s ?gnised types or, as we should prefer to call them, genera, ^Cles and varieties of tumours. In carrying out this project, \\ve Particularly when making out the series of indexes that e required, we soon made acquaintance with difficulties of enclature and of classification. These difficulties occur 0Ve?*t daily in the course of routine examinations and are th^00.1116 or evaded in varying fashion. It may be argued cl \\ln the present state of our knowledge, a satisfactory j^Slficati?n of tumours is not possible, or that it is easy to Co^ e Ossifications from an armchair for one who is not deeply p0j^erned in using them. But those remarks seem to miss the

Classification of Tumours.

Machine-learning techniques have led to remarkable advances in data extraction and analysis of medical imaging. Applications of machine learning to breast MRI continue to expand rapidly as increasingly accurate 3D breast and lesion segmentation allows the combination of radiologist-level interpretation (eg, BI-RADS lexicon), data from advanced multiparametric imaging techniques, and patient-level data such as genetic risk markers. Advances in breast MRI feature extraction have led to rapid dataset analysis, which offers promise in large pooled multiinstitutional data analysis. The object of this review is to provide an overview of machine-learning and deep-learning techniques for breast MRI, including supervised and unsupervised methods, anatomic breast segmentation, and lesion segmentation. Finally, it explores the role of machine learning, current limitations, and future applications to texture analysis, radiomics, and radiogenomics. Level of Evidence: 3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019. J. Magn. Reson. Imaging 2020;52:998-1018.

Machine learning in breast MRI.

Breast cancer is a known heterogeneous disease. Current clinically utilized histopathologic biomarkers may undersample tumor heterogeneity, resulting in higher rates of misdiagnosis for breast cancer. MRI can provide a whole-tumor sampling of disease burden and is widely utilized in clinical care. Texture analysis can provide a localized description of breast cancer, with particular emphasis on quantifying breast lesion heterogeneity. The object of this review is to provide an overview of texture analysis applications towards breast cancer diagnosis, prognosis, and treatment response evaluation and review the role of image-based texture features as noninvasive prognostic and predictive biomarkers. Level of Evidence: 5 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:927-938.

Role of texture analysis in breast MRI as a cancer biomarker: A review

Machine Learning in oncology: A clinical appraisal.

To evaluate the diagnostic performance of radiomic signatures extracted from contrast-enhanced magnetic resonance imaging (CE-MRI) for the assessment of breast cancer receptor status and molecular subtypes. One hundred and forty-three patients with biopsy-proven breast cancer who underwent CE-MRI at 3 T were included in this IRB-approved HIPAA-compliant retrospective study. The training dataset comprised 91 patients (luminal A, n = 49; luminal B, n = 8; HER2-enriched, n = 11; triple negative, n = 23), while the validation dataset comprised 52 patients from a second institution (luminal A, n = 17; luminal B, n = 17; triple negative, n = 18). Radiomic analysis of manually segmented tumors included calculation of features derived from the first-order histogram (HIS), co-occurrence matrix (COM), run-length matrix (RLM), absolute gradient (GRA), autoregressive model (ARM), discrete Haar wavelet transform (WAV), and lesion geometry (GEO). Fisher, probability of error and average correlation (POE + ACC), and mutual information coefficients were used for feature selection. Linear discriminant analysis followed by k-nearest neighbor classification (with leave-one-out cross-validation) was used for pairwise radiomic-based separation of receptor status and molecular subtypes. Histopathology served as the standard of reference. In the training dataset, radiomic signatures yielded the following accuracies > 80%: luminal B vs. luminal A, 84.2% (mainly based on COM features); luminal B vs. triple negative, 83.9% (mainly based on GEO features); luminal B vs. all others, 89% (mainly based on COM features); and HER2-enriched vs. all others, 81.3% (mainly based on COM features). Radiomic signatures were successfully validated in the separate validation dataset for luminal A vs. luminal B (79.4%) and luminal B vs. triple negative (77.1%). In this preliminary study, radiomic signatures with CE-MRI enable the assessment of breast cancer receptor status and molecular subtypes with high diagnostic accuracy. These results need to be confirmed in future larger studies.

/pdf/radiomic-signatures-with-contrast-enhanced-magnetic-7w958rca5w.pdf

Radiomic signatures with contrast-enhanced magnetic resonance imaging for the assessment of breast cancer receptor status and molecular subtypes: initial results.

The aim of this study was to use texture analysis (TA) of breast magnetic resonance (MR) images to assist in differentiating estrogen receptor (ER) positive breast cancer molecular subtypes. Twenty-seven patients with histopathologically proven invasive ductal breast cancer were selected in preliminary study. Tumors were classified into molecular subtypes: luminal A (ER-positive and/or progesterone receptor (PR)-positive, human epidermal growth factor receptor type 2 (HER2) -negative, proliferation marker Ki-67 < 20 and low grade (I)) and luminal B (ER-positive and/or PR-positive, HER2-positive or HER2-negative with high Ki-67 ≥ 20 and higher grade (II or III)). Co-occurrence matrix -based texture features were extracted from each tumor on T1-weighted non fat saturated pre- and postcontrast MR images using TA software MaZda. Texture parameters and tumour volumes were correlated with tumour prognostic factors. Textural differences were observed mainly in precontrast images. The two most discriminative texture parameters to differentiate luminal A and luminal B subtypes were sum entropy and sum variance (p = 0.003). The AUCs were 0.828 for sum entropy (p = 0.004), and 0.833 for sum variance (p = 0.003), and 0.878 for the model combining texture features sum entropy, sum variance (p = 0.001). In the LOOCV, the AUC for model combining features sum entropy and sum variance was 0.876. Sum entropy and sum variance showed positive correlation with higher Ki-67 index. Luminal B types were larger in volume and moderate correlation between larger tumour volume and higher Ki-67 index was also observed (r = 0.499, p = 0.008). Texture features which measure randomness, heterogeneity or smoothness and homogeneity may either directly or indirectly reflect underlying growth patterns of breast tumours. TA and volumetric analysis may provide a way to evaluate the biologic aggressiveness of breast tumours and provide aid in decisions regarding therapeutic efficacy.

MRI texture analysis in differentiating luminal A and luminal B breast cancer molecular subtypes - a feasibility study

Progressive hemifacial atrophy (PHA) is characterized by slow and progressive atrophy usually of one side of the face. PHA affects primarily the subcutaneous fat and muscle tissues, but may involve the bone. The cause is unknown. The treatment is symptomatic and directed at augmentation of the deficient soft-tissue volume. The reconstructive procedures may combine fat grafts, dermis fat grafts, pedicle flaps, bone grafts, microvascular free flaps, and alloplastic implants. We report a patient with of PHA whose condition was treated with a free latissimus dorsi (LD) perforator flap. The LD perforator flap was suitable for the large defect of the patient. It could easily be tailored and thinned to follow the facial contour. Minor revisions were needed for esthetic reasons. There was neither significant downward gravitation nor wasting of the flap. 23 months later, the natural appearance of the face was maintained. © 2007 Wiley-Liss, Inc. Microsurgery, 2007.

Free latissimus dorsi perforator flap for reconstruction of hemifacial atrophy: Case report

Background and Aims:Preoperative magnetic resonance imaging has become an important complementary imaging technique in patients with breast cancer, providing additional information for preoperative local staging. Magnetic resonance imaging is recommended selectively in lobular breast cancer and in patients with dense breast tissue in the case when mammography and ultrasound fail to fully evaluate the lesion, but the routine use of magnetic resonance imaging in all patients with invasive ductal carcinoma is controversial. The purpose of this randomized study was to investigate the diagnostic value of preoperative magnetic resonance imaging and its impact on short-term surgical outcome in newly diagnosed unifocal stage I invasive ductal carcinoma.Material and Methods:A total of 100 patients were randomized to either receive preoperative breast magnetic resonance imaging or to be scheduled directly to operation without magnetic resonance imaging on a 1:1 basis. There were 50 patients in both study arms.Resul...

https://journals.sagepub.com/doi/pdf/10.1177/1457496917701669

Preoperative Magnetic Resonance Imaging in Patients With Stage I Invasive Ductal Breast Cancer: A Prospective Randomized Study.

The major lactiferous ducts of the human breast branch out and ultimately end at terminal ductal lobular units (TDLUs). These glandular structures are the source of milk upon lactation, and also the most common origin of breast cancer. Despite their functional and clinical importance, the three dimensional (3D) architecture of TDLUs has remained undetermined, largely due to their absence in rodent animal models. By utilizing recent technological advances in optical tissue clearing and microscopy, we imaged the 3D structure of healthy human breast tissue to determine whether general branching patterns or cell type specific niches exist in the TDLU. Our data demonstrate that TDLUs have a consistent shape and their branch parameters are largely comparable between different TDLUs and individuals irrespective of age or parity. Simulation of TDLU branching morphogenesis in 3D by mathematical modelling suggests that evolutionarily conserved mechanisms regulate mammary gland branching in humans and mice, despite their anatomical differences. The data also demonstrate a new level of organization within the TDLU structure identifying a main branch that dominates in bifurcation events and exhibits a more duct-like keratin expression pattern. In all, our data provide the first structural insights into 3D human breast anatomy and branching, and exemplify the power of volumetric imaging in deeper understanding of human breast biology. Graphical Abstract

/pdf/morphometric-analysis-of-the-terminal-ductal-lobular-unit-3d2102co.pdf

Nina M. Brück

Papers

MRI texture analysis in differentiating luminal A and luminal B breast cancer molecular subtypes - a feasibility study

Free latissimus dorsi perforator flap for reconstruction of hemifacial atrophy: Case report

Preoperative Magnetic Resonance Imaging in Patients With Stage I Invasive Ductal Breast Cancer: A Prospective Randomized Study.

Morphometric analysis of the terminal ductal lobular unit architecture in human breast