Top

Published in:

Open Access 01-12-2024 | Meningioma | Research

Enhancing mitosis quantification and detection in meningiomas with computational digital pathology

Authors: Hongyan Gu, Chunxu Yang, Issa Al-kharouf, Shino Magaki, Nelli Lakis, Christopher Kazu Williams, Sallam Mohammad Alrosan, Ellie Kate Onstott, Wenzhong Yan, Negar Khanlou, Inma Cobos, Xinhai Robert Zhang, Neda Zarrin-Khameh, Harry V. Vinters, Xiang Anthony Chen, Mohammad Haeri

Published in: Acta Neuropathologica Communications | Issue 1/2024

Abstract

Mitosis is a critical criterion for meningioma grading. However, pathologists’ assessment of mitoses is subject to significant inter-observer variation due to challenges in locating mitosis hotspots and accurately detecting mitotic figures. To address this issue, we leverage digital pathology and propose a computational strategy to enhance pathologists’ mitosis assessment. The strategy has two components: (1) A depth-first search algorithm that quantifies the mathematically maximum mitotic count in 10 consecutive high-power fields, which can enhance the preciseness, especially in cases with borderline mitotic count. (2) Implementing a collaborative sphere to group a set of pathologists to detect mitoses under each high-power field, which can mitigate subjective random errors in mitosis detection originating from individual detection errors. By depth-first search algorithm (1) , we analyzed 19 meningioma slides and discovered that the proposed algorithm upgraded two borderline cases verified at consensus conferences. This improvement is attributed to the algorithm’s ability to quantify the mitotic count more comprehensively compared to other conventional methods of counting mitoses. In implementing a collaborative sphere (2) , we evaluated the correctness of mitosis detection from grouped pathologists and/or pathology residents, where each member of the group annotated a set of 48 high-power field images for mitotic figures independently. We report that groups with sizes of three can achieve an average precision of 0.897 and sensitivity of 0.699 in mitosis detection, which is higher than an average pathologist in this study (precision: 0.750, sensitivity: 0.667). The proposed computational strategy can be integrated with artificial intelligence workflow, which envisions the future of achieving a rapid and robust mitosis assessment by interactive assisting algorithms that can ultimately benefit patient management.

Available only for authorised users

This work defines an HPF as a square. All HPFs mentioned in this work had sizes of \(0.16mm^2\), as defined in the 2021 WHO CNS 5 Blue Book [2]. Therefore, the edge of an HPF was 0.4mm, or 1,600 pixels (\(0.25\mu m\)/pixel for 400\(\times\) scans).

https://www.leicabiosystems.com/us/digital-pathology/manage/aperio-imagescope/

The top-2 is defined by the F1 score, which is the geometry mean of precision and sensitivity.

Ostrom QT, Price M, Neff C, Cioffi G, Waite KA, Kruchko C, et al. (2022) CBTRUS Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2015–2019. Neuro-Oncology. 10;24(Supplement_5):v1–v95. https://doi.org/10.1093/neuonc/noac202. https://academic.oup.com/neuro-oncology/article-pdf/24/Supplement_5/v1/46359484/noac202.pdf

Louis DN, Perry A, Wesseling P, Brat DJ, Cree IA, Figarella-Branger D et al (2021) The 2021 WHO classification of tumors of the central nervous system: a summary. Neuro Oncol 23(8):1231–1251. https://doi.org/10.1093/neuonc/noab106CrossRefPubMedPubMedCentral

Bertram CA, Aubreville M, Gurtner C, Bartel A, Corner SM, Dettwiler M et al (2020) Computerized calculation of mitotic count distribution in canine cutaneous mast cell tumor sections: mitotic count is area dependent. Vet Pathol 57(2):214–226. https://doi.org/10.1177/0300985819890686CrossRefPubMed

Meyer JS, Alvarez C, Milikowski C, Olson N, Russo I, Russo J et al (2005) Breast carcinoma malignancy grading by Bloom–Richardson system vs proliferation index: reproducibility of grade and advantages of proliferation index. Mod Pathol 18(8):1067–1078. https://doi.org/10.1038/modpathol.3800388CrossRefPubMed

Collan YUI, Kuopio T, Baak JPA, Becker R, Bogomoletz WV, Deverell M et al (1996) Standardized mitotic counts in breast cancer evaluation of the method. Pathol Res Pract 192(9):931–941. https://doi.org/10.1016/S0344-0338(96)80075-6CrossRefPubMed

Garcia CR, Slone SA, Dolecek TA, Huang B, Neltner JH, Villano JL (2019) Primary central nervous system tumor treatment and survival in the United States, 2004–2015. J Neurooncol 144(1):179–191. https://doi.org/10.1007/s11060-019-03218-8CrossRefPubMedPubMedCentral

Cree IA, Tan PH, Travis WD, Wesseling P, Yagi Y, White VA et al (2021) Counting mitoses: SI(ze) matters! Mod Pathol 34(9):1651–1657. https://doi.org/10.1038/s41379-021-00825-7CrossRefPubMedPubMedCentral

Goldbrunner R, Stavrinou P, Jenkinson MD, Sahm F, Mawrin C, Weber DC et al (2021) EANO guideline on the diagnosis and management of meningiomas. Neuro Oncol 23(11):1821–1834. https://doi.org/10.1093/neuonc/noab150CrossRefPubMedPubMedCentral

Ohta M, Iwaki T, Kitamoto T, Takeshita I, Tateishi J, Fukui M (1994) MIB1 staining index and scoring of histologic features in meningioma. Indicators for the prediction of biologic potential and postoperative management. Cancer 74(12):3176–3189. https://doi.org/10.1002/1097-0142(19941215)74:12<3176::AID-CNCR2820741217>3.0.CO;2-NCrossRefPubMed

10.

Abry E, Thomassen IØ, Salvesen ØO, Torp SH (2010) The significance of Ki-67/MIB-1 labeling index in human meningiomas: a literature study. Pathol Res Pract 206(12):810–815. https://doi.org/10.1016/j.prp.2010.09.002CrossRefPubMed

11.

Liu N, Song SY, Jiang JB, Wang TJ, Yan CX (2020) The prognostic role of Ki-67/MIB-1 in meningioma: a systematic review with meta-analysis. Medicine 99(9):e18644. https://doi.org/10.1097/MD.0000000000018644CrossRefPubMedPubMedCentral

12.

Harter PN, Braun Y, Plate KH (2017) Classification of meningiomas-advances and controversies. Chin Clin Oncol 6(S1):S2–S2. https://doi.org/10.21037/cco.2017.05.02CrossRefPubMed

13.

Hendzel MJ, Wei Y, Mancini MA, Van Hooser A, Ranalli T, Brinkley BR et al (1997) Mitosis-specific phosphorylation of histone H3 initiates primarily within pericentromeric heterochromatin during G2 and spreads in an ordered fashion coincident with mitotic chromosome condensation. Chromosoma 106(6):348–360. https://doi.org/10.1007/s004120050256CrossRefPubMed

14.

Duregon E, Cassenti A, Pittaro A, Ventura L, Senetta R, Rudà R et al (2015) Better see to better agree: phosphohistone H3 increases interobserver agreement in mitotic count for meningioma grading and imposes new specific thresholds. Neuro Oncol 17(5):663–669. https://doi.org/10.1093/neuonc/nov002. (02)CrossRefPubMedPubMedCentral

15.

Ribalta T, McCutcheon IE, Aldape KD, Bruner JM, Fuller GN (2004) The mitosis-specific antibody anti-phosphohistone-H3 (PHH3) facilitates rapid reliable grading of meningiomas according to WHO 2000 criteria. Am J Surg Pathol 28(11):1532–1536. https://doi.org/10.1097/01.pas.0000141389.06925.d5CrossRefPubMed

16.

Kim YJ, Ketter R, Steudel WI, Feiden W (2007) Prognostic significance of the mitotic index using the mitosis marker anti-phosphohistone H3 in meningiomas. Am J Clin Pathol 128(1):118–125. https://doi.org/10.1309/HXUNAG34B3CEFDU8CrossRefPubMed

17.

Fukushima S, Terasaki M, Sakata K, Miyagi N, Kato S, Sugita Y et al (2009) Sensitivity and usefulness of anti-phosphohistone-H3 antibody immunostaining for counting mitotic figures in meningioma cases. Brain Tumor Pathol 26:51–57. https://doi.org/10.1007/s10014-009-0249-9CrossRefPubMed

18.

Singh J, Sharma R, Shukla N, Narwal P, Katiyar A, Mahajan S et al (2023) DNA methylation profiling of meningiomas highlights clinically distinct molecular subgroups. J Neurooncol 161(2):339–356. https://doi.org/10.1007/s11060-022-04220-3CrossRefPubMed

19.

Nassiri F, Mamatjan Y, Suppiah S, Badhiwala JH, Mansouri S, Karimi S et al (2019) DNA methylation profiling to predict recurrence risk in meningioma: development and validation of a nomogram to optimize clinical management. Neuro Oncol 21(7):901–910. https://doi.org/10.1093/neuonc/noz061CrossRefPubMedPubMedCentral

20.

Capper D, Stichel D, Sahm F, Jones DTW, Schrimpf D, Sill M et al (2018) Practical implementation of DNA methylation and copy-number-based CNS tumor diagnostics: the Heidelberg experience. Acta Neuropathol 136(2):181–210. https://doi.org/10.1007/s00401-018-1879-yCrossRefPubMedPubMedCentral

21.

Sahm F, Schrimpf D, Stichel D, Jones DTW, Hielscher T, Schefzyk S et al (2017) DNA methylation-based classification and grading system for meningioma: a multicentre, retrospective analysis. Lancet Oncol 18(5):682–694. https://doi.org/10.1016/S1470-2045(17)30155-9CrossRefPubMed

22.

Wang JZ, Nassiri F, Aldape K, von Deimling A, Sahm F (2023) The epigenetic landscape of meningiomas. Adv Exp Med Biol 1416:175–188. https://doi.org/10.1007/978-3-031-29750-2_13CrossRefPubMed

23.

Aubreville M, Bertram CA, Marzahl C, Gurtner C, Dettwiler M, Schmidt A et al (2020) Deep learning algorithms out-perform veterinary pathologists in detecting the mitotically most active tumor region. Sci Rep 10(1):16447. https://doi.org/10.1038/s41598-020-73246-2CrossRefPubMedPubMedCentral

24.

Veta M, Van Diest PJ, Jiwa M, Al-Janabi S, Pluim JPW (2016) Mitosis counting in breast cancer: object-level interobserver agreement and comparison to an automatic method. PLoS ONE 11(8):e0161286. https://doi.org/10.1371/journal.pone.0161286CrossRefPubMedPubMedCentral

25.

Gu H, Yang C, Haeri M, Wang J, Tang S, Yan W, et al. (2023) Augmenting Pathologists with NaviPath: Design and Evaluation of a Human-AI Collaborative Navigation System. In: Proceedings of the 2023 CHI conference on human factors in computing systems. CHI ’23. New York: Association for Computing Machinery. Available from: https://doi.org/10.1145/3544548.3580694

26.

Gu H, Liang Y, Xu Y, Williams CK, Magaki S, Khanlou N et al (2023) Improving workflow integration with XPath: design and evaluation of a human-ai diagnosis system in pathology. ACM Trans Comput-Hum Interact. https://doi.org/10.1145/3577011CrossRef

27.

Bertram CA, Aubreville M, Donovan TA, Bartel A, Wilm F, Marzahl C et al (2022) Computer-assisted mitotic count using a deep learning-based algorithm improves interobserver reproducibility and accuracy. Vet Pathol 59(2):211–226. https://doi.org/10.1177/03009858211067478CrossRefPubMed

28.

Van Bergeijk SA, Stathonikos N, Ter Hoeve ND, Lafarge MW, Nguyen TQ, Van Diest PJ et al (2023) Deep learning supported mitoses counting on whole slide images: a pilot study for validating breast cancer grading in the clinical workflow. J Pathol Inform 14:100316. https://doi.org/10.1016/j.jpi.2023.100316CrossRefPubMedPubMedCentral

29.

Balkenhol MCA, Tellez D, Vreuls W, Clahsen PC, Pinckaers H, Ciompi F et al (2019) Deep learning assisted mitotic counting for breast cancer. Lab Invest 99(11):1596–1606. https://doi.org/10.1038/s41374-019-0275-0CrossRefPubMed

30.

Bertram CA, Aubreville M, Marzahl C, Maier A, Klopfleisch R (2019) A large-scale dataset for mitotic figure assessment on whole slide images of canine cutaneous mast cell tumor. Sci Data 6(1):274. https://doi.org/10.1038/s41597-019-0290-4CrossRefPubMedPubMedCentral

31.

Aubreville M, Bertram CA, Donovan TA, Marzahl C, Maier A, Klopfleisch R (2020) A completely annotated whole slide image dataset of canine breast cancer to aid human breast cancer research. Sci Data 7(1):417. https://doi.org/10.1038/s41597-020-00756-zCrossRefPubMedPubMedCentral

32.

Roux L, Racoceanu D, Loménie N, Kulikova M, Irshad H, Klossa J et al (2013) Mitosis detection in breast cancer histological images an ICPR 2012 contest. J Pathol Inform 4(1):8. https://doi.org/10.4103/2153-3539.112693CrossRefPubMedPubMedCentral

33.

Veta M, Heng YJ, Stathonikos N, Bejnordi BE, Beca F, Wollmann T et al (2019) Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge. Med Image Anal 54:111–121. https://doi.org/10.1016/j.media.2019.02.012CrossRefPubMed

34.

Aubreville M, Stathonikos N, Bertram CA, Klopfleisch R, ter Hoeve N, Ciompi F et al (2023) Mitosis domain generalization in histopathology images—the MIDOG challenge. Med Image Anal 84:102699. https://doi.org/10.1016/j.media.2022.102699CrossRefPubMed

35.

Stacke K, Eilertsen G, Unger J, Lundstrom C (2021) Measuring domain shift for deep learning in histopathology. IEEE J Biomed Health Inform 25(2):325–336. https://doi.org/10.1109/JBHI.2020.3032060CrossRefPubMed

36.

Aubreville M, Bertram C, Veta M, Klopfleisch R, Stathonikos N, Breininger K, et al. (2021) Quantifying the scanner-induced domain gap in mitosis detection. arXiv preprint arXiv:2103.16515

37.

Wang Z, Hosseini MS, Miles A, Plataniotis KN, Wang Z (2020) FocusLiteNN: high efficiency focus quality assessment for digital pathology. In: Martel AL, Abolmaesumi P, Stoyanov D, Mateus D, Zuluaga MA, Zhou SK et al (eds) Medical image computing and computer assisted intervention - MICCAI 2020. Springer International Publishing, Cham

38.

Gu H, Haeri M, Ni S, Williams CK, Zarrin-Khameh N, Magaki S, et al. (2023) Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge. In: Mitosis domain generalization and diabetic retinopathy analysis: MICCAI challenges MIDOG 2022 and DRAC 2022, Held in Conjunction with MICCAI 2022, Singapore, Sept 18–22, 2022, Proceedings. Springer-Verlag, Berlin p. 211–216. Available from: https://doi.org/10.1007/978-3-031-33658-4_21

39.

Tan M, Le Q (2019) EfficientNet: Rethinking model scaling for convolutional neural networks. In: Chaudhuri K, Salakhutdinov R, eds. Proceedings of the 36th international conference on machine learning. vol. 97 of Proceedings of machine learning research. PMLR. pp. 6105–6114. Available from: https://proceedings.mlr.press/v97/tan19a.html

40.

Scheithauer BW (1978) Symptomatic subependymoma. Report of 21 cases with review of the literature. J Neurosurg 49(5):689–696. https://doi.org/10.3171/jns.1978.49.5.0689CrossRefPubMed

41.

Feinstein AR, Sosin DM, Wells CK (1985) The Will Rogers phenomenon: stage migration and new diagnostic techniques as a source of misleading statistics for survival in cancer. N Engl J Med 312(25):1604–1608. https://doi.org/10.1056/NEJM198506203122504CrossRefPubMed

42.

Mischel PS, Cloughesy TF, Nelson SF (2004) DNA-microarray analysis of brain cancer: molecular classification for therapy. Nat Rev Neurosci 5(10):782–792. https://doi.org/10.1038/nrn1518CrossRefPubMed

43.

Sahm F, Schrimpf D, Jones DT, Meyer J, Kratz A, Reuss D et al (2016) Next-generation sequencing in routine brain tumor diagnostics enables an integrated diagnosis and identifies actionable targets. Acta Neuropathol 131(6):903–910. https://doi.org/10.1007/s00401-015-1519-8CrossRefPubMed

44.

Kurdyukov S, Bullock M (2016) DNA methylation analysis: choosing the right method. Biology. https://doi.org/10.3390/biology5010003CrossRefPubMedPubMedCentral

45.

Aubreville M, Wilm F, Stathonikos N, Breininger K, Donovan TA, Jabari S et al (2023) A comprehensive multi-domain dataset for mitotic figure detection. Sci Data 10(1):484. https://doi.org/10.1038/s41597-023-02327-4CrossRefPubMedPubMedCentral

46.

Sohail A, Khan A, Wahab N, Zameer A, Khan S (2021) A multi-phase deep CNN based mitosis detection framework for breast cancer histopathological images. Sci Rep 11(1):6215. https://doi.org/10.1038/s41598-021-85652-1CrossRefPubMedPubMedCentral

47.

Mahmood T, Arsalan M, Owais M, Lee MB, Park KR (2020) Artificial intelligence-based mitosis detection in breast cancer histopathology images using faster R-CNN and deep CNNs. J Clin Med 9(3):749. https://doi.org/10.3390/jcm9030749CrossRefPubMedPubMedCentral

Title: Enhancing mitosis quantification and detection in meningiomas with computational digital pathology
Authors: Hongyan Gu
Chunxu Yang
Issa Al-kharouf
Shino Magaki
Nelli Lakis
Christopher Kazu Williams
Sallam Mohammad Alrosan
Ellie Kate Onstott
Wenzhong Yan
Negar Khanlou
Inma Cobos
Xinhai Robert Zhang
Neda Zarrin-Khameh
Harry V. Vinters
Xiang Anthony Chen
Mohammad Haeri
Publication date: 01-12-2024
Publisher: BioMed Central
Keywords: Meningioma
Meningioma
Artificial Intelligence
Pathology
Published in: Acta Neuropathologica Communications / Issue 1/2024
Electronic ISSN: 2051-5960
DOI: https://doi.org/10.1186/s40478-023-01707-6

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Enhancing mitosis quantification and detection in meningiomas with computational digital pathology

Abstract

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Please log in to get access to this content

Other articles of this Issue 1/2024

Gene-expression profiling of individuals resilient to Alzheimer's disease reveals higher expression of genes related to metallothionein and mitochondrial processes and no changes in the unfolded protein response

Aberrant myonuclear domains and impaired myofiber contractility despite marked hypertrophy in MYMK-related, Carey-Fineman-Ziter Syndrome

CNS-associated macrophages contribute to intracerebral aneurysm pathophysiology

Spatial transcriptomics reveals segregation of tumor cell states in glioblastoma and marked immunosuppression within the perinecrotic niche

Clinical implications of DNA methylation-based integrated classification of histologically defined grade 2 meningiomas

IFNγ drives neuroinflammation, demyelination, and neurodegeneration in a mouse model of multiple system atrophy