臨床婦人科産科77巻12号

2023年12月発行

今月の臨床 AIがもたらす産婦人科医療の変革

産科

AIによる胎児表情の識別

著者： 宮木康成¹² 秦利之³ 三宅貴仁¹³

所属機関： ¹三宅おおふくクリニック婦人科 ^{2 3}三宅医院産婦人科

ページ範囲：P.1197 - P.1205

文献概要

●胎児表情を高い精度で識別するAIを作成できた．このAIを用いたカオス的次元の計測によって，胎児脳活動状態を初めて定量的に示すことができた．

●胎児脳活動状態はカオス的次元の値から少なくとも2種類の状態（dense，sparse）が存在し（p＜0.05），両者が変動することを発見した．これは，少なくとも妊娠27週以降の胎児には意識があることを示唆している．

●胎児脳活動のカオス的次元の変動は自由エネルギー原理で解釈が可能で，胎児脳の発達評価やwell-being評価の新しい手法として期待できる．

参考文献

1）Hata T, et al : Ultrasound for evaluation of fetal neurobehavioural development : from 2-D to 4-D ultrasound. Infant Child Dev 19 : 99-118, 2010

2）Hata T, et al : HDIive and 4D ultrasound in the assessment of fetal facial expressions. Donald School J Ultrasound Obstet Gynecol 9 : 44-50, 2015

3）Hata T : Current status of fetal neurodevelopmental assessment : 4D ultrasound study. J Obstet Gynaecol Res 42 : 1211-1221, 2016

4）Nijhuis JG : Fetal behavior. Neurobiol Aging 24（Suppl） : S41-S46, 2003

5）Prechtl HF : State of the art of a new functional assessment of the young nervous system : an early predictor of cerebral palsy. Early Hum Dev 50 : 1-11, 1997

6）de Vries JI, et al : The emergence of fetal behaviour. I. Qualitative aspects. Early Hum Dev 7 : 301-322, 1982

7）de Vries JI, et al : The emergence of fetal behaviour. II. Quantitative aspects. Early Hum Dev 12 : 99-120, 1985

8）Prechtl HF : Qualitative changes of spontaneous movements in fetus and preterm infant are a marker of neurological dysfunction. Early Hum Dev 23 : 151-158, 1990

9）Prechtl HF, et al : Is neurological assessment of the fetus possible? Eur J Obstet Gynecol Reprod Biol 75 : 81-84, 1997

10）Kuno A, et al : Three-dimensional sonographic assessment of fetal behavior in the early second trimester of pregnancy. J Ultrasound Med 20 : 1271-1275, 2001

11）AboEllail MAM, et al : Fetal face as important indicator of fetal brain function. J Perinat Med 45 : 729-736, 2017

12）Bodfish J, et al : Blink rate as an index of dopamine function in adults with mental retardation and repetitive movement disorders. Am J Ment Retard 99 : 335-344, 1995

13）Kleven MS, et al : Diffetential effects of direct and indirect dopamine agonists on eye blink rate in cynomolgus monkeys. J Pharmacol Exp Ther 279 : 1211-1219, 1996

14）Dreisbach G, et al : Dopamine and cognitive control : the influence of spontaneous eyeblink rate and dopamine gene polymorphism on perseveration and distractibility. Behav Neurosci 11 : 483-490, 2005

15）Colzato LS, et al : Dopamine and inhibitory action control : evidence from spontaneous eye blink rates. Exp Brain Res 196 : 467-474, 2009

16）Horimoto N, et al : Concurrence of mouthing movement and rapid eye movement/non-rapid eye movement phases with advance in gestation of the human fetus. Am J Obstet Gynecol 161 : 344-351, 1989

17）Hata T, et al : Fetal consciousness 4D ultrasound study. Donald School J Ultrasound Obstet Gynecol 9 : 471-474, 2015

18）Reissland N, et al : Can healthy fetuses show facial expressions of “pain” or “distress”? PLoS One 8 : e65530, 2013

19）Kawakami F, et al : Smiles in the fetal period. Infant Behav Dev 35 : 466-471, 2019

20）Miyagi Y, et al : Potential of artificial intelligence for estimating Japanese fetal weights. Acta Medica Okayama 74 : 483-493, 2020

21）Miyagi Y, et al : Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types. Oncol Lett 19 : 1602-1610, 2020

22）Miyagi Y, et al : Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images. Mol Clin Oncol 11 : 583-589, 2019

23）Miyagi Y, et al : Feasibility of new method for the prediction of clinical trial results using compressive sensing of artificial intelligence. BJHR 10 : 237-267, 2023

24）Miyagi Y, et al : Studies on development of new method for the prediction of clinical trial results using compressive sensing of artificial intelligence. Ferreira MAM（ed） : Theory and practice of mathematics and computer science, vol 2, pp101-108, Book Publisher International, Hooghly, West Bengal, India, 2020

25）Miyagi Y, et al : Development of new method for the prediction of clinical trial results using compressive sensing of artificial intelligence. J Biostat Biometric 3 : 202, 2018

26）Miyagi Y, et al : Predicting a live birth by artificial intelligence incorporating both the blastocyst image and conventional embryo evaluation parameters. Artif Intell Med Imaging 1 : 94-107, 2020

27）Miyagi Y, et al : Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age. Reprod Med Biol 18 : 190-203, 2019

28）Miyagi Y, et al : Feasibility of predicting live birth by combining conventional embryo evaluation with artificial intelligence applied to a blastocyst image in patients classified by age. Reprod Med Biol 18 : 344-356, 2019

29）Miyagi Y, et al : New methods for comparing embryo selection methods by applying artificial intelligence : comparing embryo selection AI for live births. BJHR 9 : 36-44, 2022

30）Miyagi Y, et al : Feasibility of artificial intelligence for predicting live birth without aneuploidy from a blastocyst image. Reprod Med Biol 18 : 204-211, 2019

31）Miyagi Y, et al : Deep learning to predicting live births and aneuploid miscarriages from images of blastocysts combined with maternal age. Int J Bioinfor Intell Comput 1 : 10-21, 2022

32）Miyagi Y, et al : New method for determining fibrinogen and FDP threshold criteria by artificial intelligence in cases of massive hemorrhage during delivery. J Obstet Gynaecol Res 46 : 256-265, 2020

33）Tada K, et al : Feasibility of applying novel FDP threshold criteria to DIC diagnostic scoring systems in Japanese women with placental abruption. Eur J Clin Biomed Sci 8 : 27-32, 2022

34）Bengio Y, et al : Representation learning : a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35 : 1798-1828, 2013

35）LeCun YA, et al : Efficient backprop. Montavon G, et al（eds） : Neural networks : tricks of the trade, 2nd ed. pp9-48, Springer, Heidelberg, Berlin, 2012

36）LeCun Y, et al : Gradient-based learning applied to document recognition. Proc IEEE 86 : 2278-2324, 1998

37）LeCun Y, et al : Backpropagation applied to handwritten zip code recognition. Neural Comput 1 : 541-551, 1989

38）Serre T, et al : Robust object recognition with cortex-like mechanisms. IEEE Trans Pattern Anal Mach Intell 29 : 411-426, 2007

39）Wiatowski T, et al : A mathematical theory of deep convolutional neural networks for feature extraction. IEEE Trans Inf Theory 64 : 1845-1866, 2017

40）Yu L, et al : Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE Trans Med Imaging 36 : 994-1004, 2017

41）Caruana R, et al : Overfitting in neural nets : backpropagation, conjugate gradient, and early stopping. Leen TK et al（eds） : Advances in Neural Information Processing Systems 13 : Proceedings of the 2000 Conference. pp402-408, MIT Press, Cambridge, 2001

42）Baum EB, et al : What size net gives valid generalization? Neural Comput 1 : 151-160, 1989

43）Geman S, et al : Neural networks and the bias/variance dilemma. Neural Comput 4 : 1-58, 1992

44）Krogh A, et al : A simple weight decay can improve generalization. Adv Neural Inform Proc Syst 4 : 950-957, 1992

45）Moody JE : The effective number of parameters : an analysis of generalization and regularization in nonlinear learning systems. Adv Neural Infor Proc Syst 4 : 847-854, 1992

46）Krizhevsky A, et al : ImageNet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems. NIPS 2012 25 : 1097-1105, 2012

47）Bridle JS : Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition. Soulié FF, et al（eds） : Neurocomputing : algorithms, architectures and applications. pp227-236, Springer, Berlin, Heidelberg, 1990

48）Miyagi Y, et al : Recognition of facial expression of fetuses by artificial intelligence（AI）. J Perinat Med 49 : 596-603, 2021

49）Miyagi Y, et al : Recognition of fetal facial expressions using artificial intelligence deep learning. Donald School J Ultrasound Obstet Gynecol 15 : 223-228, 2021

50）Miyagi Y, et al : Variations of multifractal structure in the fetal heartbeats. Acta Med Okayama 57 : 49-52, 2003

51）Grassberger P, et al : Characterization of strange attractors. Phys Rev Lett 50 : 346-349, 1983

52）Grassberger P : Dimensions and entropies of strange attractors from a fluctuating dynamics approach. Physica D 13 : 34-54, 1984

53）Farmer JD, et al : The dimension of chaotic attractors. Physica D 7 : 153-180, 1983

54）HalseyTC, et al : Fractal measures and their singularities : the characterization of strangesets. Phys Rev A 33 : 1141-1151, 1986

55）Hentschel HE, et al : The infinite number of generalized dimensions of fractals and strange attractors. Physica D 8 : 435-444, 1983

56）Miyagi Y, et al : Artificial intelligence to understand fluctuation of fetal brain activity by recognizing facial expressions. Int J Gynecol Obstet 161 : 877-885, 2023

57）Isomura T, et al : Canonical neural networks perform active inference. Commun Biol 5 : 55, 2022

58）Friston KJ, et al : A free energy principle for the brain. J Physiol Paris 100 : 70-87, 2006

59）Friston KJ : The free-energy principle : a rough guide to the brain? Trends Cogn Sci 13 : 293-301, 2009

60）Friston KJ, et al : Action and behavior : a free-energy formulation. Biol Cybern 102 : 227-260, 2010

61）Friston KJ, et al : Reinforcement learning or active inference? PloS One 4 : e6421, 2009

62）Miyagi Y, et al : Fetal brain activity and the free energy principle. J Perinat Med 51 : 925-931, 2023

63）Joyce JM : Kullback-Leibler divergence. Lovric M （ed） : International encyclopedia of statistical science. pp720-722, Springer, Berlin, Heidelberg, 2011

64）Inui T : The free-energy principle : a unified theory of brain functions. The Brain＆Neural Networks 25 : 123-134, 2018

65）Yoshida M, et al : Free energy principle and visual consciousness. The Brain＆Neural Networks 25 : 53-70, 2018

66）Manning FA, et al : Antepartum fetal evaluation : development of a fetal biophysical profile. Am J Obstet Gynecol 136 : 787-795, 1980