SAFARI: shape analysis for AI-segmented images.
Ontology highlight
ABSTRACT: Background
Recent developments to segment and characterize the regions of interest (ROI) within medical images have led to promising shape analysis studies. However, the procedures to analyze the ROI are arbitrary and vary by study. A tool to translate the ROI to analyzable shape representations and features is greatly needed.Results
We developed SAFARI (shape analysis for AI-segmented images), an open-source R package with a user-friendly online tool kit for ROI labelling and shape feature extraction of segmented maps, provided by AI-algorithms or manual segmentation. We demonstrated that half of the shape features extracted by SAFARI were significantly associated with survival outcomes in a case study on 143 consecutive patients with stage I-IV lung cancer and another case study on 61 glioblastoma patients.Conclusions
SAFARI is an efficient and easy-to-use toolkit for segmenting and analyzing ROI in medical images. It can be downloaded from the comprehensive R archive network (CRAN) and accessed at https://lce.biohpc.swmed.edu/safari/ .
SUBMITTER: Fernandez E
PROVIDER: S-EPMC9308199 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The COVID-19 pandemic overwhelms the medical resources in the stressed intensive care unit (ICU) capacity and the shortage of mechanical ventilation (MV). We performed CT-based analysis combined with electronic health records and clinical laboratory results on Cohort 1 (n = 1662 from 17 hospitals) with prognostic estimation for the rapid stratification of PCR confirmed COVID-19 patients. These models, validated on Cohort 2 (n = 700) and Cohort 3 (n = 662) constructed from nine external hospitals, achieved satisfying performance for predicting ICU, MV, and death of COVID-19 patients (AUROC 0.916, 0.919, and 0.853), even on events happened two days later after admission (AUROC 0.919, 0.943, and 0.856). Both clinical and image features showed complementary roles in prediction and provided accurate estimates to the time of progression (p < 0.001). Our findings are valuable for optimizing the use of medical resources in the COVID-19 pandemic. The models are available here: https://github.com/terryli710/COVID_19_Rapid_Triage_Risk_Predictor .
| S-EPMC8062628 | biostudies-literature
Project description:The development of fluid transport systems was a key event in the evolution of animals and plants. While within vertebrates branched geometries predominate, the choriocapillaris, which is the microvascular bed that is responsible for the maintenance of the outer retina, has evolved a planar topology. Here we examine the flow and mass transfer properties associated with this unusual geometry. We show that as a result of the form of the choriocapillaris, the blood flow is decomposed into a tessellation of functional vascular segments of various shapes delineated by separation surfaces across which there is no flow, and in the vicinity of which the transport of passive substances is diffusion-limited. The shape of each functional segment is determined by the distribution of arterioles and venules and their respective relative flow rates. We also show that, remarkably, the mass exchange with the outer retina is a function of the shape of each functional segment. In addition to introducing a novel framework in which the structure and function of the metabolite delivery system to the outer retina may be investigated in health and disease, the present work provides a general characterisation of the flow and transfers in multipole Hele-Shaw configurations.
| S-EPMC5078844 | biostudies-other
Project description:Generalizability of deep-learning (DL) model performance is not well understood and uses anecdotal assumptions for increasing training data to improve segmentation of medical images. We report statistical methods for visual interpretation of DL models trained using ImageNet initialization with natural-world (T II) and supervised learning with medical images (L MI) for binary segmentation of skin cancer, prostate tumors, and kidneys. An algorithm for computation of Dice scores from union and intersections of individual output masks was developed for synergistic segmentation by T II and L MI models. Stress testing with non-Gaussian distributions of infrequent clinical labels and images showed that sparsity of natural-world and domain medical images can counterintuitively reduce type I and type II errors of DL models. A toolkit of 30 T II and L MI models, code, and visual outputs of 59,967 images is shared to identify the target and non-target medical image pixels and clinical labels to explain the performance of DL models.
| S-EPMC9017181 | biostudies-literature
Project description:PurposePeople with drug-refractory epilepsy are potential candidates for surgery. In many cases, epileptogenic zone localization requires intracranial investigations, e.g., via ElectroCorticoGraphy (ECoG), which uses subdural electrodes to map eloquent areas of large cortical regions. Precise electrodes localization on cortical surface is mandatory to delineate the seizure onset zone. Simple thresholding operations performed on patients' computed tomography (CT) volumes recognize electrodes but also other metal objects (e.g., wires, stitches), which need to be manually removed. A new automated method based on shape analysis is proposed, which provides substantially improved performances in ECoG electrodes recognition.MethodsThe proposed method was retrospectively tested on 24 CT volumes of subjects with drug-refractory focal epilepsy, presenting a large number (> 1700) of round platinum electrodes. After CT volume thresholding, six geometric features of voxel clusters (volume, symmetry axes lengths, circularity and cylinder similarity) were used to recognize the actual electrodes among all metal objects via a Gaussian support vector machine (G-SVM). The proposed method was further tested on seven CT volumes from a public repository. Simultaneous recognition of depth and ECoG electrodes was also investigated on three additional CT volumes, containing penetrating depth electrodes.ResultsThe G-SVM provided a 99.74% mean classification accuracy across all 24 single-patient datasets, as well as on the combined dataset. High accuracies were obtained also on the CT volumes from public repository (98.27% across all patients, 99.68% on combined dataset). An overall accuracy of 99.34% was achieved for the recognition of depth and ECoG electrodes.ConclusionsThe proposed method accomplishes automated ECoG electrodes localization with unprecedented accuracy and can be easily implemented into existing software for preoperative analysis process. The preliminary yet surprisingly good results achieved for the simultaneous depth and ECoG electrodes recognition are encouraging. Ethical approval n°NCT04479410 by "IRCCS Neuromed" (Pozzilli, Italy), 30th July 2020.
| S-EPMC8052236 | biostudies-literature
Project description:BackgroundGlioblastoma (GBM) is one of the most common malignant primary brain tumors, which accounts for 60-70% of all gliomas. Conventional diagnosis and the decision of post-operation treatment plan for glioblastoma is mainly based on the feature-based qualitative analysis of hematoxylin and eosin-stained (H&E) histopathological slides by both an experienced medical technologist and a pathologist. The recent development of digital whole slide scanners makes AI-based histopathological image analysis feasible and helps to diagnose cancer by accurately counting cell types and/or quantitative analysis. However, the technology available for digital slide image analysis is still very limited. This study aimed to build an image feature-based computer model using histopathology whole slide images to differentiate patients with glioblastoma (GBM) from healthy control (HC).MethodTwo independent cohorts of patients were used. The first cohort was composed of 262 GBM patients of the Cancer Genome Atlas Glioblastoma Multiform Collection (TCGA-GBM) dataset from the cancer imaging archive (TCIA) database. The second cohort was composed of 60 GBM patients collected from a local hospital. Also, a group of 60 participants with no known brain disease were collected. All the H&E slides were collected. Thirty-three image features (22 GLCM and 11 GLRLM) were retrieved from the tumor volume delineated by medical technologist on H&E slides. Five machine-learning algorithms including decision-tree (DT), extreme-boost (EB), support vector machine (SVM), random forest (RF), and linear model (LM) were used to build five models using the image features extracted from the first cohort of patients. Models built were deployed using the selected key image features for GBM diagnosis from the second cohort (local patients) as model testing, to identify and verify key image features for GBM diagnosis.ResultsAll five machine learning algorithms demonstrated excellent performance in GBM diagnosis and achieved an overall accuracy of 100% in the training and validation stage. A total of 12 GLCM and 3 GLRLM image features were identified and they showed a significant difference between the normal and the GBM image. However, only the SVM model maintained its excellent performance in the deployment of the models using the independent local cohort, with an accuracy of 93.5%, sensitivity of 86.95%, and specificity of 99.73%.ConclusionIn this study, we have identified 12 GLCM and 3 GLRLM image features which can aid the GBM diagnosis. Among the five models built, the SVM model proposed in this study demonstrated excellent accuracy with very good sensitivity and specificity. It could potentially be used for GBM diagnosis and future clinical application.
| S-EPMC10605241 | biostudies-literature
Project description:In this article we present a data set that contains 37 image files obtained by manual vessel segmentation of raw retinal images from Structured Analysis of the Retina (STARE) database ("The STARE Project", 2018) [1]. Our expert segmented 8 images that are associated with the single diagnosis of hypertensive retinopathy and 9 images with the single diagnosis of proliferative diabetic retinopathy (Popovic et al., 2018) [2]. To validate the manual segmentation, the same expert additionally segmented a gold standard set of 20 raw images from the STARE database. Raw images of retinas associated with either diabetic proliferative retinopathy or hypertensive retinopathy display the intricate and very different morphologies of retinal microvascular networks. Very frequently, they also have pathological changes such as exudates and hemorrhages. The presence of these changes, as well as neovascularization in proliferative diabetic retinopathy, poses a significant challenge for researchers who are developing automatic methods for retinal vessel segmentation. Therefore, this data set can be useful for the development of methods for automatic segmentation. In addition, the data can be used for development of methods for quantitation of microvascular morphology of the retina in various pathological conditions.
| S-EPMC5996258 | biostudies-literature
Project description:BackgroundThe aim of this study was to explore the feasibility of assisted diagnosis of active (peri-)aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images.MethodsThe aorta was manually segmented on FDG PET-CT in 50 patients with aortitis and 25 controls. Radiomic features (RF) (n = 107), including SUV (Standardized Uptake Value) metrics, were extracted from the segmented data and harmonized using the ComBat technique. Individual RFs and groups of RFs (i.e., signatures) were used as input in Machine Learning classifiers. The diagnostic utility of these classifiers was evaluated with area under the receiver operating characteristic curve (AUC) and accuracy using the clinical diagnosis as the ground truth.ResultsSeveral RFs had high accuracy, 84% to 86%, and AUC scores 0.83 to 0.97 when used individually. Radiomic signatures performed similarly, AUC 0.80 to 1.00.ConclusionA methodological framework for a radiomic-based approach to support diagnosis of aortitis was outlined. Selected RFs, individually or in combination, showed similar performance to the current standard of qualitative assessment in terms of AUC for identifying active aortitis. This framework could support development of a clinical decision-making tool for a more objective and standardized assessment of aortitis.
| S-EPMC9834376 | biostudies-literature
Project description:BackgroundLeprosy is an infectious disease that mostly affects underserved populations. Although it has been largely eliminated, still about 200'000 new patients are diagnosed annually. In the absence of a diagnostic test, clinical diagnosis is often delayed, potentially leading to irreversible neurological damage and its resulting stigma, as well as continued transmission. Accelerating diagnosis could significantly contribute to advancing global leprosy elimination. Digital and Artificial Intelligence (AI) driven technology has shown potential to augment health workers abilities in making faster and more accurate diagnosis, especially when using images such as in the fields of dermatology or ophthalmology. That made us start the quest for an AI-driven diagnosis assistant for leprosy, based on skin images.MethodsHere we describe the accuracy of an AI-enabled image-based diagnosis assistant for leprosy, called AI4Leprosy, based on a combination of skin images and clinical data, collected following a standardized process. In a Brazilian leprosy national referral center, 222 patients with leprosy or other dermatological conditions were included, and the 1229 collected skin images and 585 sets of metadata are stored in an open-source dataset for other researchers to exploit.FindingsWe used this dataset to test whether a CNN-based AI algorithm could contribute to leprosy diagnosis and employed three AI models, testing images and metadata both independently and in combination. AI modeling indicated that the most important clinical signs are thermal sensitivity loss, nodules and papules, feet paresthesia, number of lesions and gender, but also scaling surface and pruritus that were negatively associated with leprosy. Using elastic-net logistic regression provided a high classification accuracy (90%) and an area under curve (AUC) of 96.46% for leprosy diagnosis.InterpretationFuture validation of these models is underway, gathering larger datasets from populations of different skin types and collecting images with smartphone cameras to mimic real world settings. We hope that the results of our research will lead to clinical solutions that help accelerate global leprosy elimination.FundingThis study was partially funded by Novartis Foundation and Microsoft (in-kind contribution).
| S-EPMC9903738 | biostudies-literature
Project description:In this report, the synthesis of poly(ω-pentadecalactone) (PPDL) (co)polymers and their incorporation into polyurethanes (PUs) are reported. Optimal conditions for the ring-opening polymerization (ROP) of ω-pentadecalactone (PDL) using dibutyltin dilaurate catalyst were established. For the synthesis of linear and crosslinked PUs, 50 kDa poly(ε-caprolactone) (PCL) and 1,6-hexamethylenediisocyanate (HDI) were used. The obtained polyurethanes were characterized by Attenuated Total Reflectance Fourier-Transform Infrared spectroscopy (AT-FTIR), differential scanning calorimetry (DSC), and dynamical mechanical analysis (DMA). The DMA of the selected sample showed a rubbery plateau on the storage modulus versus temperature curve predicting shape memory behavior. Indeed, good shape memory performances were obtained with shape fixity (Rf) and shape recovery (Rr) ratios.
| S-EPMC7563291 | biostudies-literature
Project description:The distribution and appearance of nuclei are essential markers for the diagnosis and study of cancer. Despite the importance of nuclear morphology, there is a lack of large scale, accurate, publicly accessible nucleus segmentation data. To address this, we developed an analysis pipeline that segments nuclei in whole slide tissue images from multiple cancer types with a quality control process. We have generated nucleus segmentation results in 5,060 Whole Slide Tissue images from 10 cancer types in The Cancer Genome Atlas. One key component of our work is that we carried out a multi-level quality control process (WSI-level and image patch-level), to evaluate the quality of our segmentation results. The image patch-level quality control used manual segmentation ground truth data from 1,356 sampled image patches. The datasets we publish in this work consist of roughly 5 billion quality controlled nuclei from more than 5,060 TCGA WSIs from 10 different TCGA cancer types and 1,356 manually segmented TCGA image patches from the same 10 cancer types plus additional 4 cancer types.
| S-EPMC7305328 | biostudies-literature