Development of dynamic image analysis methods to measure vascularisation and syncytial nuclear aggregates in human placenta

Characterizing Histopathologic Features in Pregnancies With Chronic Histiocytic Intervillositis Using Computerized Image Analysis

CONTEXT.—

Chronic histiocytic intervillositis (CHI) is a rare condition characterized by maternal immune cell infiltration into the human placenta. CHI is strongly associated with fetal growth restriction, miscarriage, and stillbirth, and knowledge of its etiology, and consequently effective treatment, is limited. Currently, diagnosis is largely subjective and varies between centers, making comparison between studies challenging.

OBJECTIVE.—

To objectively quantify and interrelate inflammatory cells and fibrin in placentas with CHI compared with controls and determine how pathology may be altered in subsequent pregnancies following diagnosis. Macrophage phenotype was also investigated in untreated cases of CHI.

DESIGN.—

Computerized analysis was applied to immunohistochemically stained untreated (index) cases of CHI, subsequent pregnancies, and controls. Index placentas were additionally stained by immunofluorescence for M1 (CD80 and CD86) and M2 macrophage markers (CD163 and CD206).

RESULTS.—

Quantification revealed a median 32-fold increase in macrophage infiltration in index cases versus controls, with CHI recurring in 2 of 11 (18.2%) subsequent pregnancies. A total of 4 of 14 placentas (28.6%) with a diagnosis of CHI did not exhibit infiltration above controls. Macrophages in index pregnancies strongly expressed CD163. There was no significant difference in fibrin deposition between index cases and controls, although subsequent pregnancies displayed a 2-fold decrease compared with index pregnancies. CD3+ T cells were significantly elevated in index pregnancies; however, they returned to normal levels in subsequent pregnancies.

CONCLUSIONS.—

In CHI, intervillous macrophages expressed CD163, possibly representing an attempt to resolve inflammation. Computerized analysis of inflammation in CHI may be useful in determining how treatment affects recurrence, and alongside pathologist expertise in grading lesion severity.

Developing image analysis methods for digital pathology

The potential to use quantitative image analysis and artificial intelligence is one of the driving forces behind digital pathology. However, despite novel image analysis methods for pathology being described across many publications, few become widely adopted and many are not applied in more than a single study. The explanation is often straightforward: software implementing the method is simply not available, or is too complex, incomplete, or dataset‐dependent for others to use. The result is a disconnect between what seems already possible in digital pathology based upon the literature, and what actually is possible for anyone wishing to apply it using currently available software. This review begins by introducing the main approaches and techniques involved in analysing pathology images. I then examine the practical challenges inherent in taking algorithms beyond proof‐of‐concept, from both a user and developer perspective. I describe the need for a collaborative and multidisciplinary approach to developing and validating meaningful new algorithms, and argue that openness, implementation, and usability deserve more attention among digital pathology researchers. The review ends with a discussion about how digital pathology could benefit from interacting with and learning from the wider bioimage analysis community, particularly with regard to sharing data, software, and ideas. © 2022 The Author. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.