Proliferation Tumour Marker Network (PTM-NET) for the identification of tumour region in Ki67 stained breast cancer whole slide images

Artificial intelligence entering the pathology arena in oncology: current applications and future perspectives

BACKGROUND

Artificial intelligence (AI) is rapidly transforming the fields of pathology and oncology, offering novel opportunities for advancing diagnosis, prognosis, and treatment of cancer.

METHODS

Through a systematic review-based approach, the representatives from the European Society for Medical Oncology (ESMO) Precision Oncology Working Group (POWG) and international experts identified studies in pathology and oncology that applied AI-based algorithms for tumour diagnosis, molecular biomarker detection, and cancer prognosis assessment. These findings were synthesised to provide a comprehensive overview of current AI applications and future directions in cancer pathology.

RESULTS

The integration of AI tools in digital pathology is markedly improving the accuracy and efficiency of image analysis, allowing for automated tumour detection and classification, identification of prognostic molecular biomarkers, and prediction of treatment response and patient outcomes. Several barriers for the adoption of AI in clinical workflows, such as data availability, explainability, and regulatory considerations, still persist. There are currently no prognostic or predictive AI-based biomarkers supported by level IA or IB evidence. The ongoing advancements in AI algorithms, particularly foundation models, generalist models and transformer-based deep learning, offer immense promise for the future of cancer research and care. AI is also facilitating the integration of multi-omics data, leading to more precise patient stratification and personalised treatment strategies.

CONCLUSIONS

The application of AI in pathology is poised to not only enhance the accuracy and efficiency of cancer diagnosis and prognosis but also facilitate the development of personalised treatment strategies. Although barriers to implementation remain, ongoing research and development in this field coupled with addressing ethical and regulatory considerations will likely lead to a future where AI plays an integral role in cancer management and precision medicine. The continued evolution and adoption of AI in pathology and oncology are anticipated to reshape the landscape of cancer care, heralding a new era of precision medicine and improved patient outcomes.

Quantitative immunohistochemistry analysis of breast Ki67 based on artificial intelligence

Breast cancer is a common malignant tumor of women. Ki67 is an important biomarker of cell proliferation. With the quantitative analysis, it is an important indicator of malignancy for breast cancer diagnosis. However, it is difficult to accurately and quantitatively evaluate the count of positive nucleus during the diagnosis process of pathologists, and the process is time-consuming and labor-intensive. In this work, we employed a quantitative analysis method of Ki67 in breast cancer based on deep learning approach. For the diagnosis of breast cancer, according to breast cancer diagnosis guideline, we first identified the tumor region of Ki67 pathological image, neglecting the non-tumor region in the image. Then, we detect the nucleus in the tumor region to determine the nucleus location information. After that, we classify the detected nucleuses as positive and negative according to the expression level of Ki67. According to the results of quantitative analysis, the proportion of positive cells is counted. Combining the above process, we design a breast Ki67 quantitative analysis pipeline. The Ki67 quantitative analysis system was assessed on the validation set. The Dice coefficient of the tumor region segmentation model was 0.848, the Average Precision index of the nucleus detection model was 0.817, and the accuracy of the nucleus classification model was 96.66%. Besides, in clinical independent sample experiment, the results show that the proposed breast Ki67 quantitative analysis system achieve excellent correlation with the diagnosis efficiency of doctors improved more than ten times and the overall consistency of diagnosis is intra-group correlation coefficient: 0.964. The research indicates that our quantitative analysis method of Ki67 in breast cancer has high clinical application value.

Deep learning for automated scoring of immunohistochemically stained tumour tissue sections - Validation across tumour types based on patient outcomes

We aimed to develop deep learning (DL) models to detect protein expression in immunohistochemically (IHC) stained tissue-sections, and to compare their accuracy and performance with manually scored clinically relevant proteins in common cancer types. Five cancer patient cohorts (colon, two prostate, breast, and endometrial) were included. We developed separate DL models for scoring IHC-stained tissue-sections with nuclear, cytoplasmic, and membranous staining patterns. For training, we used images with annotations of cells with positive and negative staining from the colon cohort stained for Ki-67 and PMS2 (nuclear model), the prostate cohort 1 stained for PTEN (cytoplasmic model) and β-catenin (membranous model). The nuclear DL model was validated for MSH6 in the colon, MSH6 and PMS2 in the endometrium, Ki-67 and CyclinB1 in prostate, and oestrogen and progesterone receptors in the breast cancer cohorts. The cytoplasmic DL model was validated for PTEN and Mapre2, and the membranous DL model for CD44 and Flotillin1, all in prostate cohorts. When comparing the results of manual and DL scores in the validation sets, using manual scores as the ground truth, we observed an average correct classification rate of 91.5 % (76.9-98.5 %) for the nuclear model, 85.6 % (73.3-96.6 %) for the cytoplasmic model, and 78.4 % (75.5-84.3 %) for the membranous model. In survival analyses, manual and DL scores showed similar prognostic impact, with similar hazard ratios and p-values for all DL models. Our findings demonstrate that DL models offer a promising alternative to manual IHC scoring, providing efficiency and reproducibility across various data sources and markers.

Assessment of Ki-67 proliferation index in prognosis prediction in patients with nonmetastatic clear cell renal cell carcinoma and tumor thrombus

PURPOSE

To determine the optimal cut-off value of Ki-67 for predicting the survival of patients with clear cell renal cell carcinoma (ccRCC) and tumor thrombus and to explore the correlation between Ki-67 expression and pathological features.

PATIENTS AND METHODS

We retrospectively analyzed Ki-67 immunohistochemical staining of ccRCC and tumor thrombus resected from February 2006 to February 2022. The survival rate was evaluated using the Kaplan-Meier method. The optimal cut-off value of the Ki-67 expression for predicting survival was determined by the minimum P-value method. Clinicopathological data were compared based on Ki-67 status (low versus high expression). Univariate and multivariate Cox regression analysis was used to explore independent predictors.

RESULTS

A total of 202 patients (median age, 58 years [IQR, 52-65 years], 147 men) with ccRCC and tumor thrombus were included in the study. The optimal cut-off value of Ki-67 for predicting survival was 30%. 159 (78.7%) and 43 (21.3%) patients were included in the low-expression and high-expression groups. Patients with Ki-67 high expression had significantly worse recurrence-free survival (P < 0.001) and cancer-specific survival (P < 0.001). Ki-67 high expression was associated with adverse pathological features, including tumor necrosis, ISUP nuclear grade, sarcomatoid differentiation, perirenal fat invasion, renal pelvis invasion, and inferior vena cava wall invasion (all P < 0.050). Ki-67 expression ≥ 30% (P = 0.016), tumor side (P = 0.003), diabetes (P = 0.040), blood loss (P = 0.016), inferior vena cava wall invasion (P = 0.016), and sarcomatoid differentiation (P = 0.014) were independent predictors of cancer-specific survival.

CONCLUSION

The optimal cut-off level of Ki-67 in predicting the prognosis of ccRCC and tumor thrombus was 30%. The high expression of Ki-67 was associated with the aggressive pathological phenotype and poor prognosis.

Preparing Data for Artificial Intelligence in Pathology with Clinical-Grade Performance

The pathology is decisive for disease diagnosis but relies heavily on experienced pathologists. In recent years, there has been growing interest in the use of artificial intelligence in pathology (AIP) to enhance diagnostic accuracy and efficiency. However, the impressive performance of deep learning-based AIP in laboratory settings often proves challenging to replicate in clinical practice. As the data preparation is important for AIP, the paper has reviewed AIP-related studies in the PubMed database published from January 2017 to February 2022, and 118 studies were included. An in-depth analysis of data preparation methods is conducted, encompassing the acquisition of pathological tissue slides, data cleaning, screening, and subsequent digitization. Expert review, image annotation, dataset division for model training and validation are also discussed. Furthermore, we delve into the reasons behind the challenges in reproducing the high performance of AIP in clinical settings and present effective strategies to enhance AIP's clinical performance. The robustness of AIP depends on a randomized collection of representative disease slides, incorporating rigorous quality control and screening, correction of digital discrepancies, reasonable annotation, and sufficient data volume. Digital pathology is fundamental in clinical-grade AIP, and the techniques of data standardization and weakly supervised learning methods based on whole slide image (WSI) are effective ways to overcome obstacles of performance reproduction. The key to performance reproducibility lies in having representative data, an adequate amount of labeling, and ensuring consistency across multiple centers. Digital pathology for clinical diagnosis, data standardization and the technique of WSI-based weakly supervised learning will hopefully build clinical-grade AIP.

Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification

PURPOSE

Ki67 is a protein associated with tumor proliferation and metastasis in breast cancer and acts as an essential prognostic factor. Clinical work requires recognizing tumor regions on Ki67-stained whole-slide images (WSIs) before quantitation. Deep learning has the potential to provide assistance but largely relies on massive annotations and consumes a huge amount of time and energy. Hence, a novel tumor region recognition approach is proposed for more precise Ki67 quantification.

METHODS

An unsupervised domain adaptive method is proposed, which combines adversarial and self-training. The model trained on labeled hematoxylin and eosin (H&E) data and unlabeled Ki67 data can recognize tumor regions in Ki67 WSIs. Based on the UDA method, a Ki67 automated assisted quantification system is developed, which contains foreground segmentation, tumor region recognition, cell counting, and WSI-level score calculation.

RESULTS

The proposed UDA method achieves high performance in tumor region recognition and Ki67 quantification. The AUC reached 0.9915, 0.9352, and 0.9689 on the validation set and internal and external test sets, respectively, substantially exceeding baseline (0.9334, 0.9167, 0.9408) and rivaling the fully supervised method (0.9950, 0.9284, 0.9652). The evaluation of automated quantification on 148 WSIs illustrated statistical agreement with pathological reports.

CONCLUSION

The model trained by the proposed method is capable of accurately recognizing Ki67 tumor regions. The proposed UDA method can be readily extended to other types of immunohistochemical staining images. The results of automated assisted quantification are accurate and interpretable to provide assistance to both junior and senior pathologists in their interpretation.

Triptolide inhibits intrahepatic cholangiocarcinoma growth by suppressing glycolysis via the AKT/mTOR pathway

BACKGROUND

High levels of glycolysis supply large quantities of energy and biological macromolecular raw materials for cell proliferation. Triptolide (TP) is a kind of epoxy diterpene lactone extracted from the roots, flowers, leaves, or grains of the Celastraceae plant, Tripterygium wilfordii. TP has multiple biological activities, including anti-inflammatory, immunologic suppression, and anti-cancer effects. Nevertheless, it is little known regarding its anti-intrahepatic cholangiocarcinoma (ICC) growth, and the mechanism still require exploration.

PURPOSE

This research explored the effect of TP on ICC growth and investigated whether TP inhibits glycolysis via the AKT/mTOR pathway.

METHODS

Cell proliferation was analyzed by Cell Counting Kit-8 (CCK-8), clonogenic assay, and flow cytometry. The underlying molecular mechanism was identified by determining glucose consumption, ATP production, lactate production, hexokinase (HK) and pyruvate kinase (PK) activity, and Western blot analysis. A rapid ICC model of AKT/YapS127A oncogene coactivation in mice was used to clarify the effect of TP treatment on tumor growth and glycolysis.

RESULTS

The results showed that TP treatment significantly inhibited ICC cell proliferation and glycolysis in a dose- and time-dependent manner(P < 0.05). Further analysis suggested that TP suppressed ICC cell glycolysis by targeting AKT/mTOR signaling. Additionally, we found that TP inhibits tumor growth and glycolysis in AKT/YapS127A mice(P < 0.05).

CONCLUSION

Taken together, we revealed that TP suppressed ICC growth by suppressing glycolysis via the AKT/mTOR pathway and may provide a potential therapeutic target for ICC treatment.

Comparison Between Manual and Automated Assessment of Ki-67 in Breast Carcinoma: Test of a Simple Method in Daily Practice

BACKGROUND

In the era of "precision medicine," the availability of high-quality tumor biomarker tests is critical and tumor proliferation evaluated by Ki-67 antibody is one of the most important prognostic factors in breast cancer. But the evaluation of Ki-67 index has been shown to suffer from some interobserver variability. The goal of the study is to develop an easy, automated, and reliable Ki-67 assessment approach for invasive breast carcinoma in routine practice.

PATIENTS AND METHODS

A total of 151 biopsies of invasive breast carcinoma were analyzed. The Ki-67 index was evaluated by 2 pathologists with MIB-1 antibody as a global tumor index and also in a hotspot. These 2 areas were also analyzed by digital image analysis (DIA).

RESULTS

For Ki-67 index assessment, in the global and hotspot tumor area, the concordances were very good between DIA and pathologists when DIA focused on the annotations made by pathologist (0.73 and 0.83, respectively). However, this was definitely not the case when DIA was not constrained within the pathologist's annotations and automatically established its global or hotspot area in the whole tissue sample (concordance correlation coefficients between 0.28 and 0.58).

CONCLUSIONS

The DIA technique demonstrated a meaningful concordance with the indices evaluated by pathologists when the tumor area is previously identified by a pathologist. In contrast, basing Ki-67 assessment on automatic tissue detection was not satisfactory and provided bad concordance results. A representative tumoral zone must therefore be manually selected prior to the measurement made by the DIA.

A study on the diagnosis of the Helicobacter pylori coccoid form with artificial intelligence technology

Background

Helicobacter pylori (H. pylori) is an important pathogenic microorganism that causes gastric cancer, peptic ulcers and dyspepsia, and infects more than half of the world's population. Eradicating H. pylori is the most effective means to prevent and treat these diseases. H. pylori coccoid form (HPCF) causes refractory H. pylori infection and should be given more attention in infection management. However, manual HPCF recognition on slides is time-consuming and labor-intensive and depends on experienced pathologists; thus, HPCF diagnosis is rarely performed and often overlooked. Therefore, simple HPCF diagnostic methods need to be developed.

Materials and methods

We manually labeled 4,547 images from anonymized paraffin-embedded samples in the China Center for H. pylori Molecular Medicine (CCHpMM, Shanghai), followed by training and optimizing the Faster R-CNN and YOLO v5 models to identify HPCF. Mean average precision (mAP) was applied to evaluate and select the model. The artificial intelligence (AI) model interpretation results were compared with those of the pathologists with senior, intermediate, and junior experience levels, using the mean absolute error (MAE) of the coccoid rate as an evaluation metric.

Results

For the HPCF detection task, the YOLO v5 model was superior to the Faster R-CNN model (0.688 vs. 0.568, mean average precision, mAP); the optimized YOLO v5 model had a better performance (0.803 mAP). The MAE of the optimized YOLO v5 model (3.25 MAE) was superior to that of junior pathologists (4.14 MAE, p < 0.05), no worse than intermediate pathologists (3.40 MAE, p > 0.05), and equivalent to a senior pathologist (3.07 MAE, p > 0.05).

Conclusion

HPCF identification using AI has the advantage of high accuracy and efficiency with the potential to assist or replace pathologists in clinical practice for HPCF identification.

DeepHistoClass: A Novel Strategy for Confident Classification of Immunohistochemistry Images Using Deep Learning

A multitude of efforts worldwide aim to create a single-cell reference map of the human body, for fundamental understanding of human health, molecular medicine, and targeted treatment. Antibody-based proteomics using immunohistochemistry (IHC) has proven to be an excellent technology for integration with large-scale single-cell transcriptomics datasets. The golden standard for evaluation of IHC staining patterns is manual annotation, which is expensive and may lead to subjective errors. Artificial intelligence holds much promise for efficient and accurate pattern recognition, but confidence in prediction needs to be addressed. Here, the aim was to present a reliable and comprehensive framework for automated annotation of IHC images. We developed a multilabel classification of 7848 complex IHC images of human testis corresponding to 2794 unique proteins, generated as part of the Human Protein Atlas (HPA) project. Manual annotation data for eight different cell types was generated as a basis for training and testing a proposed Hybrid Bayesian Neural Network. By combining the deep learning model with a novel uncertainty metric, DeepHistoClass (DHC) Confidence Score, the average diagnostic performance improved from 86.9% to 96.3%. This metric not only reveals which images are reliably classified by the model, but can also be utilized for identification of manual annotation errors. The proposed streamlined workflow can be developed further for other tissue types in health and disease and has important implications for digital pathology initiatives or large-scale protein mapping efforts such as the HPA project.

•

A novel method for automated annotation of immunohistochemistry images.

•

Introduction of an uncertainty metric, the DeepHistoClass (DHC) confidence score.

•

Increased accuracy of automated image predictions.

•

Identification of manual annotation errors.

Clinical significance of circulating tumour cells and Ki-67 in renal cell carcinoma

Background

Renal cell carcinoma (RCC) is a common malignant tumour of the genitourinary system. We aimed to analyse the potential value of metastasis-related biomarkers, circulating tumour cells (CTCs) and the proliferative marker Ki-67 in the diagnosis of RCC.

Methods

Data from 24 laparoscopic radical nephrectomies (RNs) and 17 laparoscopic partial nephrectomies (PNs) were collected in 2018. The numbers and positive rates of CTCs and circulating tumour microemboli (CTM) in the peripheral blood were obtained at three different time points: just before surgery, immediately after surgery and 1 week after surgery. Ki-67 protein expression was evaluated in the RCC tissue by immunohistochemistry.

Results

Except for the statistically significant association between the preoperative CTC counts and tumour size, no association between the number and positive rate of perioperative CTCs and clinicopathological features was found. The CTC counts gradually decreased during the perioperative period, and at 1 week after surgery, they were significantly lower than those before surgery. High Ki-67 expression was significantly positively correlated with preoperative CTC counts. In addition, Ki-67 expression was higher in the high CTC group (≥ 5 CTCs).

Conclusion

Our results suggest that surgical nephrectomy is associated with a decrease in CTC counts in RCC patients. CTCs can act as a potential biomarker for the diagnosis and prognosis of RCC. A careful and sufficient long-term follow-up is needed for patients with high preoperative CTC counts.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12957-021-02268-5.

Synergistic Effect of Statins and Abiraterone Acetate on the Growth Inhibition of Neuroblastoma via Targeting Androgen Receptor

Neuroblastoma is the most common extracranial neuroendocrine tumor in childhood. Although many studies have tried to find effective treatments, there are still numerous limitations in current clinical targeted therapy. So, it is important to find new therapeutic targets and strategies from a new perspective. Our previous study reported that the androgen receptor (AR) promotes the growth of neuroblastoma in vitro and in vivo. Based on documentary investigation, we postulated that the AR–SCAP–SREBPs-CYP17/HMGCR axis may regulate cholesterol and androgens synthesis and form a positive enhancement loop promoting NB progression. Clinical samples and Oncomine database analysis proved the activation of AR–SCAP–SREBPs-CYP17/HMGCR axis in neuroblastoma. The combination of inhibitors of HMGCR (statins) and CYP17A1 (abiraterone acetate) showed synergistic effect that significantly inhibited the proliferation and migration with decreased expression of related genes detected in vitro and in vivo suggesting the dual-targeted therapy had the potential to inhibit the progression of neuroblastoma in spite of its MYCN status. This study provides new ideas for clinical treatment of neuroblastoma with efficacy and reduced toxicity.

piNET-An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images

In this work, a novel proliferation index (PI) calculator for Ki67 images called piNET is proposed. It is successfully tested on four datasets, from three scanners comprised of patches, tissue microarrays (TMAs) and whole slide images (WSI), representing a diverse multi-centre dataset for evaluating Ki67 quantification. Compared to state-of-the-art methods, piNET consistently performs the best over all datasets with an average PI difference of 5.603%, PI accuracy rate of 86% and correlation coefficient R = 0.927. The success of the system can be attributed to several innovations. Firstly, this tool is built based on deep learning, which can adapt to wide variability of medical images-and it was posed as a detection problem to mimic pathologists' workflow which improves accuracy and efficiency. Secondly, the system is trained purely on tumor cells, which reduces false positives from non-tumor cells without needing the usual pre-requisite tumor segmentation step for Ki67 quantification. Thirdly, the concept of learning background regions through weak supervision is introduced, by providing the system with ideal and non-ideal (artifact) patches that further reduces false positives. Lastly, a novel hotspot analysis is proposed to allow automated methods to score patches from WSI that contain "significant" activity.

Fine-Grained Breast Cancer Classification With Bilinear Convolutional Neural Networks (BCNNs)

Classification of histopathological images of cancer is challenging even for well-trained professionals, due to the fine-grained variability of the disease. Deep Convolutional Neural Networks (CNNs) showed great potential for classification of a number of the highly variable fine-grained objects. In this study, we introduce a Bilinear Convolutional Neural Networks (BCNNs) based deep learning method for fine-grained classification of breast cancer histopathological images. We evaluated our model by comparison with several deep learning algorithms for fine-grained classification. We used bilinear pooling to aggregate a large number of orderless features without taking into consideration the disease location. The experimental results on BreaKHis, a publicly available breast cancer dataset, showed that our method is highly accurate with 99.24% and 95.95% accuracy in binary and in fine-grained classification, respectively.

Sequential immunohistochemistry and virtual image reconstruction using a single slide for quantitative KI67 measurement in breast cancer

Objective

Ki67 is a prognostic and predictive marker in breast cancer (BC). However, manual scoring (MS) by visual assessment suffers from high inter-observer variability which limits its clinical use. Here, we developed a new digital image analysis (DIA) workflow, named KiQuant for automated scoring of Ki67 and investigated its equivalence with standard pathologist's assessment.

Methods

Sequential immunohistochemistry of Ki67 and cytokeratin, for precise tumor cell recognition, were performed in the same section of 5 tissue microarrays containing 329 tumor cores from different breast cancer subtypes. Slides were digitalized and subjected to DIA and MS for Ki67 assessment. The intraclass correlation coefficient (ICC) and Bland-Altman plot were used to evaluate inter-observer reproducibility. The Kaplan-Meier analysis was used to determine the prognostic potential.

Results

KiQuant showed an excellent correlation with MS (ICC:0.905,95%CI:0.878–0.926) with satisfactory inter-run (ICC:0.917,95%CI:0.884–0.942) and inter-antibody reproducibilities (ICC:0.886,95%CI:0.820–0.929). The distance between KiQuant and MS increased with the magnitude of Ki67 measurement and positively correlated with analyzed tumor area and breast cancer subtype. Agreement rates between KiQuant and MS within the clinically relevant 14% and 30% cut-off points ranged from 33% to 44% with modest interobserver reproducibility below the 20% cut-off (0.606, 95%CI:0.467–0.727). High Ki67 by KiQuant correlated with worse outcome in all BC and in the luminal subtype (P = 0.028 and P = 0.043, respectively). For MS, the association with survival was significant only in 1 out of 3 observers.

Conclusions

KiQuant represents an easy and accurate methodology for Ki67 measurement providing a step toward utilizing Ki67 in the clinical setting.

•

Automated Ki67 scoring workflow improved reproducibility.

•

Sequential immunohistochemistry in the same section for precise cell recognition.

•

Use of a tumor mask for automatic tumor region selection.

•

Outperform pathologist-based Ki67 scoring in prognostic prediction.

AI in Medical Imaging Informatics: Current Challenges and Future Directions

This paper reviews state-of-the-art research solutions across the spectrum of medical imaging informatics, discusses clinical translation, and provides future directions for advancing clinical practice. More specifically, it summarizes advances in medical imaging acquisition technologies for different modalities, highlighting the necessity for efficient medical data management strategies in the context of AI in big healthcare data analytics. It then provides a synopsis of contemporary and emerging algorithmic methods for disease classification and organ/ tissue segmentation, focusing on AI and deep learning architectures that have already become the de facto approach. The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. Concluding, integrative analytics approaches driven by associate research branches highlighted in this study promise to revolutionize imaging informatics as known today across the healthcare continuum for both radiology and digital pathology applications. The latter, is projected to enable informed, more accurate diagnosis, timely prognosis, and effective treatment planning, underpinning precision medicine.