Predicting neoadjuvant chemotherapy benefit using deep learning from stromal histology in breast cancer

Successful treatment of enormous locally advanced breast cancer through neoadjuvant chemotherapy and surgical intervention: a case report

Background

Breast cancer has become a critical international healthcare issue. Specifically, among the different subtypes, breast cancer marked by human epidermal growth factor receptor 2 (HER2)-overexpression usually correlates with low survival and a poor prognosis and poses challenges in treatment, thus leading to high mortality.

Case Description

A 54-year-old female patient was diagnosed with a large T4cN2aM0 stage IIIB breast tumor with HER2 overexpression. The tumor size was large, and there was a lack of opportunity for surgery. However, after neoadjuvant chemotherapy (NACT), the size of the tumor continuously shrank, and the patient successfully underwent a modified radical mastectomy. Even though a certain amount of mass remained and she did not complete six courses of NACT, our patient's postoperative pathological result still revealed that a pathological complete response (pCR) was achieved. The appropriate time window for choosing surgical intervention should be determined based on the patient's general condition instead of complying with the treatment guidelines. Also, imaging findings may be misleading in patients who have undergone NACT. Moreover, the regimen should be chosen flexibly.

Conclusions

Patients with locally advanced breast cancer can still achieve a radical surgical resection following appropriate comprehensive treatment. Hopefully, this case can provide new ideas for surgeons when they face similar conditions.

Artificial intelligence in digital histopathology for predicting patient prognosis and treatment efficacy in breast cancer

INTRODUCTION

Histological images contain phenotypic information predictive of patient outcomes. Due to the heavy workload of pathologists, the time-consuming nature of quantitatively assessing histological features, and human eye limitations to recognize spatial patterns, manually extracting prognostic information in routine pathological workflows remains challenging. Digital pathology has facilitated the mining and quantification of these features utilizing whole-slide image (WSI) scanners and artificial intelligence (AI) algorithms. AI algorithms to identify image-based biomarkers from the tumor microenvironment (TME) have the potential to revolutionize the field of oncology, reducing delays between diagnosis and prognosis determination, allowing for rapid stratification of patients and prescription of optimal treatment regimes, thereby improving patient outcomes.

AREAS COVERED

In this review, the authors discuss how AI algorithms and digital pathology can predict breast cancer patient prognosis and treatment outcomes using image-based biomarkers, along with the challenges of adopting this technology in clinical settings.

EXPERT OPINION

The integration of AI and digital pathology presents significant potential for analyzing the TME and its diagnostic, prognostic, and predictive value in breast cancer patients. Widespread clinical adoption of AI faces ethical, regulatory, and technical challenges, although prospective trials may offer reassurance and promote uptake, ultimately improving patient outcomes by reducing diagnosis-to-prognosis delivery delays.

Vague-Segment Technique: Automatic Computation of Tumor Stroma Ratio for Breast Cancer on Whole Slides

The calculation of Tumor Stroma Ratio (TSR) is a challenging medical issue that could improve predictions of neoadjuvant chemotherapy benefits and patient prognoses. Although several studies on breast cancer and deep learning methods have achieved promising results, the drawbacks that pixel-level semantic segmentation processes could not extract core tumor regions containing both tumor pixels and stroma pixels make it difficult to accurately calculate TSR. In this paper, we propose a Vague-Segment Technique (VST) consisting of a designed SwinV2UNet module and a modified Suzuki algorithm. Specifically, the SwinV2UNet identifies tumor pixels and generate pixel-level classification results, based on which the modified Suzuki algorithm extracts the contour of core tumor regions in terms of cosine angle. Through this way, VST obtains vaguely segmentation results of core tumor regions containing both tumor pixels and stroma pixels, where the TSR could be calculated by the formula of Intersection over Union (IOU). For the training and evaluation, we utilize the well-known The Cancer Genome Atlas (TCGA) database to create an annotated dataset, while 150 images with TSR annotations from real cases are also collected. The experimental results illustrate that the proposed VST could generate better tumor identification results compared with state-of-the-art methods, where the extracted core tumor regions lead to more consistencies of calculated TSR with senior experts compared to junior pathologists. The experimental results demonstrate the superiority of our proposed pipeline, which has promise for future clinical application.

PROACTING: predicting pathological complete response to neoadjuvant chemotherapy in breast cancer from routine diagnostic histopathology biopsies with deep learning

BACKGROUND

Invasive breast cancer patients are increasingly being treated with neoadjuvant chemotherapy; however, only a fraction of the patients respond to it completely. To prevent overtreatment, there is an urgent need for biomarkers to predict treatment response before administering the therapy.

METHODS

In this retrospective study, we developed hypothesis-driven interpretable biomarkers based on deep learning, to predict the pathological complete response (pCR, i.e., the absence of tumor cells in the surgical resection specimens) to neoadjuvant chemotherapy solely using digital pathology H&E images of pre-treatment breast biopsies. Our approach consists of two steps: First, we use deep learning to characterize aspects of the tumor micro-environment by detecting mitoses and segmenting tissue into several morphology compartments including tumor, lymphocytes and stroma. Second, we derive computational biomarkers from the segmentation and detection output to encode slide-level relationships of components of the tumor microenvironment, such as tumor and mitoses, stroma, and tumor infiltrating lymphocytes (TILs).

RESULTS

We developed and evaluated our method on slides from n = 721 patients from three European medical centers with triple-negative and Luminal B breast cancers and performed external independent validation on n = 126 patients from a public dataset. We report the predictive value of the investigated biomarkers for predicting pCR with areas under the receiver operating characteristic curve between 0.66 and 0.88 across the tested cohorts.

CONCLUSION

The proposed computational biomarkers predict pCR, but will require more evaluation and finetuning for clinical application. Our results further corroborate the potential role of deep learning to automate TILs quantification, and their predictive value in breast cancer neoadjuvant treatment planning, along with automated mitoses quantification. We made our method publicly available to extract segmentation-based biomarkers for research purposes.

Recent advancements in artificial intelligence for breast cancer: Image augmentation, segmentation, diagnosis, and prognosis approaches

Breast cancer is a significant global health burden, with increasing morbidity and mortality worldwide. Early screening and accurate diagnosis are crucial for improving prognosis. Radiographic imaging modalities such as digital mammography (DM), digital breast tomosynthesis (DBT), magnetic resonance imaging (MRI), ultrasound (US), and nuclear medicine techniques, are commonly used for breast cancer assessment. And histopathology (HP) serves as the gold standard for confirming malignancy. Artificial intelligence (AI) technologies show great potential for quantitative representation of medical images to effectively assist in segmentation, diagnosis, and prognosis of breast cancer. In this review, we overview the recent advancements of AI technologies for breast cancer, including 1) improving image quality by data augmentation, 2) fast detection and segmentation of breast lesions and diagnosis of malignancy, 3) biological characterization of the cancer such as staging and subtyping by AI-based classification technologies, 4) prediction of clinical outcomes such as metastasis, treatment response, and survival by integrating multi-omics data. Then, we then summarize large-scale databases available to help train robust, generalizable, and reproducible deep learning models. Furthermore, we conclude the challenges faced by AI in real-world applications, including data curating, model interpretability, and practice regulations. Besides, we expect that clinical implementation of AI will provide important guidance for the patient-tailored management.

Combining the tumor-stroma ratio with tumor-infiltrating lymphocytes improves the prediction of pathological complete response in breast cancer patients

PURPOSE

The tumor-stroma ratio (TSR) is a common histological parameter that measures stromal abundance and is prognostic in breast cancer (BC). However, more evidence is needed on the predictive value of the TSR for the pathological complete response (pCR) to neoadjuvant chemotherapy (NAC). The purpose of this study was to determine the importance of the TSR in predicting pCR in NAC settings.

METHOD

We evaluated the TSR on pretreatment biopsies of 912 BC patients from four independent Chinese hospitals and investigated the potential value of the TSR for predicting pCR. Meanwhile, stromal tumor-infiltrating lymphocytes (sTILs) were assessed, and we evaluated the predictive value of the combination of sTILs and TSR (TSRILs).

RESULTS

Patients with low stroma showed a higher pCR rate than those with high stroma among the four independent hospitals, and in multivariate analysis, the TSR was proven to be an independent predictor for pCR to NAC with an odds ratio of 1.945 (95% CI 1.230-3.075, P = 0.004). Moreover, we found that TSRILs could improve the area under the curve (AUC) for predicting pCR from 0.750 to 0.785 (P = 0.039); especially in HER2-negative BCs, the inclusion of TSRILs increased the AUC from 0.801 to 0.835 in the discovery dataset (P = 0.048) and 0.734 to 0.801 in the validation dataset (P = 0.003).

CONCLUSION

TSR and sTILs can be easily measured in pathological routines and provide predictive information without additional cost; with more evidence from clinical trials, TSRILs could be a candidate to better stratify patients in NAC settings.