Fuzzy Cognitive Map Applications in Medicine over the Last Two Decades: A Review Study.

Fuzzy Cognitive Maps (FCMs) have become an invaluable tool for healthcare providers because they can capture intricate associations among variables and generate precise predictions. FCMs have demonstrated their utility in diverse medical applications, from disease diagnosis to treatment planning and prognosis prediction. Their ability to model complex relationships between symptoms, biomarkers, risk factors, and treatments has enabled healthcare providers to make informed decisions, leading to better patient outcomes. This review article provides a thorough synopsis of using FCMs within the medical domain. A systematic examination of pertinent literature spanning the last two decades forms the basis of this overview, specifically delineating the diverse applications of FCMs in medical realms, including decision-making, diagnosis, prognosis, treatment optimisation, risk assessment, and pharmacovigilance. The limitations inherent in FCMs are also scrutinised, and avenues for potential future research and application are explored.

Classification models for assessing coronary artery disease instances using clinical and biometric data: an explainable man-in-the-loop approach.

The main goal driving this work is to develop computer-aided classification models relying on clinical data to identify coronary artery disease (CAD) instances with high accuracy while incorporating the expert's opinion as input, making it a "man-in-the-loop" approach. CAD is traditionally diagnosed in a definite manner by Invasive Coronary Angiography (ICA). A dataset was created using biometric and clinical data from 571 patients (21 total features, 43% ICA-confirmed CAD instances) along with the expert's diagnostic yield. Five machine learning classification algorithms were applied to the dataset. For the selection of the best feature set for each algorithm, three different parameter selection algorithms were used. Each ML model's performance was evaluated using common metrics, and the best resulting feature set for each is presented. A stratified ten-fold validation was used for the performance evaluation. This procedure was run both using the assessments of experts/doctors as input and without them. The significance of this paper lies in its innovative approach of incorporating the expert's opinion as input in the classification process, making it a "man-in-the-loop" approach. This approach not only increases the accuracy of the models but also provides an added layer of explainability and transparency, allowing for greater trust and confidence in the results. Maximum achievable accuracy, sensitivity, and specificity are 83.02%, 90.32%, and 85.49% when using the expert's diagnosis as input, compared to 78.29%, 76.61%, and 86.07% without the expert's diagnosis. The results of this study demonstrate the potential for this approach to improve the diagnosis of CAD and highlight the importance of considering the role of human expertise in the development of computer-aided classification models.

Deep learning-enhanced nuclear medicine SPECT imaging applied to cardiac studies.

Deep learning (DL) has a growing popularity and is a well-established method of artificial intelligence for data processing, especially for images and videos. Its applications in nuclear medicine are broad and include, among others, disease classification, image reconstruction, and image de-noising. Positron emission tomography (PET) and single-photon emission computerized tomography (SPECT) are major image acquisition technologies in nuclear medicine. Though several studies have been conducted to apply DL in many nuclear medicine domains, such as cancer detection and classification, few studies have employed such methods for cardiovascular disease applications. The present paper reviews recent DL approaches focused on cardiac SPECT imaging. Extensive research identified fifty-five related studies, which are discussed. The review distinguishes between major application domains, including cardiovascular disease diagnosis, SPECT attenuation correction, image denoising, full-count image estimation, and image reconstruction. In addition, major findings and dominant techniques employed for the mentioned task are revealed. Current limitations of DL approaches and future research directions are discussed.

AI-based classification algorithms in SPECT myocardial perfusion imaging for cardiovascular diagnosis: a review.

In the last few years, deep learning has made a breakthrough and established its position in machine learning classification problems in medical image analysis. Deep learning has recently displayed remarkable applicability in a range of different medical applications, as well as in nuclear cardiology. This paper implements a literature review protocol and reports the latest advances in artificial intelligence (AI)-based classification in SPECT myocardial perfusion imaging in heart disease diagnosis. The representative and most recent works are reported to demonstrate the use of AI and deep learning technologies in medical image analysis in nuclear cardiology for cardiovascular diagnosis. This review also analyses the primary outcomes of the presented research studies and suggests future directions focusing on the explainability of the deployed deep-learning systems in clinical practice.

Deep Learning Assessment for Mining Important Medical Image Features of Various Modalities.

Deep learning (DL) is a well-established pipeline for feature extraction in medical and nonmedical imaging tasks, such as object detection, segmentation, and classification. However, DL faces the issue of explainability, which prohibits reliable utilisation in everyday clinical practice. This study evaluates DL methods for their efficiency in revealing and suggesting potential image biomarkers. Eleven biomedical image datasets of various modalities are utilised, including SPECT, CT, photographs, microscopy, and X-ray. Seven state-of-the-art CNNs are employed and tuned to perform image classification in tasks. The main conclusion of the research is that DL reveals potential biomarkers in several cases, especially when the models are trained from scratch in domains where low-level features such as shapes and edges are not enough to make decisions. Furthermore, in some cases, device acquisition variations slightly affect the performance of DL models.

Deep Learning-Based Automated Diagnosis for Coronary Artery Disease Using SPECT-MPI Images.

(1) Background: Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is a long-established estimation methodology for medical diagnosis using image classification illustrating conditions in coronary artery disease. For these procedures, convolutional neural networks have proven to be very beneficial in achieving near-optimal accuracy for the automatic classification of SPECT images. (2) Methods: This research addresses the supervised learning-based ideal observer image classification utilizing an RGB-CNN model in heart images to diagnose CAD. For comparison purposes, we employ VGG-16 and DenseNet-121 pre-trained networks that are indulged in an image dataset representing stress and rest mode heart states acquired by SPECT. In experimentally evaluating the method, we explore a wide repertoire of deep learning network setups in conjunction with various robust evaluation and exploitation metrics. Additionally, to overcome the image dataset cardinality restrictions, we take advantage of the data augmentation technique expanding the set into an adequate number. Further evaluation of the model was performed via 10-fold cross-validation to ensure our model's reliability. (3) Results: The proposed RGB-CNN model achieved an accuracy of 91.86%, while VGG-16 and DenseNet-121 reached 88.54% and 86.11%, respectively. (4) Conclusions: The abovementioned experiments verify that the newly developed deep learning models may be of great assistance in nuclear medicine and clinical decision-making.

Deep learning exploration for SPECT MPI polar map images classification in coronary artery disease.

OBJECTIVE: The exploration and the implementation of a deep learning method using a state-of-the-art convolutional neural network for the classification of polar maps represent myocardial perfusion for the detection of coronary artery disease. SUBJECTS AND METHODS: In the proposed research, the dataset includes stress and rest polar maps in attenuation-corrected (AC) and non-corrected (NAC) format, counting specifically 144 normal and 170 pathological cases. Due to the small number of the dataset, the following methods were implemented: First, transfer learning was conducted using VGG16, which is applied broadly in medical industry. Furthermore, data augmentation was utilized, wherein the images are rotated and flipped for expanding the dataset. Secondly, we evaluated a custom convolutional neural network called RGB CNN, which utilizes fewer parameters and is more lightweight. In addition, we utilized the k-fold validation for evaluating variability and overall performance of the examined model. RESULTS: Our RGB CNN model achieved an agreement rating of 92.07% with a loss of 0.2519. The transfer learning technique (VGG16) attained 95.83% accuracy. CONCLUSIONS: The proposed model could be an effective tool for medical classification problems, in the case of polar map data acquired from myocardial perfusion images.

A Lightweight Convolutional Neural Network Architecture Applied for Bone Metastasis Classification in Nuclear Medicine: A Case Study on Prostate Cancer Patients.

Bone metastasis is among the most frequent in diseases to patients suffering from metastatic cancer, such as breast or prostate cancer. A popular diagnostic method is bone scintigraphy where the whole body of the patient is scanned. However, hot spots that are presented in the scanned image can be misleading, making the accurate and reliable diagnosis of bone metastasis a challenge. Artificial intelligence can play a crucial role as a decision support tool to alleviate the burden of generating manual annotations on images and therefore prevent oversights by medical experts. So far, several state-of-the-art convolutional neural networks (CNN) have been employed to address bone metastasis diagnosis as a binary or multiclass classification problem achieving adequate accuracy (higher than 90%). However, due to their increased complexity (number of layers and free parameters), these networks are severely dependent on the number of available training images that are typically limited within the medical domain. Our study was dedicated to the use of a new deep learning architecture that overcomes the computational burden by using a convolutional neural network with a significantly lower number of floating-point operations (FLOPs) and free parameters. The proposed lightweight look-behind fully convolutional neural network was implemented and compared with several well-known powerful CNNs, such as ResNet50, VGG16, Inception V3, Xception, and MobileNet on an imaging dataset of moderate size (778 images from male subjects with prostate cancer). The results prove the superiority of the proposed methodology over the current state-of-the-art on identifying bone metastasis. The proposed methodology demonstrates a unique potential to revolutionize image-based diagnostics enabling new possibilities for enhanced cancer metastasis monitoring and treatment.

Development of Convolutional Neural Networks to identify bone metastasis for prostate cancer patients in bone scintigraphy.

OBJECTIVE: The main aim of this work is to build a robust Convolutional Neural Network (CNN) algorithm that efficiently and quickly classifies bone scintigraphy images, by determining the presence or absence of prostate cancer metastasis. METHODS: CNN, widely applied in medical image classification, was used for bone scintigraphy image classification. The retrospective study included 778 sequential male patients who underwent whole-body bone scans. A nuclear medicine physician classified all the cases into 3 categories: (1) normal, (2) malignant, and (3) degenerative, which were used as the gold standard. RESULTS: An efficient CNN architecture was built, based on CNN exploration performance, achieving high prediction accuracy. The results showed that the method is sufficiently precise when it comes to differentiating a bone metastasis from other either degenerative changes or normal tissue (overall classification accuracy = 91.42% ± 1.64%). To strengthen the outcomes of this study the authors further compared the best performing CNN method to other popular CNN architectures for medical imaging, like ResNet50, VGG16 and GoogleNet, as reported in the literature. CONCLUSIONS: The prediction results reveal the efficacy of the proposed CNN-based approach and its ability for an easier and more precise interpretation of whole-body images in bone metastasis diagnosis for prostate cancer patients in nuclear medicine. This leads to marked effects on the diagnostic accuracy and decision-making regarding the treatment to be applied.

Bone metastasis classification using whole body images from prostate cancer patients based on convolutional neural networks application.

Bone metastasis is one of the most frequent diseases in prostate cancer; scintigraphy imaging is particularly important for the clinical diagnosis of bone metastasis. Up to date, minimal research has been conducted regarding the application of machine learning with emphasis on modern efficient convolutional neural networks (CNNs) algorithms, for the diagnosis of prostate cancer metastasis from bone scintigraphy images. The advantageous and outstanding capabilities of deep learning, machine learning's groundbreaking technological advancement, have not yet been fully investigated regarding their application in computer-aided diagnosis systems in the field of medical image analysis, such as the problem of bone metastasis classification in whole-body scans. In particular, CNNs are gaining great attention due to their ability to recognize complex visual patterns, in the same way as human perception operates. Considering all these new enhancements in the field of deep learning, a set of simpler, faster and more accurate CNN architectures, designed for classification of metastatic prostate cancer in bones, is explored. This research study has a two-fold goal: to create and also demonstrate a set of simple but robust CNN models for automatic classification of whole-body scans in two categories, malignant (bone metastasis) or healthy, using solely the scans at the input level. Through a meticulous exploration of CNN hyper-parameter selection and fine-tuning, the best architecture is selected with respect to classification accuracy. Thus a CNN model with improved classification capabilities for bone metastasis diagnosis is produced, using bone scans from prostate cancer patients. The achieved classification testing accuracy is 97.38%, whereas the average sensitivity is approximately 95.8%. Finally, the best-performing CNN method is compared to other popular and well-known CNN architectures used for medical imaging, like VGG16, ResNet50, GoogleNet and MobileNet. The classification results show that the proposed CNN-based approach outperforms the popular CNN methods in nuclear medicine for metastatic prostate cancer diagnosis in bones.

Efficient Bone Metastasis Diagnosis in Bone Scintigraphy Using a Fast Convolutional Neural Network Architecture.

(1) Background: Bone metastasis is among diseases that frequently appear in breast, lung and prostate cancer; the most popular imaging method of screening in metastasis is bone scintigraphy and presents very high sensitivity (95%). In the context of image recognition, this work investigates convolutional neural networks (CNNs), which are an efficient type of deep neural networks, to sort out the diagnosis problem of bone metastasis on prostate cancer patients; (2) Methods: As a deep learning model, CNN is able to extract the feature of an image and use this feature to classify images. It is widely applied in medical image classification. This study is devoted to developing a robust CNN model that efficiently and fast classifies bone scintigraphy images of patients suffering from prostate cancer, by determining whether or not they develop metastasis of prostate cancer. The retrospective study included 778 sequential male patients who underwent whole-body bone scans. A nuclear medicine physician classified all the cases into three categories: (a) benign, (b) malignant and (c) degenerative, which were used as gold standard; (3) Results: An efficient and fast CNN architecture was built, based on CNN exploration performance, using whole body scintigraphy images for bone metastasis diagnosis, achieving a high prediction accuracy. The results showed that the method is sufficiently precise when it comes to differentiate a bone metastasis case from other either degenerative changes or normal tissue cases (overall classification accuracy = 91.61% ± 2.46%). The accuracy of prostate patient cases identification regarding normal, malignant and degenerative changes was 91.3%, 94.7% and 88.6%, respectively. To strengthen the outcomes of this study the authors further compared the best performing CNN method to other popular CNN architectures for medical imaging, like ResNet50, VGG16, GoogleNet and MobileNet, as clearly reported in the literature; and (4) Conclusions: The remarkable outcome of this study is the ability of the method for an easier and more precise interpretation of whole-body images, with effects on the diagnosis accuracy and decision making on the treatment to be applied.

A risk management model for familial breast cancer: A new application using Fuzzy Cognitive Map method.

Breast cancer is the most deadly disease affecting women and thus it is natural for women aged 40-49 years (who have a family history of breast cancer or other related cancers) to assess their personal risk for developing familial breast cancer (FBC). Besides, as each individual woman possesses different levels of risk of developing breast cancer depending on their family history, genetic predispositions and personal medical history, individualized care setting mechanism needs to be identified so that appropriate risk assessment, counseling, screening, and prevention options can be determined by the health care professionals. The presented work aims at developing a soft computing based medical decision support system using Fuzzy Cognitive Map (FCM) that assists health care professionals in deciding the individualized care setting mechanisms based on the FBC risk level of the given women. The FCM based FBC risk management system uses NHL to learn causal weights from 40 patient records and achieves a 95% diagnostic accuracy. The results obtained from the proposed model are in concurrence with the comprehensive risk evaluation tool based on Tyrer-Cuzick model for 38/40 patient cases (95%). Besides, the proposed model identifies high risk women by calculating higher accuracy of prediction than the standard Gail and NSAPB models. The testing accuracy of the proposed model using 10-fold cross validation technique outperforms other standard machine learning based inference engines as well as previous FCM-based risk prediction methods for BC.

An integrated breast cancer risk assessment and management model based on fuzzy cognitive maps.

BACKGROUND: There is a growing demand for women to be classified into different risk groups of developing breast cancer (BC). The focus of the reported work is on the development of an integrated risk prediction model using a two-level fuzzy cognitive map (FCM) model. The proposed model combines the results of the initial screening mammogram of the given woman with her demographic risk factors to predict the post-screening risk of developing BC. METHODS: The level-1 FCM models the demographic risk profile. A nonlinear Hebbian learning algorithm is used to train this model and thus to help on predicting the BC risk grade based on demographic risk factors identified by domain experts. The risk grades estimated by the proposed model are validated using two standard BC risk assessment models viz. Gail and Tyrer-Cuzick. The level-2 FCM models the features of the screening mammogram concerning normal, benign and malignant cases. The data driven Hebbian learning algorithm (DDNHL) is used to train this model in order to predict the BC risk grade based on these mammographic image features. An overall risk grade is calculated by combining the outcomes of these two FCMs. RESULTS: The main limitation of the Gail model of underestimating the risk level of women with strong family history is overcome by the proposed model. IBIS is a hard computing tool based on the Tyrer-Cuzick model that is comprehensive enough in covering a wide range of demographic risk factors including family history, but it generates results in terms of numeric risk score based on predefined formulae. Thus the outcome is difficult to interpret by naive users. Besides these models are based only on the demographic details and do not take into account the findings of the screening mammogram. The proposed integrated model overcomes the above described limitations of the existing models and predicts the risk level in terms of qualitative grades. The predictions of the proposed NHL-FCM model comply with the Tyrer-Cuzick model for 36 out of 40 patient cases. With respect to tumor grading, the overall classification accuracy of DDNHL-FCM using 70 real mammogram screening images is 94.3%. The testing accuracy of the proposed model using 10-fold cross validation technique outperforms other standard machine learning based inference engines. CONCLUSION: In the perspective of clinical oncologists, this is a comprehensive front-end medical decision support system that assists them in efficiently assessing the expected post-screening BC risk level of the given individual and hence prescribing individualized preventive interventions and more intensive surveillance for high risk women.

Tc-99m depreotide SPECT/CT for lymph node staging of non-small-cell lung cancer.

OBJECTIVE: To investigate the potential role of Tc-99m depreotide (Tc-DEPR) in the preoperative lymph node (N) staging of non-small-cell lung cancer (NSCLC). METHODS: Sixty-one patients with NSCLC at the potentially operable stage were enrolled and underwent scintigraphy before surgery (n=56) or mediastinoscopy (n=5). Imaging was performed with a hybrid single photon emission computed tomography/computed tomography (SPECT/CT) system. Depreotide uptake in N stations was evaluated visually and semi-quantitatively and compared to histology. Quantification was carried out in attenuation-corrected SPECT slices. Different sites of normal uptake were used as a reference for comparison with lesional uptake. Receiver operating characteristic analysis was employed to identify the most preferable reference area and the cut-off best discriminating disease-free from disease-involved lymph nodes. RESULTS: With reference to 53 Ν1 hilar and 147 Ν2/Ν3 sampled stations, sensitivity of scintigraphy by visual interpretation was 100 and 94%, specificity 43 and 59% and accuracy 55 and 67%, respectively. No patient was down-staged, but 52% were incorrectly up-staged and 44% were misclassified as inoperable. Compared to scintigraphy, preoperative contrast-enhanced diagnostic CT demonstrated lower sensitivity (36% for hilar and 73% for N2/N3 stations), higher specificity (79 and 75%) and similar accuracy (70 and 75%). Regarding the ultimate N-stage and the prediction of surgical disease, diagnostic CT was wrong in 51 and 34% of cases. Dichotomy of quantitative scintigraphic data by the use of certain N-to-spine ratio cut-offs resulted in a significant increase of specificity (76% for hilar and 89% for N2/N3 stations), while sensitivity remained high (82% in both circumstances) and accuracy for Ν2/Ν3 stations was substantially improved (88%). By this quantitative approach, misclassifications as to the N-stage and patient operability (25 and 16%) were considerably less than that of visual Tc-DEPR and diagnostic CT interpretations. CONCLUSION: Tc-99m depreotide SPECT/CT seems to have a role in the N-staging of NSCLC, mainly because of its high sensitivity and negative predictive value. Quantification of uptake can improve specificity, at a low cost of sensitivity. If F-18 fluoro-deoxyglucose positron emission tomography is not available, this method may be used as a surrogate to conventional staging modalities.

CT-based attenuation correction in Tl-201 myocardial perfusion scintigraphy is less effective than non-corrected SPECT for risk stratification.

BACKGROUND: Previous studies advocate the use of attenuation correction in myocardial perfusion scintigraphy (MPS) for patient risk stratification. METHODS: Six-hundred and thirty-seven unselected patients underwent Tl-201 MPS by a hybrid SPECT/CT system. Attenuation-corrected (AC) and non-corrected (NAC) images were interpreted blindly and summed stress scores (SSS) were calculated. Study endpoints were all-cause mortality and the composites of death/non-fatal acute myocardial infarction (AMI) and death/AMI/late revascularization. RESULTS: During a follow-up of 42.3 ± 12.8 months 24 deaths, 13 AMIs and 28 revascularizations were recorded. SSS groups formed according to event rate distribution across SSS values were: 0-4, 5-13, >13 for NAC and 0-2, 3-9, >9 for AC. Kaplan-Meier functions were statistically significant between NAC SSS groups for all study endpoints. AC discriminated only between SSS 0-2 and >9 for death/AMI and between 0-2 and 3-9 for death/AMI/revascularization. In the univariate Cox regression abnormal NAC (SSS > 4) was accompanied with much higher hazards ratios than abnormal AC (SSS > 2). In the multivariate model abnormal AC yielded no significance for either endpoint whereas abnormal NAC proved independent from other covariates for the composite endpoints. CONCLUSION: Our results challenge the effectiveness of CT-based AC for risk stratification of patients referred for MPS.

Atypical bilateral stress fractures of the femoral shaft diagnosed by bone scintigraphy in a woman with osteoporosis.

Recent case series have identified the presence of atypical insufficiency fractures at the diaphyseal femur of osteoporotic patients, which are possibly related to the long-term use of biphosphonates. We present images of a 72-year-old woman with a history of colon cancer and osteoporosis referred for bone scintigraphy because of bilateral thigh pain. No trauma or intense exercise was reported. Bone scan revealed bilateral femoral shaft stress fractures, which were confirmed by plain radiographs. In oncologic patients with osteoporosis referred for bone scintigraphy, atypical stress fractures should be included in the differential diagnosis of focal findings in the diaphyseal femur.

Technetium-99m depreotide imaging by single photon emission tomography/low resolution computed tomography in malignant lymphomas: comparison with gallium-67 citrate.

OBJECTIVE: Previous studies have demonstrated the feasibility of targeting lymphoma lesions with somatostatin receptor binding agents, mainly with In-111-pentetreotide. In the present work another somatostatin analog, Tc-99m depreotide, is investigated. METHODS: One-hundred and six patients, 47 with Hodgkin's (HL) and 59 with various types of non-Hodgkin's lymphoma (NHL), were imaged with both Tc-99m depreotide and Ga-67 citrate. Planar whole-body and single photon emission tomography/low resolution computerized tomography (SPECT/CT) images were obtained. A total of 142 examinations were undertaken at different phases of the disease. Depreotide and gallium findings were compared visually and semi-quantitatively, with reference to the results of conventional work-up and the patients' follow-up data. RESULTS: In most HL, intermediate- and low-grade B-cell, as well as in T-cell NHL, depreotide depicted more lesions than Ga-67 and/or exhibited higher tumor uptake. The opposite was true in aggressive B-cell NHL. However, there were notable exceptions in all lymphoma subtypes. During initial staging, 93.3% of affected lymph nodes above the diaphragm, 100% of inguinal nodes and all cases with splenic infiltration were detected by depreotide. On the basis of depreotide findings, 32% of patients with early-stage HL were upstaged. However, advanced HL and NHL cases were frequently downstaged, due to low sensitivity for abdominal lymph node (22.7%), liver (45.5%) and bone marrow involvement (36.4%). Post-therapy, depreotide detected 94.7% of cases with refractory disease or recurrence. Its overall specificity was moderate (57.1%). Rebound thymic hyperplasia, various inflammatory processes and sites of unspecific uptake were the commonest causes of false positive findings. The combination of depreotide and gallium enhanced sensitivity (100%), while various false positive results of either agent could be avoided. CONCLUSION: Except perhaps for early-stage HL, Tc-99m depreotide as a stand-alone imaging modality has limited value for the initial staging of lymphomas. Post-therapy, however, depreotide scintigraphy seems useful in the evaluation of certain anatomic areas, particularly in non-aggressive lymphoma types. The combination with Ga-67 potentially enhances sensitivity and specificity. If fluorodeoxyglucose positron emission tomography is not available or in case of certain indolent lymphoma types, Tc-99m depreotide may have a role as an adjunct to conventional imaging procedures.

Tc-99m Depreotide SPECT/CT depicts myocardial involvement in a case of thrombotic thrombocytopenic purpura.

We report a case of thrombotic thrombocytopenic purpura (TTP) with cardiac involvement, imaged with Tc-99m depreotide. A 56-year-old man presented with fever, hematuria, and chest pain. Laboratory findings (angiopathic hemolytic anemia, thrombocytopenia, and uremia) were suggestive of TTP. Cardiac enzymes were elevated and diffuse left ventricular hypokinesis was demonstrated by echocardiography. Serum rheumatologic and virologic analysis were negative. A Tc-99m depreotide SPECT/CT study showed diffuse uptake in the myocardium, indicating inflammatory reaction to thrombotic/hemorrhagic myocardial damage. We suggest that Tc-99m depreotide imaging may reveal myocardial involvement in TTP; this could prompt further investigation for potential applications in myocarditis of other etiologies.