Article
Multidisciplinary Sciences
Kaveri A. Thakoor, Jiaang Yao, Darius Bordbar, Omar Moussa, Weijie Lin, Paul Sajda, Royce W. S. Chen
Summary: This study describes a deep learning approach using multimodal data to detect age-related macular degeneration (AMD) and its biomarkers. By applying Convolutional Neural Networks (CNNs), the accuracy of biomarker prediction reached up to 90.2% (with a positive predictive value of up to 75.8%), offering the potential to expedite screening of early and late-stage AMD patients.
SCIENTIFIC REPORTS
(2022)
Article
Cell Biology
Jianhao Bai, Zhongqi Wan, Ping Li, Lei Chen, Jingcheng Wang, Yu Fan, Xinjian Chen, Qing Peng, Peng Gao
Summary: The study confirmed the high accuracy, sensitivity, and specificity of artificial intelligence-assisted optical coherence tomography in the automatic detection of 15 retinal disorders. Compared with the expert group, AI had the closest performance, demonstrating its feasibility and effectiveness in community ophthalmic screening.
FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY
(2022)
Article
Ophthalmology
Emanuele Crincoli, Silvia Ferrara, Alexandra Miere, Riccardo Sacconi, Marco Battista, Fiammetta Catania, Eric H. H. Souied, Giuseppe Querques
Summary: This study aims to investigate the correlation between the AI-measured area of the lacquer cracks (LC) and the occurrence of choroidal neovascularization (CNV) in pathologic myopia patients. The study found that larger LC area is associated with a higher probability of CNV development, and the faster the increase in LC area, the earlier the onset of CNV.
Article
Engineering, Chemical
Adnan Qamar, Sarah Kerdi, Najat Amin, Xiangliang Zhang, Johannes Vrouwenvelder, Noreddine Ghaffour
Summary: This study utilizes deep neural networks and optical coherence tomography (OCT) scans to measure and predict the thickness of biofilm inside the filtration channels module. It establishes an intelligent control strategy by connecting biofilm growth with hydrodynamic parameters. The results show that the framework has a high accuracy and potential for measuring and controlling the biofilm thickness.
SEPARATION AND PURIFICATION TECHNOLOGY
(2022)
Article
Biochemical Research Methods
Alexandre Abid, Renaud Duval, Christos Boutopoulos
Summary: A method to encase OCT probes into polyimide subretinal injection cannulas was introduced and validated. The system achieved a high success rate of 95.0% for subretinal injection, with a significant portion of the injected volume reaching the subretinal space.
BIOMEDICAL OPTICS EXPRESS
(2022)
Article
Oncology
Hung-Chang Liu, Miao-Hui Lin, Wei-Chin Chang, Rui-Cheng Zeng, Yi-Min Wang, Chia-Wei Sun
Summary: This study proposes an interactive human-machine interface (HMI) that integrates a mobile OCT system, deep learning algorithms, and attention mechanisms for real-time tumor grading and accurate diagnosis. The results show that the HMI system outperforms frozen sections, achieving an overall accuracy of 84.9%. This highlights the potential of the HMI system for rapid diagnostics and improved patient outcomes.
Article
Multidisciplinary Sciences
Verina Hanna, Jonathan Oakley, Daniel Russakoff, Netan Choudhry
Summary: This study found sectoral increases in retinal outer layer thickness in the temporal and inferior sectors, as well as increases in sub-RPE space and photoreceptor complex thicknesses, and decreases in inner nuclear layer and outer nuclear layer thicknesses at 6 months post-SNL treatment. The pilot study demonstrates the use of OCT with artificial intelligence-enabled software in tracking retinal changes after SNL treatment in intermediate ARMD patients.
Article
Multidisciplinary Sciences
Yingbo Yan, Tianlu Wang, Rongjing Zhang, Yilun Liu, Wenqi Hu, Metin Sitti
Summary: Methodologies based on intravascular imaging have revolutionized the diagnosis and treatment of endovascular diseases. However, current methods are limited in detecting complicated occluded vessels. Therefore, a miniature soft tool has been proposed to visualize and cross occlusions with various morphologies, which could enhance the efficacy of minimally invasive medicine for the diagnosis and treatment of occlusions in various circulatory systems.
Article
Biochemical Research Methods
Guangqian Yang, Emile Mehanna, Chao Li, Hongyi Zhu, Chong He, Fang Lu, Ke Zhao, Yubin Gong, Zhao Wang
Summary: This study developed a deep learning method to automatically analyze stents with different thicknesses and vessels implanted with multiple stents, providing effective assistance for the evaluation of stent implantation and post-stent tissue coverage.
BIOMEDICAL OPTICS EXPRESS
(2021)
Article
Chemistry, Multidisciplinary
ByungKun Lee, Sunhong Jeong, Joosung Lee, Tae Shik Kim, Boy Braaf, Benjamin J. J. Vakoc, Wang-Yuhl Oh
Summary: This work demonstrates 3D depth-invariant cellular-resolution imaging of the living human retina over a 3 x 3 mm field of view using the first intrinsically phase-stable multi-MHz retinal swept-source OCT and novel computational methods. It provides wide-field 3D cellular-resolution imaging in the human retina, which can bring a great impact in clinical ophthalmology.
Article
Optics
Jianan Fang, Kun Huang, E. Wu, Ming Yan, Heping Zeng
Summary: This article introduces an infrared 3D imaging system capable of detecting three-dimensional structure and reflectivity information. The system operates at single-photon sensitivity and femtosecond timing resolution, enabling imaging under low-light conditions. By nonlinear frequency upconversion and recording with a silicon camera, the presented system achieves high lateral and depth resolutions for 3D reconstruction. Additionally, a numerical denoiser based on spatiotemporal correlation allows the retrieval of object profile and reflectivity even with a detected flux below 0.05 photons/pixel/second. This infrared 3D imager features high detection sensitivity, precise timing resolution, and wide-field operation, offering new possibilities in life and material sciences.
LIGHT-SCIENCE & APPLICATIONS
(2023)
Article
Ophthalmology
Namrata Sharma, Chandra Devi, Rinky Agarwal, Rahul Kumar Bafna, Amar Agarwal
Summary: In this study, i-OCT was successfully utilized in various surgical steps of PDEK, resulting in clear and well-attached grafts postoperatively, significant improvement in visual acuity, and stability in postoperative outcomes.
JOURNAL OF CATARACT AND REFRACTIVE SURGERY
(2021)
Article
Medicine, General & Internal
Gopi Maguluri, John Grimble, Aliana Caron, Ge Zhu, Savitri Krishnamurthy, Amanda McWatters, Gillian Beamer, Seung-Yi Lee, Nicusor Iftimia
Summary: This paper introduces a combined optical imaging/artificial intelligence (OI/AI) technique for real-time analysis of tissue morphology at the tip of the biopsy needle. The technique uses micron-scale-resolution optical coherence tomography (OCT) images collected with a minimally invasive needle probe and analyzed using AI software. The evaluation on a rabbit model of cancer shows very close performance between the AI model and human classification tasks, with excellent tissue segmentation and high accuracy for tumor and non-tumor classification.
Article
Computer Science, Artificial Intelligence
Mingchuan Zhou, Xiangyu Guo, Matthias Grimm, Elias Lochner, Zhongliang Jiang, Abouzar Eslami, Juan Ye, Nassir Navab, Alois Knoll, Mohammad Ali Nasseri
Summary: In this paper, a robust framework is proposed for needle detection and localisation in robot-assisted subretinal injection using microscope-integrated Optical Coherence Tomography with deep learning. Five different architectures of convolutional neural networks were evaluated, and the top performing network successfully detected all needles and localised them with an Intersection over Union value of 0.55. The algorithm was evaluated by comparing the depth of the predicted bounding box to the ground truth, and the top edge was found to have a maximum error of 8.5 mu m in predicting the depth of the needle.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Optics
Zunyue Zhang, Yi Wang, Jiarui Wang, Dan Yi, David Weng U. Chan, Wu Yuan, Hon Ki Tsang
Summary: In this study, a compact integrated scanning spectrometer is proposed, which utilizes a tunable micro-ring resonator and a single arrayed waveguide grating to achieve wide optical bandwidths and high spectral resolutions. The integrated spectrometer with germanium photodetectors demonstrates excellent performance.
PHOTONICS RESEARCH
(2022)
Article
Clinical Neurology
Eddie Luidy Imada, Diego Strianese, Deepak P. Edward, Rawan AlThaqib, Antionette Price, Antje Arnold, Hailah Al-Hussain, Luigi Marchionni, Fausto J. Rodriguez
Summary: The study identified gene expression differences between orbitofacial NFs and NFs occurring at other locations, suggesting that orbitofacial NFs may have higher local aggressiveness and treatment challenges. Further investigation may be warranted given the disproportionate morbidity associated with orbitofacial NFs.
Article
Pathology
Pouya Jamshidi, Jonathan Levi, Maria Jose Suarez, Roxana Rivera, Nicholas Mahoney, Charles G. Eberhart, Avi Rosenberg, Fausto J. Rodriguez
Summary: Ocular amyloidomas involving the ocular adnexa exhibit a variety of amyloid-related and immunoglobulin-associated peptides. The lambda light chain is predominantly present, but mixed patterns and rarely kappa light chain restriction may also be observed. The study highlights the clinicopathologic and proteomic characteristics of periocular amyloid deposition in a retrospective review of cases from 1991 to 2020.
AMERICAN JOURNAL OF CLINICAL PATHOLOGY
(2022)
Article
Clinical Neurology
Martin Hasselblatt, Christian Thomas, Aniello Federico, Susanne Bens, Mats Hellstrom, Olivera Casar-Borota, Uwe Kordes, Julia E. Neumann, Matthias Dottermusch, Fausto J. Rodriguez, Andrea C. Lo, Sylvia Cheng, Glenda Hendson, Juliette Hukin, Christian Hartmann, Arend Koch, David Capper, Reiner Siebert, Werner Paulus, Karolina Nemes, Pascal D. Johann, Michael C. Fruehwald, Marcel Kool
Summary: Low-grade diffusely infiltrative tumour (LGDIT), SMARCB1-mutant, is a distinctive low-grade lesion found in older children and young adults, showing epigenetic similarity with ATRT-MYC and having the potential for malignant progression.
NEUROPATHOLOGY AND APPLIED NEUROBIOLOGY
(2022)
Article
Ophthalmology
Sara E. Lally, Tatyana Milman, Marlana Orloff, Lauren A. Dalvin, Charles G. Eberhart, Christopher M. Heaphy, Fausto J. Rodriguez, Chun-Chieh Lin, Philip W. Dockery, Jerry A. Shields, Carol L. Shields
Summary: This study evaluates targetable mutations and molecular genetic pathways in conjunctival melanoma with clinical correlation.
Article
Biochemistry & Molecular Biology
Patience Odeniyide, Marielle E. Yohe, Kai Pollard, Angelina V. Vaseva, Ana Calizo, Lindy Zhang, Fausto J. Rodriguez, John M. Gross, Amy N. Allen, Xiaolin Wan, Romel Somwar, Karisa C. Schreck, Linda Kessler, Jiawan Wang, Christine A. Pratilas
Summary: This study suggests that the FTase inhibitor tipifarnib may be an effective therapeutic strategy for a subset of fusion-negative RMS patients, especially those with HRAS mutations.
Correction
Biochemistry & Molecular Biology
Patience Odeniyide, Marielle E. Yohe, Kai Pollard, Angelina V. Vaseva, Ana Calizo, Lindy Zhang, Fausto J. Rodriguez, John M. Gross, Amy N. Allen, Xiaolin Wan, Romel Somwar, Karisa C. Schreck, Linda Kessler, Jiawan Wang, Christine A. Pratilas
Article
Mathematics
Maria T. Orvananos-Guerrero, Mario Acevedo, Claudia N. Sanchez, Daniel U. Campos-Delgado, Amir Aminzadeh Ghavifekr, Paolo Visconti, Ramiro Velazquez
Summary: This paper presents a novel approach to complete balancing optimization of a six-bar mechanism using counterweights. By solving a multi-objective optimization problem, the system is balanced by minimizing shaking force and shaking moment. The use of fully Cartesian coordinates and the Pareto front determination contribute to the effectiveness of this approach.
Editorial Material
Clinical Neurology
Fausto J. Rodriguez
Article
Engineering, Multidisciplinary
Roberto Marani, Daniel U. Campos-Delgado
Summary: This paper presents a method for automatically analyzing surface thermograms to classify buried defects in composite materials. The time-dependent thermal contrasts captured from the sample surface are linearly unmixed to produce results independent of the defect shapes. The method shows promising results in defect classification without the need for inspections with different source excitations.
COMPOSITES PART B-ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Andres A. Valdez-Fernandez, Gerardo Escobar, Daniel U. Campos-Delgado, Moises E. Hernandez-Ruiz
Summary: This paper presents a control methodology for a three-phase cascaded H-bridge (3ph-CHB) converter in the general case of n-levels (3ph-CHB-nL). The proposed method is used to compensate reactive power and eliminate harmonic currents caused by non-linear loads. The controller solution includes a current tracking loop, regulation and balance voltage loops, and an internal control loop for line current tracking. Experimental results on a three-phase five-level CHB (3ph-CHB-5L) prototype are provided to assess the performance of the proposed controller.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2023)
Article
Computer Science, Information Systems
Omar Gutierrez-Navarro, Liliana Granados-Castro, Aldo Rodrigo Mejia-Rodriguez, Daniel U. Campos-Delgado
Summary: The increasing prevalence of vascular diseases has led to the development of minimally invasive approaches for tissue perfusion assessment. However, the current methods face a challenge of lacking clinical data validation. In this study, an open-source database was introduced to evaluate tissue perfusion during an occlusion protocol, using multi-spectral images and photoplethysmography data for validation. The findings showed a strong correlation between changes in hemoglobin levels and multi-spectral based perfusion parameters, indicating the usefulness of this database for further in-vivo perfusion research.
Article
Oncology
Raquel Leon, Himar Fabelo, Samuel Ortega, Ines A. Cruz-Guerrero, Daniel Ulises Campos-Delgado, Adam Szolna, Juan F. Pineiro, Carlos Espino, Aruma J. O'Shanahan, Maria Hernandez, David Carrera, Sara Bisshopp, Coralia Sosa, Francisco J. Balea-Fernandez, Jesus Morera, Bernardino Clavo, Gustavo M. Callico
Summary: This study demonstrates the potential of hyperspectral imaging combined with a processing framework in identifying and delineating brain tumors, including primary and secondary tumors. By analyzing a database of in-vivo brain images, the study achieved a highest median macro F1-Score of 70.2 +/- 7.9% on the test set using both spectral and spatial information.
NPJ PRECISION ONCOLOGY
(2023)
Proceedings Paper
Computer Science, Hardware & Architecture
Ines A. Cruz-Guerrero, Raquel Leon, Liliana Granados-Castro, Himar Fabelo, Samuel Ortega, Daniel U. Campos-Delgado, Gustavo Marrero Callico
Summary: Hyperspectral imaging is a powerful tool for remotely identifying the composition of an area of interest. However, unwanted effects during data acquisition can complicate the image processing stage. This study proposes a new reflectance calibration method that compensates for optical alterations and achieves high accuracy in classification tests.
2022 25TH EUROMICRO CONFERENCE ON DIGITAL SYSTEM DESIGN (DSD)
(2022)
Proceedings Paper
Computer Science, Hardware & Architecture
Liliana Granados-Castro, Omar Gutierrez-Navarro, Ines A. Cruz-Guerrero, Juan N. Mendoza-Chavarria, Eric R. Zavala-Sanchez, Daniel U. Campos-Delgado
Summary: This study presents an approach based on multispectral imaging and blind linear unmixing to estimate blood perfusion parameters in the hand palm. The results demonstrate the feasibility of non-invasive estimation of hemoglobin and the potential for calculating other perfusion parameters to diagnose and monitor pathologies.
2022 25TH EUROMICRO CONFERENCE ON DIGITAL SYSTEM DESIGN (DSD)
(2022)
Proceedings Paper
Computer Science, Hardware & Architecture
Juan Nicolas Mendoza-Chavarria, Eric R. Zavala-Sanchez, Liliana Granados-Castro, Ines A. Cruz-Guerrero, Himar Fabelo, Samuel Ortega, Gustavo Marrero Callico, Daniel U. Campos-Delgado
Summary: In this study, a classification method based on nonlinear spectral unmixing for identifying areas affected by glioblastomas in hyperspectral brain images is proposed. The method uses a semi-supervised approach to estimate the end-members in a multilinear model and varies the number of end-members per-class to improve classification results. The experimental results demonstrate high accuracy in the regions of interest, indicating the potential of the proposed method as an assistant tool in the diagnosis of glioblastoma in hyperspectral imaging.
2022 25TH EUROMICRO CONFERENCE ON DIGITAL SYSTEM DESIGN (DSD)
(2022)