Improvement of microcalcification cluster detection in mammography utilizing image enhancement techniques

All you need is data preparation: A systematic review of image harmonization techniques in Multi-center/device studies for medical support systems

BACKGROUND AND OBJECTIVES

Artificial intelligence (AI) models trained on multi-centric and multi-device studies can provide more robust insights and research findings compared to single-center studies. However, variability in acquisition protocols and equipment can introduce inconsistencies that hamper the effective pooling of multi-source datasets. This systematic review evaluates strategies for image harmonization, which standardizes appearances to enable reliable AI analysis of multi-source medical imaging.

METHODS

A literature search using PRISMA guidelines was conducted to identify relevant papers published between 2013 and 2023 analyzing multi-centric and multi-device medical imaging studies that utilized image harmonization approaches.

RESULTS

Common image harmonization techniques included grayscale normalization (improving classification accuracy by up to 24.42 %), resampling (increasing the percentage of robust radiomics features from 59.5 % to 89.25 %), and color normalization (enhancing AUC by up to 0.25 in external test sets). Initially, mathematical and statistical methods dominated, but machine and deep learning adoption has risen recently. Color imaging modalities like digital pathology and dermatology have remained prominent application areas, though harmonization efforts have expanded to diverse fields including radiology, nuclear medicine, and ultrasound imaging. In all the modalities covered by this review, image harmonization improved AI performance, with increasing of up to 24.42 % in classification accuracy and 47 % in segmentation Dice scores.

CONCLUSIONS

Continued progress in image harmonization represents a promising strategy for advancing healthcare by enabling large-scale, reliable analysis of integrated multi-source datasets using AI. Standardizing imaging data across clinical settings can help realize personalized, evidence-based care supported by data-driven technologies while mitigating biases associated with specific populations or acquisition protocols.

Deep Learning Capabilities for the Categorization of Microcalcification

Breast cancer is the most common cancer in women worldwide. It is the most frequently diagnosed cancer among women in 140 countries out of 184 reporting countries. Lesions of breast cancer are abnormal areas in the breast tissues. Various types of breast cancer lesions include (1) microcalcifications, (2) masses, (3) architectural distortion, and (4) bilateral asymmetry. Microcalcification can be classified as benign, malignant, and benign without a callback. In the present manuscript, we propose an automatic pipeline for the detection of various categories of microcalcification. We performed deep learning using convolution neural networks (CNNs) for the automatic detection and classification of all three categories of microcalcification. CNN was applied using four different optimizers (ADAM, ADAGrad, ADADelta, and RMSProp). The input images of a size of 299 × 299 × 3, with fully connected RELU and SoftMax output activation functions, were utilized in this study. The feature map was obtained using the pretrained InceptionResNetV2 model. The performance evaluation of our classification scheme was tested on a curated breast imaging subset of the DDSM mammogram dataset (CBIS–DDSM), and the results were expressed in terms of sensitivity, specificity, accuracy, and area under the curve (AUC). Our proposed classification scheme outperforms the ability of previously used deep learning approaches and classical machine learning schemes.

Deep learning-based breast region extraction of mammographic images combining pre-processing methods and semantic segmentation supported by Deeplab v3+

BACKGROUND: Breast cancer has long been one of the major global life-threatening illnesses among women. Surgery and adjuvant therapy, coupled with early detection, could save many lives. This underscores the importance of mammography, a cost-effective and accurate method for early detection. Due to the poor contrast, noise and artifacts which results in difficulty for radiologists to diagnose, Computer-Aided Diagnosis (CAD) systems are hence developed. The extraction of breast region is a fundamental and crucial preparation step for further development of CAD systems. OBJECTIVE: The proposed method aims to extract breast region accurately from mammographic images where noise is suppressed, contrast is enhanced and pectoral muscle region is removed. METHODS: This paper presents a new deep learning-based breast region extraction method that combines pre-processing methods containing noise suppression using median filter, contrast enhancement using CLAHE and semantic segmentation using Deeplab v3+ model. RESULTS: The method is trained and evaluated on mini-MIAS dataset. It has also been evaluated on INbreast dataset. The results outperform those generated by other recent researches and are indicative of the capacity of the model to retain its accuracy and runtime advantage across different databases with different image resolutions. CONCLUSIONS: The proposed method shows state-of-the-art performance at extracting breast region from mammographic images. Wide range of evaluation on two commonly used mammography datasets proves the ability and adaptability of the method.

Digital Mammograms with Image Enhancement Techniques for Breast Cancer Detection: A Systematic Review

BACKGROUND

Digital mammograms with appropriate image enhancement techniques will improve breast cancer detection, and thus increase the survival rates. The objectives of this study were to systematically review and compare various image enhancement techniques in digital mammograms for breast cancer detection.

METHODS

A literature search was conducted with the use of three online databases namely, Web of Science, Scopus, and ScienceDirect. Developed keywords strategy was used to include only the relevant articles. A Population Intervention Comparison Outcomes (PICO) strategy was used to develop the inclusion and exclusion criteria. Image quality was analyzed quantitatively based on peak signal-noise-ratio (PSNR), Mean Squared Error (MSE), Absolute Mean Brightness Error (AMBE), Entropy, and Contrast Improvement Index (CII) values.

RESULTS

Nine studies with four types of image enhancement techniques were included in this study. Two studies used histogram-based, three studies used frequency-based, one study used fuzzy-based and three studies used filter-based. All studies reported PSNR values whilst only four studies reported MSE, AMBE, Entropy and CII values. Filter-based was the highest PSNR values of 78.93, among other types. For MSE, AMBE, Entropy, and CII values, the highest were frequency-based (7.79), fuzzy-based (93.76), filter-based (7.92), and frequency-based (6.54) respectively.

CONCLUSION

In summary, image quality for each image enhancement technique is varied, especially for breast cancer detection. In this study, the frequency-based of Fast Discrete Curvelet Transform (FDCT) via the UnequiSpaced Fast Fourier Transform (USFFT) shows the most superior among other image enhancement techniques.

A Screening CAD Tool for the Detection of Microcalcification Clusters in Mammograms

Breast cancer is the most common cancer diagnosed in women worldwide. Up to 50% of non-palpable breast cancers are detected solely through microcalcification clusters in mammograms. This article presents a novel and completely automated algorithm for the detection of microcalcification clusters in a mammogram. A multiscale 2D non-linear energy operator is proposed for enhancing the contrast between the microcalcifications and the background. Several texture, shape, intensity, and histogram of oriented gradients (HOG)-based features are used to distinguish microcalcifications from other brighter mammogram regions. A new majority class data reduction technique based on data distribution is proposed to counter data imbalance problem. The algorithm is able to achieve 100% sensitivity with 2.59, 1.78, and 0.68 average false positives per image on Digital Database for Screening Mammography (scanned film), INbreast (direct radiography) database, and PGIMER-IITKGP mammogram (direct radiography) database, respectively. Thus, it might be used as a second reader as well as a screening tool to reduce the burden on radiologists.

An adaptive enhancement method for breast X-ray images based on the nonsubsampled contourlet transform domain and whale optimization algorithm

We propose a new method for breast X-ray image adaptive enhancement that combines nonsubsampled contourlet transform (NSCT) with the whale optimization algorithm (WOA). First, the mammography X-ray image was processed by histogram equalization to ensure global image contrast. The processed image was then decomposed into three layers in the NSCT domain. Each layer was each decomposed into two, four, and eight directions. A median filter was used to remove noise in the first and second layers. Then, a special edge filter was adopted to enhance each sub-band image, and two parameters are involved. WOA is used to automatically search the optimal two parameters. Blind image quality index (BIQI) adaptive function was used as an objective function of WOA. Then, inverse NSCT was employed to reconstruct the processed image, generating the final adaptive enhancement image. The digital database for screening mammography (DDSM) was used to verify the performance of the proposed method. Five objective evaluation indexes, including information entropy, average gradient, standard deviation, contrast improvement index (CII), and BIQI, are combined together to construct a new comprehensive index to evaluate the visual quality of the enhanced image. The results show that the proposed method has a good enhancement effect for mammography X-ray images. The overall performance of the proposed method is better than some existing similar methods. Graphical abstract .

A New Feature Ensemble with a Multistage Classification Scheme for Breast Cancer Diagnosis

A new and effective feature ensemble with a multistage classification is proposed to be implemented in a computer-aided diagnosis (CAD) system for breast cancer diagnosis. A publicly available mammogram image dataset collected during the Image Retrieval in Medical Applications (IRMA) project is utilized to verify the suggested feature ensemble and multistage classification. In achieving the CAD system, feature extraction is performed on the mammogram region of interest (ROI) images which are preprocessed by applying a histogram equalization followed by a nonlocal means filtering. The proposed feature ensemble is formed by concatenating the local configuration pattern-based, statistical, and frequency domain features. The classification process of these features is implemented in three cases: a one-stage study, a two-stage study, and a three-stage study. Eight well-known classifiers are used in all cases of this multistage classification scheme. Additionally, the results of the classifiers that provide the top three performances are combined via a majority voting technique to improve the recognition accuracy on both two- and three-stage studies. A maximum of 85.47%, 88.79%, and 93.52% classification accuracies are attained by the one-, two-, and three-stage studies, respectively. The proposed multistage classification scheme is more effective than the single-stage classification for breast cancer diagnosis.

Automatic intensity windowing of mammographic images based on a perceptual metric

PURPOSE

Initial auto-adjustment of the window level WL and width WW applied to mammographic images. The proposed intensity windowing (IW) method is based on the maximization of the mutual information (MI) between a perceptual decomposition of the original 12-bit sources and their screen displayed 8-bit version. Besides zoom, color inversion and panning operations, IW is the most commonly performed task in daily screening and has a direct impact on diagnosis and the time involved in the process.

METHODS

The authors present a human visual system and perception-based algorithm named GRAIL (Gabor-relying adjustment of image levels). GRAIL initially measures a mammogram's quality based on the MI between the original instance and its Gabor-filtered derivations. From this point on, the algorithm performs an automatic intensity windowing process that outputs the WL/WW that best displays each mammogram for screening. GRAIL starts with the default, high contrast, wide dynamic range 12-bit data, and then maximizes the graphical information presented in ordinary 8-bit displays. Tests have been carried out with several mammogram databases. They comprise correlations and an ANOVA analysis with the manual IW levels established by a group of radiologists. A complete MATLAB implementation of GRAIL is available at https://github.com/TheAnswerIsFortyTwo/GRAIL.

RESULTS

Auto-leveled images show superior quality both perceptually and objectively compared to their full intensity range and compared to the application of other common methods like global contrast stretching (GCS). The correlations between the human determined intensity values and the ones estimated by our method surpass that of GCS. The ANOVA analysis with the upper intensity thresholds also reveals a similar outcome. GRAIL has also proven to specially perform better with images that contain micro-calcifications and/or foreign X-ray-opaque elements and with healthy BI-RADS A-type mammograms. It can also speed up the initial screening time by a mean of 4.5 s per image.

CONCLUSIONS

A novel methodology is introduced that enables a quality-driven balancing of the WL/WW of mammographic images. This correction seeks the representation that maximizes the amount of graphical information contained in each image. The presented technique can contribute to the diagnosis and the overall efficiency of the breast screening session by suggesting, at the beginning, an optimal and customized windowing setting for each mammogram.

Mammogram Enhancement Using Intuitionistic Fuzzy Sets

OBJECTIVE

Conventional mammogram enhancement methods use transform-domain filtering, which possibly produce some artifacts or not well highlight all local details in images. This paper presents a new enhancement method based on intuitionistic fuzzy sets.

METHODS

The presented algorithm initially separates a mammogram via a global threshold and then fuzzifies the image utilizing the intuitionistic fuzzy membership function that adopts restricted equivalence functions. After that, the presented scheme hyperbolizes membership degrees of foreground and background areas, defuzzifies the fuzzy plane, and achieves a filtered image via normalization. Finally, an enhanced mammogram is obtained by fusing the original image with filtered one. These implementations can be processed in parallel.

RESULTS

This algorithm can improve the contrast and visual quality of regions of interest.

CONCLUSION

Real data experiments demonstrate that our method has better performance regarding the improvement of contrast and visual quality of abnormalities in mammograms (such as masses and/or microcalcifications), compared with classical baseline methods.

SIGNIFICANCE

This algorithm has potential for understanding and determining abnormalities.

Mining Breast Cancer Classification Rules from Mammograms

Breast cancer is a leading cause of cancer death in women. Early diagnosis and treatment are crucial to reduce the mortality rate and increase patients’ lifespan. Mammography is effective in early detection. This study proposes a computer-aided diagnosis system based on the mini-Mammographic Image Analysis Society database for analyzing mammograms. After selecting the regions of interest, we computed three typical features: the shape, spatial, and spectral domain features. We then applied the structural equation model to obtain relations between the features and the breast tissue type, lesion class, and tumor severity after feature extraction by information gain. Finally, we used the decision tree and classification and regression tree to construct computer-aided diagnosis rules; we generated 10 rules for predicting the classification of abnormal lesions and 11 rules for classifying the tumor severity. These rules can help clinicians detect and identify breast cancer efficiency from mammograms and improve medical care quality.

A Novel Cascade Classifier for Automatic Microcalcification Detection

In this paper, we present a novel cascaded classification framework for automatic detection of individual and clusters of microcalcifications (μC). Our framework comprises three classification stages: i) a random forest (RF) classifier for simple features capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated; ii) a more complex discriminative restricted Boltzmann machine (DRBM) classifier for μC candidates determined in the RF stage, which automatically learns the detailed morphology of μC appearances for improved discriminative power; and iii) a detector to detect clusters of μCs from the individual μC detection results, using two different criteria. From the two-stage RF-DRBM classifier, we are able to distinguish μCs using explicitly computed features, as well as learn implicit features that are able to further discriminate between confusing cases. Experimental evaluation is conducted on the original Mammographic Image Analysis Society (MIAS) and mini-MIAS databases, as well as our own Seoul National University Bundang Hospital digital mammographic database. It is shown that the proposed method outperforms comparable methods in terms of receiver operating characteristic (ROC) and precision-recall curves for detection of individual μCs and free-response receiver operating characteristic (FROC) curve for detection of clustered μCs.

Automatic detection of abnormalities in mammograms

Background

In recent years, an increased interest has been seen in the area of medical image processing and, as a consequence, Computer Aided Diagnostic (CAD) systems. The basic purpose of CAD systems is to assist doctors in the process of diagnosis. CAD systems, however, are quite expensive, especially, in most of the developing countries. Our focus is on developing a low-cost CAD system. Today, most of the CAD systems regarding mammogram classification target automatic detection of calcification and abnormal mass. Calcification normally indicates an early symptom of breast cancer if it appears as a small size bright spot in a mammogram image.

Methods

Based on the observation that calcification appears as small bright spots on a mammogram image, we propose a new scale-specific blob detection technique in which the scale is selected through supervised learning. By computing energy for each pixel at two different scales, a new feature “Ratio Energy” is introduced for efficient blob detection. Due to the imposed simplicity of the feature and post processing, the running time of our algorithm is linear with respect to image size.

Results

Two major types of calcification, microcalcification and macrocalcification have been identified and highlighted by drawing a circular boundary outside the area that contains calcification. Results are quite visible and satisfactory, and the radiologists can easily view results through the final detected boundary.

Conclusions

CAD systems are designed to help radiologists in verifying their diagnostics. A new way of identifying calcification is proposed based on the property that microcalcification is small in size and appears in clusters. Results are quite visible and encouraging, and can assist radiologists in early detection of breast cancer.

Machine learning applications in cancer prognosis and prediction

Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The importance of classifying cancer patients into high or low risk groups has led many research teams, from the biomedical and the bioinformatics field, to study the application of machine learning (ML) methods. Therefore, these techniques have been utilized as an aim to model the progression and treatment of cancerous conditions. In addition, the ability of ML tools to detect key features from complex datasets reveals their importance. A variety of these techniques, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Support Vector Machines (SVMs) and Decision Trees (DTs) have been widely applied in cancer research for the development of predictive models, resulting in effective and accurate decision making. Even though it is evident that the use of ML methods can improve our understanding of cancer progression, an appropriate level of validation is needed in order for these methods to be considered in the everyday clinical practice. In this work, we present a review of recent ML approaches employed in the modeling of cancer progression. The predictive models discussed here are based on various supervised ML techniques as well as on different input features and data samples. Given the growing trend on the application of ML methods in cancer research, we present here the most recent publications that employ these techniques as an aim to model cancer risk or patient outcomes.

Breast peripheral area correction in digital mammograms

Digital mammograms may present an overexposed area in the peripheral part of the breast, which is visually shown as a darker area with lower contrast. This has a direct impact on image quality and affects image visualisation and assessment. This paper presents an automatic method to enhance the overexposed peripheral breast area providing a more homogeneous and improved view of the whole mammogram. The method automatically restores the overexposed area by equalising the image using information from the intensity of non-overexposed neighbour pixels. The correction is based on a multiplicative model and on the computation of the distance map from the breast boundary. A total of 334 digital mammograms were used for evaluation. Mammograms before and after enhancement were evaluated by an expert using visual comparison. In 90.42% of the cases, the enhancement obtained improved visualisation compared to the original image in terms of contrast and detail. Moreover, results show that lesions found in the peripheral area after enhancement presented a more homogeneous intensity distribution. Hence, peripheral enhancement is shown to improve visualisation and will play a role in further development of CAD systems in mammography.

Improving image quality in medical images using a combined method of undecimated wavelet transform and wavelet coefficient mapping

We propose a method for improving image quality in medical images by using a wavelet-based approach. The proposed method integrates two components: image denoising and image enhancement. In the first component, a modified undecimated discrete wavelet transform is used to eliminate the noise. In the second component, a wavelet coefficient mapping function is applied to enhance the contrast of denoised images obtained from the first component. This methodology can be used not only as a means for improving visual quality of medical images but also as a preprocessing module for computer-aided detection/diagnosis systems to improve the performance of screening and detecting regions of interest in images. To confirm its superiority over existing state-of-the-art methods, the proposed method is experimentally evaluated via 30 mammograms and 20 chest radiographs. It is demonstrated that the proposed method can further improve the image quality of mammograms and chest radiographs, as compared to two other methods in the literature. These results reveal the effectiveness and superiority of the proposed method.

Mammographic image denoising and enhancement using the Anscombe transformation, adaptive wiener filtering, and the modulation transfer function

A new restoration methodology is proposed to enhance mammographic images through the improvement of contrast features and the simultaneous suppression of noise. Denoising is performed in the first step using the Anscombe transformation to convert the signal-dependent quantum noise into an approximately signal-independent Gaussian additive noise. In the Anscombe domain, noise is filtered through an adaptive Wiener filter, whose parameters are obtained by considering local image statistics. In the second step, a filter based on the modulation transfer function of the imaging system in the whole radiation field is applied for image enhancement. This methodology can be used as a preprocessing module for computer-aided detection (CAD) systems to improve the performance of breast cancer screening. A preliminary assessment of the restoration algorithm was performed using synthetic images with different levels of quantum noise. Afterward, we evaluated the effect of the preprocessing on the performance of a previously developed CAD system for clustered microcalcification detection in mammographic images. The results from the synthetic images showed an increase of up to 11.5 dB (p = 0.002) in the peak signal-to-noise ratio. Moreover, the mean structural similarity index increased up to 8.3 % (p < 0.001). Regarding CAD performance, the results suggested that the preprocessing increased the detectability of microcalcifications in mammographic images without increasing the false-positive rates. Receiver operating characteristic analysis revealed an average increase of 14.1 % (p = 0.01) in overall CAD performance when restored image sets were used.

Accuracy and repeatability of computer aided cervical vertebra landmarking in cephalogram

The accuracy and repeatability of computer aided cervical vertebra landmarking (CACVL) were investigated in cephalogram. 120 adolescents (60 boys, 60 girls) aged from 9.1 to 17.2 years old were randomly selected. Twenty-seven landmarks from the second to fifth cervical vertebrae on the lateral cephalogram were identified. In this study, the system of CACVL was developed and used to identify and calculate the landmarks by fast marching method and parabolic curve fitting. The accuracy and repeatability in CACVL group were compared with those in two manual landmarking groups [orthodontic experts (OE) group and orthodontic novices (ON) group]. The results showed that, as for the accuracy, there was no significant difference between CACVL group and OE group no matter in x-axis or y-axis (P>0.05), but there was significant difference between CACVL group and ON group, as well as OE group and ON group in both axes (P<0.05). As for the repeatability, CACVL group was more reliable than OE group and ON group in both axes. It is concluded that CACVL has the same or higher accuracy, better repeatability and less workload than manual landmarking methods. It's reliable for cervical parameters identification on the lateral cephalogram and cervical vertebral maturation prediction in orthodontic practice and research.

An automated blood vessel segmentation algorithm using histogram equalization and automatic threshold selection

This paper focuses on the detection of retinal blood vessels which play a vital role in reducing the proliferative diabetic retinopathy and for preventing the loss of visual capability. The proposed algorithm which takes advantage of the powerful preprocessing techniques such as the contrast enhancement and thresholding offers an automated segmentation procedure for retinal blood vessels. To evaluate the performance of the new algorithm, experiments are conducted on 40 images collected from DRIVE database. The results show that the proposed algorithm performs better than the other known algorithms in terms of accuracy. Furthermore, the proposed algorithm being simple and easy to implement, is best suited for fast processing applications.

Nonlinear unsharp masking for mammogram enhancement

This paper introduces a new unsharp masking (UM) scheme, called nonlinear UM (NLUM), for mammogram enhancement. The NLUM offers users the flexibility 1) to embed different types of filters into the nonlinear filtering operator; 2) to choose different linear or nonlinear operations for the fusion processes that combines the enhanced filtered portion of the mammogram with the original mammogram; and 3) to allow the NLUM parameter selection to be performed manually or by using a quantitative enhancement measure to obtain the optimal enhancement parameters. We also introduce a new enhancement measure approach, called the second-derivative-like measure of enhancement, which is shown to have better performance than other measures in evaluating the visual quality of image enhancement. The comparison and evaluation of enhancement performance demonstrate that the NLUM can improve the disease diagnosis by enhancing the fine details in mammograms with no a priori knowledge of the image contents. The human-visual-system-based image decomposition is used for analysis and visualization of mammogram enhancement.

Effect of Ca(v)beta subunits on structural organization of Ca(v)1.2 calcium channels

BACKGROUND

Voltage-gated Ca(v)1.2 calcium channels play a crucial role in Ca(2+) signaling. The pore-forming alpha(1C) subunit is regulated by accessory Ca(v)beta subunits, cytoplasmic proteins of various size encoded by four different genes (Ca(v)beta(1)-beta(4)) and expressed in a tissue-specific manner.

METHODS AND RESULTS

Here we investigated the effect of three major Ca(v)beta types, beta(1b), beta(2d) and beta(3), on the structure of Ca(v)1.2 in the plasma membrane of live cells. Total internal reflection fluorescence microscopy showed that the tendency of Ca(v)1.2 to form clusters depends on the type of the Ca(v)beta subunit present. The highest density of Ca(v)1.2 clusters in the plasma membrane and the smallest cluster size were observed with neuronal/cardiac beta(1b) present. Ca(v)1.2 channels containing beta(3), the predominant Ca(v)beta subunit of vascular smooth muscle cells, were organized in a significantly smaller number of larger clusters. The inter- and intramolecular distances between alpha(1C) and Ca(v)beta in the plasma membrane of live cells were measured by three-color FRET microscopy. The results confirm that the proximity of Ca(v)1.2 channels in the plasma membrane depends on the Ca(v)beta type. The presence of different Ca(v)beta subunits does not result in significant differences in the intramolecular distance between the termini of alpha(1C), but significantly affects the distance between the termini of neighbor alpha(1C) subunits, which varies from 67 A with beta(1b) to 79 A with beta(3).

CONCLUSIONS

Thus, our results show that the structural organization of Ca(v)1.2 channels in the plasma membrane depends on the type of Ca(v)beta subunits present.