Wyniki wyszukiwania - BazTech

1

A hybrid lightweight breast cancer classification framework using the histopathological images

Addo Daniel, Zhou Shijie, Sarpong Kwabena, Nartey Obed T., Abdullah Muhammed A., Ukwuoma Chiagoziem C., Al-antari Mugahed A.

Biocybernetics and Biomedical Engineering

|

2024

|

Vol. 44, no. 1

31--54

EN

A crucial element in the diagnosis of breast cancer is the utilization of a classification method that is efficient, lightweight, and precise. Convolutional neural networks (CNNs) have garnered attention as a viable approach for classifying histopathological images. However, deeper and wider models tend to rely on first-order statistics, demanding substantial computational resources and struggling with fixed kernel dimensions that limit encompassing diverse resolution data, thereby degrading the model’s performance during testing. This study introduces BCHI-CovNet, a novel lightweight artificial intelligence (AI) model for histopathological breast image classification. Firstly, a novel multiscale depth-wise separable convolution is proposed. It is introduced to split input tensors into distinct tensor fragments, each subject to unique kernel sizes integrating various kernel sizes within one depth-wise convolution to capture both low- and high-resolution patterns. Secondly, an additional pooling module is introduced to capture extensive second-order statistical information across the channels and spatial dimensions. This module works in tandem with an innovative multi-head self-attention mechanism to capture the long-range pixels contributing significantly to the learning process, yielding distinctive and discriminative features that further enrich representation and introduce pixel diversity during training. These novel designs substantially reduce computational complexities regarding model parameters and FLOPs, which is crucial for resource-constrained medical devices. The outcomes achieved by employing the suggested model on two openly accessible datasets for breast cancer histopathological images reveal noteworthy performance. Specifically, the proposed approach attains high levels of accuracy: 99.15 % at 40× magnification, 99.08 % at 100× magnification, 99.22 % at 200× magnification, and 98.87 % at 400× magnification on the BreaKHis dataset. Additionally, it achieves an accuracy of 99.38 % on the BACH dataset. These results highlight the exceptional effectiveness and practical promise of BCHI-CovNet for the classification of breast cancer histopathological images.

2

A new approach for breast cancer detection- based Machine Learning technique

Al-Nawa Malek M., Al-Hazaimeh Obaida M., Khazaaleh Mutaz Kh. Khazaaleh

Applied Computer Science

|

2024

|

Vol. 20, no 1

1--16

EN

The leading cause of cancer-related mortality is breast cancer. Breast cancer detection at an early stage is crucial. Data on breast cancer can be diagnosed using a number of different Machine learning approaches. Automated breast cancer diagnosis using a Machine Learning model is introduced in this research. Features were selected using Convolutional Neural Networks (CNNs) as a classifier model, and noise was removed using Contrast Limited Adaptive Histogram Equalization (CLAHE). On top of that, the research compares five algorithms: Random Forest, SVM, KNN, Naïve Bayes classifier, and Logistic Regression. An extensive dataset of 3002 combined images was used to test the system. The dataset included information from 1400 individuals who underwent digital mammography between 2007 and 2015. Accuracy and precision are the metrics by which the system's performance is evaluated. Due to its low computing power requirements and excellent accuracy, our suggested model is shown to be quite efficient in the simulation results.

3

Ensemble of classifiers based on deep learning for medical image recognition

Gil Fabian, Osowski Stanisław, Świderski Bartosz, Słowińska Monika

Metrology and Measurement Systems

|

2023

|

Vol. 30, nr 1

139--156

EN

The paper presents special forms of an ensemble of classifiers for analysis of medical images based on application of deep learning. The study analyzes different structures of convolutional neural networks applied in the recognition of two types of medical images: dermoscopic images for melanoma and mammograms for breast cancer. Two approaches to ensemble creation are proposed. In the first approach, the images are processed by a convolutional neural network and the flattened vector of image descriptors is subjected to feature selection by applying different selection methods. As a result, different sets of a limited number of diagnostic features are generated. In the next stage, these sets of features represent input attributes for the classical classifiers: support vector machine, a random forest of decision trees, and softmax. By combining different selection methods with these classifiers an ensemble classification system is created and integrated by majority voting. In the second approach, different structures of convolutional neural networks are directly applied as the members of the ensemble. The efficiency of the proposed classification systems is investigated and compared to medical data representing dermoscopic images of melanoma and breast cancer mammogram images. Thanks to fusion of the results of many classifiers forming an ensemble, accuracy and all other quality measures have been significantly increased for both types of medical images.

4

Numerical Simulation of Breast Cancer in the Early Diagnosis with Actual Dimension and Characteristics Using Photoacoustic Tomography

Ahangar Darband Maryam, Najafi Aghdam Esmaeil, Gharibi Arash

Archives of Acoustics

|

2023

|

Vol. 48, No. 1

25--38

EN

A numerical study and simulation of breast imaging in the early detection of tumors using the photoacoustic (PA) phenomenon are presented. There have been various reports on the simulation of the PA phenomenon in the breast, which are not in the real dimensions of the tissue. Furthermore, the different layers of the breast have not been considered. Therefore, it has not been possible to rely on the values and characteristics of the resulting data and to compare it with the actual state. Here, the real dimensions of the breast at three-dimensional and different constituent layers have been considered. After reviewing simulation methods and software for different stages of the PA phenomenon, a single suitable platform, which is commercially available finite element software (COMSOL), has been selected for simulating. The optical, thermal, elastic, and acoustic characteristics of different layers of breast and tumor at radiated laser wavelength (800 nm) were accurately calculated or obtained from a reliable source. Finally, by defining an array of 32 ultrasonic sensors on the breast cup at the defined arcs of the 2D slices, the PA waves can be collected and transmitted to MATLAB software to reconstruct the images. We can study the resulting PA wave and its changes in more detail using our scenarios.

5

Wybrane produkty spożywcze jako czynnik ograniczający ryzyko zachorowania na raka piersi

Achrem-Achremowicz Bohdan

Przemysł Spożywczy

|

2022

|

T. 76, nr 8

60--63

PL

Rak piersi jest główną przyczyną zgonów kobiet na świecie, a rocznie diagnozuje się ponad 2 mln zachorowań. W Polsce w 2020 r. stwierdzono 24 644 nowych przypadków i 8 805 zgonów. W niektórych publikacjach podano, że produkty mleczne mogą ograniczać zacho-rowania na raka piersi, natomiast w innych stwierdzono odwrotną zależność lub brak związku pomiędzy spożyciem produktów mlecznych a chorobami. Interesujące są także wyniki badań wpływu częstego spożycia warzyw kapustowatych lub ich przetworów, przeprowadzone w grupie emigrantek z Polski do USA. Wykazano i potwierdzono statystycznie istotny wpływ wysokiego spożycia przez młode kobiety surowej, krótko gotowanej oraz kiszonej kapusty na zmniejszenie ryzyka raka piersi, wyniki były także spójne na wszystkich poziomach spożycia w wieku dorosłym.

EN

Breast cancer is the leading cause of death for women worldwide, with more than 2 million illnesses being diagnosed each year. In Poland 24,644 new cases and 8,805 deaths were found in 2020. The cited publications state that dairy products can prevent breast cancer. Other studies suggest that there is an opposite relationship in some cases, or no relationship between the consumption of particular dairy products and the disease. The results of studies on the effects of high cabbage consumption; short-cooked and pickled conducted in the USA among immigrants from Poland are interesting. A statistically significant effect of high consumption of raw, short-cooked cabbage or a sauerkraut on the reduction of the risk of breast cancer in young woman was demonstrated and confirmed, and the results were also consistent with the consumption levels in adulthood.

6

Comparison of fulfilling the criteria for critical organs in irradiation of patients with breast cancer using the deep inspiration breath-hold and free breathing techniques

Matusiak Katarzyna, Mucha Magdalena, Pysklak Sylwia, Kaczmarek Anna

Polish Journal of Medical Physics and Engineering

|

2022

|

Vol. 28, Iss. 3

150--159

EN

Introduction: The aim of the study was to evaluate organ-at-risk dose sparing in treatment plans for patients with left-sided breast cancer irradiated with Deep Inspiration Breath Hold (DIBH) and Free Breathing (FB) techniques. Material and methods: Twenty patients with left-sided breast cancer were analyzed and divided into two groups. Group A included 10 patients with non-metastatic breast cancer, while group B involved 10 patients with metastatic breast cancer spreading to regional lymph nodes. All patients went through the DIBH coaching. For planning purposes, CT scans were obtained in both DIBH and FB. Mean heart dose (Dmean,heart), mean heart volume receiving 50% of the prescribed dose (V50), V20 (V20L.lung), V10 (V10L.lung) and V5 for left lung (V5L.lung), the volume of the PTV receiving a dose greater than or equal to 95% of the prescribed dose (V95 [%]), the maximum point dose (Dmax), and the volume of PTV receiving 107% of the prescribed dose were reported. Results: In all 20 analyzed pairs of plans, a reduction by more than half in the mean heart dose in DIBH technique plans was achieved, as well as a significant reduction was found in DIBH plans for the heart V50. In 19 patients, the use of the DIBH technique also reduced the volume of the left lung receiving doses of 20 Gy, 10 Gy, and 5 Gy compared to the FB technique. Conclusions: Dosimetric analysis showed that the free breathing plans don’t fulfill the criteria for a mean heart dose (group B) and the left lung receiving a 20 Gy dose (group A) compared to the DIBH plans. Radiation therapy of left breast cancer with the use of the DIBH technique results in a significant dose reduction in the heart and also reduces the dose in the left lung in the majority of patients, compared to the FB procedure.

7

Cancer therapeutics strategy using nano-carrier mediated natural drugs

Shaw S., Singh P., Mishra R., Singh R., Nayak R., Bose S.

Journal of Achievements in Materials and Manufacturing Engineering

|

2022

|

Vol. 114, nr 1

32--41

EN

Purpose: Nucleolin is a multifactorial protein, having a significant role in chromatin remodelling, mRNA stability, ribosome biogenesis, stemness, angiogenesis, etc., thus, it is potential therapeutic target in cancer. The purpose of this paper is to study porous silicon (pSi) nanocarrier-based natural drug delivery system targeting dysregulated nucleolin expression for cancer therapeutics. Design/methodology/approach: Quercetin was loaded in pre-synthesized and characterized pSi nanoparticles, and release kinetics was studied. The study compared the inhibitory concentration (IC50) of quercetin, synthetic drug doxorubicin, and quercetin-loaded pSi nanoparticles. Further, mRNA expression of a target gene, nucleolin, was tested with a quercetin treated breast cancer cell line (MCF-7). Findings: Quercetin-loaded pSi nanoparticles followed first-order release kinetics. IC50 was determined at concentrations of 312 nM, 160 μM, and 50 μM against doxorubicin, quercetin, and quercetin-loaded pSi nanoparticles, respectively. The results further indicated 16-fold downregulation of nucleolin mRNA expression after 48h of quercetin treatment of exponentially growing MCF-7 cells. Research limitations/implications: Whether pSi nanoparticle loaded quercetin can significantly downregulate nucleolin protein expression and its impact on apoptosis, cell proliferation, and angiogenic pathways need further investigation. Practical implications: The practical application of the proposed nanocarrier-based drug delivery system potentially lays out a path for developing targeted therapy against nucleolin-dysregulated cancer using natural products to minimize the side effects of conventional chemotherapeutic drugs. Originality/value: Inhibition of nucleolin and nucleolin regulated pathways using natural compounds and its targeted delivery with nanocarrier is not yet done.

8

Wpływ wstępnego schłodzenia ciała z wykorzystaniem automatycznego nawiewu na wartość diagnostyczną obrazów termicznych gruczołu piersiowego

Szurko Agnieszka, Kiełboń Agnieszka, Lasyk Dorota, Kokoszka Katarzyna, Stanek Agata, Cholewka Armand

Inżynier i Fizyk Medyczny

|

2022

|

Vol. 11, nr 6

473--478

PL

Termografia, jako nieinwazyjna metoda pozwalająca szybko i skutecznie wykryć obszary o podwyższonej temperaturze powierzchni ciała, idealnie nadaje się do celów wspomagających diagnostykę schorzeń piersi. Celem przeprowadzonych badań było udoskonalenie procedur badawczych z wykorzystaniem termowizji poprzez zastosowanie wstępnego schłodzenia ciała ochotników. Pomiary wykonano w Laboratorium Medycyny Sportowej Instytutu Inżynierii Biomedycznej na Uniwersytecie Śląskim. Grupa badawcza składała się z 5 zdrowych, młodych osób. Ciało ochotników zostało schłodzone w komorze kriogenicznej CrioSpace firmy JBG2 przy pomocy powietrza o temperaturze 0°C. Na uzyskanych termogramach gruczołów piersiowych oznaczone zostały obszary pomiarowe według stosowanej w medycynie konwencji. Analizowane termogramy oraz parametry temperaturowe jednoznacznie wykazały zwiększenie zakresu obserwowanych różnic temperaturowych po schłodzeniu piersi. Kontrast temperaturowy obliczany na podstawie różnic średnich temperatur symetrycznych obszarów piersi wzrastał nawet kilkakrotnie. Prosty zabieg ochłodzenia badanego obszaru może zatem podnieść czułość i dokładność pomiarów termowizyjnych.

EN

Thermography as a non-invasive method that allows to detect quickly and effectively areas with increased body surface temperature, is ideally suited for supporting the diagnosis of breast diseases. The aim of the research was to improve research procedures using thermovision by applying pre-cooling of the volunteers’ bodies. The measurements were made at the Sports Medicine Laboratory of the Institute of Biomedical Engineering at the University of Silesia. The research group consisted of 5 healthy young people. The body of the volunteers was cooled in the CryoSpace cryogenic chamber by JBG2, with the use of air at a temperature of 0℃. Measurement areas were marked on the obtained thermographs of the mammary glands according to the convention used in medicine. The analysed thermograms and temperature parameters clearly showed an increase in the range of observed temperature differences after breast cooling. The temperature contrast, calculated on the basis of differences in mean temperatures of symmetrical breast areas, increased even several times. A simple treatment of cooling the examined area can therefore increase the sensitivity and accuracy of thermal imaging measurements.

9

Feature selection and classification in mammography using hybrid crow search algorithm with Harris hawks optimization

Thawkar Shankar

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 4

1094--1111

EN

The purpose of this study is to develop a hybrid algorithm for feature selection and classification of masses in digital mammograms based on the Crow search algorithm (CSA) and Harris hawks optimization (HHO). The proposed CSAHHO algorithm finds the best features depending on their fitness value, which is determined by an artificial neural network. Using an artificial neural network and support vector machine classifiers, the best features determined by CSAHHO are utilized to classify masses in mammograms as benign or malignant. The performance of the suggested method is assessed using 651 mammograms. Experimental findings show that the proposed CSAHHO tends to be the best as compared to the original CSA and HHO algorithms when evaluated using ANN. It achieves an accuracy of 97.85% with a kappa value of 0.9569 and area under curve AZ = 0.982 ± 0.006. Furthermore, benchmark datasets are used to test the feasibility of the suggested approach and then compared with four state-of-the-art algorithms. The findings indicate that CSAHHO achieves high performance with the least amount of features and support to enhance breast cancer diagnosis.

10

Classification of breast cancer from histopathology images using an ensemble of deep multiscale networks

Karthik R., Menaka R., Siddharth M.V.

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

963--976

EN

Manual delineation of tumours in breast histopathology images is generally time-consuming and laborious. Computer-aided detection systems can assist pathologists by detecting abnormalities faster and more efficiently. Convolutional Neural Networks (CNN) and transfer learning have shown good results in breast cancer classification. Most of the existing research works employed State-of-the-art pre-trained architectures for classification. But the performance of these methods needs to be improved in the context of effective feature learning and refinement. In this work, we propose an ensemble of two CNN architectures integrated with Channel and Spatial attention. Features from the histopathology images are extracted parallelly by two powerful custom deep architectures namely, CSAResnet and DAMCNN. Finally, ensemble learning is employed for further performance improvement. The proposed framework was able to achieve a classification accuracy of 99.55% on the BreakHis dataset.

11

Applications of machine-learning algorithms for prediction of benign and malignant breast lesions using ultrasound radiomics signatures: A multi-center study

Homayoun Hassan, Chan Wai Yee, Kuzan Taha Yusuf, Leong Wai Ling, Altintoprak Kübra Murzoglu, Mohammadi Afshin, Vijayananthan Anushya, Rahmat Kartini, Leong Sook Sam, Mirza-Aghazadeh-Attari Mohammad, Ejtehadifar Sajjad, Faeghi Fariborz, Acharya U. Rajendra, Ardakani Ali Abbasian

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

921--933

EN

Artificial intelligence (AI) algorithms have an enormous potential to impact the field of radiology and diagnostic imaging, especially the field of cancer imaging. There have been efforts to use AI models to differentiate between benign and malignant breast lesions. However, most studies have been single-center studies without external validation. The present study examines the diagnostic efficacy of machine-learning algorithms in differentiating benign and malignant breast lesions using ultrasound images. Ultrasound images of 1259 solid non-cystic lesions from 3 different centers in 3 countries (Malaysia, Turkey, and Iran) were used for the machine-learning study. A total of 242 radiomics features were extracted from each breast lesion, and the robust features were considered for models’ development. Three machine-learning algorithms were used to carry out the classification task, namely, gradient boosting (XGBoost), random forest, and support vector machine. Sensitivity, specificity, accuracy, and area under the ROC curve (AUC) were determined to evaluate the models. Thirty-three robust features differed significantly between the two groups from all of the features. XGBoost, based on these robust features, showed the most favorable profile for all cohorts, as it achieved a sensitivity of 90.3%, specificity of 86.7%, the accuracy of 88.4%, and AUC of 0.890. The present study results show that incorporating selected robust radiomics features into well-curated machine-learning algorithms can generate high sensitivity, specificity, and accuracy in differentiating benign and malignant breast lesions. Furthermore, our results show that this optimal performance is preserved even in external validation datasets.

12

Przydatność mammografii spektralnej (CESM) w wykrywaniu raka piersi jako badania uzupełniającego po klasycznej mammografii

Warchoł Ewelina

Inżynier i Fizyk Medyczny

|

2021

|

Vol. 10, nr 3

211--214

PL

Przeprowadzono ocenę badań 40 pacjentek z potwierdzonym rakiem piersi, u których wykonano mammografię klasyczną oraz mammografię spektralną. Stwierdzono większą efektywność w wykrywaniu oraz ocenie charakteru zmiany w przypadku zastosowania techniki mammografii spektralnej. Potwierdzono to w przypadku wszystkich klas według skali BIRADS.

EN

The study of 40 patients was estimated; the women diagnosed with breast cancer underwent X-ray mammography and Contrast Enhanced Spectral Mammography. It was found to be more effective in detecting and assessing the nature of the lesion in the case of using the spectral mammography technique. This was confirmed for all classes according to the BIRADS scale

13

Breast cancer nuclei segmentation and classification based on a deep learning approach

Kowal Marek, Skobel Marcin, Gramacki Artur, Korbicz Józef

International Journal of Applied Mathematics and Computer Science

|

2021

|

Vol. 31, no. 1

85--106

EN

One of the most popular methods in the diagnosis of breast cancer is fine-needle biopsy without aspiration. Cell nuclei are the most important elements of cancer diagnostics based on cytological images. Therefore, the first step of successful classification of cytological images is effective automatic segmentation of cell nuclei. The aims of our study include (a) development of segmentation methods of cell nuclei based on deep learning techniques, (b) extraction of some morphometric, colorimetric and textural features of individual segmented nuclei, (c) based on the extracted features, construction of effective classifiers for detecting malignant or benign cases. The segmentation methods used in this paper are based on (a) fully convolutional neural networks and (b) the marker-controlled watershed algorithm. For the classification task, seven various classification methods are used. Cell nuclei segmentation achieves 90% accuracy for benign and 86% for malignant nuclei according to the F-score. The maximum accuracy of the classification reached 80.2% to 92.4%, depending on the type (malignant or benign) of cell nuclei. The classification of tumors based on cytological images is an extremely challenging task. However, the obtained results are promising, and it is possible to state that automatic diagnostic methods are competitive to manual ones.

14

Two-stage multi-scale breast mass segmentation for full mammogram analysis without user intervention

Yan Yutong, Conze Pierre-Henri, Quellec Gwenolé, Lamard Mathieu, Cochener Beatrice, Coatrieux Gouenou

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 2

746--757

EN

Mammography is the primary imaging modality used for early detection and diagnosis of breast cancer. X-ray mammogram analysis mainly refers to the localization of suspicious regions of interest followed by segmentation, towards further lesion classification into benign versus malignant. Among diverse types of breast abnormalities, masses are the most important clinical findings of breast carcinomas. However, manually segmenting breast masses from native mammograms is time-consuming and error-prone. Therefore, an integrated computer-aided diagnosis system is required to assist clinicians for automatic and precise breast mass delineation. In this work, we present a two-stage multiscale pipeline that provides accurate mass contours from high-resolution full mammograms. First, we propose an extended deep detector integrating a multi-scale fusion strategy for automated mass localization. Second, a convolutional encoder-decoder network using nested and dense skip connections is employed to fine-delineate candidate masses. Unlike most previous studies based on segmentation from regions, our framework handles mass segmentation from native full mammograms without any user intervention. Trained on INbreast and DDSM-CBIS public datasets, the pipeline achieves an overall average Dice of 80.44% on INbreast test images, outperforming state-of-the-art. Our system shows promising accuracy as an automatic full-image mass segmentation system. Extensive experiments reveals robustness against the diversity of size, shape and appearance of breast masses, towards better interaction-free computer-aided diagnosis.

15

Segmentation of pectoral muscle from digital mammograms with depth-first search algorithm towards breast density classification

Pawar Shivaji D., Sharma Kamal Kr., Sapate Suhas G., Yadav Geetanjali Y.

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 3

1224--1241

EN

Digital mammography acts as a unique screening technology to protect the lives of females against breast cancer for the past few decades. Mammographic breast density is a well-known biomarker and plays a substantial role in breast cancer prediction and treatments. Breast density is calculated based on the opacity of fibro-glandular tissue reflected on digital mammograms concerning the whole area of the breast. The opacity of pectoral muscle and fibro-glandular tissue is similar to each other; hence, the small presence of the pectoral muscle in the breast area can hamper the accuracy of breast density classification. Successful removal of pectoral muscle is challenging due to changes in shape, size, and texture of pectoral muscle in every MLO and LMO views of mammogram. In this article, the depth-first search (DFS) algorithm is proposed to remove artifacts and pectoral muscle from digital mammograms. In the proposed algorithm, image enhancement is performed to improve the pixel quality of the input image. The whole breast as a single connected component is identified from the background region to remove the artifacts and tags. The depth-first search method with and without the heuristic approach is used to delineate the pectoral muscle, and then final suppression is performed on it. This algorithm is tested on 2675 images of the DDSM dataset, which is further divided into four density classes as per BIRADs classification. Segmentation results are calculated individually on each BIRADs density class of the DDSM dataset. Results are validated subjectively by the expert’s Radiologist’s ground truth with segmentation accuracy and objectively by the Jaccard coefficient and a dice similarity coefficient. This algorithm is found robust on each density class and provides overall segmentation accuracy of 86.18%, a mean value of Jaccard index, and a Dice similarity coefficient of 0.9315 and 0.9548, respectively. The experimental results show that the proposed algorithms applied for pectoral muscle removal follow the ground truth marked by an expert radiologist. The proposed algorithm can be part of the pre-processing unit of breast density measurement and breast cancer detection system used during clinical practice.

16

Bio-algorithms for the modeling and simulation of cancer cells and the immune response

Idrees Muhammad, Sohail Ayesha

Bio-Algorithms and Med-Systems

|

2021

|

Vol. 17, no. 1

55--63

EN

There have been significant developments in clinical, experimental, and theoretical approaches to understand the biomechanics of tumor cells and immune cells. Cytotoxic T lymphocytes (CTLs) are regarded as a major antitumor mechanism of immune cells. Mathematical modeling of tumor growth is an important and useful tool to observe and understand clinical phenomena analytically. This work develops a novel two-variable mathematical model to describe the interaction of tumor cells and CTLs. The designed model is providing an integrated framework to investigate the complexity of tumor progression and answer clinical questions that cannot always be reached with experimental tools. The parameters of the model are estimated from experimental study and stability analysis of the model is performed through nullclines. A global sensitivity analysis is also performed to check the uncertainty of the parameters. The results of numerical simulations of the model support the importance of the CTLs and demonstrate that CTLs can eliminate small tumors. The proposed model provides efficacious information to study and demonstrate the complex dynamics of breast cancer.

17

Cancer prediction using cascade generalization and duo output neural network

Nilnumpetch Chatree, Amornsamankul Somkid, Kraipeerapun Pawalai

Annals of Computer Science and Information Systems

|

2021

|

Vol. 27

65--70

EN

This paper proposes the combination of cascade generalization and duo output neural network based on feedforward backpropagation neural networks for cancer prediction. Duo output neural network is a neural network that is created based on two opposite targets in order to predict two opposite results. Cascade generalization is a technique that consists of a set of machines that are sorted together in which the predicted output produced from the previous machine plus the original training input are used for the creation of each machine. In this study, cascade generalization is organized in two levels: the base level and the meta level. In this research, duo output neural network is trained in each level of cascade generalization. Two outputs produced from the base level which are truth output and non-falsity output are averaged. The average result plus the original input are used for training a machine in meta level. The proposed technique is tested using two cancer datasets from UCI machine learning repository and found that our technique provides the best overall results when compared with three individual techniques.

18

Comparative Experimental Investigation and Application of Five Classic Pre-Trained Deep Convolutional Neural Networks via Transfer Learning for Diagnosis of Breast Cancer

Nogay Hidir Selcuk, Akinci Tahir Cetin Akinci, Yilmaz Musa

Advances in Science and Technology. Research Journal

|

2021

|

Vol. 15, no 3

1--8

EN

In this study, for the diagnosis and classification of breast cancer, we used and applied five classical pre-trained deep convolutional neural network models (DCNN) which have proven successful many times in different fields (ResNet-18, AlexNet, GoogleNet and SuffleNet). To make pre-trained DCNN models suitable for the purpose of our study, we updated some layers according to the new situation by using the transfer learning technique. We did not change the weights of all layers used in these five pre-trained DCNN models. Instead, we just gave new weights to the new layers so that new layers adapt faster to emerging new DCNN models. With these five pre-trained DCNN models, we have realized a quadruple classification as "cancer", "normal", "actionable" and "benign", and a binary classification as "actionable + cancer" and "normal + benign". With these two separate classification and diagnosis studies, we have carried out comparative experimental examination and analysis of pre-trained DCNN models for breast cancer diagnosis. In the study, it was concluded that successful results can be achieved with pre-trained DCNN models without extra time-consuming procedures such as feature extraction, and DCNN can perform quite successfully in cancer diagnosis and image comment.

19

Modelling the tumor temperature distribution in anatomically correct female breast phantom

Gas Piotr, Miaskowski Arkadiusz, Dobrowolski Dariusz

Przegląd Elektrotechniczny

|

2020

|

R. 96, nr 2

146--149

EN

The presented paper focuses on a numerical analysis of temperature in the anatomical model of the female breast with a strictly defined level of power generated by the EMF source in pathological tissue saturated with ferrofluid. The aim of this study was to examine the effect of blood perfusion rate models on the resultant tumor temperature. The four tumor perfusion models were subjected to comparative analysis: constant, linear, nonlinear and completely free of blood flow. The authors have shown that taking into account the various temperature dependences of blood perfusion models within the treated tissue might play an important role in the complex process of female breast cancer treatment planning.

PL

Przedstawiona praca skupia się na numerycznej analizie temperatury w anatomicznym modelu gruczołu piersiowego kobiety o ściśle określonym poziomie mocy generowanej przez źródło PEM w patologicznej tkance nasyconej ferrofluidem. Celem tej pracy było zbadanie wpływu perfuzji krwi na wypadkową temperaturę guza. Analizie porównawczej poddano cztery modele perfuzji w guzie: stały, liniowy, nieliniowy oraz model całkowicie pozbawiony przepływu krwi. Autorzy pracy wykazali, że uwzględnienie różnych zależności temperaturowych dla modeli perfuzji krwi w leczonej tkance, może odgrywać istotną rolę w złożonym procesie planowania leczenia nowotworów piersi.

20

Multi spectral classification and recognition of breast cancer and pneumonia

Kakde Aditya, Arora Nitin, Sharma Durgansh, Sharma Subhash Chander

Polish Journal of Medical Physics and Engineering

|

2020

|

Vol. 26, Iss. 1

1--9

EN

According to the Google I/O 2018 key notes, in future artificial intelligence, which also includes machine learning and deep learning, will mostly evolve in healthcare domain. As there are lots of subdomains which come under the category of healthcare domain, the proposed paper concentrates on one such domain, that is breast cancer and pneumonia. Today, just classifying the diseases is not enough. The system should also be able to classify a particular patient’s disease. Thus, this paper shines the light on the importance of multi spectral classification which means the collection of several monochrome images of the same scene. It can be proved to be an important process in the healthcare areas to know if a patient is suffering from a specific disease or not. The convolutional layer followed by the pooling layer is used for the feature extraction process and for the classification process; fully connected layers followed by the regression layer are used.