1
|
Campos RL, Yoon SC, Chung S, Bhandarkar SM. Semisupervised Deep Learning for the Detection of Foreign Materials on Poultry Meat with Near-Infrared Hyperspectral Imaging. SENSORS (BASEL, SWITZERLAND) 2023; 23:7014. [PMID: 37631551 PMCID: PMC10459470 DOI: 10.3390/s23167014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/04/2023] [Revised: 07/28/2023] [Accepted: 08/04/2023] [Indexed: 08/27/2023]
Abstract
A novel semisupervised hyperspectral imaging technique was developed to detect foreign materials (FMs) on raw poultry meat. Combining hyperspectral imaging and deep learning has shown promise in identifying food safety and quality attributes. However, the challenge lies in acquiring a large amount of accurately annotated/labeled data for model training. This paper proposes a novel semisupervised hyperspectral deep learning model based on a generative adversarial network, utilizing an improved 1D U-Net as its discriminator, to detect FMs on raw chicken breast fillets. The model was trained by using approximately 879,000 spectral responses from hyperspectral images of clean chicken breast fillets in the near-infrared wavelength range of 1000-1700 nm. Testing involved 30 different types of FMs commonly found in processing plants, prepared in two nominal sizes: 2 × 2 mm2 and 5 × 5 mm2. The FM-detection technique achieved impressive results at both the spectral pixel level and the foreign material object level. At the spectral pixel level, the model achieved a precision of 100%, a recall of over 93%, an F1 score of 96.8%, and a balanced accuracy of 96.9%. When combining the rich 1D spectral data with 2D spatial information, the FM-detection accuracy at the object level reached 96.5%. In summary, the impressive results obtained through this study demonstrate its effectiveness at accurately identifying and localizing FMs. Furthermore, the technique's potential for generalization and application to other agriculture and food-related domains highlights its broader significance.
Collapse
Affiliation(s)
| | - Seung-Chul Yoon
- U.S. National Poultry Research Center, Agricultural Research Service, U.S. Department of Agriculture, Athens, GA 30605, USA
| | - Soo Chung
- Department of Biosystems Engineering, Integrated Major in Global Smart Farm, Research Institute of Agriculture and Life Sciences, Seoul National University, Seoul 08826, Republic of Korea;
| | | |
Collapse
|
2
|
Maric D, Jahanipour J, Li XR, Singh A, Mobiny A, Van Nguyen H, Sedlock A, Grama K, Roysam B. Whole-brain tissue mapping toolkit using large-scale highly multiplexed immunofluorescence imaging and deep neural networks. Nat Commun 2021; 12:1550. [PMID: 33692351 PMCID: PMC7946933 DOI: 10.1038/s41467-021-21735-x] [Citation(s) in RCA: 43] [Impact Index Per Article: 14.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2020] [Accepted: 02/09/2021] [Indexed: 12/17/2022] Open
Abstract
Mapping biological processes in brain tissues requires piecing together numerous histological observations of multiple tissue samples. We present a direct method that generates readouts for a comprehensive panel of biomarkers from serial whole-brain slices, characterizing all major brain cell types, at scales ranging from subcellular compartments, individual cells, local multi-cellular niches, to whole-brain regions from each slice. We use iterative cycles of optimized 10-plex immunostaining with 10-color epifluorescence imaging to accumulate highly enriched image datasets from individual whole-brain slices, from which seamless signal-corrected mosaics are reconstructed. Specific fluorescent signals of interest are isolated computationally, rejecting autofluorescence, imaging noise, cross-channel bleed-through, and cross-labeling. Reliable large-scale cell detection and segmentation are achieved using deep neural networks. Cell phenotyping is performed by analyzing unique biomarker combinations over appropriate subcellular compartments. This approach can accelerate pre-clinical drug evaluation and system-level brain histology studies by simultaneously profiling multiple biological processes in their native anatomical context.
Collapse
Affiliation(s)
- Dragan Maric
- National Institute of Neurological Disorders and Stroke, Bethesda, MD, 20892, USA.
| | - Jahandar Jahanipour
- National Institute of Neurological Disorders and Stroke, Bethesda, MD, 20892, USA
- Cullen College of Engineering, University of Houston, Houston, TX, 77204, USA
| | - Xiaoyang Rebecca Li
- Cullen College of Engineering, University of Houston, Houston, TX, 77204, USA
| | - Aditi Singh
- Cullen College of Engineering, University of Houston, Houston, TX, 77204, USA
| | - Aryan Mobiny
- Cullen College of Engineering, University of Houston, Houston, TX, 77204, USA
| | - Hien Van Nguyen
- Cullen College of Engineering, University of Houston, Houston, TX, 77204, USA
| | - Andrea Sedlock
- National Institute of Neurological Disorders and Stroke, Bethesda, MD, 20892, USA
| | - Kedar Grama
- Cullen College of Engineering, University of Houston, Houston, TX, 77204, USA
| | - Badrinath Roysam
- Cullen College of Engineering, University of Houston, Houston, TX, 77204, USA.
| |
Collapse
|
3
|
O.M. B, O.Y. P, T.M. D, Y.M. B. Paralleling process of searching objects on cytological images by a template. ARTIF INTELL 2019. [DOI: 10.15407/jai2019.03-04.073] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Modern approaches to finding image elements are analyzed. An algorithm for searching micro-objects in histological and cytological images using a database is developed. A tiered-parallel form of parallelization of the process of micro-object pattern search is designed. Micro-object pattern search software is implemented. The obtained result show that the operating time of the software module with parallelization speeds up the processing on average by 20% for cytological images
Collapse
|