Mammographic evidence of microenvironment changes in tumorous breasts

Breast Cancer Molecular Subtype Prediction: A Mammography-Based AI Approach

Breast cancer remains a leading cause of mortality among women, with molecular subtypes significantly influencing prognosis and treatment strategies. Currently, identifying the molecular subtype of cancer requires a biopsy-a specialized, expensive, and time-consuming procedure, often yielding to results that must be supported with additional biopsies due to technique errors or tumor heterogeneity. This study introduces a novel approach for predicting breast cancer molecular subtypes using mammography images and advanced artificial intelligence (AI) methodologies. Using the OPTIMAM imaging database, 1397 images from 660 patients were selected. The pretrained deep learning model ResNet-101 was employed to classify tumors into five subtypes: Luminal A, Luminal B1, Luminal B2, HER2, and Triple Negative. Various classification strategies were studied: binary classifications (one vs. all others, specific combinations) and multi-class classification (evaluating all subtypes simultaneously). To address imbalanced data, strategies like oversampling, undersampling, and data augmentation were explored. Performance was evaluated using accuracy and area under the receiver operating characteristic curve (AUC). Binary classification results showed a maximum average accuracy and AUC of 79.02% and 64.69%, respectively, while multi-class classification achieved an average AUC of 60.62% with oversampling and data augmentation. The most notable binary classification was HER2 vs. non-HER2, with an accuracy of 89.79% and an AUC of 73.31%. Binary classification for specific combinations of subtypes revealed an accuracy of 76.42% for HER2 vs. Luminal A and an AUC of 73.04% for HER2 vs. Luminal B1. These findings highlight the potential of mammography-based AI for non-invasive breast cancer subtype prediction, offering a promising alternative to biopsies and paving the way for personalized treatment plans.

WAVELET-BASED AUTOMATIC PECTORAL MUSCLE SEGMENTATION FOR MAMMOGRAMS

The computational analysis to assist radiologists in the interpretation of mammograms usually requires a pre-processing step where the image is converted into a black and white mask to separate breast tissue from the pectoral muscle and the image background. The manual delineation of the breast tissue from the mammogram image is subjective and time-consuming. The 2D Wavelet Transform Modulus Maxima (WTMM) segmentation method, a powerful and versatile multi-scale edge detection approach, is adapted and presented as a novel automated breast tissue segmentation method. The algorithm computes the local maxima of the modulus of the continuous Gaussian wavelet transform to produce candidate edge detection lines called maxima chains. These maxima chains from multiple wavelet scales are optimally sorted to produce a breast tissue segmentation mask. The mammographic mask is quantitatively compared to a manual delineation using the Dice-Sorenson Coefficient (DSC). The adaptation of the 2D WTMM segmentation method produces a median DSC of 0.9763 on 1042 mediolateral oblique (MLO) 2D Full Field Digital mammographic views from 82 patients obtained from the MaineHealth Biobank (Scarborough, Maine, USA). Our proposed approach is evaluated against OpenBreast , an open-source automated analysis software in MATLAB, through comparing each approach's masks to the manual delineations. OpenBreast produces a lower median DSC of 0.9710. To determine statistical significance, the analysis is restricted to 82 mammograms (one randomly chosen per patient), which yields DSC medians of 0.9756 for the WTMM approach vs. 0.9698 for OpenBreast ( p -value = 0.0067 using a paired Wilcoxon Rank Sum test). Thus, the 2D WTMM segmentation method can reliably delineate the pectoral muscle and produce an accurate segmentation of whole breast tissue in mammograms.

Radiomic Models Predict Tumor Microenvironment Using Artificial Intelligence-the Novel Biomarkers in Breast Cancer Immune Microenvironment

Breast cancer is the most common malignancy in women, and some subtypes are associated with a poor prognosis with a lack of efficacious therapy. Moreover, immunotherapy and the use of other novel antibody‒drug conjugates have been rapidly incorporated into the standard management of advanced breast cancer. To extract more benefit from these therapies, clarifying and monitoring the tumor microenvironment (TME) status is critical, but this is difficult to accomplish based on conventional approaches. Radiomics is a method wherein radiological image features are comprehensively collected and assessed to build connections with disease diagnosis, prognosis, therapy efficacy, the TME, etc In recent years, studies focused on predicting the TME using radiomics have increasingly emerged, most of which demonstrate meaningful results and show better capability than conventional methods in some aspects. Beyond predicting tumor-infiltrating lymphocytes, immunophenotypes, cytokines, infiltrating inflammatory factors, and other stromal components, radiomic models have the potential to provide a completely new approach to deciphering the TME and facilitating tumor management by physicians.

Elimination of Image Saturation Effects on Multifractal Statistics Using the 2D WTMM Method

Imaging artifacts such as image saturation can restrict the computational analysis of medical images. Multifractal analyses are typically restricted to self-affine, everywhere singular, surfaces. Image saturation regions in these rough surfaces rob them of these core properties, and their exclusion decreases the statistical power of clinical analyses. By adapting the powerful 2D Wavelet Transform Modulus Maxima (WTMM) multifractal method, we developed a strategy where the image can be partitioned according to its localized response to saturated regions. By eliminating the contribution from those saturated regions to the partition function calculations, we show that the estimation of the multifractal statistics can be correctly calculated even with image saturation levels up to 20% (where 20% is the number of saturated pixels over the total number of pixels in the image).

A Radiomics Nomogram for Non-Invasive Prediction of Progression-Free Survival in Esophageal Squamous Cell Carcinoma

To construct a prognostic model for preoperative prediction on computed tomography (CT) images of esophageal squamous cell carcinoma (ESCC), we created radiomics signature with high throughput radiomics features extracted from CT images of 272 patients (204 in training and 68 in validation cohort). Multivariable logistic regression was applied to build the radiomics signature and the predictive nomogram model, which was composed of radiomics signature, traditional TNM stage, and clinical features. A total of 21 radiomics features were selected from 954 to build a radiomics signature which was significantly associated with progression-free survival (p < 0.001). The area under the curve of performance was 0.878 (95% CI: 0.831–0.924) for the training cohort and 0.857 (95% CI: 0.767–0.947) for the validation cohort. The radscore of signatures' combination showed significant discrimination for survival status. Radiomics nomogram combined radscore with TNM staging and showed considerable improvement over TNM staging alone in the training cohort (C-index, 0.770 vs. 0.603; p < 0.05), and it is the same with clinical data (C-index, 0.792 vs. 0.680; p < 0.05), which were confirmed in the validation cohort. Decision curve analysis showed that the model would receive a benefit when the threshold probability was between 0 and 0.9. Collectively, multiparametric CT-based radiomics nomograms provided improved prognostic ability in ESCC.

Multiscale anisotropy analysis of second-harmonic generation collagen imaging of mouse skin

SIGNIFICANCE

Morphological collagen signatures are important for tissue function, particularly in the tumor microenvironment. A single algorithmic framework with quantitative, multiscale morphological collagen feature extraction may further the use of collagen signatures in understanding fundamental tumor progression.

AIM

A modification of the 2D wavelet transform modulus maxima (WTMM) anisotropy method was applied to both digitally simulated collagen fibers and second-harmonic-generation imaged collagen fibers of mouse skin to calculate a multiscale anisotropy factor to detect collagen fiber organization.

APPROACH

The modified 2D WTMM anisotropy method was initially validated on synthetic calibration images to establish the robustness and sensitivity of the multiscale fiber organization tool. Upon validation, the algorithm was applied to collagen fiber organization in normal wild-type skin, melanoma stimulated skin, and integrin α10KO skin.

RESULTS

Normal wild-type skin collagen fibers have an increased anisotropy factor at all sizes scales. Interestingly, the multiscale anisotropy differences highlight important dissimilarities between collagen fiber organization in normal wild-type skin, melanoma stimulated, and integrin α10KO skin. At small scales (∼2 to 3  μm), the integrin α10KO skin was vastly different than normal skin (p-value  ∼  10  -  8), whereas the melanoma stimulated skin was vastly different than normal at large scales (∼30 to 40  μm, p-value  ∼  10  -  15).

CONCLUSIONS

This objective computational collagen fiber organization algorithm is sensitive to collagen fiber organization across multiple scales for effective exploration of collagen morphological alterations associated with melanoma and the lack of α10 integrin binding.

Loss of Mammographic Tissue Homeostasis in Invasive Lobular and Ductal Breast Carcinomas vs. Benign Lesions

The 2D wavelet transform modulus maxima (WTMM) method is used to perform a comparison of the spatial fluctuations of mammographic breast tissue from patients with invasive lobular carcinoma, those with invasive ductal carcinoma, and those with benign lesions. We follow a procedure developed and validated in a previous study, in which a sliding window protocol is used to analyze thousands of small subregions in a given mammogram. These subregions are categorized according to their Hurst exponent values (H): fatty tissue (H ≤ 0.45), dense tissue (H ≥ 0.55), and disrupted tissue potentially linked with tumor-associated loss of homeostasis (0.45 < H < 0.55). Following this categorization scheme, we compare the mammographic tissue composition of the breasts. First, we show that cancerous breasts are significantly different than breasts with a benign lesion (p-value ∼ 0.002). Second, the asymmetry between a patient’s cancerous breast and its contralateral counterpart, when compared to the asymmetry from patients with benign lesions, is also statistically significant (p-value ∼ 0.006). And finally, we show that lobular and ductal cancerous breasts show similar levels of disruption and similar levels of asymmetry. This study demonstrates reproducibility of the WTMM sliding-window approach to help detect and characterize tumor-associated breast tissue disruption from standard mammography. It also shows promise to help with the detection lobular lesions that typically go undetected via standard screening mammography at a much higher rate than ductal lesions. Here both types are assessed similarly.

Fuzzy controller design for breast cancer treatment based on fractal dimension using breast thermograms

In this study, three non-linear indices consist of compression, one-dimensional (1D) and two-dimensional (2D) fractal dimensions are used for the determination of the malignancy or benignity of cancer tumours in breast thermograms. On the other hand, by developing the high-precision infrared cameras as well as new methods of image processing, biomedical thermography images have found a prominent position among the others. Furthermore, cancerous tissue can be affected by the laser. In this study, in order to treat the cancerous lesion identified by breast thermograms, the laser parameters are designed. The basis of controller designing is the obtained non-linear indices. If the indices are moved from the chaotic behaviour to normal condition, the treating tissue is going from cancerous to a healthy condition and the treatment process is completed. Radiation frequency and the energy density of laser are designed as two key elements in the cancer treatment. In this study, the type I and type II fuzzy controllers are employed for the control strategies. Using the proposed closed-loop control, the non-linear indices of the cancerous lesion will be reduced during the treatment process. The simulation results on two datasets of breast thermograms indicate the superiority of type II fuzzy controller.

False-positive reduction in computer-aided mass detection using mammographic texture analysis and classification

BACKGROUND AND OBJECTIVE

The aim of computer-aided-detection (CAD) systems for mammograms is to assist radiologists by marking region of interest (ROIs) depicting abnormalities. However, the confusing appearance of some normal tissues that visually look like masses results in a large proportion of marked ROIs with normal tissues. This paper copes with this problem and proposes a framework to reduce false positive masses detected by CAD.

METHODS

To avoid the error induced by the segmentation step, we proposed a segmentation-free framework with particular attention to improve feature extraction and classification steps. We investigated for the first time in mammogram analysis, Hilbert's image representation, Kolmogorov-Smirnov distance and maximum subregion descriptors. Then, a feature selection step is performed to select the most discriminative features. Moreover, we considered several classifiers such as Random Forest, Support Vector Machine and Decision Tree to distinguish between normal tissues and masses. Our experiments were carried out on a large dataset of 10168 ROIs (8254 normal tissues and 1914 masses) constructed from the Digital Database for Screening Mammography (DDSM). To simulate practical scenario, our normal regions are false positives asserted by a CAD system from healthy cases.

RESULTS

The combination of all the descriptors yields better results than each feature set used alone, and the difference is statistically significant. Besides, the feature selection steps yields a statistically significant increase in the accuracy values for the three classifiers. Finally, the random forest achieves the highest accuracy (81.09%), outperforming the SVM classifier (80.01%)) and decision tree (79.12%), but the difference is not statistically significant.

CONCLUSIONS

The accuracy of discrimination between normal and abnormal ROIs in mammograms obtained with the proposed gray level texture features sets are encouraging and comparable to these obtained with multiresolution features. Combination of several features as well as feature selection steps improve the results. To improve false positives reduction in CAD systems for breast cancer diagnosis, these features could be combined with multiresolution features.

Multifractal Desynchronization of the Cardiac Excitable Cell Network During Atrial Fibrillation. I. Multifractal Analysis of Clinical Data

Atrial fibrillation (AF) is a cardiac arrhythmia characterized by rapid and irregular atrial electrical activity with a high clinical impact on stroke incidence. Best available therapeutic strategies combine pharmacological and surgical means. But when successful, they do not always prevent long-term relapses. Initial success becomes all the more tricky to achieve as the arrhythmia maintains itself and the pathology evolves into sustained or chronic AF. This raises the open crucial issue of deciphering the mechanisms that govern the onset of AF as well as its perpetuation. In this study, we develop a wavelet-based multi-scale strategy to analyze the electrical activity of human hearts recorded by catheter electrodes, positioned in the coronary sinus (CS), during episodes of AF. We compute the so-called multifractal spectra using two variants of the wavelet transform modulus maxima method, the moment (partition function) method and the magnitude cumulant method. Application of these methods to long time series recorded in a patient with chronic AF provides quantitative evidence of the multifractal intermittent nature of the electric energy of passing cardiac impulses at low frequencies, i.e., for times (≳0.5 s) longer than the mean interbeat (≃ 10-1 s). We also report the results of a two-point magnitude correlation analysis which infers the absence of a multiplicative time-scale structure underlying multifractal scaling. The electric energy dynamics looks like a "multifractal white noise" with quadratic (log-normal) multifractal spectra. These observations challenge concepts of functional reentrant circuits in mechanistic theories of AF, still leaving open the role of the autonomic nervous system (ANS). A transition is indeed observed in the computed multifractal spectra which group according to two distinct areas, consistently with the anatomical substrate binding to the CS, namely the left atrial posterior wall, and the ligament of Marshall which is innervated by the ANS. In a companion paper (II. Modeling), we propose a mathematical model of a denervated heart where the kinetics of gap junction conductance alone induces a desynchronization of the myocardial excitable cells, accounting for the multifractal spectra found experimentally in the left atrial posterior wall area.

Radiomics Based on Adapted Diffusion Kurtosis Imaging Helps to Clarify Most Mammographic Findings Suspicious for Cancer

Purpose To evaluate a radiomics model of Breast Imaging Reporting and Data System (BI-RADS) 4 and 5 breast lesions extracted from breast-tissue-optimized kurtosis magnetic resonance (MR) imaging for lesion characterization by using a sensitivity threshold similar to that of biopsy. Materials and Methods This institutional study included 222 women at two independent study sites (site 1: training set of 95 patients; mean age ± standard deviation, 58.6 years ± 6.6; 61 malignant and 34 benign lesions; site 2: independent test set of 127 patients; mean age, 58.2 years ± 6.8; 61 malignant and 66 benign lesions). All women presented with a finding suspicious for cancer at x-ray mammography (BI-RADS 4 or 5) and an indication for biopsy. Before biopsy, diffusion-weighted MR imaging (b values, 0-1500 sec/mm²) was performed by using 1.5-T imagers from different MR imaging vendors. Lesions were segmented and voxel-based kurtosis fitting adapted to account for fat signal contamination was performed. A radiomics feature model was developed by using a random forest regressor. The fixed model was tested on an independent test set. Conventional interpretations of MR imaging were also assessed for comparison. Results The radiomics feature model reduced false-positive results from 66 to 20 (specificity 70.0% [46 of 66]) at the predefined sensitivity of greater than 98.0% [60 of 61] in the independent test set, with BI-RADS 4a and 4b lesions benefiting from the analysis (specificity 74.0%, [37 of 50]; 60.0% [nine of 15]) and BI-RADS 5 lesions showing no added benefit. The model significantly improved specificity compared with the median apparent diffusion coefficient (P < .001) and apparent kurtosis coefficient (P = .02) alone. Conventional reading of dynamic contrast material-enhanced MR imaging provided sensitivity of 91.8% (56 of 61) and a specificity of 74.2% (49 of 66). Accounting for fat signal intensity during fitting significantly improved the area under the curve of the model (P = .001). Conclusion A radiomics model based on kurtosis diffusion-weighted imaging performed by using MR imaging machines from different vendors allowed for reliable differentiation between malignant and benign breast lesions in both a training and an independent test data set. ^© RSNA, 2018 Online supplemental material is available for this article.

Rapid review: radiomics and breast cancer

PURPOSE

To perform a rapid review of the recent literature on radiomics and breast cancer (BC).

METHODS

A rapid review, a streamlined approach to systematically identify and summarize emerging studies was done (updated 27 September 2017). Clinical studies eligible for inclusion were those that evaluated BC using a radiomics approach and provided data on BC diagnosis (detection or characterization) or BC prognosis (response to therapy, morbidity, mortality), or provided data on technical challenges (software application: open source, repeatability of results). Descriptive statistics, results, and radiomics quality score (RQS) are presented.

RESULTS

N = 17 retrospective studies, all published after 2015, provided BC-related radiomics data on 3928 patients evaluated with a radiomics approach. Most studies were done for diagnosis and/or characterization (65%, 11/17) or to aid in prognosis (41%, 7/17). The mean number of radiomics features considered was 100. Mean RQS score was 11.88 ± 5.8 (maximum value 36). The RQS criteria related to validation, gold standard, potential clinical utility, cost analysis, and open science data had the lowest scores. The majority of studies n = 16/17 (94%) provided correlation with histological outcomes and staging variables or biomarkers. Only 4/17 (23%) studies provided evidence of correlation with genomic data. Magnetic resonance imaging (MRI) was used in most studies n = 14/17 (82%); however, ultrasound (US), mammography, or positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro-D-glucose integrated with computed tomography (18F FDG PET/CT) was also used. Much heterogeneity was found for software usage.

CONCLUSIONS

The study of radiomics in BC patients is a new and emerging translational research topic. Radiomics in BC is frequently done to potentially improve diagnosis and characterization, mostly using MRI. Substantial quality limitations were found; high-quality prospective and reproducible studies are needed to further potential application.

Wavelet-based tracking of bacteria in unreconstructed off-axis holograms

We propose an automated wavelet-based method of tracking particles in unreconstructed off-axis holograms to provide rough estimates of the presence of motion and particle trajectories in digital holographic microscopy (DHM) time series. The wavelet transform modulus maxima segmentation method is adapted and tailored to extract Airy-like diffraction disks, which represent bacteria, from DHM time series. In this exploratory analysis, the method shows potential for estimating bacterial tracks in low-particle-density time series, based on a preliminary analysis of both living and dead Serratia marcescens, and for rapidly providing a single-bit answer to whether a sample chamber contains living or dead microbes or is empty.