Advances in Thermal Image Analysis for the Detection of Pregnancy in Horses Using Infrared Thermography
Abstract
:1. Introduction
2. Materials and Methods
2.1. Mares
2.2. Data Collection
2.3. Data Processing
2.3.1. Transformation to Color Models
2.3.2. Extraction of Image Texture Features
- (i)
- Histogram Statistics (HS) is a usual method of image intensity analysis, based on the first order histogram. HS does not consider the special dependence on the intensity distribution. Moreover, the first order histogram features describe the overall number of pixels having certain intensity but independent of their location in the image [33]. For image with the dimensions and range of intensity ( is the number of bits per pixel), the normalized histogram is defined as:The 13 features from normalized are defined as [33]:
- (ii)
- Gray Level Co-occurrence Matrix (GLCM, GLCH) is a current method of image intensity analysis, based on the second order histogram. GLCM considers the mutual spatial relationship between pairs of image pixels with specific intensity levels. The GLCM method uses the second-order histogram of the image intensity distribution and can be calculated in different directions (horizontal in this study, vertical, 45°, 135°) and at different distances of pixel pairs () [32]. For image with the dimensions and range of intensity , the co-occurrence matrix is defined as:
2.4. Statistical Analysis
3. Results
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Bucca, S.; Fogarty, U.; Collins, A.; Small, V. Assessment of feto-placental well-being in the mare from mid-gestation to term: Transrectal and transabdominal ultrasonographic features. Theriogenology 2005, 64, 542–557. [Google Scholar] [CrossRef] [PubMed]
- McCue, P.M. Ultrasound Examination of the Pregnant Mare. In Equine Reproductive Procedures; John Wiley & Sons, Inc.: Hoboken, NJ, USA, 2014. [Google Scholar]
- Kirkpatrick, J.F.; Lasley, B.L.; Shideler, S.E.; Roser, J.F.; Turner, J.W., Jr. Non-instrumented immunoassay field tests for pregnancy detection in free-roaming feral horses. J. Wildl. Manag. 1993, 57, 168–173. [Google Scholar] [CrossRef]
- Hilsberg, S.; Goltenboth, R.; Eulenberger, K. Infrared thermography of zoo animals, first experience in its use for pregnancy diagnosis. Erkrankungen der Zootiere 1997, 38, 187–190. [Google Scholar]
- Durrant, B.S.; Ravida, N.; Spady, T.; Cheng, A. New technologies for the study of carnivore reproduction. Theriogenology 2006, 66, 1729–1736. [Google Scholar] [CrossRef]
- Jones, M.; Denson, A.; Williams, E.; Graves, K.; Dos Santos, A.; Kouba, A.; Willard, S. Assessing pregnancy status using digital infrared thermal imaging in Holstein dairy heifers. J. Anim. Sci. 2005, 83, 40. [Google Scholar]
- Bowers, S.; Gandy, S.; Anderson, B.; Ryan, P.; Willard, S. Assessment of pregnancy in the late-gestation mare using digital infrared thermography. Theriogenology 2009, 72, 372–377. [Google Scholar] [CrossRef]
- Maśko, M.; Zdrojkowski, Ł.; Wierzbicka, M.; Domino, M. Association between the Area of the Highest Flank Temperature and Concentrations of Reproductive Hormones during Pregnancy in Polish Konik Horses—A Preliminary Study. Animals 2021, 11, 1517. [Google Scholar] [CrossRef] [PubMed]
- Maśko, M.; Witkowska-Piłaszewicz, O.; Jasiński, T.; Domino, M. Thermal features, ambient temperature and hair coat lengths: Limitations of infrared imaging in pregnant primitive breed mares within a year. Reprod. Domest. Anim. 2021, 56, 1315–1328. [Google Scholar] [CrossRef]
- Soroko, M.; Howell, K. Infrared thermography: Current applications in equine medicine. J. Equine Vet. Sci. 2018, 60, 90–96. [Google Scholar] [CrossRef]
- Simon, E.; Gaughan, E.; Epp, T.; Spire, M. Influence of exercise on thermographically determined surface temperatures of thoracic and pelvic limbs in horses. J. Am. Vet. Med. Assoc. 2006, 229, 1940–1944. [Google Scholar] [CrossRef]
- Kastberger, G.; Stachl, R. Infrared imaging technology and biological applications. Behav. Res. Methods Instrum. Comput. 2003, 35, 429–439. [Google Scholar] [CrossRef] [Green Version]
- Eddy, A.; Van Hoogmoed, L.; Snyder, J. The role of thermography in the management of equine lameness. Vet. J. 2001, 162, 172–181. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Kastelic, J.P.; Cook, R.B.; Coulter, G.H.; Wallins, G.L.; Entz, T. Environmental factors affecting measurement of bovine scrotal surface temperature with infrared thermography. Anim. Reprod. Sci. 1996, 41, 153–159. [Google Scholar] [CrossRef]
- Soroko, M.; Howell, K.; Dudek, K. The effect of ambient temperature on infrared thermographic images of joints in the distal forelimbs of healthy racehorses. J. Therm. Biol. 2017, 66, 63–67. [Google Scholar] [CrossRef]
- Schutz, K.E.; Rogers, A.R.; Cox, N.R.; Webster, J.R.; Tucker, C.B. Dairy cattle prefer shade over sprinklers: Effects on behavior and physiology. J. Dairy Sci. 2011, 94, 273–283. [Google Scholar] [CrossRef]
- Montanholi, Y.R.; Lim, M.; Macdonald, A.; Smith, B.A.; Goldhawk, C.; Schwartzkopf-Genswein, K.; Miller, S.P. Technological, environmental and biological factors: Referent variance values for infrared imaging of the bovine. J. Anim. Sci. Biotechnol. 2015, 6, 27. [Google Scholar] [CrossRef]
- Domino, M.; Romaszewski, M.; Jasiński, T.; Maśko, M. Comparison of the surface thermal patterns of horses and donkeys in infrared thermography images. Animals 2020, 10, 2201. [Google Scholar] [CrossRef]
- Jørgensen, G.H.M.; Mejdell, C.M.; Bøe, K.E. Effects of hair coat characteristics on radiant surface temperature in horses. J. Therm. Biol. 2020, 87, 102474. [Google Scholar] [CrossRef]
- Tunley, B.V.; Henson, F.M.D. Reliability and repeatability of thermographic examination and the normal thermographic image of the thoracolumbar region in the horse. Equine Vet. J. 2004, 36, 306–312. [Google Scholar] [CrossRef]
- Howell, K.; Dudek, K.; Soroko, M. Thermal camera performance and image analysis repeatability in equine thermography. Infrared Phys. Technol. 2020, 110, 103447. [Google Scholar] [CrossRef]
- Chrysafi, A.; Athanasopoulos, N.; Siakavellas, N. Damage detection on composite materials with active thermography and digital image processing. Int. J. Therm. Sci. 2017, 116, 242–253. [Google Scholar] [CrossRef]
- Deane, S.; Avdelidis, N.P.; Ibarra-Castanedo, C.; Zhang, H.; Nezhad, H.Y.; Williamson, A.A.; Tsourdos, A. Application of NDT thermographic imaging of aerospace structures. Infrared Phys. Technol. 2019, 97, 456–466. [Google Scholar] [CrossRef] [Green Version]
- Tejedor, B.; Barreira, E.; Almeida, R.M.; Casals, M. Automated data-processing technique: 2D map for identifying the distribution of the u-value in building elements by quantitative internal thermography. Autom. Constr. 2021, 122, 103478. [Google Scholar] [CrossRef]
- Mancilla, R.B.; Daul, C.; Martínez, J.G.; Hernández, A.V.; Wolf, D.; Salas, L.L. Detection of Sore-Risk Regions on the Foot Sole with Digital Image Processing and Passive Thermography in Diabetic Patients. In Proceedings of the 2020 17th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE 2020), Mexico City, Mexico, 11–13 November 2020; pp. 1–6. [Google Scholar]
- Benjumea, E.; Morales, Y.; Torres, C.; Vilardy, J. Characterization of thermographic images of skin cancer lesions using digital image processing. J. Phys. 2019, 1221, 012076. [Google Scholar] [CrossRef]
- Silva, T.A.E.; Silva, L.F.; Muchaluat-Saade, D.C.; Conci, A. A computational method to assist the diagnosis of breast disease using dynamic thermography. Sensors 2020, 20, 3866. [Google Scholar] [CrossRef]
- Depeursinge, A.; Al-Kadi, O.S.; Mitchell, J.R. Biomedical Texture Analysis: Fundamentals, Tools and Challenges; Academic Press: Cambridge, MA, USA, 2017. [Google Scholar]
- Bębas, E.; Borowska, M.; Derlatka, M.; Oczeretko, E.; Hładuński, M.; Szumowski, P.; Mojsak, M. Machine-learning-based classification of the histological subtype of non-small-cell lung cancer using MRI texture analysis. Biomed. Signal. Process. Control. 2021, 66, 102446. [Google Scholar] [CrossRef]
- Sohail, A.S.M.; Bhattacharya, P.; Mudur, S.P.; Krishnamurthy, S. Local relative GLRLM-based texture feature extraction for classifying ultrasound medical images. In Proceedings of the 2011 24th Canadian Conference on Electrical and Computer Engineering (CCECE, IEEE), Niagara Falls, ON, Canada, 8–11 May 2011; pp. 001092–001095. [Google Scholar]
- Masko, M.; Borowska, M.; Domino, M.; Jasinski, T.; Zdrojkowski, L.; Gajewski, Z. A novel approach to thermographic images analysis of equine thoracolumbar region: The effect of effort and rider’s body weight on structural image complexity. BMC Vet. Res. 2021, 17, 99. [Google Scholar] [CrossRef]
- Haralick, R.M. Statistical and structural approaches to texture. Proc. IEEE 1979, 67, 786–804. [Google Scholar] [CrossRef]
- Materka, A.; Strzelecki, M. Texture Analysis Methods–A Review—COST B11 Report; Technical University of Lodz, Institute of Electronics: Brussels, Belgium, 1998. [Google Scholar]
- Szczypinski, P.M.; Klepaczko, A. Mazda—A framework for biomedical image texture analysis and data exploration. In Biomedical Texture Analysis; Elsevier: Amsterdam, The Netherlands, 2017; pp. 315–347. [Google Scholar]
- Szczypinski, P.M.; Klepaczko, A.; Kociołek, M. Qmazda—Software tools for image analysis and pattern recognition. In Proceedings of the 2017 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), Poznan, Poland, 20–22 September 2017; pp. 217–221. [Google Scholar]
- Szczypiński, P.; Klepaczko, A.; Pazurek, M.; Daniel, P. Texture and color based image segmentation and pathology detection in capsule endoscopy videos. Comput. Methods Programs Biomed. 2014, 113, 396–411. [Google Scholar] [CrossRef]
- Umapathy, S.; Vasu, S.; Gupta, N. Computer aided diagnosis based hand thermal image analysis: A potential tool for the evaluation of rheumatoid arthritis. J. Med. Biol. Eng. 2018, 38, 666–677. [Google Scholar] [CrossRef]
- Wu, T.; Yang, Z. Animal tumor medical image analysis based on image processing techniques and embedded system. Microprocess. Microsyst. 2021, 81, 103671. [Google Scholar] [CrossRef]
- Ibraheem, N.A.; Hasan, M.M.; Khan, R.Z.; Mishra, P.K. Understanding color models: A review. ARPN J. Sci. Technol. 2012, 2, 265–275. [Google Scholar]
- Wen, C.-Y.; Chou, C.-M. Color image models and its applications to document examination. Forensic Sci. J. 2004, 3, 23–32. [Google Scholar]
- Plataniotis, K.N.; Venetsanopoulos, A.N. Color Image Processing and Applications; Springer Science & Business Media: Berlin/Heidelberg, Germany, 2013. [Google Scholar]
- Girejko, G.; Borowska, M.; Szarmach, J. Statistical analysis of radiographic textures illustrating healing process after the guided bone regeneration surgery. In Proceedings of the International Conference on Information Technologies in Biomedicine, Springer (ITIB’2018), Kamień Śląski, Poland, 18–20 June 2018; pp. 217–226. [Google Scholar]
- Zhang, H.; Hung, C.L.; Min, G.; Guo, J.P.; Liu, M.; Hu, X. GPU-accelerated GLRLM algorithm for feature extraction of MRI. Sci. Rep. 2019, 9, 10883. [Google Scholar] [CrossRef]
- Resmini, R.; Silva, L.; Araujo, A.S.; Medeiros, P.; Muchaluat-Saade, D.; Conci, A. Combining Genetic Algorithms and SVM for Breast Cancer Diagnosis Using Infrared Thermography. Sensors 2021, 21, 4802. [Google Scholar] [CrossRef]
- Lashkari, A.; Pak, F.; Firouzmand, M. Full intelligent cancer classification of thermal breast images to assist physician in clinical diagnostic applications. JMSS 2016, 6, 12. [Google Scholar] [CrossRef] [PubMed]
- Pramanik, S.; Bhattacharjee, D.; Nasipuri, M. Texture analysis of breast thermogram for differentiation of malignant and benign breast. In Proceedings of the 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Jaipur, India, 21–24 September 2016. [Google Scholar]
- Abdel-Nasser, M.; Moreno, A.; Puig, D. Breast cancer detection in thermal infrared images using representation learning and texture analysis methods. Electronics 2019, 8, 100. [Google Scholar] [CrossRef] [Green Version]
- Sánchez-Ruiz, D.; Olmos-Pineda, I.; Olvera-López, J.A. Automatic region of interest segmentation for breast thermogram image classification. Pattern Recognit. Lett. 2020, 135, 72–81. [Google Scholar] [CrossRef]
- Faust, O.; Acharya, U.R.; Ng, E.Y.K.; Hong, T.J.; Yu, W. Application of infrared thermography in computer aided diagnosis. Infrared Phys. Technol. 2014, 66, 160–175. [Google Scholar] [CrossRef]
- McCafferty, D.J. The value of infrared thermography for research on mammals: Previous applications and future directions. Mammal Rev. 2007, 37, 207–223. [Google Scholar] [CrossRef]
- Dohoo, I.; Martin, W.; Stryhn, H. Veterinary Epidemiologic Research, 2nd ed.; VER Inc.: Charlottetown, Canada, 2009. [Google Scholar]
- Turner, T. Diagnostic thermography. Vet. Clin. N. Am. Equine Pract. 2001, 17, 95–114. [Google Scholar] [CrossRef]
- Kim, S.M.; Cho, G.J. Evaluation of Heat Distribution for the Diagnosis of the Hoof with Abscess by Infrared Thermography in Horses. Open Agric. J. 2021, 15, 48–53. [Google Scholar] [CrossRef]
- Pavelski, M.; Basten, M.; Busato, E.; Dornbusch, P. Infrared thermography evaluation from the back region of healthy horses in controlled temperature room. Ciência Rural. 2015, 45, 1274–1279. [Google Scholar] [CrossRef] [Green Version]
- Witkowska-Piłaszewicz, O.; Maśko, M.; Domino, M.; Winnicka, A. Infrared thermography correlates with lactate concentration in blood during race training in horses. Animals 2020, 11, 2072. [Google Scholar] [CrossRef] [PubMed]
- Ciutacu, O.; Tanase, A.; Miclaus, I. Digital infrared thermography in assessing soft tissues injuries on sport equines. Bull. Univ. Agric. Sci. Vet. Med. Cluj Napoca Vet. Med. 2006, 63, 228–233. [Google Scholar]
- Roberto, J.V.B.; De Souza, B.B. Use of infrared thermography in veterinary medicine and animal production. J. Anim. Behav. Biometeorol. 2020, 2, 73–84. [Google Scholar] [CrossRef]
- Drobatz, K.J. Measures of accuracy and performance of diagnostic tests. J. Vet. Cardiol. 2009, 11, S33–S40. [Google Scholar] [CrossRef] [PubMed]
- Shikichi, M.; Iwata, K.; Ito, K.; Miyakoshi, D.; Murase, H.; Sato, F.; Nambo, Y. Abnormal pregnancies associated with deviation in progestin and estrogen profiles in late pregnant mares: A diagnostic aid. Theriogenology 2017, 98, 75–81. [Google Scholar] [CrossRef]
- Górecka, A.; Słoniewski, K.; Golonka, M.; Jaworski, Z.; Jezierski, T. Heritability of hair whorl position on the forehead in Konik horses. J. Anim. Breed. Genet. 2006, 123, 396–398. [Google Scholar] [CrossRef] [PubMed]
- Kirkpatrick, J.F.; Kasman, L.H.; Lasley, B.L.; Turner, J.W., Jr. Pregnancy determination in uncaptured feral horses. J. Wildl. Manag. 1988, 35, 305–308. [Google Scholar] [CrossRef]
- Borowska, M. Entropy-based algorithms in the analysis of biomedical signals. Stud. Log. Gramm. Rhetor. 2015, 43, 21–32. [Google Scholar] [CrossRef] [Green Version]
- Fowden, A.L.; Giussani, D.A.; Forhead, A.J. Physiological development of the equine fetus during late gestation. Equine Vet. J. 2020, 52, 165–173. [Google Scholar] [CrossRef] [PubMed]
Month | 4th | 5th | 6th | 7th | 8th | 9th | 10th | 11th | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Threshold | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD |
SumEntrp of the Red component | ||||||||||||||||||||||||
Se | 0.14 | 0.64 | 1.00 | 0.14 | 0.64 | 1.00 | 0.43 | 0.71 | 1.00 | 0.50 | 0.71 | 1.00 | 0.50 | 0.86 | 1.00 | 0.50 | 0.86 | 1.00 | 0.79 | 0.93 | 1.00 | 0.86 | 0.93 | 1.00 |
Sp | 1.00 | 1.00 | 0.54 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 1.00 | 1.00 | 0.70 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.52 | 0.72 | 1.00 | 0.52 | 0.72 | 1.00 | 0.62 | 0.76 | 1.00 | 0.65 | 0.76 | 1.00 | 0.65 | 0.87 | 1.00 | 0.65 | 0.87 | 1.00 | 0.81 | 0.93 | 1.00 | 0.87 | 0.93 | 1.00 |
Entropy of the Red component | ||||||||||||||||||||||||
Se | 0.29 | 0.57 | 0.93 | 0.29 | 0.57 | 0.93 | 0.50 | 0.71 | 1.00 | 0.50 | 0.71 | 1.00 | 0.50 | 0.86 | 1.00 | 0.50 | 0.86 | 1.00 | 0.86 | 0.93 | 1.00 | 0.86 | 0.93 | 1.00 |
Sp | 1.00 | 1.00 | 0.31 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 1.00 | 1.00 | 0.59 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.57 | 0.68 | 0.80 | 0.57 | 0.68 | 0.93 | 0.65 | 0.76 | 1.00 | 0.65 | 0.76 | 1.00 | 0.65 | 0.87 | 1.00 | 0.65 | 0.87 | 1.00 | 0.87 | 0.93 | 1.00 | 0.87 | 0.93 | 1.00 |
DifEntrp of the Red component | ||||||||||||||||||||||||
Se | 0.36 | 0.71 | 0.93 | 0.36 | 0.71 | 0.93 | 0.43 | 0.79 | 0.93 | 0.50 | 0.79 | 0.93 | 0.50 | 0.86 | 1.00 | 0.50 | 0.86 | 1.00 | 0.71 | 1.00 | 1.00 | 0.79 | 1.00 | 1.00 |
Sp | 1.00 | 0.77 | 0.23 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 1.00 | 0.77 | 0.57 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.59 | 0.71 | 0.75 | 0.59 | 0.76 | 0.93 | 0.62 | 0.81 | 0.93 | 0.65 | 0.81 | 0.93 | 0.65 | 0.87 | 1.00 | 0.65 | 0.87 | 1.00 | 0.76 | 1.00 | 1.00 | 0.81 | 1.00 | 1.00 |
Perc10 of the Green component | ||||||||||||||||||||||||
Se | 0.64 | 0.79 | 0.86 | 0.64 | 0.79 | 0.86 | 0.64 | 0.86 | 0.86 | 0.64 | 0.86 | 0.86 | 0.79 | 0.93 | 1.00 | 0.79 | 0.93 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
Sp | 0.69 | 0.46 | 0.31 | 1.00 | 0.46 | 0.23 | 0.92 | 0.77 | 0.54 | 1.00 | 0.92 | 0.92 | 1.00 | 0.92 | 0.85 | 1.00 | 0.92 | 0.85 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 0.69 | 0.61 | 0.57 | 1.00 | 0.61 | 0.55 | 0.90 | 0.80 | 0.67 | 1.00 | 0.92 | 0.92 | 1.00 | 0.93 | 0.88 | 1.00 | 0.93 | 0.88 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.64 | 0.67 | 0.67 | 0.72 | 0.67 | 0.60 | 0.71 | 0.83 | 0.78 | 0.72 | 0.86 | 0.86 | 0.81 | 0.92 | 1.00 | 0.81 | 0.92 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
InvDfMom of the Blue component | ||||||||||||||||||||||||
Se | 0.50 | 0.79 | 1.00 | 0.50 | 0.79 | 1.00 | 0.43 | 0.71 | 0.93 | 0.43 | 0.71 | 0.93 | 0.57 | 0.86 | 1.00 | 0.57 | 0.86 | 1.00 | 0.50 | 0.93 | 1.00 | 0.50 | 0.93 | 1.00 |
Sp | 0.15 | 0.00 | 0.00 | 0.54 | 0.46 | 0.31 | 0.85 | 0.69 | 0.69 | 0.77 | 0.69 | 0.54 | 0.92 | 0.92 | 0.54 | 1.00 | 1.00 | 1.00 | 1.00 | 0.85 | 0.85 | 0.85 | 0.85 | 0.69 |
PPV | 0.39 | 0.46 | 0.52 | 0.54 | 0.61 | 0.61 | 0.75 | 0.71 | 0.76 | 0.67 | 0.71 | 0.68 | 0.89 | 0.92 | 0.70 | 1.00 | 1.00 | 1.00 | 1.00 | 0.87 | 0.88 | 0.78 | 0.87 | 0.78 |
NPV | 0.22 | 0.00 | 1.00 | 0.50 | 0.67 | 1.00 | 0.58 | 0.69 | 0.90 | 0.56 | 0.69 | 0.88 | 0.67 | 0.86 | 1.00 | 0.68 | 0.87 | 1.00 | 0.65 | 0.92 | 1.00 | 0.61 | 0.92 | 1.00 |
Month | 4th | 5th | 6th | 7th | 8th | 9th | 10th | 11th | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Threshold | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD | Mean | m ± SD | m ± 2SD |
SumEntrp of the I-component | ||||||||||||||||||||||||
Se | 0.43 | 0.57 | 1.00 | 0.50 | 0.57 | 1.00 | 0.50 | 0.71 | 1.00 | 0.57 | 0.71 | 1.00 | 0.43 | 0.86 | 1.00 | 0.43 | 0.86 | 1.00 | 0.79 | 0.93 | 1.00 | 0.86 | 0.93 | 1.00 |
Sp | 1.00 | 0.92 | 0.23 | 1.00 | 1.00 | 0.92 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 1.00 | 0.89 | 0.57 | 1.00 | 1.00 | 0.93 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.62 | 0.67 | 1.00 | 0.65 | 0.68 | 1.00 | 0.65 | 0.76 | 1.00 | 0.68 | 0.76 | 1.00 | 0.62 | 0.87 | 1.00 | 0.62 | 0.87 | 1.00 | 0.81 | 0.93 | 1.00 | 0.87 | 0.93 | 1.00 |
Entropy of the I-component | ||||||||||||||||||||||||
Se | 0.29 | 0.64 | 1.00 | 0.29 | 0.64 | 1.00 | 0.50 | 0.64 | 1.00 | 0.50 | 0.71 | 1.00 | 0.57 | 0.79 | 1.00 | 0.57 | 0.86 | 1.00 | 0.79 | 0.93 | 1.00 | 0.79 | 0.93 | 1.00 |
Sp | 1.00 | 0.85 | 0.23 | 1.00 | 1.00 | 0.85 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 1.00 | 0.82 | 0.58 | 1.00 | 1.00 | 0.88 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.57 | 0.69 | 1.00 | 0.57 | 0.72 | 1.00 | 0.65 | 0.72 | 1.00 | 0.65 | 0.76 | 1.00 | 0.68 | 0.81 | 1.00 | 0.68 | 0.87 | 1.00 | 0.81 | 0.93 | 1.00 | 0.81 | 0.93 | 1.00 |
Mean of the Q-component | ||||||||||||||||||||||||
Se | 0.43 | 0.93 | 0.93 | 0.43 | 0.93 | 0.93 | 0.50 | 0.93 | 0.93 | 0.50 | 0.93 | 0.93 | 0.50 | 1.00 | 1.00 | 0.50 | 1.00 | 1.00 | 0.71 | 1.00 | 1.00 | 0.71 | 1.00 | 1.00 |
Sp | 0.85 | 0.31 | 0.31 | 1.00 | 0.23 | 0.23 | 1.00 | 0.62 | 0.62 | 1.00 | 0.85 | 0.85 | 1.00 | 0.92 | 0.92 | 1.00 | 0.85 | 0.85 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 0.75 | 0.59 | 0.59 | 1.00 | 0.57 | 0.57 | 1.00 | 0.72 | 0.72 | 1.00 | 0.87 | 0.87 | 1.00 | 0.93 | 0.93 | 1.00 | 0.88 | 0.88 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.58 | 0.80 | 0.80 | 0.62 | 0.75 | 0.75 | 0.65 | 0.89 | 0.89 | 0.65 | 0.92 | 0.92 | 0.65 | 1.00 | 1.00 | 0.65 | 1.00 | 1.00 | 0.76 | 1.00 | 1.00 | 0.76 | 1.00 | 1.00 |
Variance of the Q-component | ||||||||||||||||||||||||
Se | 0.36 | 0.57 | 0.86 | 0.36 | 0.57 | 0.86 | 0.36 | 0.79 | 0.93 | 0.36 | 0.79 | 0.93 | 0.64 | 0.93 | 1.00 | 0.64 | 0.93 | 1.00 | 0.79 | 1.00 | 1.00 | 0.79 | 1.00 | 1.00 |
Sp | 0.46 | 0.23 | 0.15 | 0.54 | 0.23 | 0.08 | 0.85 | 0.54 | 0.00 | 0.92 | 0.85 | 0.38 | 0.92 | 0.85 | 0.15 | 0.85 | 0.85 | 0.23 | 1.00 | 0.92 | 0.54 | 1.00 | 1.00 | 0.69 |
PPV | 0.42 | 0.44 | 0.52 | 0.45 | 0.44 | 0.50 | 0.71 | 0.65 | 0.50 | 0.83 | 0.85 | 0.62 | 0.90 | 0.87 | 0.56 | 0.82 | 0.87 | 0.58 | 1.00 | 0.93 | 0.70 | 1.00 | 1.00 | 0.78 |
NPV | 0.40 | 0.33 | 0.50 | 0.44 | 0.33 | 0.33 | 0.55 | 0.70 | 1.00 | 0.57 | 0.79 | 0.83 | 0.71 | 0.92 | 1.00 | 0.69 | 0.92 | 1.00 | 0.81 | 1.00 | 1.00 | 0.81 | 1.00 | 1.00 |
Perc50 of the Q-component | ||||||||||||||||||||||||
Se | 0.29 | 0.64 | 1.00 | 0.29 | 0.64 | 1.00 | 0.43 | 0.79 | 1.00 | 0.43 | 0.79 | 1.00 | 0.50 | 0.86 | 1.00 | 0.50 | 0.86 | 1.00 | 0.71 | 0.86 | 1.00 | 0.71 | 0.86 | 1.00 |
Sp | 0.77 | 0.69 | 0.00 | 1.00 | 1.00 | 0.08 | 1.00 | 1.00 | 0.23 | 1.00 | 1.00 | 0.38 | 1.00 | 1.00 | 0.54 | 1.00 | 1.00 | 0.54 | 1.00 | 1.00 | 0.77 | 1.00 | 1.00 | 0.92 |
PPV | 0.57 | 0.69 | 0.52 | 1.00 | 1.00 | 0.54 | 1.00 | 1.00 | 0.58 | 1.00 | 1.00 | 0.64 | 1.00 | 1.00 | 0.70 | 1.00 | 1.00 | 0.70 | 1.00 | 1.00 | 0.82 | 1.00 | 1.00 | 0.93 |
NPV | 0.50 | 0.64 | 1.00 | 0.57 | 0.72 | 1.00 | 0.62 | 0.81 | 1.00 | 0.62 | 0.81 | 1.00 | 0.65 | 0.87 | 1.00 | 0.65 | 0.87 | 1.00 | 0.76 | 0.87 | 1.00 | 0.76 | 0.87 | 1.00 |
SumAverg of the Q-component | ||||||||||||||||||||||||
Se | 0.43 | 0.64 | 0.93 | 0.43 | 0.64 | 0.93 | 0.43 | 0.71 | 0.93 | 0.50 | 0.79 | 0.93 | 0.50 | 0.86 | 1.00 | 0.50 | 0.86 | 1.00 | 0.71 | 0.86 | 1.00 | 0.71 | 0.86 | 1.00 |
Sp | 0.85 | 0.69 | 0.31 | 1.00 | 1.00 | 0.23 | 1.00 | 1.00 | 0.62 | 1.00 | 1.00 | 0.85 | 1.00 | 1.00 | 0.92 | 1.00 | 1.00 | 0.85 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 0.75 | 0.69 | 0.59 | 1.00 | 1.00 | 0.57 | 1.00 | 1.00 | 0.72 | 1.00 | 1.00 | 0.87 | 1.00 | 1.00 | 0.93 | 1.00 | 1.00 | 0.88 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.58 | 0.64 | 0.80 | 0.62 | 0.72 | 0.75 | 0.62 | 0.76 | 0.89 | 0.65 | 0.81 | 0.92 | 0.65 | 0.87 | 1.00 | 0.65 | 0.87 | 1.00 | 0.76 | 0.87 | 1.00 | 0.76 | 0.87 | 1.00 |
SumVarnc of the Q-component | ||||||||||||||||||||||||
Se | 0.36 | 0.57 | 0.92 | 0.36 | 0.57 | 0.92 | 0.79 | 0.79 | 0.92 | 0.79 | 0.79 | 0.92 | 0.64 | 0.86 | 0.92 | 0.64 | 0.93 | 1.00 | 0.36 | 1.00 | 1.00 | 0.36 | 1.00 | 1.00 |
Sp | 0.46 | 0.23 | 0.15 | 0.54 | 0.23 | 0.08 | 0.85 | 0.54 | 0.00 | 0.92 | 0.92 | 0.38 | 0.92 | 0.85 | 0.15 | 0.92 | 0.85 | 0.23 | 1.00 | 0.92 | 0.54 | 1.00 | 1.00 | 0.69 |
PPV | 0.42 | 0.44 | 0.52 | 0.45 | 0.44 | 0.50 | 0.85 | 0.65 | 0.48 | 0.92 | 0.92 | 0.60 | 0.90 | 0.86 | 0.52 | 0.90 | 0.87 | 0.57 | 1.00 | 0.93 | 0.68 | 1.00 | 1.00 | 0.76 |
NPV | 0.40 | 0.33 | 0.67 | 0.44 | 0.33 | 0.50 | 0.79 | 0.70 | 0.00 | 0.80 | 0.80 | 0.83 | 0.71 | 0.85 | 0.67 | 0.71 | 0.92 | 1.00 | 0.59 | 1.00 | 1.00 | 0.59 | 1.00 | 1.00 |
Month | 4th | 5th | 6th | 7th | 8th | 9th | 10th | 11th | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Threshold | Mean | m +SD | m +2SD | Mean | m +SD | m +2SD | Mean | m +SD | m +2SD | Mean | m +SD | m +2SD | Mean | m +SD | m +2SD | Mean | m +SD | m +2SD | Mean | m +SD | m +2SD | Mean | m +SD | m +2SD |
Variance of the Saturation component | ||||||||||||||||||||||||
Se | 0.71 | 0.86 | 0.93 | 0.71 | 0.86 | 0.93 | 0.57 | 0.86 | 0.93 | 0.57 | 0.86 | 0.93 | 0.71 | 0.93 | 0.93 | 0.71 | 0.93 | 0.93 | 0.86 | 1.00 | 1.00 | 0.86 | 1.00 | 1.00 |
Sp | 0.38 | 0.38 | 0.31 | 0.85 | 0.77 | 0.62 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
PPV | 0.56 | 0.60 | 0.59 | 0.83 | 0.80 | 0.72 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 | 1.00 |
NPV | 0.56 | 0.71 | 0.80 | 0.73 | 0.83 | 0.89 | 0.68 | 0.87 | 0.93 | 0.68 | 0.87 | 0.93 | 0.76 | 0.93 | 0.93 | 0.76 | 0.93 | 0.93 | 0.87 | 1.00 | 1.00 | 0.87 | 1.00 | 1.00 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Domino, M.; Borowska, M.; Kozłowska, N.; Zdrojkowski, Ł.; Jasiński, T.; Smyth, G.; Maśko, M. Advances in Thermal Image Analysis for the Detection of Pregnancy in Horses Using Infrared Thermography. Sensors 2022, 22, 191. https://doi.org/10.3390/s22010191
Domino M, Borowska M, Kozłowska N, Zdrojkowski Ł, Jasiński T, Smyth G, Maśko M. Advances in Thermal Image Analysis for the Detection of Pregnancy in Horses Using Infrared Thermography. Sensors. 2022; 22(1):191. https://doi.org/10.3390/s22010191
Chicago/Turabian StyleDomino, Małgorzata, Marta Borowska, Natalia Kozłowska, Łukasz Zdrojkowski, Tomasz Jasiński, Graham Smyth, and Małgorzata Maśko. 2022. "Advances in Thermal Image Analysis for the Detection of Pregnancy in Horses Using Infrared Thermography" Sensors 22, no. 1: 191. https://doi.org/10.3390/s22010191
APA StyleDomino, M., Borowska, M., Kozłowska, N., Zdrojkowski, Ł., Jasiński, T., Smyth, G., & Maśko, M. (2022). Advances in Thermal Image Analysis for the Detection of Pregnancy in Horses Using Infrared Thermography. Sensors, 22(1), 191. https://doi.org/10.3390/s22010191