Histologic grading of breast carcinoma: a multi-institution study of interobserver variation using virtual microscopy

Validation of prostate and breast cancer detection artificial intelligence algorithms for accurate histopathological diagnosis and grading: a retrospective study with a Japanese cohort

Prostate and breast cancer incidence rates have been on the rise in Japan, emphasising the need for precise histopathological diagnosis to determine patient prognosis and guide treatment decisions. However, existing diagnostic methods face numerous challenges and are susceptible to inconsistencies between observers. To tackle these issues, artificial intelligence (AI) algorithms have been developed to aid in the diagnosis of prostate and breast cancer. This study focuses on validating the performance of two such algorithms, Galen Prostate and Galen Breast, in a Japanese cohort, with a particular focus on the grading accuracy and the ability to differentiate between invasive and non-invasive tumours. The research entailed a retrospective examination of 100 consecutive prostate and 100 consecutive breast biopsy cases obtained from a Japanese institution. Our findings demonstrated that the AI algorithms showed accurate cancer detection, with AUCs of 0.969 and 0.997 for the Galen Prostate and Galen Breast, respectively. The Galen Prostate was able to detect a higher Gleason score in four adenocarcinoma cases and detect a previously unreported cancer. The two algorithms successfully identified relevant pathological features, such as perineural invasions and lymphovascular invasions. Although further improvements are required to accurately differentiate rare cancer subtypes, these findings highlight the potential of these algorithms to enhance the precision and efficiency of prostate and breast cancer diagnosis in Japan. Furthermore, this validation paves the way for broader adoption of these algorithms as decision support tools within the Asian population.

Targeted pH- and redox-responsive AuS/micelles with low CMC for highly efficient sonodynamic therapy of metastatic breast cancer

The efficacy of injectable micellar carriers is hindered due to the disassembly of micelles into free surfactants in the body, resulting in their dilution below the critical micelle concentration (CMC). Copolymer micelles were developed to address this issue, containing a superhydrophilic zwitterionic block and a superhydrophobic block with a disulfide bond, which exhibited a CMC lower than conventional micellar carriers. Cleavable copolymers composed of 2-methacryloyloxyethyl phosphorylcholine (MPC) zwitterion and polycaprolactone CHLZW as the shell, with gold nanoparticles as their core, were studied to deliver doxorubicin to tumor cells while reducing the side effect of the free cytotoxic agent. The research focused on the impact of gold nanoparticles present in targeted TMT-micelles core on stability and in vivo bioavailability and sonotoxicity of the nanoparticles, as well as their synergistic effect on targeted chemotherapy. The nanomicelles prepared in this study demonstrated excellent biocompatibility and responsiveness to stimuli. PCL-SS-MPC nanomicelles displayed drug release in response to GSH and pH, resulting in high DOX release at GSH 10 mM and pH 5. Our findings, supported by MTT, flow cytometry, and confocal laser scanning microscopy, demonstrated that AuS-PM-TMTM-DOX micelles effectively induced apoptosis and enhanced cellular uptake in MCF7 and MDA-MB231 cell lines. The cytotoxic effects of AuS-PM-DOX/US on cancer cells were approximately 38 % higher compared to AuS-PM-DOX samples at a concentration of IC50 0.68 nM. This increase in cellular toxicity was primarily attributed to the promotion of apoptosis. The introduction of disulfide linkages in AuSNPs resulted in increased ROS production when exposed to ultrasound stimulation, due to a reduction in GSH levels. Compared to other commercially available nanosensitizers such as titanium dioxide, exposure of AuS-PM to ultrasound radiation (1.0 W/cm, 2 min) significantly enhanced cavitation effects and resulted in 3 to 5 times higher ROS production. Furthermore, laboratory experiments using human breast cancer cells (MDA-MB-231, MCF7) demonstrated that the toxicity of AuS-PM in response to ultrasound waves is dose-dependent. The findings of this study suggest that this formulated nanocarrier holds great potential as a viable treatment option for breast cancer. It can induce apoptosis in cancer cells, reduce tumor size, and display notable therapeutic efficacy.

Analytical Validation of the PreciseDx Digital Prognostic Breast Cancer Test in Early-Stage Breast Cancer

BACKGROUND

PreciseDx Breast (PDxBr) is a digital test that predicts early-stage breast cancer recurrence within 6-years of diagnosis.

MATERIALS AND METHODS

Using hematoxylin and eosin-stained whole slide images of invasive breast cancer (IBC) and artificial intelligence-enabled morphology feature array, microanatomic features are generated. Morphometric attributes in combination with patient's age, tumor size, stage, and lymph node status predict disease free survival using a proprietary algorithm. Here, analytical validation of the automated annotation process and extracted histologic digital features of the PDxBr test, including impact of methodologic variability on the composite risk score is presented. Studies of precision, repeatability, reproducibility and interference were performed on morphology feature array-derived features. The final risk score was assessed over 20-days with 2-operators, 2-runs/day, and 2-replicates across 8-patients, allowing for calculation of within-run repeatability, between-run and within-laboratory reproducibility.

RESULTS

Analytical validation of features derived from whole slide images demonstrated a high degree of precision for tumor segmentation (0.98, 0.98), lymphocyte detection (0.91, 0.93), and mitotic figures (0.85, 0.84). Correlation of variation of the assay risk score for both reproducibility and repeatability were less than 2%, and interference from variation in hematoxylin and eosin staining or tumor thickness was not observed demonstrating assay robustness across standard histopathology preparations.

CONCLUSION

In summary, the analytical validation of the digital IBC risk assessment test demonstrated a strong performance across all features in the model and complimented the clinical validation of the assay previously shown to accurately predict recurrence within 6-years in early-stage invasive breast cancer patients.

Development and prognostic validation of a three-level NHG-like deep learning-based model for histological grading of breast cancer

BACKGROUND

Histological grade is a well-known prognostic factor that is routinely assessed in breast tumours. However, manual assessment of Nottingham Histological Grade (NHG) has high inter-assessor and inter-laboratory variability, causing uncertainty in grade assignments. To address this challenge, we developed and validated a three-level NHG-like deep learning-based histological grade model (predGrade). The primary performance evaluation focuses on prognostic performance.

METHODS

This observational study is based on two patient cohorts (SöS-BC-4, N = 2421 (training and internal test); SCAN-B-Lund, N = 1262 (test)) that include routine histological whole-slide images (WSIs) together with patient outcomes. A deep convolutional neural network (CNN) model with an attention mechanism was optimised for the classification of the three-level histological grading (NHG) from haematoxylin and eosin-stained WSIs. The prognostic performance was evaluated by time-to-event analysis of recurrence-free survival and compared to clinical NHG grade assignments in the internal test set as well as in the fully independent external test cohort.

RESULTS

We observed effect sizes (hazard ratio) for grade 3 versus 1, for the conventional NHG method (HR = 2.60 (1.18-5.70 95%CI, p-value = 0.017)) and the deep learning model (HR = 2.27, 95%CI 1.07-4.82, p-value = 0.033) on the internal test set after adjusting for established clinicopathological risk factors. In the external test set, the unadjusted HR for clinical NHG 2 versus 1 was estimated to be 2.59 (p-value = 0.004) and clinical NHG 3 versus 1 was estimated to be 3.58 (p-value < 0.001). For predGrade, the unadjusted HR for predGrade 2 versus 1 HR = 2.52 (p-value = 0.030), and 4.07 (p-value = 0.001) for preGrade 3 versus 1 was observed in the independent external test set. In multivariable analysis, HR estimates for neither clinical NHG nor predGrade were found to be significant (p-value > 0.05). We tested for differences in HR estimates between NHG and predGrade in the independent test set and found no significant difference between the two classification models (p-value > 0.05), confirming similar prognostic performance between conventional NHG and predGrade.

CONCLUSION

Routine histopathology assessment of NHG has a high degree of inter-assessor variability, motivating the development of model-based decision support to improve reproducibility in histological grading. We found that the proposed model (predGrade) provides a similar prognostic performance as clinical NHG. The results indicate that deep CNN-based models can be applied for breast cancer histological grading.

Proficiency testing of diagnosis in histopathology and immunohistochemistry of breast pathology in China: results from a pilot work of National Single Disease Quality Control Program for breast cancer

AIM

Pathologists are currently supposed to be aware of both domestic and international guidelines for breast cancer diagnosis, but it is unclear how successfully these guidelines have been integrated into routine clinical practice in China. Thus, this national proficiency testing (PT) scheme for breast pathology was set up to conduct a baseline assessment of the diagnostic capability of pathologists in China.

METHODS

This national PT plan is designed and implemented according to the "Conformity assessment-General requirements for proficiency testing" (GB/T27043-2012/ISO/IEC 17043:2010). Five cases of breast cancer with six key items, including histologic type, grade, ER, PR, HER2, and Ki67, were selected for testing among 96 participants. The final PT results were published on the website of the National Quality Control Center for Cancer ( http://117.133.40.88:3927/cn/col22/362 ).

RESULTS

Our study demonstrated that the median PT score was 89.5 (54-100). Two institutions with scores < 67 were deemed unacceptable. The accuracy of histologic type, ER, PR, HER2, and Ki67 was satisfactory (all > 86%). However, the histologic grade showed low accuracy (74.0%). The unacceptable results mainly included incorrect evaluation of histologic grade (36.7%), inaccurate evaluation of ER/PR/HER2/Ki67 (28.2%), incorrect identification of C-AD as IBC-NST (15.7%), inappropriate use of 1+/2+/3+ rather than staining percentage for ER/PR (6.1%), misclassification of ER/PR < 1% weak expression as positive staining (1.4%), and no evaluation of histologic grade in ILC, MC, and IMC (5.8%).

CONCLUSIONS

our nationwide PT program exhibited a satisfactory baseline assessment of the diagnostic capability of pathologists in China. More importantly, we identify some areas for further improvement.

Domain and Histopathology Adaptations-Based Classification for Malignancy Grading System

Accurate proliferation rate quantification can be used to devise an appropriate treatment for breast cancer. Pathologists use breast tissue biopsy glass slides stained with hematoxylin and eosin to obtain grading information. However, this manual evaluation may lead to high costs and be ineffective because diagnosis depends on the facility and the pathologists' insights and experiences. Convolutional neural network acts as a computer-based observer to improve clinicians' capacity in grading breast cancer. Therefore, this study proposes a novel scheme for automatic breast cancer malignancy grading from invasive ductal carcinoma. The proposed classifiers implement multistage transfer learning incorporating domain and histopathologic transformations. Domain adaptation using pretrained models, such as InceptionResNetV2, InceptionV3, NASNet-Large, ResNet50, ResNet101, VGG19, and Xception, was applied to classify the ×40 magnification BreaKHis data set into eight classes. Subsequently, InceptionV3 and Xception, which contain the domain and histopathology pretrained weights, were determined to be the best for this study and used to categorize the Databiox database into grades 1, 2, or 3. To provide a comprehensive report, this study offered a patchless automated grading system for magnification-dependent and magnification-independent classifications. With an overall accuracy (means ± SD) of 90.17% ± 3.08% to 97.67% ± 1.09% and an F1 score of 0.9013 to 0.9760 for magnification-dependent classification, the classifiers in this work achieved outstanding performance. The proposed approach could be used for breast cancer grading systems in clinical settings.

Agreement on risk assessment and chemotherapy recommendations among breast cancer specialists: A survey within the MINDACT cohort

PURPOSE

Tailored recommendation for adjuvant chemotherapy in breast cancer patients is of great importance. This survey assessed agreement among oncologists on risk assessment and chemotherapy recommendation, the impact of adding the 70-gene signature to clinical-pathological characteristics, and changes over time.

METHODS

A survey consisting of 37 discordant patient cases from the MINDACT trial (T1-3N0-1M0) was sent to European breast cancer specialists for assessment of risk (high or low) and chemotherapy administration (yes or no). In 2015 the survey was sent twice (survey 1 and 2), several weeks apart, and in 2021 a third time (survey 3). Only the second and third surveys included the 70-gene signature result.

RESULTS

41 breast cancer specialists participated in all three surveys. Overall agreement between respondents decreased slightly between survey 1 and 2, but increased again in survey 3. Over time there was an increase in agreement with the 70-gene signature result on risk assessment, 23% in survey 2 versus 1 and 11% in survey 3 versus 2. With information available indicating a low risk 70-gene signature (n = 25 cases), 20% of risk assessments changed from high to low and 19% of recommendations changed from yes to no chemotherapy in survey 2 versus 1, further increasing with 18% and 21%, respectively, in survey 3 versus 2.

CONCLUSION

There is a variability in risk assessment of early breast cancer patients among breast cancer specialists. The 70-gene signature provided valuable information, resulting in fewer patients being assessed as high risk and fewer recommendations for chemotherapy, increasing over time.

Comparative Evaluation of Breast Ductal Carcinoma Grading: A Deep-Learning Model and General Pathologists' Assessment Approach

Breast cancer is the most prevalent neoplasia among women, with early and accurate diagnosis critical for effective treatment. In clinical practice, however, the subjective nature of histological grading of infiltrating ductal adenocarcinoma of the breast (DAC-NOS) often leads to inconsistencies among pathologists, posing a significant challenge to achieving optimal patient outcomes. Our study aimed to address this reproducibility problem by leveraging artificial intelligence (AI). We trained a deep-learning model using a convolutional neural network-based algorithm (CNN-bA) on 100 whole slide images (WSIs) of DAC-NOS from the Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA) dataset. Our model demonstrated high precision, sensitivity, and F1 score across different grading components in about 17.5 h with 19,000 iterations. However, the agreement between the model's grading and that of general pathologists varied, showing the highest agreement for the mitotic count score. These findings suggest that AI has the potential to enhance the accuracy and reproducibility of breast cancer grading, warranting further refinement and validation of this approach.

Deep learning supported mitoses counting on whole slide images: A pilot study for validating breast cancer grading in the clinical workflow

Introduction

Breast cancer (BC) prognosis is largely influenced by histopathological grade, assessed according to the Nottingham modification of Bloom-Richardson (BR). Mitotic count (MC) is a component of histopathological grading but is prone to subjectivity. This study investigated whether mitoses counting in BC using digital whole slide images (WSI) compares better to light microscopy (LM) when assisted by artificial intelligence (AI), and to which extent differences in digital MC (AI assisted or not) result in BR grade variations.

Methods

Fifty BC patients with paired core biopsies and resections were randomly selected. Component scores for BR grade were extracted from pathology reports. MC was assessed using LM, WSI, and AI. Different modalities (LM-MC, WSI-MC, and AI-MC) were analyzed for correlation with scatterplots and linear regression, and for agreement in final BR with Cohen's κ.

Results

MC modalities strongly correlated in both biopsies and resections: LM-MC and WSI-MC (R² 0.85 and 0.83, respectively), LM-MC and AI-MC (R² 0.85 and 0.95), and WSI-MC and AI-MC (R² 0.77 and 0.83). Agreement in BR between modalities was high in both biopsies and resections: LM-MC and WSI-MC (κ 0.93 and 0.83, respectively), LM-MC and AI-MC (κ 0.89 and 0.83), and WSI-MC and AI-MC (κ 0.96 and 0.73).

Conclusion

This first validation study shows that WSI-MC may compare better to LM-MC when using AI. Agreement between BR grade based on the different mitoses counting modalities was high. These results suggest that mitoses counting on WSI can well be done, and validate the presented AI algorithm for pathologist supervised use in daily practice. Further research is required to advance our knowledge of AI-MC, but it appears at least non-inferior to LM-MC.

Deep learning for fully-automated nuclear pleomorphism scoring in breast cancer

To guide the choice of treatment, every new breast cancer is assessed for aggressiveness (i.e., graded) by an experienced histopathologist. Typically, this tumor grade consists of three components, one of which is the nuclear pleomorphism score (the extent of abnormalities in the overall appearance of tumor nuclei). The degree of nuclear pleomorphism is subjectively classified from 1 to 3, where a score of 1 most closely resembles epithelial cells of normal breast epithelium and 3 shows the greatest abnormalities. Establishing numerical criteria for grading nuclear pleomorphism is challenging, and inter-observer agreement is poor. Therefore, we studied the use of deep learning to develop fully automated nuclear pleomorphism scoring in breast cancer. The reference standard used for training the algorithm consisted of the collective knowledge of an international panel of 10 pathologists on a curated set of regions of interest covering the entire spectrum of tumor morphology in breast cancer. To fully exploit the information provided by the pathologists, a first-of-its-kind deep regression model was trained to yield a continuous scoring rather than limiting the pleomorphism scoring to the standard three-tiered system. Our approach preserves the continuum of nuclear pleomorphism without necessitating a large data set with explicit annotations of tumor nuclei. Once translated to the traditional system, our approach achieves top pathologist-level performance in multiple experiments on regions of interest and whole-slide images, compared to a panel of 10 and 4 pathologists, respectively.

Deep learning models for histologic grading of breast cancer and association with disease prognosis

Histologic grading of breast cancer involves review and scoring of three well-established morphologic features: mitotic count, nuclear pleomorphism, and tubule formation. Taken together, these features form the basis of the Nottingham Grading System which is used to inform breast cancer characterization and prognosis. In this study, we develop deep learning models to perform histologic scoring of all three components using digitized hematoxylin and eosin-stained slides containing invasive breast carcinoma. We first evaluate model performance using pathologist-based reference standards for each component. To complement this typical approach to evaluation, we further evaluate the deep learning models via prognostic analyses. The individual component models perform at or above published benchmarks for algorithm-based grading approaches, achieving high concordance rates with pathologist grading. Further, prognostic performance using deep learning-based grading is on par with that of pathologists performing review of matched slides. By providing scores for each component feature, the deep-learning based approach also provides the potential to identify the grading components contributing most to prognostic value. This may enable optimized prognostic models, opportunities to improve access to consistent grading, and approaches to better understand the links between histologic features and clinical outcomes in breast cancer.

Reproducibility and Feasibility of Classification and National Guidelines for Histological Diagnosis of Canine Mammary Gland Tumours: A Multi-Institutional Ring Study

Simple Summary

Tumours of the mammary gland are common in humans, as in canine species. They are very heterogenous with numerous morphological variants and different biologic behaviours. In the last few decades, several efforts have been made to classify these tumours histologically and establish the level of malignancy by using histologic grading systems. However, reproducibility and diagnostic agreement of such classification and grading have been only rarely assessed. In this study, we tested the variability in diagnoses performed by 15 pathologists using the same classification and grading system. Prior to the study, pathologists agreed on guidelines regarding how to apply these systems. Pathologists worked blindly on 36 digital histologic slides of canine mammary tumours. The agreement was statistically analysed using Cohen’s kappa coefficient that, when equal to 1, indicates perfect agreement. The overall agreement in the identification of hyperplastic-dysplastic/benign/malignant lesions was substantial (kappa 0.76), while outcomes on morphological classification had only a moderate agreement (k = 0.54). Tumour grade assigned by pathologists was the least concordant and kappa could not be calculated. Although promising, the results underline that each diagnostic/grading system should be assessed and optimized for standardization and high diagnostic agreement.

Abstract

Histological diagnosis of Canine Mammary Tumours (CMTs) provides the basis for proper treatment and follow-up. Nowadays, its accuracy is poorly understood and variable interpretation of histological criteria leads to a lack of standardisation and impossibility to compare studies. This study aimed to quantify the reproducibility of histological diagnosis and grading in CMTs. A blinded ring test on 36 CMTs was performed by 15 veterinary pathologists with different levels of education, after discussion of critical points on the Davis-Thompson Foundation Classification and providing consensus guidelines. Kappa statistics were used to compare the interobserver variability. The overall concordance rate of diagnostic interpretations of WP on identification of hyperplasia-dysplasia/benign/malignant lesions showed a substantial agreement (average k ranging from 0.66 to 0.82, with a k-combined of 0.76). Instead, outcomes on ICD-O-3.2 morphological code /diagnosis of histotype had only a moderate agreement (average k ranging from 0.44 and 0.64, with a k-combined of 0.54). The results demonstrated that standardised classification and consensus guidelines can produce moderate to substantial agreement; however, further efforts are needed to increase this agreement in distinguishing benign versus malignant lesions and in histological grading.

Utility of Oncotype DX score in clinical management for T1 estrogen receptor positive, HER2 negative, and lymph node negative breast cancer

BACKGROUND

The management of estrogen receptor positive (ER+)/HER2- and lymph node (LN) negative breast cancers can be influenced by Oncotype DX recurrence score (RS) in the USA. However, the benefit of RS in T1 tumors (≤ 1 cm) is not clear.

METHODS

We retrieved 199 T1 ER+/HER2-/LN- breast cancer diagnosed between 1993 and 2016 that had undergone RS testing. The median follow-up time was 51 months. We examined the disease-free survival (DFS) and distant metastasis and their association with RS and other clinicopathologic features.

RESULTS

Of the 199 cases, 40 were T1a (≤ 0.5 cm) and 159 were T1b (> 0.5 cm to 1 cm) tumors. In the 40 T1a tumors, 11 would benefit from chemotherapy by the TAILORx study results. Of these T1a tumors, 36 were Nottingham grade 1/2, 3 were grade 3, and 1 was microinvasive carcinoma; 2 (5%) had local recurrence and 1 (2.5%) had distant metastasis to the bone. The only patient with T1a tumor (Nottingham grade 3, RS = 42) and distant metastasis to bone had received adjuvant chemotherapy. In the 159 T1b tumors, 25 would benefit chemotherapy by the TAILORx results. Of the T1b tumors, 149 were Nottingham grade 1/2 and 10 were grade 3. Nine (5.7%) had local recurrence and 2 (1.3%) had distant metastasis to bone and mediastinum, respectively. The two T1b tumors with distant metastasis had a RS 20 and Nottingham grade 2, and RS 27 and Nottingham grade 3, respectively. Both patients received adjuvant chemotherapy. In multivariate analysis of the entire cohort (T1a and T1b tumors), Nottingham tumor grade and receiving chemotherapy were significantly associated with DFS. In univariate analysis of the entire cohort, Nottingham tumor grade, receiving adjuvant chemotherapy, and RS were significantly associated with distant metastasis.

CONCLUSION

This study demonstrates that the metastatic rate of T1a and T1b ER+/HER2-/LN- breast cancer is very low. Patients with low grade (1 or 2), T1a ER+/HER2-/LN- breast cancer may not need RS for treatment decision-making; however, in patients with high-grade T1a or T1b ER+/HER2-/LN- breast cancer, RS analysis should be strongly considered.

Cytology Reporting System for Lung Cancer from the Japan Lung Cancer Society and the Japanese Society of Clinical Cytology: An Extensive Study Containing More Benign Lesions

INTRODUCTION

The Japan Lung Cancer Society (JLCS) and the Japanese Society of Clinical Cytology (JSCC) have proposed a new four-tiered cytology reporting system for lung carcinoma (JLCS-JSCC system). Prior to the proposal, the Papanicolaou Society of Cytopathology (PSC) had proposed a revised reporting system (PSC system), which comprises the "neoplastic, benign neoplasm, and low-grade carcinoma" category (N-B-LG category), in addition to the 4 categories of the JLCS-JSCC system. This study aimed to evaluate the interobserver agreement of the JLCS-JSCC system with an additional dataset with more benign lesions in comparison with the PSC system.

METHODS

We analyzed 167 cytological samples, which included 17 benign lesions, obtained from the respiratory system. Seven observers classified these cases into each category by reviewing one Papanicolaou-stained slide per case according to the JLCS-JSCC system and PSC system.

RESULTS

The interobserver agreement was moderate in the JLCS-JSCC (k = 0.499) and PSC (k = 0.485) systems. Of the 167 samples, 17 samples were benign lesions: 7 pulmonary hamartomas, 5 sclerosing pneumocytomas, 2 squamous papillomas, one solitary fibrous tumor, one meningioma, and one lymphocytic proliferation. There were diverse sample types as follows: 11 touch smears, 3 brushing smears, 2 aspirations, and one sputum sample. Fourteen samples (82.3%) were categorized into "negative" or "atypical" by more than half of the observers in the JLCS-JSCC system. Conversely, 3 samples were categorized as "suspicious" or "malignant" by more than half of the observers in the JLCS-JSCC system. On the other hand, 11 samples (64.7%) were categorized into the N-B-LG category by more than half of the observers in the PSC system.

CONCLUSIONS

The concordance rate in the JLCS-JSCC system was slightly higher than that in the PSC system; however, the interobserver agreement was moderate in both the JLCS-JSCC and PSC systems. These results indicate that both the JLCS-JSCC and PSC systems are clinically useful. Therefore, both systems are expected to have clinical applications. It may be important to integrate the 2 systems and construct a universal system that can be used more widely in clinical practice.

Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade

Background: Evaluating histologic grade for breast cancer diagnosis is standard and associated with prognostic outcomes. Current challenges include the time required for manual microscopic evaluation and interobserver variability. This study proposes a computer-aided diagnostic (CAD) pipeline for grading tumors using artificial intelligence. Methods: There were 138 patients included in this retrospective study. Breast core biopsy slides were prepared using standard laboratory techniques, digitized, and pre-processed for analysis. Deep convolutional neural networks (CNNs) were developed to identify the regions of interest containing malignant cells and to segment tumor nuclei. Imaging-based features associated with spatial parameters were extracted from the segmented regions of interest (ROIs). Clinical datasets and pathologic biomarkers (estrogen receptor, progesterone receptor, and human epidermal growth factor 2) were collected from all study subjects. Pathologic, clinical, and imaging-based features were input into machine learning (ML) models to classify histologic grade, and model performances were tested against ground-truth labels at the patient-level. Classification performances were evaluated using receiver-operating characteristic (ROC) analysis. Results: Multiparametric feature sets, containing both clinical and imaging-based features, demonstrated high classification performance. Using imaging-derived markers alone, the classification performance demonstrated an area under the curve (AUC) of 0.745, while modeling these features with other pathologic biomarkers yielded an AUC of 0.836. Conclusion: These results demonstrate an association between tumor nuclear spatial features and tumor grade. If further validated, these systems may be implemented into pathology CADs and can assist pathologists to expeditiously grade tumors at the time of diagnosis and to help guide clinical decisions.

Grading of invasive breast carcinoma: the way forward

Histologic grading has been a simple and inexpensive method to assess tumor behavior and prognosis of invasive breast cancer grading, thereby identifying patients at risk for adverse outcomes, who may be eligible for (neo)adjuvant therapies. Histologic grading needs to be performed accurately, on properly fixed specimens, and by adequately trained dedicated pathologists that take the time to diligently follow the protocol methodology. In this paper, we review the history of histologic grading, describe the basics of grading, review prognostic value and reproducibility issues, compare performance of grading to gene expression profiles, and discuss how to move forward to improve reproducibility of grading by training, feedback and artificial intelligence algorithms, and special stains to better recognize mitoses. We conclude that histologic grading, when adequately carried out, remains to be of important prognostic value in breast cancer patients.