Table Info

Table 7.

P-value of combined univariate analysis of all tumors groups for MRI semantic features

MRI features		Ependy-moma, n = 14	Medullo-Blastoma, n = 21	Pilocytic astrocytoma, n = 19	Brainstem glioma, n = 21	P-value
T1WI	Hypointense	12 (85.7%)	21 (100.0%)	17 (89.5%)	20 (95.2%)	0.336
T1WI	Isointense	2 (14.3%)	0	2 (10.5%)	1 (4.8%)	0.336
T2WI	Hyperintense	2 (14.3%)	0	6 (31.6%)	6 (28.6%)	0.047
	Hypointense	1 (7.1%)	0	0	0
	Isointense	11 (78.6%)	21 (100.0%)	13 (68.4%)	15 (71.4%)
FLAIR	Hyperintense	11 (78.6%)	1 (4.8%)	12 (63.2%)	6 (28.6%)	< 0.001
FLAIR	Isointense	3 (21.4%)	20 (95.2%)	7 (36.8%)	15 (71.4%)	< 0.001
Enhancement pattern	Homogenous	1 (7.1%)	5 (23.8%)	5 (26.3%)	0	0.053
Enhancement pattern	Heterogeneous	13 (92.9%)	16 (76.2%)	14 (73.7%)	21 (100.0%)	0.053
Enhancement pattern	Mild < 25%	3 (21.4%)	6 (28.6%)	5 (26.3%)	17 (81.0%)	0.001
	Moderate 25–75%	5 (35.7%)	5 (23.8%)	6 (31.6%)	4 (19.0%)
	Severe > 75%	6 (42.9%)	10 (47.6%)	8 (42.1%)	0
Haemorrhage	No	5 (35.7%)	13 (61.9%)	18 (94.7%)	16 (76.2%)	0.003
Haemorrhage	Yes	9 (64.3%)	8 (38.1%)	1 (5.3%)	5 (23.8%)	0.003
Calcification	No	9 (64.3%)	20 (95.2%)	19 (100.0%)	21 (100.0%)	< 0.001
Calcification	Yes	5 (35.7%)	1 (4.8%)	0	0	< 0.001
DWI	No restriction	10 (76.9%)	1 (5.9%)	13 (76.5%)	14 (70%)	< 0.001
DWI	Restriction	3 (23.1%)	16 (94.1%)	4 (23.5%)	6 (30%)	< 0.001
Cyst	No	4 (28.6%)	2 (9.5%)	5 (26.3%)	20 (95.2%)	< 0.001
Cyst	Yes	10 (71.4%)	19 (90.5%)	14 (73.7%)	1 (4.8%)	< 0.001
Necrosis	No	4 (28.6%)	20 (95.2%)	19 (100.0%)	13 (61.9%)	< 0.001
Necrosis	Yes	10 (71.4%)	1 (4.8%)	0	8 (38.1%)	< 0.001
Tumor margins	Well defined	6 (42.9%)	19 (90.5%)	15 (78.9%)	3 (14.3%)	< 0.001
Tumor margins	Ill defined	8 (57.1%)	2 (9.5%)	4 (21.1%)	18 (85.7%)	< 0.001
Tumor location	Forebrain	6 (42.9%)	0	13 (68.4%)	0	< 0.001
	Brainstem	0	0	0	21 (100.0%)
	Cerebellum and fourth ventricle	8 (57.1%)	21 (100.0%)	6 (31.6%)	0
Laterality	Right	2 (14.3%)	1 (4.8%)	4 (21.1%)	3 (14.3%)	0.225
	Left	4 (28.6%)	1 (4.8%)	4 (21.1%)	2 (9.5%)
	Midline	8 (57.1%)	19 (90.5%)	11 (57.9%)	16 (76.2%)
Oedema	No	4 (28.6%)	15 (71.4%)	7 (36.8%)	5 (23.8%)	0.048
	Less than tumor volume	9 (64.3%)	6 (28.6%)	10 (52.6%)	16 (76.2%)
	Equal to tumor volume	0	0	1 (5.3%)	0
	More than tumor volume	1 (7.1%)	0	1 (5.3%)	0
Midline shift	No	12 (85.7%)	21 (100.0%)	17 (89.5%)	21 (100.0%)	0.133
Midline shift	Yes	2 (14.3%)	0	2 (10.5%)	0	0.133
Hydrocephalus	Absent	5 (35.7%)	0	8 (42.1%)	12 (57.1%)	0.001
Hydrocephalus	Present	9 (64.3%)	21 (100.0%)	11 (57.9%)	9 (42.9%)	0.001

Declarations

Acknowledgments

We acknowledge our institute Tata Memorial Hospital, for providing us with the means and resources to be able to write this article and access the images.

Author contributions

A Mahajan: Conceptualization, Project administration, Investigation, Methodology, Supervision, Validation, Writing—review & editing. MB: Conceptualization, Data curation, Formal analysis, Investigation, Writing—review & editing, Writing—original draft. BK: Supervision. A Mlv: Data curation, Formal analysis, Software. MB, UA, BKSS, A Mlv, AG, A Sahu, AC, V Pawar, V Punia, SE, A Sahay, TG, GC, PS and A Moiyadi: Data curation, Investigation. All authors read and approved the submitted version.

Conflicts of interest

The authors declare that there is no conflict of interest.

Ethical approval

The study was conducted after clearance from Institutional Ethics Committee [3296] and conducted in accordance with the guidelines of the Indian Council of Medical Research 2017. The research of this article meets the requirements of the Declaration of Helsinki.

Consent to participate

Informed consent to participate in the study was obtained from all participants.

Consent to publication

Informed consent to publication was obtained from relevant participants.

Availability of data and materials

The datasets generated in this study are available on request to the corresponding author, Abhishek Mahajan (drabhishek.mahajan@yahoo.in; abhiradiology@gmail.com).

Funding

Not applicable.

Copyright

References

Madhavan R, Kannabiran BP, Nithya AM, Kani J, Balasubramaniam P, Shanmugakumar S. Pediatric brain tumors: an analysis of 5 years of data from a tertiary cancer care center, India. Indian J Cancer. 2016;53:562–5. [DOI] [PubMed]

AlRayahi J, Zapotocky M, Ramaswamy V, Hanagandi P, Branson H, Mubarak W, et al. Pediatric brain tumor genetics: what radiologists need to know. Radiographics. 2018;38:2102–22. [DOI] [PubMed]

Lacayo A, Farmer PM. Brain tumors in children: a review. Ann Clin Lab Sci. 1991;21:26–35. [PubMed]

Panigrahy A, Blüml S. Neuroimaging of pediatric brain tumors: from basic to advanced magnetic resonance imaging (MRI). J Child Neurol. 2009;24:1343–65. [DOI] [PubMed]

Packer RJ. Childhood brain tumors: accomplishments and ongoing challenges. J Child Neurol. 2008;23:1122–7. [DOI] [PubMed] [PMC]

Hong S, Kim IH, Wang KC. Outcome and prognostic factors of childhood diffuse brainstem glioma. Cancer Res Treat. 2005;37:109–13. [DOI] [PubMed] [PMC]

Ali ZA, Habib RM, Fotoh SA. Role of magnetic resonance imaging in diagnosis of pediatric posterior fossa tumors. Menoufia Medical J. 2020;33:326–31. [DOI]

Mahajan A, Vaidya T, Gupta A, Rane S, Gupta S. Artificial intelligence in healthcare in developing nations: the beginning of a transformative journey. Cancer Res Stat Treat. 2019;2:182. [DOI]

Bothra M, Mahajan A. Mining artificial intelligence in oncology: Tata Memorial Hospital journey. Cancer Res Stat Treat. 2020;3:622–4. [DOI]

10.

Davatzikos C, Barnholtz-Sloan JS, Bakas S, Colen R, Mahajan A, Quintero CB, et al. AI-based prognostic imaging biomarkers for precision neuro-oncology: the ReSPOND consortium. Neuro Oncol. 2020;22:886–8. [DOI] [PubMed] [PMC]

11.

Cherian Kurian N, Sethi A, Reddy Konduru A, Mahajan A, Rane SU. A 2021 update on cancer image analytics with deep learning. WIREs Data Mining Knowl Discov. 2021;11:e1410. [DOI]

12.

Akbari H, Mohan S, Garcia JA, Kazerooni AF, Sako C, Bakas S, et al. NIMG-22. Prediction of glioblastoma cellular infiltration and recurrence using machine learning and multi-parametric mri analysis: results from the multi-institutional respond consortium. Neuro-Oncology. 2021;23:vi132–3. [DOI]

13.

Bakas S, Reyes M, Jakab A, Bauer S, Rempfler M, Crimi A, et al. Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. arXiv: 1811.02629 [Preprint]. 2019 [cited 2019 Apr 23]. Available from: https://doi.org/10.48550/arXiv.1811.02629

14.

Baid U, Rane SU, Talbar S, Gupta S, Thakur MH, Moiyadi A, et al. Overall survival prediction in glioblastoma with radiomic features using machine learning. Front Comput Neurosci. 2020;14:61. [DOI] [PubMed] [PMC]

15.

Baid U, Ghodasara S, Mohan S, Bilello M, Calabrese E, Colak E, et al. RSNA-ASNR-MICCAI BraTS 2021 Benchmarkon brain tumor segmentation and radiogenomic classification. arXiv:2107.02314 [Preprint]. 2021 [cited 2021 Sep 12]. Available from: https://doi.org/10.48550/arXiv.2107.02314

16.

Mehta R, Filos A, Baid U, Sako C, McKinley R, Rebsamen M, et al. QU-BraTS: MICCAI BraTS 2020 challenge on quantifying uncertainty in brain tumor segmentation--analysis of ranking metrics and benchmarking results. arXiv:2112.10074 [Preprint]. 2022 [cited 2022 Aug 23]. Available from: https://doi.org/10.48550/arXiv.2112.10074

17.

Baid U, Talbar S, Rane S, Gupta S, Thakur MH, Moiyadi A, et al. A novel approach for fully automatic intra-tumor segmentation with 3D U-Net architecture for gliomas. Front Comput Neurosci. 2020;14:10. [DOI] [PubMed] [PMC]

18.

Rudie JD, Weiss DA, Colby JB, Rauschecker AM, Laguna B, Braunstein S, et al. Three-dimensional U-Net convolutional neural network for detection and segmentation of intracranial metastases. Radiol Artif Intell. 2021;3:e200204. [DOI] [PubMed] [PMC]

19.

Zhang J, Shen X, Zhuo T, Zhou H. Brain tumor segmentation based on refined fully convolutional neural networks with a hierarchical dice loss. arXiv:1712.09093 [Preprint]. 2018 [cited 2018 Feb 13]. Available from: https://doi.org/10.48550/arXiv.1712.09093

20.

Sudre CH, Li W, Vercauteren T, Ourselin S, Jorge Cardoso M. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso MJ, Arbel T, Carneiro G, Syeda-Mahmood T, Tavares JMRS, Moradi M, et al., editors. Deep learning in medical image analysis and multimodal learning for clinical decision support. Cham: Springer International Publishing; 2017. pp. 240–8. [DOI] [PubMed] [PMC]

21.

Piramuthu S. The Hausdorff distance measure for feature selection in learning applications. In: Proceedings of the 32nd Annual Hawaii International Conference on Systems Sciences. 1999. HICSS-32. Abstracts and CD-ROM of full papers. 32nd Annual Hawaii International Conference on System Sciences; 1999 Jan 5–8; Maui, HI, USA. IEEE; 2002. [DOI]

22.

Zimmerman RA. Neuroimaging of pediatric brain stem diseases other than brain stem glioma. Pediatr Neurosurg. 1996;25:83–92. [DOI] [PubMed]

23.

Duc NM, Huy HQ. Magnetic resonance imaging features of common posterior fossa brain tumors in children: a preliminary vietnamese study. Open Access Maced J Med Sci. 2019;7:2413–8. [DOI] [PubMed] [PMC]

24.

Mangalore S, Aryan S, Prasad C, Santosh V. Imaging characteristics of supratentorial ependymomas: study on a large single institutional cohort with histopathological correlation. Asian J Neurosurg. 2015;10:276–81. [DOI] [PubMed] [PMC]

25.

Arora RS, Alston RD, Eden TO, Estlin EJ, Moran A, Birch JM. Age–incidence patterns of primary CNS tumors in children, adolescents, and adults in England. Neuro-oncology. 2009;11:403–13. [DOI] [PubMed] [PMC]

26.

Hussain IZ, Mohd Zaki F, Mukari SA, Md Pauzi SH, Loh CK, Alias H. Correlation between MRI characteristics of medulloblastoma with histopathological subtypes and 2-year survival. Indian J Radiol Imaging. 2020;30:46–51. [DOI] [PubMed] [PMC]

27.

Yeom KW, Mobley BC, Lober RM, Andre JB, Partap S, Vogel H, et al. Distinctive MRI features of pediatric medulloblastoma subtypes. AJR Am J Roentgenol. 2013;200:895–903. [DOI] [PubMed]

28.

Poretti A, Meoded A, Huisman TA. Neuroimaging of pediatric posterior fossa tumors including review of the literature. J Magn Reson Imaging. 2012;35:32–47. [DOI] [PubMed]

29.

Plaza MJ, Borja MJ, Altman N, Saigal G. Conventional and advanced MRI features of pediatric intracranial tumors: posterior fossa and suprasellar tumors. AJR Am J Roentgenol. 2013;200:1115–24. [DOI] [PubMed]

30.

Camacho AC, Chaljub G, Uribe T, Patterson JT, Swischuk LE. MR imaging of pediatric posterior fossa tumors. Contemp Diagn Radiol. 2007;30:1–6. [DOI] [PubMed]

31.

Quon JL, Bala W, Chen LC, Wright J, Kim LH, Han M, et al. Deep learning for pediatric posterior fossa tumor detection and classification: a multi-institutional study. AJNR Am J Neuroradiol. 2020;41:1718–25. [DOI] [PubMed] [PMC]

32.

Zhou H, Hu R, Tang O, Hu C, Tang L, Chang K, et al. Automatic machine learning to differentiate pediatric posterior fossa tumors on routine MR imaging. AJNR Am J Neuroradiol. 2020;41:1279–85. [DOI] [PubMed] [PMC]