An official website of the United States government
As the most lethal major cancer, pancreatic cancer is a global healthcare challenge. Personalized medicine utilizing cutting-edge multi-omics data holds potential for major breakthroughs in tackling this critical problem. Radiomics and deep learning, two trendy quantitative imaging methods that take advantage of data science and modern medical imaging, have shown increasing promise in advancing the precision management of pancreatic cancer via diagnosing of precursor diseases, early detection, accurate diagnosis, and treatment personalization and optimization. Radiomics employs manually-crafted features, while deep learning applies computer-generated automatic features. These two methods aim to mine hidden information in medical images that is missed by conventional radiology and gain insights by systematically comparing the quantitative image information across different patients in order to characterize unique imaging phenotypes. Both methods have been studied and applied in various pancreatic cancer clinical applications. In this review, we begin with an introduction to the clinical problems and the technology. After providing technical overviews of the two methods, this review focuses on the current progress of clinical applications in precancerous lesion diagnosis, pancreatic cancer detection and diagnosis, prognosis prediction, treatment stratification, and radiogenomics. The limitations of current studies and methods are discussed, along with future directions. With better standardization and optimization of the workflow from image acquisition to analysis and with larger and especially prospective high-quality datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through big data-based high-precision personalization.
more »
« less
Towards AR-assisted Visualization and Guidance for Imaging of Dental Decay
Untreated dental decay is the most prevalent dental problem in the world, affecting up to 2.4 billion people and leading to significant economic and social burden. Early detection can greatly mitigate irreversible effects of dental decay, avoiding the need for expensive restorative treatment that forever disrupts the enamel protective layer of teeth. However, two key challenges exist that make early decay management difficult: unreliable detection, and lack of quantitative monitoring during treatment. New optically-based imaging through the enamel provides the dentist a safe means to detect, locate, and monitor the healing process. This work explores the use of an Augmented Reality (AR) headset to improve the workflow of early decay therapy and monitoring. The proposed workflow includes two novel AR-enabled features: 1) in-situ visualization of pre-operative optically-based dental images and 2) augmented guidance for repetitive imaging during therapy monitoring. The workflow is designed to minimize distraction, mitigate hand-eye coordination problems, and help guide monitoring of early decay during therapy in both clinical and mobile environments. The results from quantitative evaluations as well as a formative qualitative user study uncover the potentials of our system and indicates that AR can serve as a promising tool in tooth decay management.
more »
« less
- Award ID(s):
- 1631146
- PAR ID:
- 10117242
- Date Published:
- Journal Name:
- Healthcare technology letters
- ISSN:
- 2053-3713
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Several studies have shown that near-infrared imaging has great potential for the detection of dental caries lesions. A miniature scanning fiber endoscope (SFE) operating at near-infrared (NIR) wavelengths was developed and used in this study to test whether the device could be used to discriminate demineralized enamel from sound enamel. Varying depths of artificial enamel caries lesions were prepared on 20 bovine blocks with smooth enamel surfaces. Samples were imaged with a SFE operating in the reflectance mode at 1310-nm and 1460-nm in both wet and dry conditions. The measurements acquired by the SFE operating at 1460-nm show significant difference between the sound and the demineralized enamel. There was a moderate positive correlation between the SFE measurements and micro-CT measurements, and the NIR SFE was able to detect the presence of demineralization with high sensitivity (0.96) and specificity (0.85). This study demonstrates that the NIR SFE can be used to detect early demineralization from sound enamel. In addition, the NIR SFE can differentiate varying severities of demineralization. With its very small form factor and maneuverability, the NIR SFE should allow clinicians to easily image teeth from multiple viewing angles in real-time.more » « less
-
BackgroundComponents of diet known as fallback foods are argued to be critical in shaping primate dental anatomy. Such foods of low(er) nutritional quality are often non-preferred, mechanically challenging resources that species resort to during ecological crunch periods. An oft-cited example of the importance of dietary fallbacks in shaping primate anatomy is the grey-cheeked mangabeyLophocebus albigena. This species relies upon hard seeds only when softer, preferred resources are not available, a fact which has been linked to its thick dental enamel. Another mangabey species with thick enamel, the sooty mangabeyCercocebus atys, processes a mechanically challenging food year-round. That the two mangabey species are both thickly-enameled suggests that both fallback and routine consumption of hard foods are associated with the same anatomical feature, complicating interpretations of thick enamel in the fossil record. We anticipated that aspects of enamel other than its thickness might differ betweenCercocebus atysandLophocebus albigena.We hypothesized that to function adequately under a dietary regime of routine hard-object feeding, the molars ofCercocebus atyswould be more fracture and wear resistant than those ofLophocebus albigena. MethodsHere we investigated critical fracture loads, nanomechanical properties of enamel, and enamel decussation inCercocebus atysandLophocebus albigena.Molars ofCercopithecus, a genus not associated with hard-object feeding, were included for comparison. Critical loads were estimated using measurements from 2D µCT slices of upper and lower molars. Nanomechanical properties (by nanoindentation) and decussation of enamel prisms (by SEM-imaging) in trigon basins of one upper second molar per taxon were compared. ResultsProtocone and protoconid critical fracture loads were significantly greater inCercocebus atysthanLophocebus albigenaand greater in both than inCercopithecus. Elastic modulus, hardness, and elasticity index in most regions of the crown were greater inCercocebus atysthan in the other two taxa, with the greatest difference in the outer enamel. All taxa had decussated enamel, but that ofCercocebus atysuniquely exhibited a bundle of transversely oriented prisms cervical to the radial enamel. Quantitative comparison of in-plane and out-of-plane prism angles suggests that decussation in trigon basin enamel is more complex inCercocebus atysthan it is in eitherLophocebus albigenaorCercopithecus cephus. These findings suggest thatCercocebus atysmolars are more fracture and wear resistant than those ofLophocebus albigenaandCercopithecus. Recognition of these differences betweenCercocebus atysandLophocebus albigenamolars sharpens our understanding of associations between hard-object feeding and dental anatomy under conditions of routine vs. fallback hard-object feeding and provides a basis for dietary inference in fossil primates, including hominins.more » « less
-
Augmented Reality (AR) experiences tightly associate virtual contents with environmental entities. However, the dissimilarity of different environments limits the adaptive AR content behaviors under large-scale deployment. We propose ScalAR, an integrated workflow enabling designers to author semantically adaptive AR experiences in Virtual Reality (VR). First, potential AR consumers collect local scenes with a semantic understanding technique. ScalAR then synthesizes numerous similar scenes. In VR, a designer authors the AR contents’ semantic associations and validates the design while being immersed in the provided scenes. We adopt a decision-tree-based algorithm to fit the designer’s demonstrations as a semantic adaptation model to deploy the authored AR experience in a physical scene. We further showcase two application scenarios authored by ScalAR and conduct a two-session user study where the quantitative results prove the accuracy of the AR content rendering and the qualitative results show the usability of ScalAR.more » « less
-
Biomarkers are vital in healthcare as they provide valuable insights into disease diagnosis, prognosis, treatment response, and personalized medicine. They serve as objective indicators, enabling early detection and intervention, leading to improved patient outcomes and reduced costs. Biomarkers also guide treatment decisions by predicting disease outcomes and facilitating individualized treatment plans. They play a role in monitoring disease progression, adjusting treatments, and detecting early signs of recurrence. Furthermore, biomarkers enhance drug development and clinical trials by identifying suitable patients and accelerating the approval process. In this review paper, we described a variety of biomarkers applicable for cancer detection and diagnosis, such as imaging-based diagnosis (CT, SPECT, MRI, and PET), blood-based biomarkers (proteins, genes, mRNA, and peptides), cell imaging-based diagnosis (needle biopsy and CTC), tissue imaging-based diagnosis (IHC), and genetic-based biomarkers (RNAseq, scRNAseq, and spatial transcriptomics).more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
