Cell Counting and Segmentation of Immunohistochemical Images in the Spinal Cord: Comparing Deep Learning and Traditional Approaches

Deep learning imaging analysis to identify bacterial metabolic states associated with carcinogen production

Background

Colorectal cancer (CRC) is a globally prevalent cancer. Emerging research implicates the gut microbiome in CRC pathogenesis. Bacteria such as Clostridium scindens can produce the carcinogenic bile acid deoxycholic acid (DCA). It is unknown whether imaging methods can differentiate DCA-producing and DCA-non-producing C. scindens cells.

Methods

Light microscopy images of anaerobically cultured C. scindens in four conditions were acquired at 100× magnification using the Tissue FAX system: C. scindens in media alone (DCA-non-producing state), C. scindens in media with cholic acid (DCA-producing state), or C. scindens in co-culture with one of two Bacteroides species (intermediate DCA production states). We evaluated three approaches: whole-image classification, per-cell classification, and image segmentation-based classification. For whole-image classification, we used a custom Convolutional Neural Network (CNN), pre-trained DenseNet, pre-trained ResNet, and ResNet enhanced by integrating the Digital Images of Bacterial Species (DIBaS) dataset. For cell detection and classification, we applied thresholding (OTSU or adaptive thresholding) followed by a ResNet model. Finally, image segmentation-based classification was performed using nnU-Net.

Results

For whole-image analysis, DIBaS-enhanced ResNet models achieved the best performance in distinguishing C. scindens states in monoculture (accuracy 0.89 ± 0.006) and in co-cultures (accuracy 0.86 ± 0.004). Per-cell analysis was optimal at a C constant value of 3, with the ResNet model achieving 62-74% accuracy for C. scindens states in monoculture. Segmentation-based analysis using nnU-Net resulted in Dice coefficients of 87% for C. scindens and 74-76% for the Bacteroides species.

Conclusions

This study demonstrates feasibility of image-based deep learning models in identifying health-relevant gut bacterial metabolic states.

Supplementary Information

The online version contains supplementary material available at 10.1007/s44352-025-00006-1.

Different spatial distribution of inflammatory cells in the tumor microenvironment of ABC and GBC subgroups of diffuse large B cell lymphoma

Diffuse Large B-Cell Lymphoma (DLBCL) presents a high clinical and biological heterogeneity, and the tumor microenvironment chracteristics are important in its  progression. The aim of this study was to evaluate tumor T, B cells, macrophages and mast cells distribution in GBC and ABC DLBCL subgroups through a set of morphometric parameters allowing to provide a quantitative evaluation of the morphological features of the spatial patterns generated by these inflammatory cells.   Histological ABC and GCB samples were immunostained for CD4, CD8, CD68, CD 163, and tryptase in order to determine both percentage and position of positive cells in the tissue characterizing their spatial distribution. The results evidenced that cell patterns generated by CD4-, CD8-, CD68-, CD163- and tryptase-positive cell profiles exhibited a significantly higher uniformity index in ABC than in GCB subgroup. The positive-cell distributions appeared clustered in tissues from GCB, while in tissues from ABC such a feature was lower or absent. The combinations of spatial statistics-derived parameters can lead to better predictions of tumor cell infiltration than any classical morphometric method providing a more accurate description of the functional status of the tumor, useful for patient prognosis.

Machine Learning Based on Morphological Features Enables Classification of Primary Intestinal T-Cell Lymphomas

The aim of this study was to investigate the feasibility of using machine learning techniques based on morphological features in classifying two subtypes of primary intestinal T-cell lymphomas (PITLs) defined according to the WHO criteria: monomorphic epitheliotropic intestinal T-cell lymphoma (MEITL) versus intestinal T-cell lymphoma, not otherwise specified (ITCL-NOS), which is considered a major challenge for pathological diagnosis. A total of 40 histopathological whole-slide images (WSIs) from 40 surgically resected PITL cases were used as the dataset for model training and testing. A deep neural network was trained to detect and segment the nuclei of lymphocytes. Quantitative nuclear morphometrics were further computed from these predicted contours. A decision-tree-based machine learning algorithm, XGBoost, was then trained to classify PITL cases into two disease subtypes using these nuclear morphometric features. The deep neural network achieved an average precision of 0.881 in the cell segmentation work. In terms of classifying MEITL versus ITCL-NOS, the XGBoost model achieved an area under receiver operating characteristic curve (AUC) of 0.966. Our research demonstrated an accurate, human-interpretable approach to using machine learning algorithms for reducing the high dimensionality of image features and classifying T cell lymphomas that present challenges in morphologic diagnosis. The quantitative nuclear morphometric features may lead to further discoveries concerning the relationship between cellular phenotype and disease status.

A novel retinal ganglion cell quantification tool based on deep learning

Glaucoma is a disease associated with the loss of retinal ganglion cells (RGCs), and remains one of the primary causes of blindness worldwide. Major research efforts are presently directed towards the understanding of disease pathogenesis and the development of new therapies, with the help of rodent models as an important preclinical research tool. The ultimate goal is reaching neuroprotection of the RGCs, which requires a tool to reliably quantify RGC survival. Hence, we demonstrate a novel deep learning pipeline that enables fully automated RGC quantification in the entire murine retina. This software, called RGCode (Retinal Ganglion Cell quantification based On DEep learning), provides a user-friendly interface that requires the input of RBPMS-immunostained flatmounts and returns the total RGC count, retinal area and density, together with output images showing the computed counts and isodensity maps. The counting model was trained on RBPMS-stained healthy and glaucomatous retinas, obtained from mice subjected to microbead-induced ocular hypertension and optic nerve crush injury paradigms. RGCode demonstrates excellent performance in RGC quantification as compared to manual counts. Furthermore, we convincingly show that RGCode has potential for wider application, by retraining the model with a minimal set of training data to count FluoroGold-traced RGCs.

Redundancy and multifunctionality among spinal locomotor networks

c-Fos is used to identify system-wide neural activation with cellular resolution in vivo. However, c-Fos can only capture neural activation of one event. Targeted recombination in active populations (TRAP) allows the capture of two different c-Fos activation patterns in the same animal. So far, TRAP has only been used to examine brain circuits. This study uses TRAP to investigate spinal circuit activation during resting and stepping, giving novel insights of network activation during these events. The level of colabeled (c-Fos+ and TRAP+) neurons observed after performing two bouts of stepping suggests that there is a probabilistic-like phenomenon that can recruit many combinations of neural populations (synapses) when repetitively generating many step cycles. Between two 30-min bouts of stepping, each consisting of thousands of steps, only ∼20% of the neurons activated from the first bout of stepping were also activated by the second bout. We also show colabeling of interneurons that have been active during stepping and resting. The use of the FosTRAP methodology in the spinal cord provides a new tool to compare the engagement of different populations of spinal interneurons in vivo under different motor tasks or under different conditions.NEW & NOTEWORTHY The results are consistent with there being an extensive amount of redundancy among spinal locomotor circuits. Using the newly developed FosTRAP mouse model, only ∼20% of neurons that were active (labeled by Fos-linked tdTomato expression) during a first bout of 30-min stepping were also labeled for c-Fos during a second bout of stepping. This finding suggests variability of neural networks that enables selection of many combinations of neurons (synapses) when generating each step cycle.

Combining multiple spatial statistics enhances the description of immune cell localisation within tumours

Digital pathology enables computational analysis algorithms to be applied at scale to histological images. An example is the identification of immune cells within solid tumours. Image analysis algorithms can extract precise cell locations from immunohistochemistry slides, but the resulting spatial coordinates, or point patterns, can be difficult to interpret. Since localisation of immune cells within tumours may reflect their functional status and correlates with patient prognosis, novel descriptors of their spatial distributions are of biological and clinical interest. A range of spatial statistics have been used to analyse such point patterns but, individually, these approaches only partially describe complex immune cell distributions. In this study, we apply three spatial statistics to locations of CD68+ macrophages within human head and neck tumours, and show that images grouped semi-quantitatively by a pathologist share similar statistics. We generate a synthetic dataset which emulates human samples and use it to demonstrate that combining multiple spatial statistics with a maximum likelihood approach better predicts human classifications than any single statistic. We can also estimate the error associated with our classifications. Importantly, this methodology is adaptable and can be extended to other histological investigations or applied to point patterns outside of histology.

Artificial Intelligence in Lung Cancer Pathology Image Analysis

OBJECTIVE

Accurate diagnosis and prognosis are essential in lung cancer treatment selection and planning. With the rapid advance of medical imaging technology, whole slide imaging (WSI) in pathology is becoming a routine clinical procedure. An interplay of needs and challenges exists for computer-aided diagnosis based on accurate and efficient analysis of pathology images. Recently, artificial intelligence, especially deep learning, has shown great potential in pathology image analysis tasks such as tumor region identification, prognosis prediction, tumor microenvironment characterization, and metastasis detection.

MATERIALS AND METHODS

In this review, we aim to provide an overview of current and potential applications for AI methods in pathology image analysis, with an emphasis on lung cancer.

RESULTS

We outlined the current challenges and opportunities in lung cancer pathology image analysis, discussed the recent deep learning developments that could potentially impact digital pathology in lung cancer, and summarized the existing applications of deep learning algorithms in lung cancer diagnosis and prognosis.

DISCUSSION AND CONCLUSION

With the advance of technology, digital pathology could have great potential impacts in lung cancer patient care. We point out some promising future directions for lung cancer pathology image analysis, including multi-task learning, transfer learning, and model interpretation.