1
|
Carboni E, Marxfeld H, Tuoken H, Klukas C, Eggers T, Gröters S, van Ravenzwaay B. A Workflow for the Performance of the Differential Ovarian Follicle Count Using Deep Neuronal Networks. Toxicol Pathol 2020; 49:843-850. [PMID: 33287654 DOI: 10.1177/0192623320969130] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
Abstract
In order to automate the counting of ovarian follicles required in multigeneration reproductive studies performed in the rat according to Organization for Economic Co-operation and Development guidelines 443 and 416, the application of deep neural networks was tested. The manual evaluation of the differential ovarian follicle count is a tedious and time-consuming task that requires highly trained personnel. In this regard, deep learning outputs provide overlay pictures for a more detailed documentation, together with an increased reproducibility of the counts. To facilitate the planned good laboratory practice (GLP) validation a workflow was set up using MLFlow to make all steps from generating of scans, training of the neural network, uploading of study images to the neural network, generation and storage of the results in a compliant manner controllable and reproducible. PyTorch was used as main framework to build the Faster region-based convolutional neural network for the training. We compared the performances of different depths of ResNet models with specific regard to the sensitivity, specificity, accuracy of the models. In this paper, we describe all steps from data labeling, training of networks, and the performance metrics chosen to evaluate different network architectures. We also make recommendation on steps, which should be taken into consideration when GLP validation is aimed for.
Collapse
Affiliation(s)
- Eleonora Carboni
- 5184BASF SE, Ludwigshafen, Rheinland-Pfalz, Germany. Carboni is now with the JOHNSON AND JOHNSON, Beerse, Antwerp, Belgium
| | - Heike Marxfeld
- 5184BASF SE, Ludwigshafen, Rheinland-Pfalz, Germany. Carboni is now with the JOHNSON AND JOHNSON, Beerse, Antwerp, Belgium
| | - Hanati Tuoken
- 5184BASF SE, Ludwigshafen, Rheinland-Pfalz, Germany. Carboni is now with the JOHNSON AND JOHNSON, Beerse, Antwerp, Belgium
| | - Christian Klukas
- 5184BASF SE, Ludwigshafen, Rheinland-Pfalz, Germany. Carboni is now with the JOHNSON AND JOHNSON, Beerse, Antwerp, Belgium
| | - Till Eggers
- 5184BASF SE, Ludwigshafen, Rheinland-Pfalz, Germany. Carboni is now with the JOHNSON AND JOHNSON, Beerse, Antwerp, Belgium
| | - Sibylle Gröters
- 5184BASF SE, Ludwigshafen, Rheinland-Pfalz, Germany. Carboni is now with the JOHNSON AND JOHNSON, Beerse, Antwerp, Belgium
| | - Bennard van Ravenzwaay
- 5184BASF SE, Ludwigshafen, Rheinland-Pfalz, Germany. Carboni is now with the JOHNSON AND JOHNSON, Beerse, Antwerp, Belgium
| |
Collapse
|
2
|
Regan KS, Cline JM, Creasy D, Davis B, Foley GL, Lanning L, Latendresse JR, Makris S, Morton D, Rehm S, Stebbins K. STP Position Paper: Ovarian Follicular Counting in the Assessment of Rodent Reproductive Toxicity. Toxicol Pathol 2016; 33:409-12. [PMID: 15805082 DOI: 10.1080/01926230490515355] [Citation(s) in RCA: 19] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
3
|
Muskhelishvili L, Wingard SK, Latendresse JR. Proliferating Cell Nuclear Antigen—A Marker for Ovarian Follicle Counts. Toxicol Pathol 2016; 33:365-8. [PMID: 15805074 DOI: 10.1080/01926230590930164] [Citation(s) in RCA: 25] [Impact Index Per Article: 3.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
Abstract
Enumerating ovarian follicles is an effective way to estimate the extent of ovarian toxicity in female rodents exposed to xenobiotics. Differential follicle counts are useful in safety assessment bioassays and in interspecies extrapolation of ovarian toxicity. Counting the follicles in H&E-stained sections is labor intensive, tedious, and costly. In the present study we demonstrated that in rat formalin-fixed, paraffin-embedded ovary sections follicles of all degrees of maturity can be visualized by the use of antibody directed against proliferating cell nuclear antigen (PCNA). Follicles are easily distinguished from ovarian background with the ability to detect and identify primordial follicles being enhanced. This translates into a significant decrease in variability of follicle counts, labor, and cost. Specifically, variability dropped from 11% to 0.2%, the counting time was reduced by 46%, and the cost by 48%.
Collapse
Affiliation(s)
- Levan Muskhelishvili
- Toxicologic Pathology Associates at National Center for Toxicological Research, Jefferson, Arkansas 72079, USA.
| | | | | |
Collapse
|
4
|
Phoophitphong D, Wangnaitham S, Srisuwatanasagul S, Tummaruk P. The use of proliferating cell nuclear antigen (PCNA) immuno-staining technique to determine number and type of follicles in the gilt ovary. Livest Sci 2012. [DOI: 10.1016/j.livsci.2012.10.008] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
|
5
|
Christophersen OA. Should autism be considered a canary bird telling that Homo sapiens may be on its way to extinction? MICROBIAL ECOLOGY IN HEALTH AND DISEASE 2012; 23:19008. [PMID: 23990819 PMCID: PMC3747741 DOI: 10.3402/mehd.v23i0.19008] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
There has been a dramatic enhancement of the reported incidence of autism in different parts of the world over the last 30 years. This can apparently not be explained only as a result of improved diagnosis and reporting, but may also reflect a real change. The causes of this change are unknown, but if we shall follow T.C. Chamberlin's principle of multiple working hypotheses, we need to take into consideration the possibility that it partly may reflect an enhancement of the average frequency of responsible alleles in large populations. If this hypothesis is correct, it means that the average germline mutation rate must now be much higher in the populations concerned, compared with the natural mutation rate in hominid ancestors before the agricultural and industrial revolutions. This is compatible with the high prevalence of impaired human semen quality in several countries and also with what is known about high levels of total exposure to several different unnatural chemical mutagens, plus some natural ones at unnaturally high levels. Moreover, dietary deficiency conditions that may lead to enhancement of mutation rates are also very widespread, affecting billions of people. However, the natural mutation rate in hominids has been found to be so high that there is apparently no tolerance for further enhancement of the germline mutation rate before the Eigen error threshold will be exceeded and our species will go extinct because of mutational meltdown. This threat, if real, should be considered far more serious than any disease causing the death only of individual patients. It should therefore be considered the first and highest priority of the best biomedical scientists in the world, of research-funding agencies and of all medical doctors to try to stop the express train carrying all humankind as passengers on board before it arrives at the end station of our civilization.
Collapse
|
6
|
Kilic S, Yuksel B, Lortlar N, Sertyel S, Aksu T, Batioglu S. Environmental tobacco smoke exposure during intrauterine period promotes granulosa cell apoptosis: a prospective, randomized study. J Matern Fetal Neonatal Med 2012; 25:1904-8. [DOI: 10.3109/14767058.2012.678440] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022]
|
7
|
Sakurada Y, Kudo S, Iwasaki S, Miyata Y, Nishi M, Masumoto Y. Collaborative work on evaluation of ovarian toxicity. 5) Two- or four-week repeated-dose studies and fertility study of busulfan in female rats. J Toxicol Sci 2009; 34 Suppl 1:SP65-72. [PMID: 19265291 DOI: 10.2131/jts.34.s65] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
Abstract
Busulfan, an antineoplastic agent that targets small follicles (primordial and primary follicles), was given orally to female Sprague-Dawley rats (0, 0.1, 0.5, or 1.5 mg/kg/day; n = 10 in each group) for 2 or 4 weeks to assess the optimal administration period for detection of the toxic effects on ovarian morphology. Isolated ovaries were used for histopathological analysis and follicle counts. In addition, a female fertility study was conducted by giving the same dose levels of busulfan from 2 weeks before mating to day 7 of pregnancy to determine the non-observed-adverse-effect-level (NOAEL) for female reproduction. In the 2-week study, all rats treated with busulfan showed normal estrous cyclicity and no toxicological changes in weight or histopathology of the ovaries. In the 4-week study, a decrease in small follicles was found histopathologically in 1 rat, even at 0.5 mg/kg, and in 4 rats at 1.5 mg/kg. Proliferating cell nuclear antigen immunohistochemistry of the follicles confirmed the above decrease in number of small follicles at 1.5 mg/kg. In the female fertility study, increases in dead embryos and post-implantation loss were found in rats at 1.5 mg/kg. Taken together, the NOAELs were 1.5 mg/kg for reproductive performance and 0.5 mg/kg for early embryonic development. In conclusion, the present study indicates that a 4-week administration period and appropriate assessment, including careful histopathological analysis of stage-based follicles are needed to detect small follicle depletion in a general toxicity study used as a first-titer screen.
Collapse
Affiliation(s)
- Yosuke Sakurada
- Research Center, Kyorin Pharmaceutical Co., Ltd., Simotsuga-gun, Tochigi, Japan.
| | | | | | | | | | | |
Collapse
|
8
|
Picut CA, Swanson CL, Scully KL, Roseman VC, Parker RF, Remick AK. Ovarian follicle counts using proliferating cell nuclear antigen (PCNA) and semi-automated image analysis in rats. Toxicol Pathol 2008; 36:674-9. [PMID: 18467674 DOI: 10.1177/0192623308317428] [Citation(s) in RCA: 42] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Ovarian follicle counting is a method to assess ovarian toxicity in reproductive toxicity studies in rats. Although ovarian follicle counting has been traditionally performed manually on hematoxylin and eosin (H&E)-stained sections, the use of immunohistochemical methods, including human cytochrome P450 1B1 (CYP1B1) and proliferating cell nuclear antigen (PCNA), have been used to enhance the visibility of the primordial and primary follicles to facilitate manual counting. In this study, serial sections from both ovaries from ten 3-month-old female Sprague Dawley rats were stained using routine H&E and immunohistochemistry for PCNA. Counting of primordial and primary follicles was performed manually using these two stains and by semi-automated image analysis of PCNA-stained slides. Although manual counting of PCNA-stained slides is preferable to manual counting of H&E-stained slides, manual counting involves variability between individual counters. Semi-automated image analysis of PCNA-stained slides yields an accurate and consistent count of these primordial/primary follicles and eliminates variability between individual counters.
Collapse
Affiliation(s)
- Catherine A Picut
- WIL Research Laboratories-Biotechnics, LLC, Hillsborough, North Carolina 27278, USA.
| | | | | | | | | | | |
Collapse
|