Computer-Aided Diagnosis in Mammography Using Content-based Image Retrieval Approaches: Current Status and Future Perspectives.

In this chapter we discuss rationale and methods for computer-aided diagnosis in mammography. Computer-aided diagnosis (CAD) is a diagnosis made by a clinician who uses the output from a computerized analysis of medical images as a €œsecond opinion in detecting lesions and in making diagnostic decisions. The final diagnosis is rendered by the clinician, e.g., the radiologist. Computer vision and artificial intelligence techniques are developed and customized to accommodate lesions such as cancer and their radiographic presentations on the normal parenchymal background of the breast. Mammography, x-ray imaging of the breast, is currently the best method for the early detection of breast cancer. Between 10 and 30% of women who have breast cancer and undergo mammography have negative mammograms, however. In approximately two-thirds of these false-negative mammograms, the radiologist failed to detect a cancer that was evident retrospectively. The missed detections may be due to the subtle nature of the radiographic findings (i.e., low conspicuity of the lesion), poor image quality, eye fatigue, or oversight by the radiologists. It has been suggested that double reading (by two radiologists) may increase sensitivity. Thus, one aim of CAD is to increase the efficiency and effectiveness of screening procedures by using a computer system, as a second reader (like a €œspell checker€), to indicate locations of suspicious abnormalities in mammograms as an aid to the radiologist leaving the final decision regarding the likelihood of the presence of a cancer and patient management to the radiologist. The interpretation of screening mammograms lends itself to CAD since it is a repetitive task involving mostly normal images. Figure 15.1 shows a schematic diagram of a computerized detection method for use in screening mammography. If a suspicious region is detected, the radiologist then decides if the abnormality is likely to be malignant or benign, and what course of action should be recommended (i.e., return to screening, return for short term follow-up, or return for biopsy). Many patients are referred for surgical biopsy on the basis of a radiographically detected mass lesion or cluster of microcalcifications. Although general rules for the differentiation between benign and malignant breast lesions exist, considerable variability occurs in the interpretation of findings by radiologists with current radiographic techniques. On average, only 10-€“20% of masses referred for surgical breast biopsy are actually malignant. Thus, another aim of CAD is to extract and analyze the characteristics of benign and malignant lesions seen at mammography in an objective manner in order to aid the radiologist. This has the potential for increasing diagnostic accuracy and reducing the numbers of false-positive diagnoses of malignancies, thereby decreasing patient morbidity by reducing the number of surgical biopsies performed and their associated complications. Figure 15.2 shows a schematic diagram of a computerized diagnosis method for use in the mammographie workup of a suspect lesion.

To develop a new computer-aided diagnosis (CAD) scheme that computes visually sensitive image features routinely used by radiologists to develop a machine learning classifier and distinguish between the malignant and benign breast masses detected from digital mammograms. An image dataset including 301 breast masses was retrospectively selected. From each segmented mass region, we computed image features that mimic five categories of visually sensitive features routinely used by radiologists in reading mammograms. We then selected five optimal features in the five feature categories and applied logistic regression models for classification. A new CAD interface was also designed to show lesion segmentation, computed feature values and classification score. Areas under ROC curves (AUC) were 0.786±0.026 and 0.758±0.027 when to classify mass regions depicting on two view images, respectively. By fusing classification scores computed from two regions, AUC increased to 0.806±0.025. This study demonstrated a new approach to develop CAD scheme based on 5 visually sensitive image features. Combining with a "visual aid" interface, CAD results may be much more easily explainable to the observers and increase their confidence to consider CAD generated classification results than using other conventional CAD approaches, which involve many complicated and visually insensitive texture features.

Artificial intelligence (AI) has the potential to transform medical informatics by supporting clinical decision-making, reducing diagnostic errors, and improving workflows and efficiency. However, successful integration of AI-based decision support systems depends on careful consideration of human-AI collaboration, trust, skill maintenance, and automation bias. This work proposes five central questions to guide future research in medical informatics and human-computer interface (HCI). We focus on AI-based clinical decision support systems, including computer vision algorithms for medical imaging (radiology, pathology), natural language processing for structured and unstructured electronic health record (EHR) data, and rule-based systems. Relevant data modalities include clinician-acquired images, EHR text, and increasingly, patient-generated content in telehealth contexts. We review existing evidence regarding diagnostic errors across specialties, the effectiveness and risks of AI tools in reducing perceptual and interpretive errors, and the human factors influencing diagnostic decision-making in AI-enabled contexts. We synthesize insights from medicine, cognitive science, and HCI to identify gaps in knowledge and propose five key questions for continued research. Diagnostic errors remain common across medicine, with AI offering potential to reduce both perceptual and interpretive errors. However, the impact of AI depends critically on how and when information is presented. Studies indicate that delayed or toggleable cues may outperform immediate ones, but attentional capture, overreliance, and bias remain significant risks. Explainable AI provides transparency but can also bias decisions. Long-term reliance on AI may erode clinician skills, particularly for trainees and in low-prevalence contexts. Historical failures of computer-aided diagnosis in mammography highlight these challenges. Effective AI integration requires human-centered and adaptive design. Five central research questions address: (1) what type and format of information AI should provide; (2) when information should be presented; (3) how explainable AI affects diagnostic decisions; (4) how AI influences automation bias and complacency; and (5) the risks of skill decay due to reliance on AI. Each question underscores the importance of balancing efficiency, accuracy, and clinician expertise while mitigating bias and skill degradation. AI holds promise for improving diagnostic accuracy and efficiency, but realizing its potential requires post-deployment evaluation, equitable access, clinician oversight, and targeted training. AI must complement, rather than replace, human expertise, ensuring safe, effective, and sustainable integration into diagnostic decision-making. Addressing these challenges proactively can maximize AI's potential across healthcare and other high-stakes domains.

: In this research we developed a highly sensitive and specific computer-aided diagnosis classifier based on the likelihood ratio (LRb). The classifier is designed to aid physicians to identify mammographic lesions that should not be sent to biopsy. The classifier was developed using a large database of over five thousand breast biopsy cases from several medical centers. As a result of our research, we have developed a likelihood ratio classifier that can predict biopsy outcome for mass lesions. The performance of the classifier has been tested rigorously including testing on data that was not used for training, and also on data that originated from different medical centers. The results suggest that the LRb is a robust classifier for prediction of biopsy outcome. By decreasing the number of benign mass cases sent to biopsy, the classifier could be a valuable tool for physicians and ultimately beneficial to hospitals and patients.

Database characteristics can affect significantly the performance of a mammography CAD scheme. Hence adequate performance comparison among different CAD schemes is not suitable since a single scheme could present different results depending on the set of chosen cases. Images in database shou ld follow a set of quality criteria, since the imaging process up to digital file. CAD schemes can not be developed without a database used to test their efficacy, but each database with particular characteristics may in fluence on the processing scheme performance. A possible solution could be using information on the imaging equipment characteristics. This work describes a preprocessing in order to compensateŽ the image degradation during the acquisition steps, assuring a better uniformityŽ relative to the images quality. Thus, poor quality images would be restored, providing therefore some independen ce on the images source to CAD schemes and allowing to reach the better possible performance. Tests performed with mammography images sets reported a 14% increase in sensitivity for microcalcifications detection. Although this result was followed by a little increase in false positive rates, simple changes in techniques pa rameters can provide the same improvement but with a reduction of the false positive detections. Keywords: Computer-aided diagnosis in Mammography, mi crocalcifications detection, mammography images database

Computer-vision techniques based on wavelets are presented with applications to computer-aided diagnosis (CAD) in medical images. CAD is a method for assisting radiologists’ interpretation of medical images. CAD schemes act as a second reader and alert radiologists to suspicious lesions. Development of CAD schemes is an active area of research, motivated by the fact that radiologists tend to misdiagnose cancerous lesions in medical images. In the past several years, we have been extensively developing wavelet-based techniques for CAD schemes. Development of these techniques has led to a new CAD scheme and has yielded significant improvements in the performance of the existing CAD schemes. This chapter describes two wavelet-based, low-level computer vision techniques: simultaneous segmentation and registration, and matching pursuit with optimally weighted wavelet packets. We present their application to the computer-aided detection of lung nodules in chest radiographs and microcalcifications in mammograms.

Content-based image retrieval approach was used in our computer-aided detection (CAD) schemes for breast cancer detection with mammography. In this study, we assessed CAD performance and reliability using a reference database including 1500 positive (breast mass) regions of interest (ROIs) and 1500 normal ROIs. To test the relationship between CAD performance and the similarity level between the queried ROI and the retrieved ROIs, we applied a set of similarity thresholds to the retrieved similar ROIs selected by the CAD schemes for all queried suspicious regions, and used only the ROIs that were above the threshold for assessing CAD performance at each threshold level. Using the leave-one-out testing method, we computed areas under receiver operating characteristic (ROC) curves (AZ) to assess CAD performance. The experimental results showed that as threshold increase, (1) less true positive ROIs can be referenced in the database than normal ROIs and (2) the AZ value was monotonically increased from 0.854±0.004 to 0.932±0.016. This study suggests that (1) in order to more accurately detect and diagnose subtle masses, a large and diverse database is required, and (2) assessing the reliability of the decision scores based on the similarity measurement is important in application of the CBIR-based CAD schemes when the limited database is used.

The purpose of this study was to evaluate the performance of a computer-aided diagnosis (CAD) system on the detection of pulmonary nodules in multidetector row computed tomography (MDCT) images by using two independent datasets. We collected CT cases of 63 patients with 132 nodules ranging 4–30 mm in diameter from a hospital in Spain (20 patients) and a hospital in France (43 patients). CT examinations were acquired by using a SOMATOM Emotion CT scanner in Spain, and a dual-source SOMATOM Definition CT scanner in France (Siemens Medical System, Forchheim, Germany), with the following parameters: 6 × 1.0 mm collimation, 130 kVp, 70 mA (Emotion 6); or 64 × 0.6 mm collimation, 100–120 kVp, and 100–110 mAs (Definition 64). Nodules were detected independently by three experienced chest radiologists, and their detection results were used as the reference standard. The CAD scheme was developed with an advanced 3D iris filter for improving nodule detection. The performance of the CAD scheme was tested with an independent evaluation method based on the two databases. Free-response receiver operating characteristic curves, sensitivity and number of false-positive per scan, were employed to evaluate the performance of the CAD scheme. The study was approved by the Institutional Review Board. At an average false positive (FP) rate of 5 per scan, our CAD scheme achieved sensitivities of 79.5% for all nodules, 80.3% for solid, 60.0% for non-solid, 58.1% for spiculated, and 86.1% for non-spiculated nodules. In conclusion, our CAD scheme could be utilized to help radiologists in the detection of lung nodules in CT. However, in this study we confirmed that significant differences could be found in the performance of the system depending on the testing database.

We have developed a novel method called local contralateral subtraction for reduction of false positives reported by a computer-aided diagnosis (CAD) scheme for detection of lung nodules in chest radiographs. Our method is based on the removal of normal structures in the regions of interest (ROIs), based on symmetry between the left and right lungs. In our method, two ROIs were extracted, one from the position where a candidate of a nodule is located, and the other from the anatomically corresponding location in the opposite lung, which contains similar normal structures. We employed a wavelet-based multiresolution image registration method to match the two ROIs, and subtraction was performed. A signal- to-noise ratio (SNR) between a central region and the adjacent background region was calculated for quantification of the remaining structures in the subtracted ROI. The SNR was then used for distinction between nodules and false positives. In an analysis of 550 ROIs consisting of 51 nodules and 499 false positives reported as detected nodules by our current CAD scheme, we were able to eliminate 44% of false positives with loss of only one nodule with this new method. This result indicates that our new method is effective in reducing false positives due to normal anatomic structures, and thus can improve the performance of our CAD scheme for detection of pulmonary nodules in chest radiographs.

To assess whether a computer-aided, diagnosis (CAD) system can predict pathological CompleteResponse (pCR) to neoadjuvant chemotherapy (NAC) prior to treatment using texture features. Response to treatment of 44 patients was defined according to the histopatology of resected tumour and extracted axillary nodes in two ways: (a) pCR+ (Smith's Grade = 5) vs pCR- (Smith's Grade<5); (b) pCRN+ (pCR+ and absence of residual lymph node metastases) vs pCRN - . A CAD system was developed to: (i) segment the breasts; (ii) register the DCE-MRI sequence; (iii) detect the lesion and (iv) extract 27 3D texture features. The role of individual texture features, multiparametric models and Bayesian classifiers in predicting patients' response to NAC were evaluated. A cross-validated Bayesian classifier fed with 6 features was able to predict pCR with a specificity of 72% and a sensitivity of 67%. Conversely, 2 features were used by the Bayesian classifier to predict pCRN, obtaining a sensitivity of 69% and a specificity of 61%. A CAD scheme, that extracts texture features from an automatically segmented 3D mask of the tumour, could predict pathological response to NAC. Additional research should be performed to validate these promising results on a larger cohort of patients and using different classification strategies. Advances in knowledge: This is the first study assessing the role of an automatic CAD system in predicting the pathological response to NAC before treatment. Fully automatic methods represent the backbone of standardized analysis and may help in timely managing patients candidate to NAC.

A relevance feedback (RF) approach for content-based image retrieval (CBIR) is proposed, which is based on Support Vector Machines (SVMs) and uses a feature selection technique to reduce the dimensionality of the image feature space. Specifically, each image is described by a multidimensional vector combining color, texture and shape information. In each RF round, the positive and negative examples provided by the user are used to determine a relatively small number of the most important features for the corresponding classification task, via a feature selection methodology. After the feature selection has been performed, an SVM classifier is trained to distinguish between relevant and irrelevant images according to the preferences of the user, using the restriction of the user examples on the set of selected features. The trained classifier is subsequently used to provide an updated ranking of the database images represented in the space of the selected features. Numerical experiments are presented that demonstrate the merits of the proposed relevance feedback methodology.KeywordsContent-based image retrievalrelevance feedbacksupport vector machinesfeature selection

The techniques of clustering and space transformation have been successfully used in the past to solve a number of pattern recognition problems. In this article, the authors propose a new approach to content‐based image retrieval (CBIR) that uses (a) a newly proposed similarity‐preserving space transformation method to transform the original low‐level image space into a high‐level vector space that enables efficient query processing, and (b) a clustering scheme that further improves the efficiency of our retrieval system. This combination is unique and the resulting system provides synergistic advantages of using both clustering and space transformation. The proposed space transformation method is shown to preserve the order of the distances in the transformed feature space. This strategy makes this approach to retrieval generic as it can be applied to object types, other than images, and feature spaces more general than metric spaces. The CBIR approach uses the inexpensive “estimated” distance in the transformed space, as opposed to the computationally inefficient “real” distance in the original space, to retrieve the desired results for a given query image. The authors also provide a theoretical analysis of the complexity of their CBIR approach when used for color‐based retrieval, which shows that it is computationally more efficient than other comparable approaches. An extensive set of experiments to test the efficiency and effectiveness of the proposed approach has been performed. The results show that the approach offers superior response time (improvement of 1–2 orders of magnitude compared to retrieval approaches that either use pruning techniques like indexing, clustering, etc., or space transformation, but not both) with sufficiently high retrieval accuracy.

Content Based Image retrieval(CBIR) has a important place in research field. This paper deals with the realization of different approaches used in image retrieval based on content. In CBIR, a query image is searched from larger database by selecting features from image and then exact match is retrieved using efficient algorithms. The various CBIR approaches are reviewed such as relevance feedback, SVM, graphs, wavelet transform, Gabor filter, Semantic templates, GMM, Fuzzy logic, Object ontology, Machine intelligence and Histogram. In this paper, the various graph theory algorithms used in CBIR have been discussed and compared viz. NN Graphs, Collocation Tree, Graphlets, Efficient Manifold Ranking, A* algorithm and segmentation algorithm.

One of the important practical applications of computer vision techniques is computer-aided diagnosis (CAD) in medical imaging. It has been shown that CAD can improve the accuracy of breast cancer detection and characterization by radiologists on mammograms. In this chapter, we discuss an important step — feature selection — in classifier design for CAD algorithms. Feature selection reduces the dimensionality of an available feature space and is therefore often used to prevent over-parameterization of a classifier. Many feature selection techniques have been proposed in the literature. We will illustrate the usefulness of genetic algorithms (GAs) for feature selection by comparing GA with a commonly used sequential selection method. A brief introduction to the GA is given and several examples using GA feature selection for the characterization of mammographic lesions are discussed. The examples illustrate the design of a fitness function for optimizing classification accuracy in terms of the receiver operating characteristics of the classifier, the dependence of GA performance on its evolution parameters, and the design of a fitness function tailored to a specific classification task.

There is a growing trend for using content‐based image retrieval (CBIR) systems these days because of the constantly growing interest in digital content. Therefore, the ability of the CBIR to perform the CBIR process will depend on the feature extraction process and its basis, for the retrieval will be done on. Numerous researchers put forward various techniques for feature extraction to enhance the nature of the system. Since features play a very key role in enhancing performance, various features can be used collectively to attain the requisite goal. To retain this in mind, we present in this paper a multifeature fusion system, where three features are integrated and form one feature to improve the situation of retrieval. For this purpose, scale‐invariant feature transform (SIFT), speeded‐up robust features (SURF), and histogram of oriented gradients (HOG) features are adopted. These features are common features that deliver information about the shape of the object and for matching purposes, two techniques of distance matching such as Euclidean and Hausdrauff distance are adopted. To assess the performance of the proposed multifeature‐based CBIR approach, experiments were conducted with the usage of a MATLAB simulator. The Corel‐1000 dataset, consisting of 10,000 images in 100 semantic classes, turned into applied, with each magnificence containing 100 images. A subset of 2500 images across 50 semantic classes was used to train the system. This research aligns with industry, innovation, and infrastructure by contributing to advancements in image processing and retrieval systems. Key characteristic descriptors, along with SIFT, SURF, HOG, texture, and multicharacteristic combinations, were extracted for retrieval functions. The results display that the usage of the Hausdrauff distance as a similarity degree outperforms Euclidean distance, accomplishing retrieval accuracies of 80.02% for HOG, 77.9% for SIFT, 79. 8% for SURF, 77.2% for texture, and 84.2% for multicharacteristic combinations, surpassing Euclidean distance results via 1.7%–3.6% across capabilities. These findings underscore the effectiveness of Hausdrauff distance in enhancing retrieval precision within the CBIR framework.