DiReCT, yielding accurate and reliable cortical thickness measures in a short time. We evaluate the methods on two independent datasets and compare the results against surface-based measures from FreeSurfer. Good correlation of DL+DiReCT with FreeSurfer was observed (r = .887) for global mean cortical thickness compared to ANTs versus FreeSurfer (r = .608). Experiments suggest that both DiReCT-based methods had higher sensitivity to changes in cortical thickness than Freesurfer. However, while ANTs showed low scan-rescan robustness, DL+DiReCT showed similar robustness to Freesurfer. Effect-sizes for group-wise differences of healthy controls compared to individuals with dementia were highest with the deep learning-based segmentation. DL+DiReCT is a promising combination of a deep learning-based method with a traditional registration technique to detect subtle changes in cortical thickness.

Brain SegNet: 3D local refinement network for brain lesion segmentation.

MR images (MRIs) accurate segmentation of brain lesions is important for improving cancer diagnosis, surgical planning, and prediction of outcome. However, manual and accurate segmentation of brain lesions from 3D MRIs is highly expensive, time-consuming, and prone to user biases. We present an efficient yet conceptually simple brain segmentation network (referred as Brain SegNet), which is a 3D residual framework for automatic voxel-wise segmentation of brain lesion. Our model is able to directly predict dense voxel segmentation of brain tumor or ischemic stroke regions in 3D brain MRIs. The proposed 3D segmentation network can run at about 0.5s per MRIs - about 50 times faster than previous approaches Med Image Anal 43: 98-111, 2018, Med Image Anal 36:61-78, 2017. Our model is evaluated on the BRATS 2015 benchmark for brain tumor segmentation, where it obtains state-of-the-art results, by surpassing recently published results reported in Med Image Anal 43: 98-111, 2018, Med Image Anal 36:61-78, 2017. We further applied the proposed Brain SegNet for ischemic stroke lesion outcome prediction, with impressive results achieved on the Ischemic Stroke Lesion Segmentation (ISLES) 2017 database.

Analysis of metabolic abnormalities in high-grade glioma using MRSI and convex NMF.

Clinical use of MRSI is limited by the level of experience required to properly translate MRSI examinations into relevant clinical information. To solve this, several methods have been proposed to automatically recognize a predefined set of reference metabolic patterns. Given the variety of metabolic patterns seen in glioma patients, the decision on the optimal number of patterns that need to be used to describe the data is not trivial. In this paper, we propose a novel framework to (1) separate healthy from abnormal metabolic patterns and (2) retrieve an optimal number of reference patterns describing the most important types of abnormality. Using 41 MRSI examinations (1.5 T, PRESS, TE 135 ms) from 22 glioma patients, four different patterns describing different types of abnormality were detected: edema, healthy without Glx, active tumor and necrosis. The identified patterns were then evaluated on 17 MRSI examinations from nine different glioma patients. The results were compared against BraTumIA, an automatic segmentation method trained to identify different tumor compartments on structural MRI data. Finally, the ability to predict future contrast enhancement using the proposed approach was also evaluated.

Cutting-edge microangio-CT: new dimensions in vascular imaging and kidney morphometry.

In the last decades, the contrast-enhanced micro-computed tomography (micro-CT) imaging of a whole animal kidney became increasingly important. The visualization was mainly limited to middle-sized vessels. Since modern desktop micro-CT scanners provide the necessary detail resolution, we developed an approach for rapid visualization and consistent assessment of kidney vasculature and glomeruli number. This method is based on µAngiofil, a new polymerizing contrast agent with homogenous X-ray absorption, which provides continuous filling of the complete vasculature and enables correlative imaging approaches. For rapid and reliable kidney morphometry, the microangio-CT (µaCT) data sets from glial cell line-derived neurotrophic factor (GDNF)+/- mice and their wild-type littermates were used. The results were obtained much faster compared with the current gold standard, histology-based stereology, and without processing artifacts. The histology-based morphometry was done afterward on the same kidneys. Both approaches revealed that the GDNF+/- male mice had about 40% fewer glomeruli. Furthermore, our approach allows for the definition of sites of interest for further histological investigation, i.e., correlative morphology. The polymerized µAngiofil stays in perfused vessels and is autofluorescent, which is what greatly facilitates the matching of histological sections with µaCT data. The presented approach is a time-efficient, reliable, qualitative, and quantitative methodology. Besides glomerular morphometry, the µaCT data can be used for qualitative and quantitative analysis of the kidney vasculature and correlative morphology.

On the relation between MR spectroscopy features and the distance to MRI-visible solid tumor in GBM patients.

PURPOSE: To improve the detection of peritumoral changes in GBM patients by exploring the relation between MRSI information and the distance to the solid tumor volume (STV) defined using structural MRI (sMRI). METHODS: Twenty-three MRSI studies (PRESS, TE 135 ms) acquired from different patients with untreated GBM were used in this study. For each MRSI examination, the STV was identified by segmenting the corresponding sMRI images using BraTumIA, an automatic segmentation method. The relation between different metabolite ratios and the distance to STV was analyzed. A regression forest was trained to predict the distance from each voxel to STV based on 14 metabolite ratios. Then, the trained model was used to determine the expected distance to tumor (EDT) for each voxel of the MRSI test data. EDT maps were compared against sMRI segmentation. RESULTS: The features showing abnormal values at the longest distances to the tumor were: %NAA, Glx/NAA, Cho/NAA, and Cho/Cr. These four features were also the most important for the prediction of the distances to STV. Each EDT value was associated with a specific metabolic pattern, ranging from normal brain tissue to actively proliferating tumor and necrosis. Low EDT values were highly associated with malignant features such as elevated Cho/NAA and Cho/Cr. CONCLUSION: The proposed method enables the automatic detection of metabolic patterns associated with different distances to the STV border and may assist tumor delineation of infiltrative brain tumors such as GBM.

The effect of muscle ageing and sarcopenia on spinal segmental loads.

PURPOSE: The interrelations between age-related muscle deterioration (sarcopenia) and vertebral fractures have been suggested based on clinical observations, but the biomechanical relationships have not been explored. The study aim was to investigate the effects of muscle ageing and sarcopenia on muscle recruitment patterns and spinal loads, using musculoskeletal multi-body modelling. METHODS: A generic AnyBody model of the thoracolumbar spine, including > 600 fascicles representing trunk musculature, was used. Several stages of normal ageing and sarcopenia were modelled by reduced strength of erector spinae and multifidus muscles (ageing from 3rd to 6th life decade: ≥ 60% of normal strength; sarcopenia: mild 60%, moderate 48%, severe 36%, very severe 24%), reflecting the reported decrease in cross-sectional area and increased fat infiltration. All other model parameters were kept unchanged. Full-range flexion was simulated using inverse dynamics with muscle optimization to predict spinal loads and muscle recruitment patterns. RESULTS: The muscle changes due to normal ageing (≥ 60% strength) had a minor effect on predicted loads and provoked only slightly elevated muscle activities. Severe (36%) and very severe (24%) stages of sarcopenia, however, were associated with substantial increases in compression (by up to 36% or 318N) at the levels of the upper thoracic spine (T1T2-T5T6) and shear loading (by up to 75% or 176N) along the whole spine (T1T2-L4L5). The muscle activities increased for almost all muscles, up to 100% of their available strength. CONCLUSIONS: The study highlights the distinct and detrimental consequences of sarcopenia, in contrast to normal ageing, on spinal loading and required muscular effort. These slides can be retrieved under Electronic Supplementary Material.

Diffusion tensor imaging of the human kidney: Does image registration permit scanning without respiratory triggering?

PURPOSE: To investigate if image registration of diffusion tensor imaging (DTI) allows omitting respiratory triggering for both transplanted and native kidneys MATERIALS AND METHODS: Nine kidney transplant recipients and eight healthy volunteers underwent renal DTI on a 3T scanner with and without respiratory triggering. DTI images were registered using a multimodal nonrigid registration algorithm. Apparent diffusion coefficient (ADC), the contribution of perfusion (FP ), and the fractional anisotropy (FA) were determined. Relative root mean square errors (RMSE) of the fitting and the standard deviations of the derived parameters within the regions of interest (SDROI ) were evaluated as quality criteria. RESULTS: Registration significantly reduced RMSE in all DTI-derived parameters of triggered and nontriggered measurements in cortex and medulla of both transplanted and native kidneys (P < 0.05 for all). In addition, SDROI values were lower with registration for all 16 parameters in transplanted kidneys (14 of 16 SDROI values were significantly reduced, P < 0.04) and for 15 of 16 parameters in native kidneys (9 of 16 SDROI values were significantly reduced, P < 0.05). Comparing triggered versus nontriggered DTI in transplanted kidneys revealed no significant difference for RMSE (P > 0.14) and for SDROI (P > 0.13) of all parameters. In contrast, in native kidneys relative RMSE from triggered scans were significantly lower than those from nontriggered scans (P < 0.02), while SDROI was slightly higher in triggered compared to nontriggered measurements in 15 out of 16 comparisons (significantly for two, P < 0.05). CONCLUSION: Registration improves the quality of DTI in native and transplanted kidneys. Diffusion parameters in renal allografts can be measured without respiratory triggering. In native kidneys, respiratory triggering appears advantageous. J. Magn. Reson. Imaging 2016;44:327-334.

Results of Therapy for Wilms Tumor and Other Malignant Kidney Tumors: A Report From the Chilean Pediatric National Cancer Program (PINDA).

OBJECTIVE: The aim of this study was to analyze the survival of children with Wilms tumor and other malignant renal tumors treated with the TWPINDA-99 protocol. MATERIALS AND METHODS: Between January 1999 and December 2013, 226 patients were registered on this trial, based on National Wilms Tumor Study-5. Patient characteristics and survival were evaluated. RESULTS: Two hundred seven patients were diagnosed with Wilms tumor, which represented 91.6% of renal tumors. The male to female ratio was 0.7:1. The median age at diagnosis was 3.3 years. Stage III was the most frequent (39.2%). Metastatic disease was present in 16.7% of the cases. Synchronous bilateral disease was observed in 9.3% of the cases. Favorable histology was diagnosed in 93.6% and anaplastic histology in 6.4% of the patients. Median follow-up was 7.5 years. Ten-year event-free survival and overall survival (OS) for assessable patients with Wilms tumor (n=192) were 82.0% and 89.9%, respectively. OS for patients with stage I was 100% (n=36), stage II: 97.1% (n=35), stage III: 88.6% (n=71), stage IV: 77.9% (n=32), and stage V: 80.8% (n=18). OS for favorable histology (n=180) and anaplastic histology tumors (n=12) were 91.0% and 72.9%, respectively. Other malignant renal tumors had a poorer survival. CONCLUSION: Prognosis for patients with Wilms tumor treated on TWPINDA-99 seems to be better than previous national trials and is similar to developed countries.

Image registration for triggered and non-triggered DTI of the human kidney: reduced variability of diffusion parameter estimation.

BACKGROUND: To investigate if non-rigid image-registration reduces motion artifacts in triggered and non-triggered diffusion tensor imaging (DTI) of native kidneys. A secondary aim was to determine, if improvements through registration allow for omitting respiratory-triggering. METHODS: Twenty volunteers underwent coronal DTI of the kidneys with nine b-values (10-700 s/mm(2) ) at 3 Tesla. Image-registration was performed using a multimodal nonrigid registration algorithm. Data processing yielded the apparent diffusion coefficient (ADC), the contribution of perfusion (FP ), and the fractional anisotropy (FA). For comparison of the data stability, the root mean square error (RMSE) of the fitting and the standard deviations within the regions of interest (SDROI ) were evaluated. RESULTS: RMSEs decreased significantly after registration for triggered and also for non-triggered scans (P < 0.05). SDROI for ADC, FA, and FP were significantly lower after registration in both medulla and cortex of triggered scans (P < 0.01). Similarly the SDROI of FA and FP decreased significantly in non-triggered scans after registration (P < 0.05). RMSEs were significantly lower in triggered than in non-triggered scans, both with and without registration (P < 0.05). CONCLUSION: Respiratory motion correction by registration of individual echo-planar images leads to clearly reduced signal variations in renal DTI for both triggered and particularly non-triggered scans. Secondarily, the results suggest that respiratory-triggering still seems advantageous.

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification.

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the presence of limited labeled data. Another effective technique to enlarge datasets in a small labeled data regime is data augmentation. An intuitive active learning approach thus consists of combining informative sample selection and data augmentation to leverage their respective advantages and improve the performance of AL systems. In this paper, we propose a novel approach called GANDALF (Graph-based TrANsformer and Data Augmentation Active Learning Framework) to combine sample selection and data augmentation in a multi-label setting. Conventional sample selection approaches in AL have mostly focused on the single-label setting where a sample has only one disease label. These approaches do not perform optimally when a sample can have multiple disease labels (e.g., in chest X-ray images). We improve upon state-of-the-art multi-label active learning techniques by representing disease labels as graph nodes and use graph attention transformers (GAT) to learn more effective inter-label relationships. We identify the most informative samples by aggregating GAT representations. Subsequently, we generate transformations of these informative samples by sampling from a learned latent space. From these generated samples, we identify informative samples via a novel multi-label informativeness score, which beyond the state of the art, ensures that (i) generated samples are not redundant with respect to the training data and (ii) make important contributions to the training stage. We apply our method to two public chest X-ray datasets, as well as breast, dermatology, retina and kidney tissue microscopy MedMNIST datasets, and report improved results over state-of-the-art multi-label AL techniques in terms of model performance, learning rates, and robustness.

Ammonium loss microbiologically mediated by Fe(III) and Mn(IV) reduction along a coastal lagoon system.

Anaerobic ammonium oxidation, associated with both iron (Feammox) and manganese (Mnammox) reduction, is a microbial nitrogen (N) removal mechanism recently identified in natural ecosystems. Nevertheless, the spatial distributions of these non-canonical Anammox (NC-Anammox) pathways and their environmental drivers in subtidal coastal sediments are still unknown. Here, we determined the potential NC-Anammox rates and abundance of dissimilatory metal-reducing bacteria (Acidomicrobiaceae A6 and Geobacteraceae) at different horizons (0-20 cm at 5 cm intervals) of subtidal coastal sediments using the 15N isotope-tracing technique and molecular analyses. Sediments were collected across three sectors (inlet, transition, and inner) in a coastal lagoon system (Bahia de San Quintin, Mexico) dominated by seagrass meadows. The positive relationship between 30N2 production rates and dissimilatory Fe and Mn reduction provided evidence for Feammox's and Mnammox's co-occurrence. N loss through NC-Anammox was detected in subtidal sediments, with potential rates of 0.07-0.62 µg N g-1 day-1. NC-Anammox process in vegetated sediments tended to be higher than those in adjacent unvegetated ones. NC-Anammox rates showed a subsurface peak (between 5 and 15 cm) in the vegetated sediments but decreased consistently with depth in the adjacent bare bottoms. Thus, the presence/absence of seagrasses and sediment characteristics, particularly the availability of organic carbon and microbiologically reducible Fe(III) and Mn(IV), affected the abundance of dissimilatory metal-reducing bacteria, which mediated NC-Anammox activity and the associated N removal. An annual loss of 32.31 ± 3.57 t N was estimated to be associated with Feammox and Mnammox within the investigated area, accounting for 2.8-4.7% of the gross total import of reactive N from the ocean into the Bahia de San Quintin. Taken as a whole, this study reveals the distribution patterns and controlling factors of the NC-Anammox pathways along a coastal lagoon system. It improves our understanding of the coupling between N and trace metal cycles in coastal environments.

Current and Evolving Multimodality Cardiac Imaging in Managing Transthyretin Amyloid Cardiomyopathy.

Amyloid transthyretin (ATTR) amyloidosis is a protein-misfolding disease characterized by fibril accumulation in the extracellular space that can result in local tissue disruption and organ dysfunction. Cardiac involvement drives morbidity and mortality, and the heart is the major organ affected by ATTR amyloidosis. Multimodality cardiac imaging (ie, echocardiography, scintigraphy, and cardiac magnetic resonance) allows accurate diagnosis of ATTR cardiomyopathy (ATTR-CM), and this is of particular importance because ATTR-targeting therapies have become available and probably exert their greatest benefit at earlier disease stages. Apart from establishing the diagnosis, multimodality cardiac imaging may help to better understand pathogenesis, predict prognosis, and monitor treatment response. The aim of this review is to give an update on contemporary and evolving cardiac imaging methods and their role in diagnosing and managing ATTR-CM. Further, an outlook is presented on how artificial intelligence in cardiac imaging may improve future clinical decision making and patient management in the setting of ATTR-CM.

Analysis of 3D soft tissue changes after 1- and 2-jaw orthognathic surgery in mandibular prognathism patients.

PURPOSE: Orthognathic surgery has the objective of altering facial balance to achieve esthetic results in patients who have severe disharmony of the jaws. The purpose was to quantify the soft tissue changes after orthognathic surgery, as well as to assess the differences in 3D soft tissue changes in the middle and lower third of the face between the 1- and 2-jaw surgery groups, in mandibular prognathism patients. MATERIALS AND METHODS: We assessed soft tissue changes of patients who have been diagnosed with mandibular prognathism and received either isolated mandibular surgery or bimaxillary surgery. The quantitative surface displacement was assessed by superimposing preoperative and postoperative volumetric images. An observer measured a surface-distance value that is shown as a contour line. Differences between the groups were determined by the Mann-Whitney U test. The Spearman correlation coefficient was used to evaluate a potential correlation between patients' surgical and cephalometric variables and soft tissue changes after orthognathic surgery in each group. RESULTS: There were significant differences in the middle third of the face between the 1- and 2-jaw surgery groups. Soft tissues in the lower third of the face changed in both surgery groups, but not significantly. The correlation patterns were more evident in the lower third of the face. CONCLUSION: The overall soft tissue changes of the midfacial area were more evident in the 2-jaw surgery group. In 2-jaw surgery, significant changes would be expected in the midfacial area, but caution should be exercised in patients who have a wide alar base.

A refractive index sensor based on the resonant coupling to cladding modes in a fiber loop.

We report an easy-to-build, compact, and low-cost optical fiber refractive index sensor. It consists of a single fiber loop whose transmission spectra exhibit a series of notches produced by the resonant coupling between the fundamental mode and the cladding modes in a uniformly bent fiber. The wavelength of the notches, distributed in a wavelength span from 1,400 to 1,700 nm, can be tuned by adjusting the diameter of the fiber loop and are sensitive to refractive index changes of the external medium. Sensitivities of 170 and 800 nm per refractive index unit for water solutions and for the refractive index interval 1.40-1.442, respectively, are demonstrated. We estimate a long range resolution of 3 × 10(-4) and a short range resolution of 2 × 10(-5) for water solutions.

Validity of an automatic measure protocol in distal femur for allograft selection from a three-dimensional virtual bone bank system.

Osteoarticular allograft is one possible treatment in wide surgical resections with large defects. Performing best osteoarticular allograft selection is of great relevance for optimal exploitation of the bone databank, good surgery outcome and patient's recovery. Current approaches are, however, very time consuming hindering these points in practice. We present a validation study of a software able to perform automatic bone measurements used to automatically assess the distal femur sizes across a databank. 170 distal femur surfaces were reconstructed from CT data and measured manually using a size measure protocol taking into account the transepicondyler distance (A), anterior-posterior distance in medial condyle (B) and anterior-posterior distance in lateral condyle (C). Intra- and inter-observer studies were conducted and regarded as ground truth measurements. Manual and automatic measures were compared. For the automatic measurements, the correlation coefficients between observer one and automatic method, were of 0.99 for A measure and 0.96 for B and C measures. The average time needed to perform the measurements was of 16 h for both manual measurements, and of 3 min for the automatic method. Results demonstrate the high reliability and, most importantly, high repeatability of the proposed approach, and considerable speed-up on the planning.

Graph Node Based Interpretability Guided Sample Selection for Active Learning.

While supervised learning techniques have demonstrated state-of-the-art performance in many medical image analysis tasks, the role of sample selection is important. Selecting the most informative samples contributes to the system attaining optimum performance with minimum labeled samples, which translates to fewer expert interventions and cost. Active Learning (AL) methods for informative sample selection are effective in boosting performance of computer aided diagnosis systems when limited labels are available. Conventional approaches to AL have mostly focused on the single label setting where a sample has only one disease label from the set of possible labels. These approaches do not perform optimally in the multi-label setting where a sample can have multiple disease labels (e.g. in chest X-ray images). In this paper we propose a novel sample selection approach based on graph analysis to identify informative samples in a multi-label setting. For every analyzed sample, each class label is denoted as a separate node of a graph. Building on findings from interpretability of deep learning models, edge interactions in this graph characterize similarity between corresponding interpretability saliency map model encodings. We explore different types of graph aggregation to identify informative samples for active learning. We apply our method to public chest X-ray and medical image datasets, and report improved results over state-of-the-art AL techniques in terms of model performance, learning rates, and robustness.