Detection of Cancer from Microscopic Biopsy Images Using Image Processing Tools

A fourth order PDE based fuzzy c- means approach for segmentation of microscopic biopsy images in presence of Poisson noise for cancer detection

Breast cancer remains a major global health concern, particularly among women, where early detection is crucial for effective treatment and increased survival rates. Manual diagnosis through histopathological examination is often time-consuming, prone to human error, and requires expert interpretation. In response to this challenge, we developed a deep learning-based system to automate the detection and classification of breast cancer using microscopic biopsy images, aimed at enhancing diagnostic accuracy and speed in clinical workflows. Our project employs convolutional neural networks (CNNs) to classify histopathological images into three distinct categories: normal, benign, and malignant. We utilized a publicly available dataset containing high-resolution microscopic images and implemented preprocessing techniques to improve image quality, normalize input dimensions, and optimize feature extraction. The model was developed and trained using TensorFlow with GPU support, allowing for efficient computation and faster training cycles. Key Words: Breast cancer, Cancer detection, Cancer classification, Histopathological images, microscopic images, Digital pathology, medical imaging

Oral cancer is a dangerous and extensive cancer with a high death ratio. Oral cancer is the most usual cancer in the world, with more than 300,335 deaths every year. The cancerous tumor appears in the neck, oral glands, face, and mouth. To overcome this dangerous cancer, there are many ways to detect like a biopsy, in which small chunks of tissues are taken from the mouth and tested under a secure and hygienic microscope. However, microscope results of tissues to detect oral cancer are not up to the mark, a microscope cannot easily identify the cancerous cells and normal cells. Detection of cancerous cells using microscopic biopsy images helps in allaying and predicting the issues and gives better results if biologically approaches apply accurately for the prediction of cancerous cells, but during the physical examinations microscopic biopsy images for cancer detection there are major chances for human error and mistake. So, with the development of technology deep learning algorithms plays a major role in medical image diagnosing. Deep learning algorithms are efficiently developed to predict breast cancer, oral cancer, lung cancer, or any other type of medical image. In this study, the proposed model of transfer learning model using AlexNet in the convolutional neural network to extract rank features from oral squamous cell carcinoma (OSCC) biopsy images to train the model. Simulation results have shown that the proposed model achieved higher classification accuracy 97.66% and 90.06% of training and testing, respectively.

Nonalcoholic fatty liver disease (NAFLD) is one of the most frequent liver conditions representing a wide range of intrahepatic disorders, varying from steatosis to nonalcoholic steatohepatitis (NASH). Steatosis refers to the accumulation of benign fat cells, which at higher rates leads to NASH progression, as the major risk factor for hepatic fibrosis and cirrhosis, as well as for hepatocellular carcinoma (HCC). In recent years the medical field has focused on preventing the progression of these diseases, with microscopic biopsy images being the gold standard imaging modality in modern clinical trials. The proposed work aims at the high classification ability of four histological liver structures, by training a convolutional neural network (CNN) and comparing its diagnostic performance with various pre-trained deep CNN architectures. All diagnostic attempts were made on an augmented image dataset, with the new CNN model achieving a 95.8% classification accuracy, while AlexNet emerging as the most efficient architecture with a corresponding performance of 97.8%.

The accurate prediction of cancer from microscopic biopsy images has always been a major challenge for medical practitioners and pathologists who manually observe the shape and structure of the cells from tissues under a microscope. Mathematical modelling of cell proliferation helps to predict tumour sizes and optimizes the treatment procedure. This paper introduces a cell growth estimation function that uncovers the growth behaviour of benign and malignant cells. To analyse the cellular level information from tissue images, we propose a minimized cellular graph (MCG) development method. The method extracts cells and produces different features that are useful in classifying benign and malignant tissues. The method’s graphical features enable a precise and timely exploration of huge amounts of data and can help in making predictions and informed decisions. This paper introduces an algorithm for constructing a minimized cellular graph which reduces the computational complexity. A comparative study is performed based on the state-of-the-art classifiers, SVM, decision tree, random forest, nearest neighbor, LDA, Naive Bayes, and ANN. The experimental data are obtained from the BreakHis dataset, which contains 2480 benign and 5429 malignant histopathological images. The proposed technique achieves a 97.7% classification accuracy which is 7% higher than that of the other graph feature-based classification methods. A comparative study reveals a performance improvement for breast cancer classification compared to the state-of-the-art techniques.

In this paper, a multi-instance learning framework is introduced to solve the problem of skin biopsy image features recognition. Previously reported methods for skin surface images were mostly based on color features extraction. They are incapable to be directly applied to skin biopsy image features recognition because biopsy images are often dyed and have obvious inner structures with different textures. Therefore, we regard skin biopsy images as multi-instance samples, whose instances are regions or structures captured by applying Normalized Cut. Texture feature extraction methods are used to express each region as a vectorial expression. Then two multi-instance learning algorithms reported successful in various image retrieval tasks were applied. Nine features were manually selected as target features to evaluate the proposed method on a skin disease diagnosis datasets of 6579 biopsy images from 2010 to 2011. The result showed that the proposed method is effective and medically acceptable.

Doctors face difficulty in the diagnosis of lung cancer due to the complex nature and clinical interrelations of computer-diagnosed scan images. Hence, the visual inspection and subjective evaluation methods are time consuming and tedious, which leads to inter and intra observer inconsistency or imprecise classification. The Computer-Aided Detection (CAD) can help the clinicians for objective decision-making, early diagnosis, and classification of cancerous abnormalities. In this work, CAD has been employed to enhance the accuracy, sensitivity, and specificity of automated detection in which, the phases of lung cancer are discriminated using image processing tools. Cancer is the second leading cause of death in non-communicable diseases worldwide. Lung cancer is, in fact, the most dangerous form of cancer that affects both the genders. Either or both sides of the lung begin to expand during the uncontrolled growth of extraordinary cells. The most widely used imaging technique for lung cancer diagnosis is Computerised Tomography (CT) scanning. In this work, the CAD method is used to differentiate between the phases of pictures of lung cancer stages. Abnormality detection consists of 4 steps: pre-processing, segmentation, extraction of features, and classification of input CT images. For the segmentation process, Marker-controlled watershed segmentation and the K-means algorithm are used. From CT images, normal and abnormal information is extracted and its characteristics are determined. Stages 1–4 of cancerous imaging were discriminated and graded with approximately 80% efficiency using neural network feedforward backpropagation algorithm. Input data is collected from the Lung Image Database Consortium (LIDC), which out of 1018 dataset cases uses 100 cases. For the output display, a graphical user interface (GUI) is developed. This automated and robust CAD system is necessary for accurate and quick screening of the mass population.

Active contour model (ACM) approaches for image segmentation and feature extraction have emerged as very appealing and powerful tools in image processing. The basis of ACM approach is to evolve a curve, called level set, to extract the desired object (s) under some constraints. In this course, various extensions of earlier Osher's level set model have been suggested in the litareture. More recently, a new ACM model referred to selective binary and Gaussian filtering regularized level set (SBGFRIL) has been put forward as a fruitful combination of geodesic active contour model (GAC) and Chan-Vese (C-V) active contour models. This paper attempts to put forward some appealing performance indices to assess the performances of the suggested SBGFRIL compared with GAC and V-C models. The performance metrics involve the clustering based quality evaluations.

Describes a study of two fuzzy based segmentation algorithms to model successfully ambiguities and uncertainties inherent in assigning an image pixel to an object of interest and to help choosing the threshold for binarizing images using the index of fuzziness and fuzzy compactness. The methods detect object contours to different degrees of certainty on the basis of the information provided by the user, who define a reference point inside the object around which is construct the contours. First, we obtain a connectedness or a similarity map related to the indicated reference point and then for the pixels surrounding that point, if their membership-values are high they are regarded as being inside the object. We also present the connectedness and similarity maps as a useful tool in image processing, so as to obtain better gradient images.

Directional filtering is commonly known as a technique for selective linear enhancement. In addition to this traditional utility, we present in this paper some examples demonstrating that it can be used as a multi-purpose tool in image processing, by adjusting its parameters. These examples show that: (1) applying directional filtering in conjugate directions simultaneously can lead to the enhancement of specific conjugate linear features on an image, which is useful in interpretation of geophysical and Landsat images, satellite and aerial photographs that contain many conjugate linear features; (2) directional filtering can be used as illuminating sources to produce shaded relief images that show 3D effect; by combining the directional filtered result with its original image, this 3D effect becomes much more profound; (3) the directional filtered result can be weighted by different factors, which allows some subtle features on an image to be identified.

This paper puts forth a framework of a medical image analysis system for brain tumour segmentation. Image segmentation helps to segregate objects right from the background, thus proving to be a powerful tool in medical image processing. This paper presents an improved segmentation algorithm rooted in support vector machine and genetic algorithm. SVM is the basis technique used for segmentation and classification of medical images. The MRI database used consists of FLAIR images. The proposed system consists of two stages. The first stage performs preprocessing the MRI image, followed by block division. The second stage includes - feature extraction, feature selection and finally, the SVM-based training and testing. The feature extraction is done by first order histogram and co-occurrence matrix and GA using KNN is used to select subset features. The performance of the proposed system is evaluated in terms of specificity, sensitivity, accuracy, time elapsed and figure of merit.

Lung cancer is one kind of cancer which is causing deaths at an alarming rate across the globe. For patients to recover, early identification and treatment are essential. Histopathological images of tissue biopsies from possibly infected lung regions are used by medical practitioners to make diagnoses. The majority of the time, lung cancer cases are difficult to diagnose and take a long time. Convolutional neural networks are essential for figuring out the best course of therapy for patients and their chance of survival since they can quickly and accurately recognize and categorize different forms of lung cancer. In this paper, A deep learning framework is proposed for automatic detection of lung cancer. The convolutional Neural Network (CNN) model is enhanced for better diagnosis of lung cancer. An algorithm known as a learning-based Method for Lung Cancer Detection (LbM-LCD) is proposed to realize our framework. The empirical study is made with the LUNA-16 dataset. Our experimental results showed that the enhanced CNN outperforms the baseline CNN model with 98.34% accuracy.

NCM: Neutrosophic c-means clustering algorithm

The LIP (logarithmic image processing) tools are mathematical models dedicated to the representation and processing of gray tones images. The underlying model is derived from the observation that digital camera response function can be described as a multiplication in logarithmic domain. In this paper we extend the logarithmic models to process color images and show how they can be used to implement low-light image enhancement in digital cameras.

Supervized statistical classification is a vital tool for satellite image processing. It is useful not only when a discrete result, such as feature extraction or surface type, is required, but also for continuum retrievals by dividing the quantity of interest into discrete ranges. Because of the high resolution of modern satellite instruments and because of the requirement for real-time processing, any algorithm has to be fast to be useful. Here we describe an algorithm based on kernel estimation called Adaptive Gaussian Filtering that incorporates several innovations to produce superior efficiency as compared to three other popular methods: k-nearest-neighbour (KNN), Learning Vector Quantisation (LVQ) and Support Vector Machines (SVM). This efficiency is gained with no compromises: accuracy is maintained, while estimates of the conditional probabilities are returned. These are useful not only to gauge the accuracy of an estimate in the absence of its true value, but also to re-calibrate a retrieved image and as a proxy for a discretized continuum variable. The algorithm is demonstrated and compared with the other three on a pair of synthetic test classes and to map the waterways of the Netherlands.