The purpose of this study is to assess the "real-world" impact of an artificial intelligence (AI) tool designed to detect breast cancer in digital breast tomosynthesis (DBT) screening exams following 12 months of utilization in a subspecialized academic breast center.Following IRB approval, mammography audit reports, as specified in the BI-RADS atlas, were retrospectively generated for five radiologists reading at three locations during a 12-month time frame. One location had the AI tool (iCAD ProFound AI v2.0), and the other two locations did not. The co-primary endpoints were cancer detection rate (CDR) and abnormal interpretation rate (AIR). Secondary endpoints included positive predictive values (PPVs) for cancer among screenings with abnormal interpretations (PPV1) and for biopsies performed (PPV3). Odds ratios (OR) with two-sided 95% confidence intervals (CIs) summarized the impact of AI across radiologists using generalized estimating equations.Nonsignificant differences were observed in CDR, AIR, and PPVs. The CDR was 7.3 with AI and 5.9 without AI (OR 1.3, 95% CI: 0.9-1.7). The AIR was 11.7% with AI and 11.8% without AI (OR 1.0, 95% CI: 0.8-1.3). The PPV1 was 6.2% with AI and 5.0% without AI (OR 1.3, 95% CI: 0.97-1.7). The PPV3 was 33.3% with AI and 32.0% without AI (OR 1.1, 95% CI: 0.8-1.5).Although we are unable to show statistically significant changes in CDR and AIR outcomes in the two groups, the results are consistent with prior reader studies. There is a nonsignificant trend toward improvement in CDR with AI, without significant increases in AIR.© The Authors 2023.

Screening mammography reduces breast cancer mortality, but studies analyzing interval cancers diagnosed after negative screens have shown that many cancers are missed. Supplemental screening using magnetic resonance imaging (MRI) can reduce the number of missed cancers. However, as qualified MRI staff are lacking, the equipment is expensive to purchase and cost-effectiveness for screening may not be convincing, the utilization of MRI is currently limited. An effective method for triaging individuals to supplemental MRI screening is therefore needed. We conducted a randomized clinical trial, ScreenTrustMRI, using a recently developed artificial intelligence (AI) tool to score each mammogram. We offered trial participation to individuals with a negative screening mammogram and a high AI score (top 6.9%). Upon agreeing to participate, individuals were assigned randomly to one of two groups: those receiving supplemental MRI and those not receiving MRI. The primary endpoint of ScreenTrustMRI is advanced breast cancer defined as either interval cancer, invasive component larger than 15 mm or lymph node positive cancer, based on a 27-month follow-up time from the initial screening. Secondary endpoints, prespecified in the study protocol to be reported before the primary outcome, include cancer detected by supplemental MRI, which is the focus of the current paper. Compared with traditional breast density measures used in a previous clinical trial, the current AI method was nearly four times more efficient in terms of cancers detected per 1,000 MRI examinations (64 versus 16.5). Most additional cancers detected were invasive and several were multifocal, suggesting that their detection was timely. Altogether, our results show that using an AI-based score to select a small proportion (6.9%) of individuals for supplemental MRI after negative mammography detects many missed cancers, making the cost per cancer detected comparable with screening mammography. ClinicalTrials.gov registration: NCT04832594.© 2024. The Author(s).

In the past decade, advances in precision oncology have resulted in an increased demand for predictive assays that enable the selection and stratification of patients for treatment. The enormous divergence of signalling and transcriptional networks mediating the crosstalk between cancer, stromal and immune cells complicates the development of functionally relevant biomarkers based on a single gene or protein. However, the result of these complex processes can be uniquely captured in the morphometric features of stained tissue specimens. The possibility of digitizing whole-slide images of tissue has led to the advent of artificial intelligence (AI) and machine learning tools in digital pathology, which enable mining of subvisual morphometric phenotypes and might, ultimately, improve patient management. In this Perspective, we critically evaluate various AI-based computational approaches for digital pathology, focusing on deep neural networks and 'hand-crafted' feature-based methodologies. We aim to provide a broad framework for incorporating AI and machine learning tools into clinical oncology, with an emphasis on biomarker development. We discuss some of the challenges relating to the use of AI, including the need for well-curated validation datasets, regulatory approval and fair reimbursement strategies. Finally, we present potential future opportunities for precision oncology.

Advances in the quality of whole-slide images have set the stage for the clinical use of digital images in anatomic pathology. Along with advances in computer image analysis, this raises the possibility for computer-assisted diagnostics in pathology to improve histopathologic interpretation and clinical care. To evaluate the potential impact of digital assistance on interpretation of digitized slides, we conducted a multireader multicase study utilizing our deep learning algorithm for the detection of breast cancer metastasis in lymph nodes. Six pathologists reviewed 70 digitized slides from lymph node sections in 2 reader modes, unassisted and assisted, with a wash-out period between sessions. In the assisted mode, the deep learning algorithm was used to identify and outline regions with high likelihood of containing tumor. Algorithm-assisted pathologists demonstrated higher accuracy than either the algorithm or the pathologist alone. In particular, algorithm assistance significantly increased the sensitivity of detection for micrometastases (91% vs. 83%, P=0.02). In addition, average review time per image was significantly shorter with assistance than without assistance for both micrometastases (61 vs. 116 s, P=0.002) and negative images (111 vs. 137 s, P=0.018). Lastly, pathologists were asked to provide a numeric score regarding the difficulty of each image classification. On the basis of this score, pathologists considered the image review of micrometastases to be significantly easier when interpreted with assistance (P=0.0005). Utilizing a proof of concept assistant tool, this study demonstrates the potential of a deep learning algorithm to improve pathologist accuracy and efficiency in a digital pathology workflow.

Background: A major challenge in studies of etiologic heterogeneity in breast cancer has been the limited throughput, accuracy, and reproducibility of measuring tissue markers. Computerized image analysis systems may help address these concerns, but published reports of their use are limited. We assessed agreement between automated and pathologist scores of a diverse set of immunohistochemical assays done on breast cancer tissue microarrays (TMA).

Machine learning techniques have great potential to improve medical diagnostics, offering ways to improve accuracy, reproducibility and speed, and to ease workloads for clinicians. In the field of histopathology, deep learning algorithms have been developed that perform similarly to trained pathologists for tasks such as tumor detection and grading. However, despite these promising results, very few algorithms have reached clinical implementation, challenging the balance between hope and hype for these new techniques. This Review provides an overview of the current state of the field, as well as describing the challenges that still need to be addressed before artificial intelligence in histopathology can achieve clinical value.

Digital pathology allows computerized analysis of tumor ecosystem using whole slide images (WSIs). Here, we present single-cell morphological and topological profiling (sc-MTOP) to characterize tumor ecosystem by extracting the features of nuclear morphology and intercellular spatial relationship for individual cells. We construct a single-cell atlas comprising 410 million cells from 637 breast cancer WSIs and dissect the phenotypic diversity within tumor, inflammatory and stroma cells respectively. Spatially-resolved analysis identifies recurrent micro-ecological modules representing locoregional multicellular structures and reveals four breast cancer ecotypes correlating with distinct molecular features and patient prognosis. Further analysis with multiomics data uncovers clinically relevant ecosystem features. High abundance of locally-aggregated inflammatory cells indicates immune-activated tumor microenvironment and favorable immunotherapy response in triple-negative breast cancers. Morphological intratumor heterogeneity of tumor nuclei correlates with cell cycle pathway activation and CDK inhibitors responsiveness in hormone receptor-positive cases. sc-MTOP enables using WSIs to characterize tumor ecosystems at the single-cell level.© 2023. Springer Nature Limited.

Breast cancers are complex ecosystems of malignant cells and the tumour microenvironment1. The composition of these tumour ecosystems and interactions within them contribute to responses to cytotoxic therapy2. Efforts to build response predictors have not incorporated this knowledge. We collected clinical, digital pathology, genomic and transcriptomic profiles of pre-treatment biopsies of breast tumours from 168 patients treated with chemotherapy with or without HER2 (encoded byERBB2)-targeted therapy before surgery. Pathology end points (complete response or residual disease) at surgery3were then correlated with multi-omic features in these diagnostic biopsies. Here we show that response to treatment is modulated by the pre-treated tumour ecosystem, and its multi-omics landscape can be integrated in predictive models using machine learning. The degree of residual disease following therapy is monotonically associated with pre-therapy features, including tumour mutational and copy number landscapes, tumour proliferation, immune infiltration and T cell dysfunction and exclusion. Combining these features into a multi-omic machine learning model predicted a pathological complete response in an external validation cohort (75 patients) with an area under the curve of 0.87. In conclusion, response to therapy is determined by the baseline characteristics of the totality of the tumour ecosystem captured through data integration and machine learning. This approach could be used to develop predictors for other cancers.

Recent genomic and bioinformatic technological advances have made it possible to dissect the immune response to personalized neoantigens encoded by tumor-specific mutations. However, timely and efficient identification of neoantigens is still one of the major obstacles to using personalized neoantigen-based cancer immunotherapy.Two different pipelines of neoantigens identification were established in this study: (1) Clinical grade targeted sequencing was performed in patients with refractory solid tumor, and mutant peptides with high variant allele frequency and predicted high HLA-binding affinity were de novo synthesized. (2) An inventory-shared neoantigen peptide library of common solid tumors was constructed, and patients' hotspot mutations were matched to the neoantigen peptide library. The candidate neoepitopes were identified by recalling memory T-cell responses in vitro. Subsequently, neoantigen-loaded dendritic cell vaccines and neoantigen-reactive T cells were generated for personalized immunotherapy in six patients.Immunogenic neo-epitopes were recognized by autologous T cells in 3 of 4 patients who utilized the de novo synthesis mode and in 6 of 13 patients who performed shared neoantigen peptide library, respectively. A metastatic thymoma patient achieved a complete and durable response beyond 29 months after treatment. Immune-related partial response was observed in another patient with metastatic pancreatic cancer. The remaining four patients achieved the prolonged stabilization of disease with a median PFS of 8.6 months.The current study provided feasible pipelines for neoantigen identification. Implementing these strategies to individually tailor neoantigens could facilitate the neoantigen-based translational immunotherapy research.TRIAL REGSITRATION. ChiCTR.org ChiCTR-OIC-16010092, ChiCTR-OIC-17011275, ChiCTR-OIC-17011913; ClinicalTrials.gov NCT03171220.This work was funded by grants from the National Key Research and Development Program of China (Grant No. 2017YFC1308900), the National Major Projects for "Major New Drugs Innovation and Development" (Grant No.2018ZX09301048-003), the National Natural Science Foundation of China (Grant No. 81672367, 81572329, 81572601), and the Key Research and Development Program of Jiangsu Province (No. BE2017607).

Human leukocyte antigen class I (HLA-I) molecules are encoded by major histocompatibility complex (MHC) class I loci in humans. The binding and interaction between HLA-I molecules and intracellular peptides derived from a variety of proteolytic mechanisms play a crucial role in subsequent T-cell recognition of target cells and the specificity of the immune response. In this context, tools that predict the likelihood for a peptide to bind to specific HLA class I allotypes are important for selecting the most promising antigenic targets for immunotherapy. In this article, we comprehensively review a variety of currently available tools for predicting the binding of peptides to a selection of HLA-I allomorphs. Specifically, we compare their calculation methods for the prediction score, employed algorithms, evaluation strategies and software functionalities. In addition, we have evaluated the prediction performance of the reviewed tools based on an independent validation data set, containing 21 101 experimentally verified ligands across 19 HLA-I allotypes. The benchmarking results show that MixMHCpred 2.0.1 achieves the best performance for predicting peptides binding to most of the HLA-I allomorphs studied, while NetMHCpan 4.0 and NetMHCcons 1.1 outperform the other machine learning-based and consensus-based tools, respectively. Importantly, it should be noted that a peptide predicted with a higher binding score for a specific HLA allotype does not necessarily imply it will be immunogenic. That said, peptide-binding predictors are still very useful in that they can help to significantly reduce the large number of epitope candidates that need to be experimentally verified. Several other factors, including susceptibility to proteasome cleavage, peptide transport into the endoplasmic reticulum and T-cell receptor repertoire, also contribute to the immunogenicity of peptide antigens, and some of them can be considered by some predictors. Therefore, integrating features derived from these additional factors together with HLA-binding properties by using machine-learning algorithms may increase the prediction accuracy of immunogenic peptides. As such, we anticipate that this review and benchmarking survey will assist researchers in selecting appropriate prediction tools that best suit their purposes and provide useful guidelines for the development of improved antigen predictors in the future.© The Author(s) 2019. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Cytotoxic T cells are of central importance in the immune system's response to disease. They recognize defective cells by binding to peptides presented on the cell surface by MHC class I molecules. Peptide binding to MHC molecules is the single most selective step in the Ag-presentation pathway. Therefore, in the quest for T cell epitopes, the prediction of peptide binding to MHC molecules has attracted widespread attention. In the past, predictors of peptide-MHC interactions have primarily been trained on binding affinity data. Recently, an increasing number of MHC-presented peptides identified by mass spectrometry have been reported containing information about peptide-processing steps in the presentation pathway and the length distribution of naturally presented peptides. In this article, we present NetMHCpan-4.0, a method trained on binding affinity and eluted ligand data leveraging the information from both data types. Large-scale benchmarking of the method demonstrates an increase in predictive performance compared with state-of-the-art methods when it comes to identification of naturally processed ligands, cancer neoantigens, and T cell epitopes.Copyright © 2017 by The American Association of Immunologists, Inc.

\n Messenger RNA (mRNA) vaccines are being used to combat the spread of COVID-19 (refs.\n 1–3\n ), but they still exhibit critical limitations caused by mRNA instability and degradation, which are major obstacles for the storage, distribution and efficacy of the vaccine products\n 4\n. Increasing secondary structure lengthens mRNA half-life, which, together with optimal codons, improves protein expression\n 5\n. Therefore, a principled mRNA design algorithm must optimize both structural stability and codon usage. However, owing to synonymous codons, the mRNA design space is prohibitively large—for example, there are around 2.4 × 10\n 632\n candidate mRNA sequences for the SARS-CoV-2 spike protein. This poses insurmountable computational challenges. Here we provide a simple and unexpected solution using the classical concept of lattice parsing in computational linguistics, where finding the optimal mRNA sequence is analogous to identifying the most likely sentence among similar-sounding alternatives\n 6\n. Our algorithm LinearDesign finds an optimal mRNA design for the spike protein in just 11 minutes, and can concurrently optimize stability and codon usage. LinearDesign substantially improves mRNA half-life and protein expression, and profoundly increases antibody titre by up to 128 times in mice compared to the codon-optimization benchmark on mRNA vaccines for COVID-19 and varicella-zoster virus. This result reveals the great potential of principled mRNA design and enables the exploration of previously unreachable but highly stable and efficient designs. Our work is a timely tool for vaccines and other mRNA-based medicines encoding therapeutic proteins such as monoclonal antibodies and anti-cancer drugs\n 7,8\n.\n

DeepMind presented remarkably accurate predictions at the recent CASP14 protein structure prediction assessment conference. We explored network architectures incorporating related ideas and obtained the best performance with a three-track network in which information at the 1D sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The three-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables the rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate protein-protein complex models from sequence information alone, short circuiting traditional approaches which require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research.Copyright © 2021, American Association for the Advancement of Science.

Breast cancer stands as the most prevalent cancer globally, necessitating comprehensive care. A multidisciplinary approach proves crucial for precise diagnosis and treatment, ultimately leading to effective disease management. While surgical interventions continue to evolve and remain integral for curative treatment, imaging assumes a fundamental role in breast cancer detection. Advanced imaging techniques not only facilitate improved diagnosis but also contribute significantly to the overall enhancement of breast cancer management. This review article aims to provide an overview of innovative technologies such as virtual reality, augmented reality, and three-dimensional imaging, utilized in the medical field to elevate the diagnosis and treatment of breast cancer. Additionally, the article delves into an emerging technology known as the metaverse, still under development. Through the analysis of impactful research and comparison of their findings, this study offers valuable insights into the advantages of each innovative technique. The goal is to provide physicians, surgeons, and radiologists with information on how to enhance breast cancer management.

The use of Indocyanine green angiography (ICG-A) in oncoplastic breast-conserving surgery (OBCS) has not yet been investigated. This prospective trial applied ICG-A in volume displacement and replacement OBCS to localize perforators and determine tissue supplied by the perforator. Furthermore, to investigate and correlate the intraoperative ICG-A to postoperative surgical site infection, skin necrosis, epidermolysis, and timely onset of adjuvant therapy.ICG-A was performed at three pre-set timepoints during surgery; after lumpectomy, upon dissection of possible perforators, and after wound closure. All patients were followed with clinical evaluations before surgery, 4 weeks, 4-6 months, and 12 months postoperatively.Eleven patients were included: seven volume displacement and four volume replacement OBCS. ICG-A located the tissue supplied by the perforator and demonstrated sufficient perfusion in all cases. The ICG-A corresponded to the surgeons' clinical assessment. One patient developed a postoperative infection and seroma and was treated conservatively. No patients had postoperative necrosis, loss of reconstruction, or lymphedema of the arm. Edema of the breast occurred in four patients (36.4%). Scar assessments were significantly worse at 4-weeks and 4-6 months. The quality of life improved significantly during follow-up. Adjuvant treatment was administered timely in all cases.ICG-A was feasible for OBCS in assessing intraoperative perfusion. Perfusion was sufficient in all patients and corresponded to the surgeon's clinical evaluation. No patients developed postoperative necrosis. Though edema of the breast occurred in 36.4%, a larger sample size is needed to investigate a possible correlation with ICG-A. Further studies, which includes patients requiring extensive tissue replacement challenging the borders of perfusion, are needed.Copyright © 2023 British Association of Plastic, Reconstructive and Aesthetic Surgeons. Published by Elsevier Ltd. All rights reserved.

Complete tumor removal during cancer surgery remains challenging due to the lack of accurate techniques for intraoperative margin assessment. This study evaluates the use of hyperspectral imaging for margin assessment by reporting its use in fresh human breast specimens.Hyperspectral data were first acquired on tissue slices from 18 patients after gross sectioning of the resected breast specimen. This dataset, which contained over 22,000 spectra, was well correlated with histopathology and was used to develop a support vector machine classification algorithm and test the classification performance. In addition, we evaluated hyperspectral imaging in clinical practice by imaging the resection surface of six lumpectomy specimens. With the developed classification algorithm, we determined if hyperspectral imaging could detect malignancies in the resection surface.The diagnostic performance of hyperspectral imaging on the tissue slices was high; invasive carcinoma, ductal carcinoma, connective tissue, and adipose tissue were correctly classified as tumor or healthy tissue with accuracies of 93%, 84%, 70%, and 99%, respectively. These accuracies increased with the size of the area, consisting of one tissue type. The entire resection surface was imaged within 10 minutes, and data analysis was performed fast, without the need of an experienced operator. On the resection surface, hyperspectral imaging detected 19 of 20 malignancies that, according to the available histopathology information, were located within 2 mm of the resection surface.These findings show the potential of using hyperspectral imaging for margin assessment during breast-conserving surgery to improve surgical outcome.©2019 American Association for Cancer Research.

Artificial intelligence (AI) shows great potential to streamline the treatment planning process. However, its clinical adoption is slow due to the limited number of clinical evaluation studies and because often, the translation of the predicted dose distribution to a deliverable plan is lacking. This study evaluates two different, deliverable AI plans in terms of their clinical acceptability based on quantitative parameters and qualitative evaluation by four radiation oncologists.For 20 left-sided node-negative breast cancer patients, treated with a prescribed dose of 40.05 Gy, using tangential beam intensity modulated radiotherapy, two model-based treatment plans were evaluated against the corresponding manual plan. The two models used were an in-house developed U-net model and a vendor-developed contextual atlas regression forest model (cARF). Radiation oncologists evaluated the clinical acceptability of each blinded plan and ranked plans according to preference. Furthermore, a comparison with the manual plan was made based on dose volume histogram parameters, clinical evaluation criteria and preparation time.The U-net model resulted in a higher average and maximum dose to the PTV (median difference 0.37 Gy and 0.47 Gy respectively) and a slightly higher mean heart dose (MHD) (0.01 Gy). The cARF model led to higher average and maximum doses to the PTV (0.30 and 0.39 Gy respectively) and a slightly higher MHD (0.02 Gy) and mean lung dose (MLD, 0.04 Gy). The maximum MHD/MLD difference was ≤ 0.5 Gy for both AI plans. Regardless of these dose differences, 90-95% of the AI plans were considered clinically acceptable versus 90% of the manual plans. Preferences varied between the radiation oncologists. Plan preparation time was comparable between the U-net model and the manual plan (287 s vs 253 s) while the cARF model took longer (471 s). When only considering user interaction, plan generation time was 121 s for the cARF model and 137 s for the U-net model.Two AI models were used to generate deliverable plans for breast cancer patients, in a time-efficient manner, requiring minimal user interaction. Although the AI plans resulted in slightly higher doses overall, radiation oncologists considered 90-95% of the AI plans clinically acceptable.© 2022. The Author(s).

Evaluating patients’ experiences is essential when incorporating the patients’ perspective in improving healthcare. Experiences are mainly collected using closed-ended questions, although the value of open-ended questions is widely recognized. Natural language processing (NLP) can automate the analysis of open-ended questions for an efficient approach to patient-centeredness.

Patient-centered care (PCC) is an innovative approach to the diagnosis and treatment of malignancy that aims to improve patients' experience during the management of their disease. However, despite growing interest, the concept and specifics of PCC remain unclear. This consensus document addresses this gap by providing a literature review and a clear definition of PCC and outlines its main components as observed in real-world practice. These components include daytime diagnostic and treatment procedures, in-hospital and community-based infusion centers, home-based diagnostic and treatment services, smart healthcare solutions, and integration of traditional Chinese medicine. This document delves into the implementation of PCC and explores its potential benefits.© 2024 The Author(s). Cancer Innovation published by John Wiley & Sons Ltd on behalf of Tsinghua University Press.