Search

Breast cancer is a common and fatal disease among women worldwide. Therefore, the early and precise diagnosis of breast cancer plays a pivotal role to improve the prognosis of patients with this disease. Several studies have developed automated techniques using different medical imaging modalities to predict breast cancer development. However, few review studies are available to recapitulate the existing literature on breast cancer classification. These studies provide an overview of the classification, segmentation, or grading of many cancer types, including breast cancer, by using traditional machine learning approaches through hand-engineered features. This review focuses on breast cancer classification by using medical imaging multimodalities through state-of-the-art artificial deep neural network approaches. It is anticipated to maximize the procedural decision analysis in five aspects, such as types of imaging modalities, datasets and their categories, pre-processing techniques, types of deep neural network, and performance metrics used for breast cancer classification. Forty-nine journal and conference publications from eight academic repositories were methodically selected and carefully reviewed from the perspective of the five aforementioned aspects. In addition, this study provided quantitative, qualitative, and critical analyses of the five aspects. This review showed that mammograms and histopathologic images were mostly used to classify breast cancer. Moreover, about 55% of the selected studies used public datasets, and the remaining used exclusive datasets. Several studies employed augmentation, scaling, and image normalization pre-processing techniques to minimize inconsistencies in breast cancer images. Several types of shallow and deep neural network architecture were employed to classify breast cancer using images. The convolutional neural network was utilized frequently to construct an effective breast cancer classification model. Some of the selected studies employed a pre-trained network or developed new deep neural networks to classify breast cancer. Most of the selected studies used accuracy and area-under-the-curve metrics followed by sensitivity, precision, and F-measure metrics to evaluate the performance of the developed breast cancer classification models. Finally, this review presented 10 open research challenges for future scholars who are interested to develop breast cancer classification models through various imaging modalities. This review could serve as a valuable resource for beginners on medical image classification and for advanced scientists focusing on deep learning-based breast cancer classification through different medical imaging modalities.

The present investigation deals with the assessment of clinicians perceived views on the impact of PET-CT in esophageal cancer management from practicality, clinical efficacy and cost –effectiveness point of views. Review of publication and retrospective data to develop and carry out a decision making model-based economic evaluation to investigate the relative cost-effectiveness of PET/CT in esophageal cancer management staging compared with conventional pathway. Clinicians identified from patient medical records included in the survey. Retrospective analysis of patient data from 2001-2008 taken from esophageal cancer patient medical records and North West Cancer Intelligence Services (NWCIS) database. A decision tree was developed using TREEAGE software. The results of the cost-effectiveness analysis are presented in terms of the incremental cost-effectiveness ratios (ICERs). PET compared with conventional work-up results for ICER for the strategy estimated at £28,460 per QALY; PET/CT compared with PET for ICER was £ 32,590 per QALY; and the ICER for PET/CT combined with conventional work-up versus PET/CT was £ 44,118. The package become more expensive with each additional diagnostic test added to PET and more effective in terms of QALYs gained. The conventional work-up is the preferred options as probabilistic sensitivity analysis shows at a willingness-to-pay threshold of £ 20,000 per QALY. Result of the current analysis suggests that the use of PET/CT in the diagnosis of esophageal cancer is unlikely to be cost-effective given the current willingness-to-pay thresholds that are accepted in the United Kingdom by decision-making bodies such as the National Institute for Health and Clinical Excellence.

BackgroundThe accessibility to radiotherapy facilities may affect the willingness to undergo treatment. We sought to quantify the distance and travel time of Malaysian population to the closest radiotherapy centre and to estimate the megavoltage unit (MV)/million population based on the regions.Materials & methodsData for subdistricts in Malaysia and radiotherapy services were extracted from Department of Statistics Malaysia and Directory of Radiotherapy Centres (DIRAC). Data from DIRAC were validated by direct communication with centres. Locations of radiotherapy centres, distance and travel time to the nearest radiotherapy were estimated using web mapping service, Google Map.ResultsThe average distance and travel time from Malaysian population to the closest radiotherapy centre were 82.5km and 83.4mins, respectively. The average distance and travel were not homogenous; East Malaysia (228.1km, 236.1mins), Central (14.4km, 20.1mins), East Coast (124.2km, 108.8mins), Northern (42.9km, 42.8mins) and Southern (36.0km, 39.8mins). The MV/million population for the country is 2.47, East Malaysia (1.76), Central (4.19), East Coast (0.54), Northern (2.40), Southern (2.36). About 25% of the population needs to travel >100 km to get to the closest radiotherapy facility.ConclusionOn average, Malaysians need to travel far and long to reach radiotherapy facilities. The accessibility to radiotherapy facilities is not equitable. The disparity may be reduced by adding centres in East Malaysia and the East Coast.

Breast cancer (BC) infection, which is peculiar to women, brings about the high rate of deaths among women in every part of the world. The early investigation of BC has minimized the severe effects of cancer as compared to the last stage diagnosis. Doctors for diagnostic tests usually suggest the medical imaging modalities like mammograms or biopsy histopathology (Hp) images. However, Hp image analysis gives doctors more confidence to diagnose BC as compared to mammograms. Many studies used Hp images to develop BC classification models to assist doctors in early BC diagnosis. However, these models lack better and reliable results in terms of reporting multiple performance evaluation metrics. Therefore, the goal of this study is to create a reliable, more accurate model that consumes minimum resources by using transfer learning based convolution neural network model. The proposed model uses the trained model after fine tuning, hence requires less number of images and can show better results on minimum resources. BreakHis dataset, which is available publicly has been employed in overall experiments in this research. BreakHis dataset is separated into training, testing, and validation for the experimentation. In addition, the dataset for training was augmented followed by stain normalization. By using the concept of transfer learning (TL), AleNext was retained after fine-tuning the last layer for binary classification like benign and malignant. Afterward, preprocessed images are fed into the TL based model for training. The model training was performed many times by changing the hyper-parameters randomly until the minimum validation loss was achieved. Now the trained model was used for feature extraction. The extracted features were further evaluated by using six ML classifiers (i.e. softmax, Decision tree, Naïve Bayes, Linear discriminant analysis, Support vector machine, k-nearest neighbor) through five performance measures such as precision, F-measure, accuracy, specificity, and sensitivity for experimental evaluation. The softmax has outperformed among all classifiers. Furthermore, to reduce the wrong prediction, a misclassification reducing (MR) algorithm was developed. After using the MR algorithm the proposed model produced better and reliable results. The observed accuracy, specificity, sensitivity, precision and F measure are 81.25%, 77.47%, 82.49%, 91.70%, and 86.80% respectively. These results show that the proposed TL based model along with misclassification reduction algorithm produced comparable results to the current baseline models. Hence, the expected model could serve as a second opinion for BC classification in any healthcare center.

This study is carried out to determine the geotechnical properties and compressibility characteristics of marine clay collected at Sabak Bernam. The compressibility characteristics of this soil are determined from 1-D consolidation test and verified by existing correlations by other researchers. No literature has been found on the compressibility characteristics of Sabak Bernam Marine Clay. It is important to carry out this study since this type of marine clay covers large coastal area of west coast Malaysia. This type of marine clay was found on the main road connecting Klang to Perak and the road keeps experiencing undulation and uneven settlement which jeopardise the safety of the road users. The soil is indicated in the Generalised Soil Map of Peninsular Malaysia as a CLAY with alluvial soil on recent marine and riverine alluvium. Based on the British Standard Soil Classification and Plasticity Chart, the soil is classified as a CLAY with very high plasticity (CV). Results from laboratory test on physical properties and compressibility parameters show that Sabak Bernam Marine Clay (SBMC) is highly compressible, has low permeability and poor drainage characteristics. The compressibility parameters obtained for SBMC is in a good agreement with other researchers in the same field.