Effort-Free Automated Skeletal Abnormality Detection of Rat Fetuses on Whole-Body Micro-Ct Scans

AbstractComputational decision support systems could provide clinical value in whole-body FDG-PET/CT workflows. However, limited availability of labeled data combined with the large size of PET/CT imaging exams make it challenging to apply existing supervised machine learning systems. Leveraging recent advancements in natural language processing, we describe a weak supervision framework that extracts imperfect, yet highly granular, regional abnormality labels from free-text radiology reports. Our framework automatically labels each region in a custom ontology of anatomical regions, providing a structured profile of the pathologies in each imaging exam. Using these generated labels, we then train an attention-based, multi-task CNN architecture to detect and estimate the location of abnormalities in whole-body scans. We demonstrate empirically that our multi-task representation is critical for strong performance on rare abnormalities with limited training data. The representation also contributes to more accurate mortality prediction from imaging data, suggesting the potential utility of our framework beyond abnormality detection and location estimation.

Download Full-text

Simple low dose radiography allows precise lung volume assessment in mice

Scientific Reports ◽

10.1038/s41598-021-83319-5 ◽

2021 ◽

Vol 11 (1) ◽

Cited By ~ 1

Author(s):

Amara Khan ◽

Andrea Markus ◽

Thomas Rittmann ◽

Jonas Albers ◽

Frauke Alves ◽

...

Keyword(s):

Lung Function ◽

Whole Body ◽

Acquisition Time ◽

Micro Ct ◽

Lung Volumes ◽

X Ray ◽

Promising Tool ◽

Volume Assessment ◽

Set Up ◽

Time Required

AbstractX-ray based lung function (XLF) as a planar method uses dramatically less X-ray dose than computed tomography (CT) but so far lacked the ability to relate its parameters to pulmonary air volume. The purpose of this study was to calibrate the functional constituents of XLF that are biomedically decipherable and directly comparable to that of micro-CT and whole-body plethysmography (WBP). Here, we developed a unique set-up for simultaneous assessment of lung function and volume using XLF, micro-CT and WBP on healthy mice. Our results reveal a strong correlation of lung volumes obtained from radiographic XLF and micro-CT and demonstrate that XLF is superior to WBP in sensitivity and precision to assess lung volumes. Importantly, XLF measurement uses only a fraction of the radiation dose and acquisition time required for CT. Therefore, the redefined XLF approach is a promising tool for preclinical longitudinal studies with a substantial potential of clinical translation.

Download Full-text

Micro-CT to Document the Coffee Bean Weevil, Araecerus fasciculatus (Coleoptera: Anthribidae), Inside Field-Collected Coffee Berries (Coffea canephora)

Insects ◽

10.3390/insects9030100 ◽

2018 ◽

Vol 9 (3) ◽

pp. 100 ◽

Cited By ~ 1

Author(s):

Ignacio Alba-Alejandre ◽

Javier Alba-Tercedor ◽

Fernando Vega

Keyword(s):

Computerized Tomography ◽

Instar Larva ◽

Coffea Canephora ◽

Ct Scans ◽

Coffee Bean ◽

Micro Ct ◽

Adult Beetle ◽

Bean Weevil ◽

Coffee Berry ◽

First Time

The coffee bean weevil, Araecerus fasciculatus (De Geer) (Coleoptera: Anthribidae), is a cosmopolitan insect with >100 hosts, and has been reported as a pest of stored coffee. During a study involving the coffee berry borer, we observed coffee bean weevils emerging from field-collected coffee berries and used micro-computerized tomography (micro-CT) scans to observe the insect inside the berry. Two eggs had eclosed inside the berry, resulting in observations of a newly eclosed adult beetle and a 5th instar larva, each feeding on one of the two seeds. This is the first time since 1775, when the insect was first described, that the insect has been observed inside a coffee berry.

Download Full-text

Histomorphologic Analysis of the Late-term Rat Fetus and Placenta

Toxicologic Pathology ◽

10.1177/0192623318755135 ◽

2018 ◽

Vol 46 (2) ◽

pp. 158-168 ◽

Cited By ~ 3

Author(s):

Phanie L. Charest ◽

Vanessa Vrolyk ◽

Pauline Herst ◽

Maryse Lessard ◽

Deborah M. Sloboda ◽

...

Keyword(s):

Cutting Planes ◽

Whole Body ◽

Future Research ◽

Serial Sectioning ◽

Sprague Dawley ◽

Rat Fetus ◽

Rat Fetuses ◽

Toxicological Studies ◽

Hematoxylin Eosin ◽

Gross Examination

Histological examination of the rat placenta and fetus is uncommon. Toxicological studies mainly rely on gross examination of the fetus and on fetal and placental weights. These are often insufficient to assess the fetal and placental toxicity of xenobiotics. The small size of the fetus makes its dissection labor-intensive. Thus, our objective was to develop a simple and accurate technique to evaluate the rat fetus and placenta. Sprague-Dawley rat fetuses at gestational day 19.5 ( n = 18) and their placentas ( n = 32) were fixed in formalin. Placentas were cut transversally in the center. Fetuses were cut following a freehand whole-body serial sectioning diagram adapted from Wilson’s method. Sections were stained with hematoxylin–eosin–phloxine–saffron, and histomorphometry was used to measure the area of the fetal placental region (27.2 ± 1.7 mm2), including the labyrinth (22.2 ± 1.0 mm2) and the basal zone (4.8 ± 0.8 mm2). Our whole-fetus serial sectioning technique resulted in 12 precise cutting planes that fit on 3 histological slides, enabling the examination of most organs without labor-intensive dissection. Quantitative analysis of placental areas improves the understanding of the pathogenesis of treatment-related changes. This technique provides a standardized method for future research in pertinent fields such as developmental biology and toxicology.

Download Full-text

Deep Learning Based Automated Orthotopic Lung Tumor Segmentation in Whole-Body Mouse CT-Scans

Cancers ◽

10.3390/cancers13184585 ◽

2021 ◽

Vol 13 (18) ◽

pp. 4585

Author(s):

Wouter R. P. H. van de Worp ◽

Brent van der Heyden ◽

Georgios Lappas ◽

Ardy van Helvoort ◽

Jan Theys ◽

...

Keyword(s):

Lung Cancer ◽

Deep Learning ◽

Tumor Growth ◽

Tumor Volume ◽

Learning Algorithm ◽

Lung Tumor ◽

Whole Body ◽

Ct Scans ◽

Therapeutic Effects ◽

Deep Learning Algorithm

Lung cancer is the leading cause of cancer related deaths worldwide. The development of orthotopic mouse models of lung cancer, which recapitulates the disease more realistically compared to the widely used subcutaneous tumor models, is expected to critically aid the development of novel therapies to battle lung cancer or related comorbidities such as cachexia. However, follow-up of tumor take, tumor growth and detection of therapeutic effects is difficult, time consuming and requires a vast number of animals in orthotopic models. Here, we describe a solution for the fully automatic segmentation and quantification of orthotopic lung tumor volume and mass in whole-body mouse computed tomography (CT) scans. The goal is to drastically enhance the efficiency of the research process by replacing time-consuming manual procedures with fast, automated ones. A deep learning algorithm was trained on 60 unique manually delineated lung tumors and evaluated by four-fold cross validation. Quantitative performance metrics demonstrated high accuracy and robustness of the deep learning algorithm for automated tumor volume analyses (mean dice similarity coefficient of 0.80), and superior processing time (69 times faster) compared to manual segmentation. Moreover, manual delineations of the tumor volume by three independent annotators was sensitive to bias in human interpretation while the algorithm was less vulnerable to bias. In addition, we showed that besides longitudinal quantification of tumor development, the deep learning algorithm can also be used in parallel with the previously published method for muscle mass quantification and to optimize the experimental design reducing the number of animals needed in preclinical studies. In conclusion, we implemented a method for fast and highly accurate tumor quantification with minimal operator involvement in data analysis. This deep learning algorithm provides a helpful tool for the noninvasive detection and analysis of tumor take, tumor growth and therapeutic effects in mouse orthotopic lung cancer models.

Download Full-text

Investigations of size effect in concrete during splitting using DEM combined with X-Ray Micro-CT scans

10.21012/fc10.233583 ◽

2019 ◽

Author(s):

J Suchorzewski

Keyword(s):

Size Effect ◽

Ct Scans ◽

Micro Ct ◽

X Ray

Download Full-text

An ornithurine bird coracoid from the Late Cretaceous of Alberta, Canada

Canadian Journal of Earth Sciences ◽

10.1139/cjes-2019-0202 ◽

2020 ◽

pp. 1-7

Author(s):

Sydney R. Mohr ◽

John H. Acorn ◽

Gregory F. Funston ◽

Philip J. Currie

Keyword(s):

North America ◽

Late Cretaceous ◽

Ct Scans ◽

Micro Ct ◽

Internal Structures ◽

Postcranial Remains ◽

Dinosaur Park Formation ◽

Upper Campanian

The Cretaceous birds of Alberta are poorly known, as skeletal elements are rare and typically consist of fragmentary postcranial remains. A partial avian coracoid from the upper Campanian Dinosaur Park Formation of Alberta, Canada, can be referred to the Ornithurae, and is referred to here as Ornithurine G (cf. Cimolopteryx). Its structure is similar to previously described ornithurine coracoids from Alberta and other localities in North America, particularly those belonging to the genus Cimolopteryx. A comparison of these elements indicates that the new coracoid is distinct; however, its preservation prevents complete diagnosis. As other Cimolopteryx are Maastrichtian in age, Ornithurine G (cf. Cimolopteryx) also represents the earliest occurrence of a Cimolopteryx-like anatomy. A pneumatized coracoid is a diagnostic trait of Neornithes, identified by the presence of a pneumatic foramen. Ornithurine G (cf. Cimolopteryx) does not preserve this feature. CT and micro-CT scans of both pneumatic and apneumatic coracoids of modern birds show similar internal structures to Ornithurine G (cf. Cimolopteryx), indicating that pneumaticity of the coracoid cannot be determined in the absence of an external pneumatic foramen. A comparison between members of Cimolopterygidae, including Cimolopteryx and Lamarqueavis, raises questions about the assignment of Lamarqueavis to the Cimolopterygidae, and the validity of this family as a whole.

Download Full-text