Toward confident prostate cancer detection using ultrasound: a multi-center study.

PURPOSE: Deep learning-based analysis of micro-ultrasound images to detect cancerous lesions is a promising tool for improving prostate cancer (PCa) diagnosis. An ideal model should confidently identify cancer while responding with appropriate uncertainty when presented with out-of-distribution inputs that arise during deployment due to imaging artifacts and the biological heterogeneity of patients and prostatic tissue. METHODS: Using micro-ultrasound data from 693 patients across 5 clinical centers who underwent micro-ultrasound guided prostate biopsy, we train and evaluate convolutional neural network models for PCa detection. To improve robustness to out-of-distribution inputs, we employ and comprehensively benchmark several state-of-the-art uncertainty estimation methods. RESULTS: PCa detection models achieve performance scores up to 76 % average AUROC with a 10-fold cross validation setup. Models with uncertainty estimation obtain expected calibration error scores as low as 2 % , indicating that confident predictions are very likely to be correct. Visualizations of the model output demonstrate that the model correctly identifies healthy versus malignant tissue. CONCLUSION: Deep learning models have been developed to confidently detect PCa lesions from micro-ultrasound. The performance of these models, determined from a large and diverse dataset, is competitive with visual analysis of magnetic resonance imaging, the clinical benchmark to identify PCa lesions for targeted biopsy. Deep learning with micro-ultrasound should be further studied as an avenue for targeted prostate biopsy.

LensePro: label noise-tolerant prototype-based network for improving cancer detection in prostate ultrasound with limited annotations.

PURPOSE: The standard of care for prostate cancer (PCa) diagnosis is the histopathological analysis of tissue samples obtained via transrectal ultrasound (TRUS) guided biopsy. Models built with deep neural networks (DNNs) hold the potential for direct PCa detection from TRUS, which allows targeted biopsy and subsequently enhances outcomes. Yet, there are ongoing challenges with training robust models, stemming from issues such as noisy labels, out-of-distribution (OOD) data, and limited labeled data. METHODS: This study presents LensePro, a unified method that not only excels in label efficiency but also demonstrates robustness against label noise and OOD data. LensePro comprises two key stages: first, self-supervised learning to extract high-quality feature representations from abundant unlabeled TRUS data and, second, label noise-tolerant prototype-based learning to classify the extracted features. RESULTS: Using data from 124 patients who underwent systematic prostate biopsy, LensePro achieves an AUROC, sensitivity, and specificity of 77.9%, 85.9%, and 57.5%, respectively, for detecting PCa in ultrasound. Our model shows it is effective for detecting OOD data in test time, critical for clinical deployment. Ablation studies demonstrate that each component of our method improves PCa detection by addressing one of the three challenges, reinforcing the benefits of a unified approach. CONCLUSION: Through comprehensive experiments, LensePro demonstrates its state-of-the-art performance for TRUS-based PCa detection. Although further research is necessary to confirm its clinical applicability, LensePro marks a notable advancement in enhancing automated computer-aided systems for detecting prostate cancer in ultrasound.

ImSpect: Image-driven self-supervised learning for surgical margin evaluation with mass spectrometry.

PURPOSE: Real-time assessment of surgical margins is critical for favorable outcomes in cancer patients. The iKnife is a mass spectrometry device that has demonstrated potential for margin detection in cancer surgery. Previous studies have shown that using deep learning on iKnife data can facilitate real-time tissue characterization. However, none of the existing literature on the iKnife facilitate the use of publicly available, state-of-the-art pretrained networks or datasets that have been used in computer vision and other domains. METHODS: In a new framework we call ImSpect, we convert 1D iKnife data, captured during basal cell carcinoma (BCC) surgery, into 2D images in order to capitalize on state-of-the-art image classification networks. We also use self-supervision to leverage large amounts of unlabeled, intraoperative data to accommodate the data requirements of these networks. RESULTS: Through extensive ablation studies, we show that we can surpass previous benchmarks of margin evaluation in BCC surgery using iKnife data, achieving an area under the receiver operating characteristic curve (AUC) of 81%. We also depict the attention maps of the developed DL models to evaluate the biological relevance of the embedding space CONCLUSIONS: We propose a new method for characterizing tissue at the surgical margins, using mass spectrometry data from cancer surgery.

From quantitative metrics to clinical success: assessing the utility of deep learning for tumor segmentation in breast surgery.

PURPOSE: Preventing positive margins is essential for ensuring favorable patient outcomes following breast-conserving surgery (BCS). Deep learning has the potential to enable this by automatically contouring the tumor and guiding resection in real time. However, evaluation of such models with respect to pathology outcomes is necessary for their successful translation into clinical practice. METHODS: Sixteen deep learning models based on established architectures in the literature are trained on 7318 ultrasound images from 33 patients. Models are ranked by an expert based on their contours generated from images in our test set. Generated contours from each model are also analyzed using recorded cautery trajectories of five navigated BCS cases to predict margin status. Predicted margins are compared with pathology reports. RESULTS: The best-performing model using both quantitative evaluation and our visual ranking framework achieved a mean Dice score of 0.959. Quantitative metrics are positively associated with expert visual rankings. However, the predictive value of generated contours was limited with a sensitivity of 0.750 and a specificity of 0.433 when tested against pathology reports. CONCLUSION: We present a clinical evaluation of deep learning models trained for intraoperative tumor segmentation in breast-conserving surgery. We demonstrate that automatic contouring is limited in predicting pathology margins despite achieving high performance on quantitative metrics.

Self-Supervised Learning With Limited Labeled Data for Prostate Cancer Detection in High-Frequency Ultrasound.

Deep learning-based analysis of high-frequency, high-resolution micro-ultrasound data shows great promise for prostate cancer (PCa) detection. Previous approaches to analysis of ultrasound data largely follow a supervised learning (SL) paradigm. Ground truth labels for ultrasound images used for training deep networks often include coarse annotations generated from the histopathological analysis of tissue samples obtained via biopsy. This creates inherent limitations on the availability and quality of labeled data, posing major challenges to the success of SL methods. However, unlabeled prostate ultrasound data are more abundant. In this work, we successfully apply self-supervised representation learning to micro-ultrasound data. Using ultrasound data from 1028 biopsy cores of 391 subjects obtained in two clinical centers, we demonstrate that feature representations learned with this method can be used to classify cancer from noncancer tissue, obtaining an AUROC score of 91% on an independent test set. To the best of our knowledge, this is the first successful end-to-end self-SL (SSL) approach for PCa detection using ultrasound data. Our method outperforms baseline SL approaches, generalizes well between different data centers, and scales well in performance as more unlabeled data are added, making it a promising approach for future research using large volumes of unlabeled data. Our code is publicly available at https://www.github.com/MahdiGilany/SSL_micro_ultrasound.

TRUSformer: improving prostate cancer detection from micro-ultrasound using attention and self-supervision.

PURPOSE: A large body of previous machine learning methods for ultrasound-based prostate cancer detection classify small regions of interest (ROIs) of ultrasound signals that lie within a larger needle trace corresponding to a prostate tissue biopsy (called biopsy core). These ROI-scale models suffer from weak labeling as histopathology results available for biopsy cores only approximate the distribution of cancer in the ROIs. ROI-scale models do not take advantage of contextual information that are normally considered by pathologists, i.e., they do not consider information about surrounding tissue and larger-scale trends when identifying cancer. We aim to improve cancer detection by taking a multi-scale, i.e., ROI-scale and biopsy core-scale, approach. METHODS: Our multi-scale approach combines (i) an "ROI-scale" model trained using self-supervised learning to extract features from small ROIs and (ii) a "core-scale" transformer model that processes a collection of extracted features from multiple ROIs in the needle trace region to predict the tissue type of the corresponding core. Attention maps, as a by-product, allow us to localize cancer at the ROI scale. RESULTS: We analyze this method using a dataset of micro-ultrasound acquired from 578 patients who underwent prostate biopsy, and compare our model to baseline models and other large-scale studies in the literature. Our model shows consistent and substantial performance improvements compared to ROI-scale-only models. It achieves [Formula: see text] AUROC, a statistically significant improvement over ROI-scale classification. We also compare our method to large studies on prostate cancer detection, using other imaging modalities. CONCLUSIONS: Taking a multi-scale approach that leverages contextual information improves prostate cancer detection compared to ROI-scale-only models. The proposed model achieves a statistically significant improvement in performance and outperforms other large-scale studies in the literature. Our code is publicly available at www.github.com/med-i-lab/TRUSFormer .

Metabolically Active Zones Involving Fatty Acid Elongation Delineated by DESI-MSI Correlate with Pathological and Prognostic Features of Colorectal Cancer.

Colorectal cancer (CRC) is the second leading cause of cancer deaths. Despite recent advances, five-year survival rates remain largely unchanged. Desorption electrospray ionization mass spectrometry imaging (DESI) is an emerging nondestructive metabolomics-based method that retains the spatial orientation of small-molecule profiles on tissue sections, which may be validated by 'gold standard' histopathology. In this study, CRC samples were analyzed by DESI from 10 patients undergoing surgery at Kingston Health Sciences Center. The spatial correlation of the mass spectral profiles was compared with histopathological annotations and prognostic biomarkers. Fresh frozen sections of representative colorectal cross sections and simulated endoscopic biopsy samples containing tumour and non-neoplastic mucosa for each patient were generated and analyzed by DESI in a blinded fashion. Sections were then hematoxylin and eosin (H and E) stained, annotated by two independent pathologists, and analyzed. Using PCA/LDA-based models, DESI profiles of the cross sections and biopsies achieved 97% and 75% accuracies in identifying the presence of adenocarcinoma, using leave-one-patient-out cross validation. Among the m/z ratios exhibiting the greatest differential abundance in adenocarcinoma were a series of eight long-chain or very-long-chain fatty acids, consistent with molecular and targeted metabolomics indicators of de novo lipogenesis in CRC tissue. Sample stratification based on the presence of lympovascular invasion (LVI), a poor CRC prognostic indicator, revealed the abundance of oxidized phospholipids, suggestive of pro-apoptotic mechanisms, was increased in LVI-negative compared to LVI-positive patients. This study provides evidence of the potential clinical utility of spatially-resolved DESI profiles to enhance the information available to clinicians for CRC diagnosis and prognosis.

Automated Cell Phenotyping for Imaging Mass Cytometry.

Imaging mass cytometry (IMC) is a new advancement in tissue imaging that is quickly gaining wider usage since its recent launch. It improves upon current tissue imaging methods by allowing for a significantly higher number of proteins to be imaged at once on a single tissue slide. For most analyses of IMC data, determining the phenotype of each cell is a crucial step. Current methods of phenotyping require sufficient biological knowledge regarding the protein expression profile of the various cell types. Here, we develop a deep convolutional autoencoder-classifier to automate the cell phenotyping process into four basic cell types. Biopsy tissue from bladder cancer patients is used to evaluate the efficacy of the classification. The model is evaluated and validated through feature importance, confirming that the significant features are biologically relevant. Our results demonstrate the potential of deep learning to automate the task of cell phenotyping for high-dimensional IMC data.

Uncertainty estimation for margin detection in cancer surgery using mass spectrometry.

PURPOSE: Rapid evaporative ionization mass spectrometry (REIMS) is an emerging technology for clinical margin detection. Deployment of REIMS depends on construction of reliable deep learning models that can categorize tissue according to its metabolomic signature. Challenges associated with developing these models include the presence of noise during data acquisition and the variance in tissue signatures between patients. In this study, we propose integration of uncertainty estimation in deep models to factor predictive confidence into margin detection in cancer surgery. METHODS: iKnife is used to collect 693 spectra of cancer and healthy samples acquired from 91 patients during basal cell carcinoma resection. A Bayesian neural network and two baseline models are trained on these data to perform classification as well as uncertainty estimation. The samples with high estimated uncertainty are then removed, and new models are trained using the clean data. The performance of proposed and baseline models, with different ratios of filtered data, is then compared. RESULTS: The data filtering does not improve the performance of the baseline models as they cannot provide reliable estimations of uncertainty. In comparison, the proposed model demonstrates a statistically significant improvement in average balanced accuracy (75.2%), sensitivity (74.1%) and AUC (82.1%) after removing uncertain training samples. We also demonstrate that if highly uncertain samples are predicted and removed from the test data, sensitivity further improves to 88.2%. CONCLUSIONS: This is the first study that applies uncertainty estimation to inform model training and deployment for tissue recognition in cancer surgery. Uncertainty estimation is leveraged in two ways: by factoring a measure of input noise in training the models and by including predictive confidence in reporting the outputs. We empirically show that considering uncertainty for model development can help improve the overall accuracy of a margin detection system using REIMS.

Sensor-Based Automated Detection of Electrosurgical Cautery States.

In computer-assisted surgery, it is typically required to detect when the tool comes into contact with the patient. In activated electrosurgery, this is known as the energy event. By continuously tracking the electrosurgical tools' location using a navigation system, energy events can help determine locations of sensor-classified tissues. Our objective was to detect the energy event and determine the settings of electrosurgical cautery-robustly and automatically based on sensor data. This study aims to demonstrate the feasibility of using the cautery state to detect surgical incisions, without disrupting the surgical workflow. We detected current changes in the wires of the cautery device and grounding pad using non-invasive current sensors and an oscilloscope. An open-source software was implemented to apply machine learning on sensor data to detect energy events and cautery settings. Our methods classified each cautery state at an average accuracy of 95.56% across different tissue types and energy level parameters altered by surgeons during an operation. Our results demonstrate the feasibility of automatically identifying energy events during surgical incisions, which could be an important safety feature in robotic and computer-integrated surgery. This study provides a key step towards locating tissue classifications during breast cancer operations and reducing the rate of positive margins.

A Computational Approach to Identification of Candidate Biomarkers in High-Dimensional Molecular Data.

Complex high-dimensional datasets that are challenging to analyze are frequently produced through '-omics' profiling. Typically, these datasets contain more genomic features than samples, limiting the use of multivariable statistical and machine learning-based approaches to analysis. Therefore, effective alternative approaches are urgently needed to identify features-of-interest in '-omics' data. In this study, we present the molecular feature selection tool, a novel, ensemble-based, feature selection application for identifying candidate biomarkers in '-omics' data. As proof-of-principle, we applied the molecular feature selection tool to identify a small set of immune-related genes as potential biomarkers of three prostate adenocarcinoma subtypes. Furthermore, we tested the selected genes in a model to classify the three subtypes and compared the results to models built using all genes and all differentially expressed genes. Genes identified with the molecular feature selection tool performed better than the other models in this study in all comparison metrics: accuracy, precision, recall, and F1-score using a significantly smaller set of genes. In addition, we developed a simple graphical user interface for the molecular feature selection tool, which is available for free download. This user-friendly interface is a valuable tool for the identification of potential biomarkers in gene expression datasets and is an asset for biomarker discovery studies.

Training deep neural networks with noisy clinical labels: toward accurate detection of prostate cancer in US data.

PURPOSE: Ultrasound is the standard-of-care to guide the systematic biopsy of the prostate. During the biopsy procedure, up to 12 biopsy cores are randomly sampled from six zones within the prostate, where the histopathology of those cores is used to determine the presence and grade of the cancer. Histopathology reports only provide statistical information on the presence of cancer and do not normally contain fine-grain information of cancer distribution within each core. This limitation hinders the development of machine learning models to detect the presence of cancer in ultrasound so that biopsy can be more targeted to highly suspicious prostate regions. METHODS: In this paper, we tackle this challenge in the form of training with noisy labels derived from histopathology. Noisy labels often result in the model overfitting to the training data, hence limiting its generalizability. To avoid overfitting, we focus on the generalization of the features of the model and present an iterative data label refinement algorithm to amend the labels gradually. We simultaneously train two classifiers, with the same structure, and automatically stop the training when we observe any sign of overfitting. Then, we use a confident learning approach to clean the data labels and continue with the training. This process is iteratively applied to the training data and labels until convergence. RESULTS: We illustrate the performance of the proposed method by classifying prostate cancer using a dataset of ultrasound images from 353 biopsy cores obtained from 90 patients. We achieve area under the curve, sensitivity, specificity, and accuracy of 0.73, 0.80, 0.63, and 0.69, respectively. CONCLUSION: Our approach is able to provide clinicians with a visualization of regions that likely contain cancerous tissue to obtain more accurate biopsy samples. The results demonstrate that our proposed method produces superior accuracy compared to the state-of-the-art methods.

Real-time automatic tumor segmentation for ultrasound-guided breast-conserving surgery navigation.

PURPOSE: Ultrasound-based navigation is a promising method in breast-conserving surgery, but tumor contouring often requires a radiologist at the time of surgery. Our goal is to develop a real-time automatic neural network-based tumor contouring process for intraoperative guidance. Segmentation accuracy is evaluated by both pixel-based metrics and expert visual rating. METHODS: This retrospective study includes 7318 intraoperative ultrasound images acquired from 33 breast cancer patients, randomly split between 80:20 for training and testing. We implement a u-net architecture to label each pixel on ultrasound images as either tumor or healthy breast tissue. Quantitative metrics are calculated to evaluate the model's accuracy. Contour quality and usability are also assessed by fellowship-trained breast radiologists and surgical oncologists. Additionally, the viability of using our u-net model in an existing surgical navigation system is evaluated by measuring the segmentation frame rate. RESULTS: The mean dice similarity coefficient of our u-net model is 0.78, with an area under the receiver-operating characteristics curve of 0.94, sensitivity of 0.95, and specificity of 0.67. Expert visual ratings are positive, with 93% of responses rating tumor contour quality at or above 7/10, and 75% of responses rating contour quality at or above 8/10. Real-time tumor segmentation achieved a frame rate of 16 frames-per-second, sufficient for clinical use. CONCLUSION: Neural networks trained with intraoperative ultrasound images provide consistent tumor segmentations that are well received by clinicians. These findings suggest that neural networks are a promising adjunct to alleviate radiologist workload as well as improving efficiency in breast-conserving surgery navigation systems.

Coarse label refinement for improving prostate cancer detection in ultrasound imaging.

PURPOSE: Ultrasound-guided biopsy plays a major role in prostate cancer (PCa) detection, yet is limited by a high rate of false negatives and low diagnostic yield of the current systematic, non-targeted approaches. Developing machine learning models for accurately identifying cancerous tissue in ultrasound would help sample tissues from regions with higher cancer likelihood. A plausible approach for this purpose is to use individual ultrasound signals corresponding to a core as inputs and consider the histopathology diagnosis for the entire core as labels. However, this introduces significant amount of label noise to training and degrades the classification performance. Previously, we suggested that histopathology-reported cancer involvement can be a reasonable approximation for the label noise. METHODS: Here, we propose an involvement-based label refinement (iLR) method to correct corrupted labels and improve cancer classification. The difference between predicted and true cancer involvements is used to guide the label refinement process. We further incorporate iLR into state-of-the-art methods for learning with noisy labels and predicting cancer involvement. RESULTS: We use 258 biopsy cores from 70 patients and demonstrate that our proposed label refinement method improves the performance of multiple noise-tolerant approaches and achieves a balanced accuracy, correlation coefficient, and mean absolute error of 76.7%, 0.68, and 12.4, respectively. CONCLUSIONS: Our key contribution is to leverage a data-centric method to deal with noisy labels using histopathology reports, and improve the performance of prostate cancer diagnosis through a hierarchical training process with label refinement.

Application of Intraoperative Mass Spectrometry and Data Analytics for Oncological Margin Detection, A Review.

OBJECTIVE: A common phase of early-stage oncological treatment is the surgical resection of cancerous tissue. The presence of cancer cells on the resection margin, referred to as positive margin, is correlated with the recurrence of cancer and may require re-operation, negatively impacting many facets of patient outcomes. There exists a significant gap in the surgeon's ability to intraoperatively delineate between tissues. Mass spectrometry methods have shown considerable promise as intraoperative tissue profiling tools that can assist with the complete resection of cancer. To do so, the vastness of the information collected through these modalities must be digested, relying on robust and efficient extraction of insights through data analysis pipelines. METHODS: We review clinical mass spectrometry literature and prioritize intraoperatively applied modalities. We also survey the data analysis methods employed in these studies. RESULTS: Our review outlines the advantages and shortcomings of mass spectrometry imaging and point-based tissue probing methods. For each modality, we identify statistical, linear transformation and machine learning techniques that demonstrate high performance in classifying cancerous tissues across several organ systems. A limited number of studies presented results captured intraoperatively. CONCLUSION: Through continued research of data centric techniques, like mass spectrometry, and the development of robust analysis approaches, intraoperative margin assessment is becoming feasible. SIGNIFICANCE: By establishing the relatively short history of mass spectrometry techniques applied to surgical studies, we hope to inform future applications and aid in the selection of suitable data analysis frameworks for the development of intraoperative margin detection technologies.

TITAN: An end-to-end data analysis environment for the Hyperion™ imaging system.

Imaging Mass Cytometry (IMC) is a powerful high-throughput technique enabling resolution of up to 37 markers in a single fixed tissue section while also preserving in situ spatial relationships. Currently, IMC processing and analysis necessitates the use of multiple different software, labour-intensive pipeline development, different operating systems and knowledge of bioinformatics, all of which are a barrier to many potential users. Here we present TITAN - an open-source, single environment, end-to-end pipeline that can be utilized for image visualization, segmentation, analysis and export of IMC data. TITAN is implemented as an extension within the publicly available 3D Slicer software. We demonstrate the utility, application, reliability and comparability of TITAN using publicly available IMC data from recently-published breast cancer and COVID-19 lung injury studies. Compared with current IMC analysis methods, TITAN provides a user-friendly, efficient single environment to accurately visualize, segment, and analyze IMC data for all users.

Topology preserving stratification of tissue neoplasticity using Deep Neural Maps and microRNA signatures.

BACKGROUND: Accurate cancer classification is essential for correct treatment selection and better prognostication. microRNAs (miRNAs) are small RNA molecules that negatively regulate gene expression, and their dyresgulation is a common disease mechanism in many cancers. Through a clearer understanding of miRNA dysregulation in cancer, improved mechanistic knowledge and better treatments can be sought. RESULTS: We present a topology-preserving deep learning framework to study miRNA dysregulation in cancer. Our study comprises miRNA expression profiles from 3685 cancer and non-cancer tissue samples and hierarchical annotations on organ and neoplasticity status. Using unsupervised learning, a two-dimensional topological map is trained to cluster similar tissue samples. Labelled samples are used after training to identify clustering accuracy in terms of tissue-of-origin and neoplasticity status. In addition, an approach using activation gradients is developed to determine the attention of the networks to miRNAs that drive the clustering. Using this deep learning framework, we classify the neoplasticity status of held-out test samples with an accuracy of 91.07%, the tissue-of-origin with 86.36%, and combined neoplasticity status and tissue-of-origin with an accuracy of 84.28%. The topological maps display the ability of miRNAs to recognize tissue types and neoplasticity status. Importantly, when our approach identifies samples that do not cluster well with their respective classes, activation gradients provide further insight in cancer subtypes or grades. CONCLUSIONS: An unsupervised deep learning approach is developed for cancer classification and interpretation. This work provides an intuitive approach for understanding molecular properties of cancer and has significant potential for cancer classification and treatment selection.

Multi-Omic Graph Transformers for Cancer Classification and Interpretation.

Next-generation sequencing has provided rapid collection and quantification of 'big' biological data. In particular, multi-omics and integration of different molecular data such as miRNA and mRNA can provide important insights to disease classification and processes. There is a need for computational methods that can correctly model and interpret these relationships, and handle the difficulties of large-scale data. In this study, we develop a novel method of representing miRNA-mRNA interactions to classify cancer. Specifically, graphs are designed to account for the interactions and biological communication between miRNAs and mRNAs, using message-passing and attention mechanisms. Patient-matched miRNA and mRNA expression data is obtained from The Cancer Genome Atlas for 12 cancers, and targeting information is incorporated from TargetScan. A Graph Transformer Network (GTN) is selected to provide high interpretability of classification through self-attention mechanisms. The GTN is able to classify the 12 different cancers with an accuracy of 93.56% and is compared to a Graph Convolutional Network, Random Forest, Support Vector Machine, and Multilayer Perceptron. While the GTN does not outperform all of the other classifiers in terms of accuracy, it allows high interpretation of results. Multi-omics models are compared and generally outperform their respective single-omics performance. Extensive analysis of attention identifies important targeting pathways and molecular biomarkers based on integrated miRNA and mRNA expression.

Towards targeted ultrasound-guided prostate biopsy by incorporating model and label uncertainty in cancer detection.

PURPOSE: Systematic prostate biopsy is widely used for cancer diagnosis. The procedure is blind to underlying prostate tissue micro-structure; hence, it can lead to a high rate of false negatives. Development of a machine-learning model that can reliably identify suspicious cancer regions is highly desirable. However, the models proposed to-date do not consider the uncertainty present in their output or the data to benefit clinical decision making for targeting biopsy. METHODS: We propose a deep network for improved detection of prostate cancer in systematic biopsy considering both the label and model uncertainty. The architecture of our model is based on U-Net, trained with temporal enhanced ultrasound (TeUS) data. We estimate cancer detection uncertainty using test-time augmentation and test-time dropout. We then use uncertainty metrics to report the cancer probability for regions with high confidence to help the clinical decision making during the biopsy procedure. RESULTS: Experiments for prostate cancer classification includes data from 183 prostate biopsy cores of 41 patients. We achieve an area under the curve, sensitivity, specificity and balanced accuracy of 0.79, 0.78, 0.71 and 0.75, respectively. CONCLUSION: Our key contribution is to automatically estimate model and label uncertainty towards enabling targeted ultrasound-guided prostate biopsy. We anticipate that such information about uncertainty can decrease the number of unnecessary biopsy with a higher rate of cancer yield.

Discriminating Neoplastic from Nonneoplastic Tissues Using an miRNA-Based Deep Cancer Classifier.

Next-generation sequencing has enabled the collection of large biological data sets, allowing novel molecular-based classification methods to be developed for increased understanding of disease. miRNAs are small regulatory RNA molecules that can be quantified using next-generation sequencing and are excellent classificatory markers. Herein, a deep cancer classifier (DCC) was adapted to differentiate neoplastic from nonneoplastic samples using comprehensive miRNA expression profiles from 1031 human breast and skin tissue samples. The classifier was fine-tuned and evaluated using 750 neoplastic and 281 nonneoplastic breast and skin tissue samples. Performance of the DCC was compared with two machine-learning classifiers: support vector machine and random forests. In addition, performance of feature extraction through the DCC was also compared with a developed feature selection algorithm, cancer specificity. The DCC had the highest performance of area under the receiver operating curve and high performance in both sensitivity and specificity, unlike machine-learning and feature selection models, which often performed well in one metric compared with the other. In particular, deep learning had noticeable advantages with highly heterogeneous data sets. In addition, our cancer specificity algorithm identified candidate biomarkers for differentiating neoplastic and nonneoplastic tissue samples (eg, miR-144 and miR-375 in breast cancer and miR-375 and miR-451 in skin cancer).