Cancerous and Non-Cancerous MRI Classification Using Dual DCNN Approach.

Brain cancer is a life-threatening disease requiring close attention. Early and accurate diagnosis using non-invasive medical imaging is critical for successful treatment and patient survival. However, manual diagnosis by radiologist experts is time-consuming and has limitations in processing large datasets efficiently. Therefore, efficient systems capable of analyzing vast amounts of medical data for early tumor detection are urgently needed. Deep learning (DL) with deep convolutional neural networks (DCNNs) emerges as a promising tool for understanding diseases like brain cancer through medical imaging modalities, especially MRI, which provides detailed soft tissue contrast for visualizing tumors and organs. DL techniques have become more and more popular in current research on brain tumor detection. Unlike traditional machine learning methods requiring manual feature extraction, DL models are adept at handling complex data like MRIs and excel in classification tasks, making them well-suited for medical image analysis applications. This study presents a novel Dual DCNN model that can accurately classify cancerous and non-cancerous MRI samples. Our Dual DCNN model uses two well-performed DL models, i.e., inceptionV3 and denseNet121. Features are extracted from these models by appending a global max pooling layer. The extracted features are then utilized to train the model with the addition of five fully connected layers and finally accurately classify MRI samples as cancerous or non-cancerous. The fully connected layers are retrained to learn the extracted features for better accuracy. The technique achieves 99%, 99%, 98%, and 99% of accuracy, precision, recall, and f1-scores, respectively. Furthermore, this study compares the Dual DCNN's performance against various well-known DL models, including DenseNet121, InceptionV3, ResNet architectures, EfficientNetB2, SqueezeNet, VGG16, AlexNet, and LeNet-5, with different learning rates. This study indicates that our proposed approach outperforms these established models in terms of performance.

Aligning Small Datasets Using Domain Adversarial Learning: Applications in Automated in Vivo Oral Cancer Diagnosis.

Deep learning approaches for medical image analysis are limited by small data set size due to factors such as patient privacy and difficulties in obtaining expert labelling for each image. In medical imaging system development pipelines, phases for system development and classification algorithms often overlap with data collection, creating small disjoint data sets collected at numerous locations with differing protocols. In this setting, merging data from different data collection centers increases the amount of training data. However, a direct combination of datasets will likely fail due to domain shifts between imaging centers. In contrast to previous approaches that focus on a single data set, we add a domain adaptation module to a neural network and train using multiple data sets. Our approach encourages domain invariance between two multispectral autofluorescence imaging (maFLIM) data sets of in vivo oral lesions collected with an imaging system currently in development. The two data sets have differences in the sub-populations imaged and in the calibration procedures used during data collection. We mitigate these differences using a gradient reversal layer and domain classifier. Our final model trained with two data sets substantially increases performance, including a significant increase in specificity. We also achieve a significant increase in average performance over the best baseline model train with two domains (p = 0.0341). Our approach lays the foundation for faster development of computer-aided diagnostic systems and presents a feasible approach for creating a robust classifier that aligns images from multiple data centers in the presence of domain shifts.

Clinical label-free endoscopic imaging of biochemical and metabolic autofluorescence biomarkers of benign, precancerous, and cancerous oral lesions.

Early detection is critical for improving the survival rate and quality of life of oral cancer patients; unfortunately, dysplastic and early-stage cancerous oral lesions are often difficult to distinguish from oral benign lesions during standard clinical oral examination. Therefore, there is a critical need for novel clinical technologies that would enable reliable oral cancer screening. The autofluorescence properties of the oral epithelial tissue provide quantitative information about morphological, biochemical, and metabolic tissue and cellular alterations accompanying carcinogenesis. This study aimed to identify novel biochemical and metabolic autofluorescence biomarkers of oral dysplasia and cancer that could be clinically imaged using novel multispectral autofluorescence lifetime imaging (maFLIM) endoscopy technologies. In vivo maFLIM clinical endoscopic images of benign, precancerous, and cancerous lesions from 67 patients were acquired using a novel maFLIM endoscope. Widefield maFLIM feature maps were generated, and statistical analyses were applied to identify maFLIM features providing contrast between dysplastic/cancerous vs. benign oral lesions. A total of 14 spectral and time-resolved maFLIM features were found to provide contrast between dysplastic/cancerous vs. benign oral lesions, representing novel biochemical and metabolic autofluorescence biomarkers of oral epithelial dysplasia and cancer. To the best of our knowledge, this is the first demonstration of clinical widefield maFLIM endoscopic imaging of novel biochemical and metabolic autofluorescence biomarkers of oral dysplasia and cancer, supporting the potential of maFLIM endoscopy for early detection of oral cancer.

End-to-End Neural Network for Feature Extraction and Cancer Diagnosis of In Vivo Fluorescence Lifetime Images of Oral Lesions.

In contrast to previous studies that focused on classical machine learning algorithms and hand-crafted features, we present an end-to-end neural network classification method able to accommodate lesion heterogeneity for improved oral cancer diagnosis using multispectral autofluorescence lifetime imaging (maFLIM) endoscopy. Our method uses an autoencoder framework jointly trained with a classifier designed to handle overfitting problems with reduced databases, which is often the case in healthcare applications. The autoencoder guides the feature extraction process through the reconstruction loss and enables the potential use of unsupervised data for domain adaptation and improved generalization. The classifier ensures the features extracted are task-specific, providing discriminative information for the classification task. The data-driven feature extraction method automatically generates task-specific features directly from fluorescence decays, eliminating the need for iterative signal reconstruction. We validate our proposed neural network method against support vector machine (SVM) baselines, with our method showing a 6.5%-8.3% increase in sensitivity. Our results show that neural networks that implement data-driven feature extraction provide superior results and enable the capacity needed to target specific issues, such as inter-patient variability and the heterogeneity of oral lesions.Clinical relevance- We improve standard classification algorithms for in vivo diagnosis of oral cancer lesions from maFLIm for clinical use in cancer screening, reducing unnecessary biopsies and facilitating early detection of oral cancer.

Machine-Learning Assisted Discrimination of Precancerous and Cancerous from Healthy Oral Tissue Based on Multispectral Autofluorescence Lifetime Imaging Endoscopy.

Multispectral autofluorescence lifetime imaging (maFLIM) can be used to clinically image a plurality of metabolic and biochemical autofluorescence biomarkers of oral epithelial dysplasia and cancer. This study tested the hypothesis that maFLIM-derived autofluorescence biomarkers can be used in machine-learning (ML) models to discriminate dysplastic and cancerous from healthy oral tissue. Clinical widefield maFLIM endoscopy imaging of cancerous and dysplastic oral lesions was performed at two clinical centers. Endoscopic maFLIM images from 34 patients acquired at one of the clinical centers were used to optimize ML models for automated discrimination of dysplastic and cancerous from healthy oral tissue. A computer-aided detection system was developed and applied to a set of endoscopic maFLIM images from 23 patients acquired at the other clinical center, and its performance was quantified in terms of the area under the receiver operating characteristic curve (ROC-AUC). Discrimination of dysplastic and cancerous from healthy oral tissue was achieved with an ROC-AUC of 0.81. This study demonstrates the capabilities of widefield maFLIM endoscopy to clinically image autofluorescence biomarkers that can be used in ML models to discriminate dysplastic and cancerous from healthy oral tissue. Widefield maFLIM endoscopy thus holds potential for automated in situ detection of oral dysplasia and cancer.

Clinical label-free biochemical and metabolic fluorescence lifetime endoscopic imaging of precancerous and cancerous oral lesions.

INTRODUCTION: Incomplete head and neck cancer resection occurs in up to 85% of cases, leading to increased odds of local recurrence and regional metastases; thus, image-guided surgical tools for accurate, in situ and fast detection of positive margins during head and neck cancer resection surgery are urgently needed. Oral epithelial dysplasia and cancer development is accompanied by morphological, biochemical, and metabolic tissue and cellular alterations that can modulate the autofluorescence properties of the oral epithelial tissue. OBJECTIVE: This study aimed to test the hypothesis that autofluorescence biomarkers of oral precancer and cancer can be clinically imaged and quantified by means of multispectral fluorescence lifetime imaging (FLIM) endoscopy. METHODS: Multispectral autofluorescence lifetime images of precancerous and cancerous lesions from 39 patients were imaged in vivo using a novel multispectral FLIM endoscope and processed to generate widefield maps of biochemical and metabolic autofluorescence biomarkers of oral precancer and cancer. RESULTS: Statistical analyses applied to the quantified multispectral FLIM endoscopy based autofluorescence biomarkers indicated their potential to provide contrast between precancerous/cancerous vs. healthy oral epithelial tissue. CONCLUSION: To the best of our knowledge, this study represents the first demonstration of label-free biochemical and metabolic clinical imaging of precancerous and cancerous oral lesions by means of widefield multispectral autofluorescence lifetime endoscopy. Future studies will focus on demonstrating the capabilities of endogenous multispectral FLIM endoscopy as an image-guided surgical tool for positive margin detection during head and neck cancer resection surgery.

Accelerated positive contrast MRI of interventional devices using parallel compressed sensing imaging.

Susceptibility-based magnetic resonance imaging (MRI) method can image small MR-compatible devices with positive contrast. However, the relatively long data acquisition time required by the method hinders its practical applications. This study presents a parallel compressive sensing technique with a modified fast spin echo to accelerate data acquisition for the susceptibility-based positive contrast MRI. The method integrates the generalized autocalibrating partially parallel acquisitions and the compressive sensing techniques in the reconstruction algorithm. MR imaging data acquired from several phantoms containing interventional devices such as biopsy needles, stent, and brachytherapy seeds, used for validating the proposed technique. The results show that it can speed up data acquisition by a factor of about five while preserving the quality of the positive contrast images.

MARBLES - Metal Artifact Based Landmark Enhanced Susceptibility Weighted Imaging For Interventional Device Localization In MRI.

Susceptibility Weighted Imaging (SWI) is a method extensively studied for its application to improve contrast in MR imaging modality. The method enhances the visualization of magnetically susceptible content such as iron, calcium and zinc in the tissues by using the susceptibility differences in tissues to generate a unique image contrast. In this study, we propose an SWI based approach to improve the visualization of interventional devices in MRI data. Results obtained from two datasets (biopsy needle and brachytherapy seeds), indicate SWI to be suitable for visualization of the interventional devices, while also being computationally faster when compared with quantitative susceptibility mapping (QSM).

Accelerated susceptibility-based positive contrast imaging of MR compatible metallic devices based on modified fast spin echo sequences.

This study aims to develop an accelerated susceptibility-based positive contrast MR imaging method for visualizing MR compatible metallic devices. A modified fast spin echo sequence is used to accelerate data acquisition. Each readout gradient in the modified fast spin echo is slightly shifted by a short distance T shift. Phase changes accumulated within T shift are then used to calculate the susceptibility map by using a kernel deconvolution algorithm with a regularized ℓ1 minimization. To evaluate the proposed fast spin echo method, three phantom experiments were conducted and compared to a spin echo based technique and the gold standard CT for visualizing biopsy needles and brachytherapy seeds. Compared to the spin echo based technique, the data sampling speed of the proposed method was faster by 2-4 times while still being able to accurately visualize and identify the location of the biopsy needle and brachytherapy seeds. These results were confirmed by CT images of the same devices. Results also demonstrated that the proposed fast spin echo method can achieve good visualization of the brachytherapy seeds in positive contrast and in different orientations. It is also capable of correctly differentiating brachytherapy seeds from other similar structures on conventional magnitude images.

Susceptibility-based positive contrast MRI of brachytherapy seeds.

PURPOSE: To provide visualization of the brachytherapy seeds and differentiation with natural structures in MRI by taking advantage of their high magnetic susceptibility to generate positive-contrast images. METHODS: The method is based on mapping the susceptibility using an equivalent short-TE sequence and a kernel deconvolution algorithm with a regularized L1 minimization. An appealing aspect of the method is that signals from the surrounding areas where signal to noise ratio (SNR) is sufficiently high are used to derive the susceptibility of the seeds, even though the SNR in the immediate vicinity of the seeds can be extremely low due to rapid signal decay. RESULTS: The method is tested using computer simulations and experimental data. Comparing to conventional methods, the proposed method improves seed definition by a factor of >70% in the experiments. It produces the enhanced contrast at the exact seed location, whereas methods based on susceptibility gradient mapping produce highlighted regions surrounding the seeds. The proposed method is capable to perform the function for a wide range of resolutions and SNRs. CONCLUSION: The results show that the proposed method provides positive contrast for the seeds and correctly differentiates them from other structures that appear similar to the seeds on conventional magnitude images.

MRI of biopsy needles by susceptibility mapping based on Wiener filter F and L1-regularization.

Biopsy needles are devices that have been used for intravenous therapy. However, the high susceptibility of needles results in signal loss and distortion which makes the location of needles hard to identify in the MRI images. A variety of approaches has been proposed to quantify the susceptibility of the materials being imaged because susceptibility is an intrinsic property that can be used to make a good contrast between different materials. Although previous techniques on susceptibility mapping seem quite effective, they usually consume too much time due to the iterations. In this paper, a method based on Wiener filter is developed to improve the speed of susceptibility mapping. Simulation and phantom experiment demonstrate the effectiveness and high efficiency of the proposed method.

Efficient method to design RF pulses for parallel excitation MRI using gridding and conjugate gradient.

Parallel excitation (pTx) techniques with multiple transmit channels have been widely used in high field MRI imaging to shorten the RF pulse duration and/or reduce the specific absorption rate (SAR). However, the efficiency of pulse design still needs substantial improvement for practical real-time applications. In this paper, we present a detailed description of a fast pulse design method with Fourier domain gridding and a conjugate gradient method. Simulation results of the proposed method show that the proposed method can design pTx pulses at an efficiency 10 times higher than that of the conventional conjugate-gradient based method, without reducing the accuracy of the desirable excitation patterns.

Improving multi-channel compressed sensing MRI with reweighted l 1 minimization.

Integrating compressed sensing (CS) and parallel imaging (PI) with multi-channel receiver has proven to be an effective technology to speed up magnetic resonance imaging (MRI). In this paper, we propose a method that extends the reweighted l 1 minimization to the CS-MRI with multi-channel data. The method applies a reweighted l 1 minimization algorithm to reconstruct each channel image, and then generates the final image by a sum-of-squares method. Computer simulations based on synthetic data and in vivo MRI imaging data show that the new method can improve the reconstruction quality at a slightly increased computation cost.

Imaging and localizing interventional devices by susceptibility mapping using MRI.

MRI has been used for imaging interventional procedures with devices such as brachytherapy seeds, biopsy needles, markers, and stents. However, the high susceptibility of these devices leads to signal loss and distortion in the MRI images. Previously, we proposed a method to generate positive contrast of the brachytherapy seeds using a regularized L1 minimization algorithm. In this paper, we further developed and tested the method to image larger interventional devices based on susceptibility mapping. Computer simulations and experiments were performed using phantoms made of platinum wires and titanium needles. The results show that the proposed method provide positive contrast images of devices, therefore improves the visualization and localization of the devices.

Localization of brachytherapy seeds in MRI by deconvolution.

MRI has the potential to be used as a preferred imaging method for brachytherapy during the seed insertion and post-surgery evaluation. However, the brachytherapy seeds usually appear dark in the MRI magnitude images. Previously, we have developed a method based on susceptibility mapping to generate positive contrast of the seeds, which allows improved seed localization. In this paper, we propose a new method to localize the seeds by deconvolution using a seed kernel (i.e. the calculated magnetic field surrounding a seed). The deconvolution is solved using a regularized L1 minimization. Results from simulated and experimental data sets show that the seeds can be identified and localized using the proposed method more precisely.

Positive contrast MRI of prostate brachytherapy seeds by susceptibility mapping.

MRI can provide high-resolution images to assist physicians during intraoperative and post-operative phases of prostate brachytherapy. However, the brachytherapy seeds usually show as dark spots, i.e. negative contrast, on the MRI images. In this paper, we propose a new method to generate positive contrast seed images by mapping their susceptibility. The method is based on an improved kernel deconvolution algorithm using l1 regularization. Simulation results show the positive contrast seeds can be identified and differentiated using the proposed method.

Parameter estimation in arterial spin labeling MRI: Comparing the four phase model and the buxton model with fourier transform.

This paper presents a comparison between two algorithms that analyze and extract brain perfusion parameters from pulsed arterial spin labeling (ASL) MRI images. One algorithm is based on a Four Phase Single Capillary Stepwise (FPSCS) model, which divides the time course of the signal difference between the control and labeled images into four phases. The other algorithm utilizes the Buxton model and Fourier transformation (FTB). Both algorithms were implemented on MATLAB to extract the bolus arrival time (BAT) and the cerebral blood flow (CBF). In-vivo brain MRI images acquired at 4T from health volunteers were used in the comparison. Results indicated that the FTB algorithm had similar estimations of the BAT and CBF compared to the FPSCS model when the time signals are sufficiently sampled, but the former had faster processing speed while the FPSCS method provides additional information.

Positive contrast MRI of prostate brachytherapy seeds based on resonant frequency offset mapping.

MRI provides a safe, high-resolution imaging modality that can be used to assist physicians during intra-operative and post-operative phases of prostate brachytherapy. The metallic outer structure of brachytherapy seeds, however, naturally produces dark features in MR imagery, which can be confused with other image voids. This work explores the application of resonant frequency offset maps to predict the shift in resonant frequency that occurs in the vicinity of a metallic cylindrical seed-like object. An off-resonance imaging approach is then proposed to generate positive contrast markers that may aid in automatic unambiguous detection and localization of brachytherapy seeds in MR imagery.