The DOI matches its Crossref record; 81 of the 81 references it cites were found in a registry or an index.
Artificial intelligence in digital breast pathology: Techniques and applications
Open accessAbstract
Breast cancer is the most common cancer and second leading cause of cancer-related death worldwide. The mainstay of breast cancer workup is histopathological diagnosis - which guides therapy and prognosis. However, emerging knowledge about the complex nature of cancer and the availability of tailored therapies have exposed opportunities for improvements in diagnostic precision. In parallel, advances in artificial intelligence (AI) along with the growing digitization of pathology slides for the primary diagnosis are a promising approach to meet the demand for more accurate detection, classification and prediction of behaviour of breast tumours. In this article, we cover the current and prospective uses of AI in digital pathology for breast cancer, review the basics of digital pathology and AI, and outline outstanding challenges in the field.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“AI algorithms skillfully analyze medical imaging and electronic health records to detect health changes that indicate the presence of cancer.”
From Edge AI for Early Detection of Chronic Diseases and the Spread of Infectious Diseases: Opportunities, Challenges, and Future Directions (2023) · cites this paper as [48]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“Deep learning techniques utilize millions of neuron-like units in order to learn complex relationship between image pixel values and its semantic labels, without the need for manual feature engineering–the features are learned automatically from data [20,21].”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Neural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 1×
“Most ML algorithms can be viewed as mathematical models that map a set of observed variables, known as ‘ features ’ or ‘ predictors ’ , of a data point or sample, into a set of outcome variables, known as ‘ labels ’ or ‘ targets ’ [18,19].”
BackgroundAdvances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248 · cited 1×
“Previous study [35] also explored interpretability methods [71,72] to understand what were the input features that triggers the model’s activation in identifying tumor.”
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
Neural networks: A comprehensive foundation
Tadeusiewicz, R. (1995) · Control Engineering Practice · doi:10.1016/0967-0661(95)90080-2 · Cited by 7,217
Ehteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293 · cited 2×
“Babaketal.,2017 detected lymph node metastasis in breast cancer patients with a higher diagnostic achievement over 11 pathologists [33]”
BackgroundMethodPattern recognition and machine learning
(2007) · Choice Reviews Online · doi:10.5860/choice.44-5091 · Cited by 2,783
Opportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310 · cited 2×
“In the medical community, the lack of interpretability could hinder trusts from physicians [70].”
BackgroundA Dataset for Breast Cancer Histopathological Image Classification
Spanhol, F. A., Oliveira, L. S., Petitjean, C., & Heutte, L. (2015) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2015.2496264 · Cited by 1,944 · cited 1×
“Han et al. [31] use the BreaKHis dataset [32] to train a classi fi er which can distinguish between eight classes of benign and malignant breast tumours with 93.2% accuracy.”
MethodInfluentialSmoothGrad: removing noise by adding noise
Smilkov, D., Thorat, N., Kim, B., Viégas, F., & Wattenberg, M. (2017) · arXiv · doi:10.48550/arxiv.1706.03825 · Cited by 1,467 · cited 1×
“Previous study [35] also explored interpretability methods [71,72] to understand what were the input features that triggers the model’s activation in identifying tumor.”
Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases
Janowczyk, A. R., & Madabhushi, A. (2016) · Journal of Pathology Informatics · doi:10.4103/2153-3539.186902 · Cited by 1,387
Image analysis and machine learning in digital pathology: challenges and opportunities
Madabhushi, A., & Lee, G. (2016) · Medical Image Analysis · doi:10.1016/j.media.2016.06.037 · Cited by 1,093
Saltz, J., Gupta, R., Hou, L., Kurc, T., Singh, P., Nguyen, V., Samaras, D., Shroyer, K. R., Zhao, T., Batiste, R., et al. (2018) · Cell Reports · doi:10.1016/j.celrep.2018.03.086 · Cited by 1,027
Prewitt, J. M. S., & Mendelsohn, M. L. (1966) · Annals of the New York Academy of Sciences · doi:10.1111/j.1749-6632.1965.tb11715.x · Cited by 781 · cited 1×
“In 1966, Prewitt [9 e 11] and Mendelsohn [12] fi rst proposed a method to scan images from a microscopic fi eld of a blood smear and use these scanned images to discern the presence of different cell types.”
MethodSystematic Analysis of Breast Cancer Morphology Uncovers Stromal Features Associated with Survival
Beck, A. H., Sangoi, A. R., Leung, S. C. Y., Marinelli, R. J., Nielsen, T. O., van de Vijver, M. J., West, R. B., van de Rijn, M., & Koller, D. (2011) · Science Translational Medicine · doi:10.1126/scitranslmed.3002564 · Cited by 780 · cited 1×
“Beck et al. [60] showed that the features relating to morphology as well as to spatial relationships and global image features of epithelial and stromal regions were extracted from digitized WSIs of specimens from patients with breast cancer.”
BackgroundBreast Cancer Multi-classification from Histopathological Images with Structured Deep Learning Model
Han, Z., Wei, B., Zheng, Y., Yin, Y., Li, K., & Li, S. (2017) · Scientific Reports · doi:10.1038/s41598-017-04075-z · Cited by 696 · cited 1×
“Han et al. [31] use the BreaKHis dataset [32] to train a classi fi er which can distinguish between eight classes of benign and malignant breast tumours with 93.2% accuracy.”
MethodInfluentialImproved Automatic Detection and Segmentation of Cell Nuclei in Histopathology Images
Al-Kofahi, Y., Lassoued, W., Lee, W., & Roysam, B. (2010) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2009.2035102 · Cited by 681 · cited 1×
“Other algorithms were developed to allow objective enumeration of mitotic fi gures [26], measurements of nuclear shape and size, and with the automatic detection and segmentation of cell nuclei in histopathology images [74].”
MethodHow to Read Articles That Use Machine Learning
Liu, Y., Chen, P.-H. C., Krause, J., & Peng, L. H. (2019) · JAMA · doi:10.1001/jama.2019.16489 · Cited by 547 · cited 2×
“Over the last several decades, due to algorithmic advances, more accessible computing power, and the curation of large datasets, machine learning techniques have come to de fi ne the state-of-the-art in many computer vision tasks - including many healthcare applications [4,5].”
BackgroundArtificial Intelligence and Digital Pathology: Challenges and Opportunities
Tizhoosh, H. R., & Pantanowitz, L. (2018) · Journal of Pathology Informatics · doi:10.4103/jpi.jpi_53_18 · Cited by 544 · cited 1×
“In this regard, interpretability of the model becomes an important topic [64,69,70].”
BackgroundRoa, Á. A. C., Gilmore, H. L., Basavanhally, A. N., Feldman, M. D., Ganesan, S., Shih, N. N. C., Tomaszewski, J., Gonzalez, F. A., & Madabhushi, A. (2017) · Scientific Reports · doi:10.1038/srep46450 · Cited by 542 · cited 2×
“[30] built CNN to classify images patches from breast cancer WSIs as either containing invasive ductal carcinoma or not.”
BackgroundSteiner, D. F., MacDonald, R., Liu, Y., Truszkowski, P., Hipp, J. D., Gammage, C., Thng, F., Peng, L., & Stumpe, M. C. (2018) · American Journal of Surgical Pathology · doi:10.1097/pas.0000000000001151 · Cited by 489 · cited 2×
“Displaying con fi dence level or limiting the amount of information shown to the physician may alleviate this issue [34].”
BackgroundAssessment of algorithms for mitosis detection in breast cancer histopathology images
Veta, M., van Diest, P. J., Willems, S. M., Wang, H., Madabhushi, A., Cruz-Roa, Á., Gonzalez, F. A., Larsen, A., Vestergaard, J. S., Dahl, A. B., et al. (2014) · Medical Image Analysis · doi:10.1016/j.media.2014.11.010 · Cited by 480 · cited 1×
“proposed a public mitosis detection challenge [36] with a dataset containing 12 training, 11 testing slides, and roughly one thousand mitotic figures annotated.”
BackgroundXu, J., Luo, X., Wang, G., Gilmore, H. L., & Madabhushi, A. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.01.034 · Cited by 461 · cited 1×
“CNN-based approaches have been used for image-based detection and segmentation tasks to identify and quantify cells [22 e 25] and histological features [26 e 29].”
MethodLiu, Y., Kohlberger, T., Norouzi, M., Dahl, G. E., Smith, J. L., Mohtashamian, A., Olson, N. H., Peng, L. H., Hipp, J., & Stumpe, M. C. (2018) · Archives of Pathology & Laboratory Medicine · doi:10.5858/arpa.2018-0147-oa · Cited by 413 · cited 2×
“A similar study had 6 pathologists reviewed 70 digitized slides with and without ML assistance [34,35].”
BackgroundMukhopadhyay, S., Feldman, M. D., Abels, E., Ashfaq, R., Beltaifa, S., Cacciabeve, N. G., Cathro, H. P., Cheng, L., Cooper, K., Dickey, G. E., et al. (2018) · American Journal of Surgical Pathology · doi:10.1097/pas.0000000000000948 · Cited by 399
Automatic Nuclei Segmentation in H&E Stained Breast Cancer Histopathology Images
Veta, M., van Diest, P. J., Kornegoor, R., Huisman, A., Viergever, M. A., & Pluim, J. P. W. (2013) · PLoS ONE · doi:10.1371/journal.pone.0070221 · Cited by 370 · cited 1×
“proposed a series of non-CNN algorithms to segment and detect nuclei [41,42].”
BackgroundCouture, H. D., Williams, L. A., Geradts, J., Nyante, S. J., Butler, E. N., Marron, J. S., Perou, C. M., Troester, M. A., & Niethammer, M. (2018) · npj Breast Cancer · doi:10.1038/s41523-018-0079-1 · Cited by 327 · cited 4×
“…of tumour in fi ltrating lymphocytic (TILs) in HER2 þ breast cancer [78] have been developed Receptor status and intrinsic subtype assessment AI algorithms have been developed to provide quantitative measurements of immunohistochemically stained Ki-67 [52], ER [50], PR and Her2neu images [75].”
MethodInfluentialPredicting breast tumor proliferation from whole-slide images: The TUPAC16 challenge
Veta, M., Heng, Y. J., Stathonikos, N., Bejnordi, B. E., de Beça, F. F., Wollmann, T., Rohr, K., Shah, M., Wang, D., Rousson, M., et al. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.02.012 · Cited by 309 · cited 1×
“In 2016, Veta et al. published a follow up challenge that focuses on slide-level mitotic score [37].”
BackgroundRobertson, S., Azizpour, H., Smith, K., & Hartman, J. (2017) · Translational research · doi:10.1016/j.trsl.2017.10.010 · Cited by 300 · cited 1×
“The trend towards digitization in pathology opens the door to computerbased image analysis solutions which have the potential to provide a more objective and quantitative slide reviews [3].”
BackgroundTellez, D., Balkenhol, M., Otte-Höller, I., van de Loo, R., Vogels, R., Bult, P., Wauters, C., Vreuls, W., Mol, S., Karssemeijer, N., et al. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2820199 · Cited by 288 · cited 11×
“Veta et al. proposed a series of non-CNN algorithms to segment and detect nuclei [41,42].”
MethodInfluentialHow to develop machine learning models for healthcare
Chen, P.-H. C., Liu, Y., & Peng, L. (2019) · Nature Materials · doi:10.1038/s41563-019-0345-0 · Cited by 274 · cited 1×
“First, the validation should be appropriate for the anticipated use cases [5,67].”
BackgroundSelf-citationBasavanhally, A. N., Ganesan, S., Agner, S. C., Monaco, J., Feldman, M. D., Tomaszewski, J. E., Bhanot, G., & Madabhushi, A. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2009.2035305 · Cited by 272
Doyle, S. T., Feldman, M. D., Tomaszewski, J., & Madabhushi, A. (2010) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2053540 · Cited by 258 · cited 1×
“For an AI approach to segment biological structures, the performance is dependent on the fi delity of the annotations byexpert pathologists in the learning set [30,66].”
BackgroundAndré, F., Ismaila, N., Henry, N. L., Somerfield, M. R., Bast, R. C., Barlow, W. E., Collyar, D. E., Hammond, M. E. H., Kuderer, N. M., Liu, M., et al. (2019) · Journal of Clinical Oncology · doi:10.1200/jco.19.00945 · Cited by 232
Thomson, T. A., Hayes, M. M., Spinelli, J. J., Hilland, E., Sawrenko, C., Phillips, D., Dupuis, B., & Parker, R. L. (2001) · Modern Pathology · doi:10.1038/modpathol.3880440 · Cited by 215 · cited 8×
“Although this approach is wellvalidated and widely used, there is significant inter-observer variability in manual biomarker status assessment from IHC [45,46] suggesting an opportunity for machine-learning based systems to assist pathologists with biomarker status assessments.”
BackgroundInfluentialMengel, M., von Wasielewski, R., Wiese, B., Rüdiger, T., Müller‐Hermelink, H. K., & Kreipe, H. H. (2002) · The Journal of Pathology · doi:10.1002/path.1218 · Cited by 213 · cited 1×
“Although this approach is well-validated and widely used, there is signi fi cant inter-observer variability in manual biomarker status assessment from IHC [45,46] suggesting an opportunity for machine-learning based systems to assist pathologists with biomarker status assessments.”
MethodFitzgibbons, P. L., Dillon, D. A. R., Alsabeh, R., Berman, M. A., Hayes, D. F., Hicks, D. G., Hughes, K. S., & Nofech‐Mozes, S. (2013) · Archives of Pathology & Laboratory Medicine · doi:10.5858/arpa.2013-0566-cp · Cited by 188 · cited 1×
“Current clinical practice relies on immunohistochemical (IHC) staining and manual comparison of staining intensity against a set of biomarker-speci fi c scoring systems [43,44].”
MethodMachine learning techniques to diagnose breast cancer
Osareh, A., & Shadgar, B. (2010) · International Symposium on Health Informatics and Bioinformatics (HIBIT) · doi:10.1109/hibit.2010.5478895 · Cited by 178 · cited 1×
“In breast pathology, 10 cellular features introduced by Osareh et al. [53] into ML that were identi fi ed by an expert breast pathologist to differentiate between malignant and benign tumours using images of fi ne-needle aspiration biopsy samples [53].”
Heindl, A., Šestak, I., Naidoo, K., Cuzick, J. M., Dowsett, M., & Yuan, Y. (2017) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/djx137 · Cited by 162 · cited 2×
“These investigators further expanded this method and found that the spatial distribution of immune cells was also associated with late recurrence in ER-positive breast cancer [57].”
BackgroundMethodComplete Digital Pathology for Routine Histopathology Diagnosis in a Multicenter Hospital Network
Retámero, J. A., Aneiros‐Fernández, J., & del Moral, R. G. (2019) · Archives of Pathology & Laboratory Medicine · doi:10.5858/arpa.2018-0541-oa · Cited by 161 · cited 1×
“showed a 21% average increase in annual per-pathologist case sign-outs [11].”
BackgroundFuture-proofing pathology: the case for clinical adoption of digital pathology
Williams, B. J., Bottoms, D., & Treanor, D. E. (2017) · Journal of Clinical Pathology · doi:10.1136/jclinpath-2017-204644 · Cited by 142 · cited 1×
“…tissue loss or damage, better case tracking and workload allocation, streamlined retrieval of archival cases, and improved telepathology consultations in addition to facilitating cross coverage between hospitals for primary diagnosis, remote reporting centralisation of pathology laboratories [17].”
BackgroundAssessment of HER-2/neu Status in Breast Cancer
Wang, S., Saboorian, M. H., Frenkel, E. P., Haley, B., Siddiqui, M. T., Gokaslan, S. T., Wians, F. H., Hynan, L. S., & Ashfaq, R. (2001) · American Journal of Clinical Pathology · doi:10.1309/tmuw-g4wb-lxj2-fudn · Cited by 138
Rexhepaj, E., Brennan, D. J., Holloway, P., Kay, E. W., McCann, A. H., Landberg, G., Duffy, M. J., Jirström, K., & Gallagher, W. M. (2008) · Breast Cancer Research · doi:10.1186/bcr2187 · Cited by 137 · cited 1×
“In a similar approach, Rexhepaj et al. [48] designed a nuclear detection algorithm and used it to quantify IHC staining for ER and PR expression and found a correlation of 0.9 between manual and algorithmic quanti fi cation.”
MethodInfluentialShamai, G., Binenbaum, Y., Slossberg, R., Duek, I., Gil, Z., & Kimmel, R. (2019) · JAMA Network Open · doi:10.1001/jamanetworkopen.2019.7700 · Cited by 133 · cited 1×
“[51] built a deep learning system to predict the statuses of 19 biomarkers including ER and PR.”
BackgroundGomes, D. S., Porto, S., Balabram, D., & Gobbi, H. (2014) · Diagnostic Pathology · doi:10.1186/1746-1596-9-121 · Cited by 129 · cited 1×
“This strati fi cation is primarily based on manual interpretation of pathology slides - a time-consuming process with signi fi cant interobserver variability [1,2].”
BackgroundYuan, Y. (2014) · Journal of The Royal Society Interface · doi:10.1098/rsif.2014.1153 · Cited by 128 · cited 1×
“…architecture of different tissue elements such as TILs within the tumour have been developed and demonstrated their value in predicting survival [79] and that the spatial distribution of TILs among tumour cells expression pro fi ling is associated with late recurrence in ER-positive breast…”
BackgroundWhitney, J. R., Corredor, G., Janowczyk, A. R., Ganesan, S., Doyle, S. T., Tomaszewski, J., Feldman, M. D., Gilmore, H. L., & Madabhushi, A. (2018) · BMC Cancer · doi:10.1186/s12885-018-4448-9 · Cited by 116 · cited 2×
“[54] showed that quantitative features of nuclear shape, texture and architecture independently enable prediction of recurrence risk in patients with ER-positive breast tumours (on the basis of the 21-gene expression-based companion diagnostic test Oncotype DX).”
BackgroundDeep Learning Nuclei Detection in Digitized Histology Images by Superpixels
Sornapudi, S., Stanley, R. J., Stoecker, W. V., Almubarak, H. A., Long, L. R., Antani, S., Thoma, G. R., Zuna, R. E., & Frazier, S. R. (2018) · Journal of Pathology Informatics · doi:10.4103/jpi.jpi_74_17 · Cited by 105
Applications and challenges of digital pathology and whole slide imaging
Higgins, C. D. (2015) · Biotechnic & Histochemistry · doi:10.3109/10520295.2015.1044566 · Cited by 103 · cited 3×
“Moreover, illumination variations and the level of noise are affecting the morphological and architectural structure of the histological regions [62].”
BackgroundMethodRomo‐Bucheli, D., Janowczyk, A. R., Gilmore, H. L., Romero, E., & Madabhushi, A. (2016) · Scientific Reports · doi:10.1038/srep32706 · Cited by 102 · cited 1×
“train a CNN to detect tubule nuclei, and compute statistics about the nuclei to predict Oncotype DX risk categories [39,40].”
MethodAllison, K. H., Reisch, L. M., Carney, P. A., Weaver, D. L., Schnitt, S. J., O’Malley, F. P., Geller, B. M., & Elmore, J. G. (2014) · Histopathology · doi:10.1111/his.12387 · Cited by 101 · cited 1×
“This strati fi cation is primarily based on manual interpretation of pathology slides - a time-consuming process with signi fi cant interobserver variability [1,2].”
BackgroundWhole-Slide Image Focus Quality: Automatic Assessment and Impact on AI Cancer Detection
Kohlberger, T., Liu, Y., Moran, M., Chen, P.-H. C., Brown, T., Hipp, J., Mermel, C. H., & Stumpe, M. C. (2019) · Journal of Pathology Informatics · doi:10.4103/jpi.jpi_11_19 · Cited by 94 · cited 1×
“Kohlberger et al. developed a technique that uses synthetic data to train a CNN to detect out of focus area, which helps ensure image quality of the scanned images [65].”
MethodAli, H. R., Dariush, A., Provenzano, E., Bardwell, H. A., Abraham, J., Iddawela, M. Y., Vallier, A.-L., Hiller, L., Dunn, J., Bowden, S. J., et al. (2016) · Breast Cancer Research · doi:10.1186/s13058-016-0682-8 · Cited by 93 · cited 1×
“Ali et al. used classical ML methods to count features on breast cancer biopsies, and were able to predict neoadjuvant response [58].”
MethodDeep learning nuclei detection: A simple approach can deliver state-of-the-art results
Höfener, H., Homeyer, A., Weiss, N., Molin, J., Lundström, C. F., & Hahn, H. K. (2018) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2018.08.010 · Cited by 88
Veta, M., Kornegoor, R., Huisman, A., Verschuur‐Maes, A. H. J., Viergever, M. A., Pluim, J. P. W., & van Diest, P. J. (2012) · Modern Pathology · doi:10.1038/modpathol.2012.126 · Cited by 84 · cited 4×
“Nonetheless, their subsequent work shows that using CNN mitosis detection as an assistant can help improve the level of concordance among human pathologists [39].”
BackgroundMethodInfluentialMarker-controlled watershed segmentation of nuclei in H&E stained breast cancer biopsy images
Veta, M., Huisman, A., Viergever, M. A., van Diest, P. J., & Pluim, J. P. W. (2011) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2011.5872483 · Cited by 82 · cited 1×
“proposed a series of non-CNN algorithms to segment and detect nuclei [41,42].”
BackgroundEvaluating Imaging and Computer-aided Detection and Diagnosis Devices at the FDA
Gallas, B. D., Chan, H.-P., D’Orsi, C. J., Dodd, L. E., Giger, M. L., Gur, D., Krupinski, E. A., Metz, C. E., Myers, K. J., Obuchowski, N. A., et al. (2012) · Academic Radiology · doi:10.1016/j.acra.2011.12.016 · Cited by 81 · cited 1×
“To validate an ML-based tool for peri-diagnosis, additional evaluation on the human-computer interface through a multi-case multi-reader study is required [68].”
MethodWilliams, B. J., Hanby, A. M., Millican-Slater, R. A., Nijhawan, A., Verghese, E. T., & Treanor, D. E. (2017) · Histopathology · doi:10.1111/his.13403 · Cited by 78 · cited 2×
“In 1966, Prewitt [9 e 11] and Mendelsohn [12] fi rst proposed a method to scan images from a microscopic fi eld of a blood smear and use these scanned images to discern the presence of different cell types.”
BackgroundMethodInfluentialGAN-based Virtual Re-Staining: A Promising Solution for Whole Slide Image AnalysisPreprint
Xu, Z., Huang, X., Moro, C. F., Bozóky, B., & Zhang, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.04059 · Cited by 74 · cited 1×
“H&E stained WSIs that potentially obviates the need for IHC-based tissue testing [52,76]”
BackgroundA Systematic Analysis of Discordant Diagnoses in Digital Pathology Compared With Light Microscopy
Williams, B. J., DaCosta, P., Goacher, E., & Treanor, D. E. (2017) · Archives of Pathology & Laboratory Medicine · doi:10.5858/arpa.2016-0494-oa · Cited by 71 · cited 1×
“[10].”
Enterprise Implementation of Digital Pathology: Feasibility, Challenges, and Opportunities
Hartman, D., Pantanowitz, L., McHugh, J., Piccoli, A. L., O'Leary, M. M., & Lauro, G. R. (2017) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-017-9946-9 · Cited by 67 · cited 2×
“AI-based approach is markedly dependent on the quantity and quality of the input data, for instance the lack of agreed fi le format for digitized slides and absence of information system integration [61].”
BackgroundAutomatic Lymphocyte Detection on Gastric Cancer IHC Images Using Deep Learning
Garcia, E., Hermoza, R., Beltrán, C., Cano, L., Castillo, M., & Castaneda, C. (2017) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2017.94 · Cited by 67
Klimov, S., Miligy, I. M., Gertych, A., Jiang, Y., Toss, M. S., Rida, P. C. G., Ellis, I. O., Green, A. R., Krishnamurti, U., Rakha, E. A., et al. (2019) · Breast Cancer Research · doi:10.1186/s13058-019-1165-5 · Cited by 63 · cited 2×
“Furthermore, it signi fi cantly identi fi ed patients that might bene fi t from additional therapy (validation cohort p ¼ 0.0006) [59].”
BackgroundMethodInfluentialSkaland, I., Øvestad, I. T., Janssen, E. A. M., Kłos, J., Kjellevold, K. H., Helliesen, T., & Baak, J. P. A. (2007) · Journal of Clinical Pathology · doi:10.1136/jcp.2007.046763 · Cited by 62 · cited 1×
“Skaland et al. [49] used open source digital image analysis software to analyse HER2 IHC stains from 60 breast cancer cases with scores of 2 þ or 3 þ and found 100% concordance between the algorithm ’ s prediction and the consensus clinical status assessment.”
MethodReview of the national external quality assessment (EQA) scheme for breast pathology in the UK
Rakha, E. A., Bennett, R. L., Coleman, D., Pinder, S. E., & Ellis, I. O. (2016) · Journal of Clinical Pathology · doi:10.1136/jclinpath-2016-203800 · Cited by 61
Computer-aided gleason grading of prostate cancer histopathological images using texton forests
Khurd, P., Bahlmann, C., Maday, P., Kamen, A., Gibbs‐Strauss, S. L., Genega, E. M., & Frangioni, J. V. (2010) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2010.5490096 · Cited by 60 · cited 1×
“In this regard, interpretability of the model becomes an important topic [64,69,70].”
BackgroundBreast cancer histologic grading using digital microscopy: concordance and outcome association
Rakha, E. A., Aleskandarani, M., Toss, M. S., Green, A. R., Ball, G., Ellis, I. O., & Dalton, L. W. (2018) · Journal of Clinical Pathology · doi:10.1136/jclinpath-2017-204979 · Cited by 51 · cited 1×
“However, this is often not straightforward and signi fi cant research has gone into improving reliability and reducing variability of the assessment [6 e 8].”
BackgroundDiagnostic Efficiency in Digital Pathology
Mills, A. M., Gradecki, S. E., Horton, B. J., Blackwell, R., Moskaluk, C. A., Mandell, J. W., Mills, S. E., & Cathro, H. P. (2017) · The American Journal of Surgical Pathology · doi:10.1097/pas.0000000000000930 · Cited by 47 · cited 1×
“A similar study conducted by Mills et al. assessed diagnostic ef fi ciency on 510 surgical pathology cases and found a median increase in diagnostic time of 4 s per case for digital reads compared to glass [16].”
MethodRakha, E. A., Ahmed, M., Aleskandarany, M. A., Hodi, Z., Lee, A. H. S., Pinder, S. E., & Ellis, I. O. (2016) · Histopathology · doi:10.1111/his.13117 · Cited by 36
Microarray data analysis for cancer classification
Osareh, A., & Shadgar, B. (2010) · International Symposium on Health Informatics and Bioinformatics (HIBIT) · doi:10.1109/hibit.2010.5478893 · Cited by 33 · cited 1×
“using digitalized images of fine-needle aspiration biopsy samples [73].”
MethodMulti-Pass Adaptive Voting for Nuclei Detection in Histopathological Images
Lu, C. Y., Xu, H., Xu, J., Gilmore, H. L., Mandal, M. K., & Madabhushi, A. (2016) · Scientific Reports · doi:10.1038/srep33985 · Cited by 31 · cited 2×
“tumour microenvironment AI-based assays to measure tumour intra-tumour and inter-tumour heterogeneity [26,56], identify and quantify nonepithelial cells such as fibroblast, neutrophils, lymphocytes and macrophages [77] and computerized image-based detection and grading of tumour infiltrating lymphocytic (TILs) in HER2…”
BackgroundMethodHossain, M. S., Hanna, M. G., Uraoka, N., Nakamura, T., Edelweiss, M., Brogi, E., Hameed, M., Yamaguchi, M., Ross, D. S., & Yagi, Y. (2019) · Journal of medical imaging · doi:10.1117/1.jmi.6.4.047501 · Cited by 29 · cited 1×
“[52], ER [50], PR and Her2neu images [75].”
BackgroundAutomatic Lymphocyte Detection in H&E Images with Deep Neural NetworksPreprint
Chen, J., & Srinivas, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.03217 · Cited by 24
Sahiner, B., Tozbikian, G. H., Lozanski, G., Gürcan, M. N., & Şenaras, Ç. (2018) · SPIE Medical Imaging: Digital and Computational Pathology · doi:10.1117/12.2294999 · Cited by 14 · cited 2×
“…of tumour in fi ltrating lymphocytic (TILs) in HER2 þ breast cancer [78] have been developed Receptor status and intrinsic subtype assessment AI algorithms have been developed to provide quantitative measurements of immunohistochemically stained Ki-67 [52], ER [50], PR and Her2neu images [75].”
MethodInfluentialTőkés, T., Tőkés, A.-M., Szentmártoni, G., Kiszner, G., Madaras, L., Kulka, J., Krenács, T., & Dank, M. (2016) · Archiv für Pathologische Anatomie und Physiologie und für Klinische Medicin · doi:10.1007/s00428-016-1925-x · Cited by 11 · cited 1×
“[80] or the presence of certain morphological features in the tumour to the response of specific therapy.”
BackgroundAndré, F., Ismaila, N., & Stearns, V. (2019) · Journal of Oncology Practice · doi:10.1200/jop.19.00264 · Cited by 9 · cited 1×
“Current clinical practice relies on immunohistochemical (IHC) staining and manual comparison of staining intensity against a set of biomarker-speci fi c scoring systems [43,44].”
Method
Research works printed but not linked: 3
- Mukhopadhyay, 2017, Whole slide imaging versus microscopy for primary diagnosis in surgical pathology, Am J Surg Pathol, 1
- 2015, Website. the spatial heterogeneity and molecular correlates of lymphocytic infiltration in triple-negative breast cancer, J R Soc Interface
- Basavanhally, 2010, Computerized image-based detection and grading of lymphocytic infiltration in HER2 breast cancer histopathology, IEEE (Inst Electr Electron Eng) Trans Biomed Eng, 57, 642
Cited by
Sorted by citations
RETRACTED ARTICLE: Artificial intelligence and machine learning in precision and genomic medicine
Quazi, S. (2022) · Medical Oncology · doi:10.1007/s12032-022-01711-1 · Cited by 466
“In particular, ML and DL centered methodologies have gained popularity and developed as critical components of biomedical data analysis, owing to the abundance of medical data and the rapid advancement of analytics tools [9–13].”
RetractedArtificial intelligence (AI) and big data in cancer and precision oncology
Dlamini, Z., Francies, F. Z., Hull, R., & Marima, R. M. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.08.019 · Cited by 419
“Whole slide imaging (WSI) in the latest innovation in digital pathology [55].”
BackgroundArtificial intelligence in diagnostic pathology
Shafi, S., & Parwani, A. V. (2023) · Diagnostic Pathology · doi:10.1186/s13000-023-01375-z · Cited by 371
“WSIs can be used to extract several features using computer vision algorithms, thereby enabling diagnostic predictions [64–69].”
BackgroundMethodA framework for breast cancer classification using Multi-DCNNs
Ragab, D. A., Attallah, O., Sharkas, M., Ren, J., & Marshall, S. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104245 · Cited by 211
Hierarchical graph representations in digital pathology
Pati, P., Jaume, G., Foncubierta–Rodríguez, A., Feroce, F., Anniciello, A. M., Scognamiglio, G., Brancati, N., Fiche, M., Dubruc, E., Riccio, D., et al. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102264 · Cited by 185
“Further, they enabled computed aided diagnostics to leverage artificial intelligence [7], [8], especially deep learning, to address various digital pathology tasks in breast diagnosis [9], such as nuclei segmentation [10], [11], nuclei classification [12], [13], gland segmentation [14], [15], tumor detection [16]–[18]…”
Background
Metadata
- Authors
- Ibrahim, A., Gamble, P., Jaroensri, R., Abdelsamea, M. M., Mermel, C. H., Chen, P.-H. C., & Rakha, E. A.
- Affiliations
- Nottingham University Hospitals NHS Trust (GB)
- Google (United States) (US)
- Birmingham City University (GB)
- Corresponding author
- Rakha, Emad A.
- Venue
- The Breast
- Publisher
- Elsevier BV
- Published
- 2020-02
- Volume
- 49
- Pages
- 267-273
- ISSN
- 0960-9776 (ISSN-L)
- PMC
- PMC7375550
- OpenAlex
- W2995106101
- Cited by
- 202
- References
- 81
- Citations by year
- 2026: 15 · 2025: 27 · 2024: 39 · 2023: 45 · 2022: 34 · 2021: 30 · 2020: 11
- FWCI
- 1.25
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- The Breast (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- artificial intelligence, digital pathology, breast cancer, histopathological diagnosis, diagnostic precision
- MeSH terms
- Artificial Intelligence, Breast, Breast Neoplasms, Female, Humans, Image Interpretation, Computer-Assisted
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
