Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

"cancer detection": models, code, and papers

A Computer Vision Pipeline for Automated Determination of Cardiac Structure and Function and Detection of Disease by Two-Dimensional Echocardiography

Jan 12, 2018
Jeffrey Zhang, Sravani Gajjala, Pulkit Agrawal, Geoffrey H. Tison, Laura A. Hallock, Lauren Beussink-Nelson, Eugene Fan, Mandar A. Aras, ChaRandle Jordan, Kirsten E. Fleischmann, Michelle Melisko, Atif Qasim, Alexei Efros, Sanjiv J. Shah, Ruzena Bajcsy, Rahul C. Deo

Automated cardiac image interpretation has the potential to transform clinical practice in multiple ways including enabling low-cost serial assessment of cardiac function in the primary care and rural setting. We hypothesized that advances in computer vision could enable building a fully automated, scalable analysis pipeline for echocardiogram (echo) interpretation. Our approach entailed: 1) preprocessing; 2) convolutional neural networks (CNN) for view identification, image segmentation, and phasing of the cardiac cycle; 3) quantification of chamber volumes and left ventricular mass; 4) particle tracking to compute longitudinal strain; and 5) targeted disease detection. CNNs accurately identified views (e.g. 99% for apical 4-chamber) and segmented individual cardiac chambers. Cardiac structure measurements agreed with study report values (e.g. mean absolute deviations (MAD) of 7.7 mL/kg/m2 for left ventricular diastolic volume index, 2918 studies). We computed automated ejection fraction and longitudinal strain measurements (within 2 cohorts), which agreed with commercial software-derived values [for ejection fraction, MAD=5.3%, N=3101 studies; for strain, MAD=1.5% (n=197) and 1.6% (n=110)], and demonstrated applicability to serial monitoring of breast cancer patients for trastuzumab cardiotoxicity. Overall, we found that, compared to manual measurements, automated measurements had superior performance across seven internal consistency metrics with an average increase in the Spearman correlation coefficient of 0.05 (p=0.02). Finally, we developed disease detection algorithms for hypertrophic cardiomyopathy and cardiac amyloidosis, with C-statistics of 0.93 and 0.84, respectively. Our pipeline lays the groundwork for using automated interpretation to support point-of-care handheld cardiac ultrasound and large-scale analysis of the millions of echos archived within healthcare systems.

* 9 figures, 2 tables 
Access Paper or Ask Questions

Deep learning assessment of breast terminal duct lobular unit involution: towards automated prediction of breast cancer risk

Oct 31, 2019
Suzanne C Wetstein, Allison M Onken, Christina Luffman, Gabrielle M Baker, Michael E Pyle, Kevin H Kensler, Ying Liu, Bart Bakker, Ruud Vlutters, Marinus B van Leeuwen, Laura C Collins, Stuart J Schnitt, Josien PW Pluim, Rulla M Tamimi, Yujing J Heng, Mitko Veta

Terminal ductal lobular unit (TDLU) involution is the regression of milk-producing structures in the breast. Women with less TDLU involution are more likely to develop breast cancer. A major bottleneck in studying TDLU involution in large cohort studies is the need for labor-intensive manual assessment of TDLUs. We developed a computational pathology solution to automatically capture TDLU involution measures. Whole slide images (WSIs) of benign breast biopsies were obtained from the Nurses' Health Study (NHS). A first set of 92 WSIs was annotated for TDLUs, acini and adipose tissue to train deep convolutional neural network (CNN) models for detection of acini, and segmentation of TDLUs and adipose tissue. These networks were integrated into a single computational method to capture TDLU involution measures including number of TDLUs per tissue area, median TDLU span and median number of acini per TDLU. We validated our method on 40 additional WSIs by comparing with manually acquired measures. Our CNN models detected acini with an F1 score of 0.73$\pm$0.09, and segmented TDLUs and adipose tissue with Dice scores of 0.86$\pm$0.11 and 0.86$\pm$0.04, respectively. The inter-observer ICC scores for manual assessments on 40 WSIs of number of TDLUs per tissue area, median TDLU span, and median acini count per TDLU were 0.71, 95% CI [0.51, 0.83], 0.81, 95% CI [0.67, 0.90], and 0.73, 95% CI [0.54, 0.85], respectively. Intra-observer reliability was evaluated on 10/40 WSIs with ICC scores of >0.8. Inter-observer ICC scores between automated results and the mean of the two observers were: 0.80, 95% CI [0.63, 0.90] for number of TDLUs per tissue area, 0.57, 95% CI [0.19, 0.77] for median TDLU span, and 0.80, 95% CI [0.62, 0.89] for median acini count per TDLU. TDLU involution measures evaluated by manual and automated assessment were inversely associated with age and menopausal status.

Access Paper or Ask Questions

Colon Nuclei Instance Segmentation using a Probabilistic Two-Stage Detector

Mar 01, 2022
Pedro Costa, Yongpan Fu, João Nunes, Aurélio Campilho, Jaime S. Cardoso

Cancer is one of the leading causes of death in the developed world. Cancer diagnosis is performed through the microscopic analysis of a sample of suspicious tissue. This process is time consuming and error prone, but Deep Learning models could be helpful for pathologists during cancer diagnosis. We propose to change the CenterNet2 object detection model to also perform instance segmentation, which we call SegCenterNet2. We train SegCenterNet2 in the CoNIC challenge dataset and show that it performs better than Mask R-CNN in the competition metrics.

Access Paper or Ask Questions

Skin Lesion Synthesis with Generative Adversarial Networks

Feb 08, 2019
Alceu Bissoto, Fábio Perez, Eduardo Valle, Sandra Avila

Skin cancer is by far the most common type of cancer. Early detection is the key to increase the chances for successful treatment significantly. Currently, Deep Neural Networks are the state-of-the-art results on automated skin cancer classification. To push the results further, we need to address the lack of annotated data, which is expensive and require much effort from specialists. To bypass this problem, we propose using Generative Adversarial Networks for generating realistic synthetic skin lesion images. To the best of our knowledge, our results are the first to show visually-appealing synthetic images that comprise clinically-meaningful information.

* Conference: ISIC Skin Image Analysis Workshop and Challenge @ MICCAI 2018 
Access Paper or Ask Questions

Breast Cancer Detection Using Multilevel Thresholding

Nov 03, 2009
Y. Ireaneus Anna Rejani, S. Thamarai Selvi

This paper presents an algorithm which aims to assist the radiologist in identifying breast cancer at its earlier stages. It combines several image processing techniques like image negative, thresholding and segmentation techniques for detection of tumor in mammograms. The algorithm is verified by using mammograms from Mammographic Image Analysis Society. The results obtained by applying these techniques are described.

* International Journal of Computer Science and Information Security, IJCSIS, Vol. 6, No. 1, pp. 111-115, October 2009, USA 
* 5 pages IEEE format, International Journal of Computer Science and Information Security, IJCSIS 2009, ISSN 1947 5500, Impact Factor 0.423, 
Access Paper or Ask Questions

Capsule GAN for Prostate MRI Super-Resolution

May 20, 2021
Mahdiyar Molahasani Majdabadi, Younhee Choi, S. Deivalakshmi, Seokbum Ko

Prostate cancer is a very common disease among adult men. One in seven Canadian men is diagnosed with this cancer in their lifetime. Super-Resolution (SR) can facilitate early diagnosis and potentially save many lives. In this paper, a robust and accurate model is proposed for prostate MRI SR. The model is trained on the Prostate-Diagnosis and PROSTATEx datasets. The proposed model outperformed the state-of-the-art prostate SR model in all similarity metrics with notable margins. A new task-specific similarity assessment is introduced as well. A classifier is trained for severe cancer detection and the drop in the accuracy of this model when dealing with super-resolved images is used for evaluating the ability of medical detail reconstruction of the SR models. The proposed SR model is a step towards an efficient and accurate general medical SR platform.

Access Paper or Ask Questions

Mammography Dual View Mass Correspondence

Jul 02, 2018
Shaked Perek, Alon Hazan, Ella Barkan, Ayelet Akselrod-Ballin

Standard breast cancer screening involves the acquisition of two mammography X-ray projections for each breast. Typically, a comparison of both views supports the challenging task of tumor detection and localization. We introduce a deep learning, patch-based Siamese network for lesion matching in dual-view mammography. Our locally-fitted approach generates a joint patch pair representation and comparison with a shared configuration between the two views. We performed a comprehensive set of experiments with the network on standard datasets, among them the large Digital Database for Screening Mammography (DDSM). We analyzed the effect of transfer learning with the network between different types of datasets and compared the network-based matching to using Euclidean distance by template matching. Finally, we evaluated the contribution of the matching network in a full detection pipeline. Experimental results demonstrate the promise of improved detection accuracy using our approach.

Access Paper or Ask Questions

Deep Multi-Resolution Dictionary Learning for Histopathology Image Analysis

Apr 01, 2021
Nima Hatami, Mohsin Bilal, Nasir Rajpoot

The problem of recognizing various types of tissues present in multi-gigapixel histology images is an important fundamental pre-requisite for downstream analysis of the tumor microenvironment in a bottom-up analysis paradigm for computational pathology. In this paper, we propose a deep dictionary learning approach to solve the problem of tissue phenotyping in histology images. We propose deep Multi-Resolution Dictionary Learning (deepMRDL) in order to benefit from deep texture descriptors at multiple different spatial resolutions. We show the efficacy of the proposed approach through extensive experiments on four benchmark histology image datasets from different organs (colorectal cancer, breast cancer and breast lymphnodes) and tasks (namely, cancer grading, tissue phenotyping, tumor detection and tissue type classification). We also show that the proposed framework can employ most off-the-shelf CNNs models to generate effective deep texture descriptors.

Access Paper or Ask Questions

Segmenting Microcalcifications in Mammograms and its Applications

Feb 01, 2021
Roee Zamir, Shai Bagon, David Samocha, Yael Yagil, Ronen Basri, Miri Sklair-Levy Meirav Galun

Microcalcifications are small deposits of calcium that appear in mammograms as bright white specks on the soft tissue background of the breast. Microcalcifications may be a unique indication for Ductal Carcinoma in Situ breast cancer, and therefore their accurate detection is crucial for diagnosis and screening. Manual detection of these tiny calcium residues in mammograms is both time-consuming and error-prone, even for expert radiologists, since these microcalcifications are small and can be easily missed. Existing computerized algorithms for detecting and segmenting microcalcifications tend to suffer from a high false-positive rate, hindering their widespread use. In this paper, we propose an accurate calcification segmentation method using deep learning. We specifically address the challenge of keeping the false positive rate low by suggesting a strategy for focusing the hard pixels in the training phase. Furthermore, our accurate segmentation enables extracting meaningful statistics on clusters of microcalcifications.

* To appear in SPIE medical imaging 2021 
Access Paper or Ask Questions

Analysis of supervised and semi-supervised GrowCut applied to segmentation of masses in mammography images

Dec 20, 2017
Filipe Rolim Cordeiro, Wellington Pinheiro dos Santos, Abel Guilhermino da Silva Filho

Breast cancer is already one of the most common form of cancer worldwide. Mammography image analysis is still the most effective diagnostic method to promote the early detection of breast cancer. Accurately segmenting tumors in digital mammography images is important to improve diagnosis capabilities of health specialists and avoid misdiagnosis. In this work, we evaluate the feasibility of applying GrowCut to segment regions of tumor and we propose two GrowCut semi-supervised versions. All the analysis was performed by evaluating the application of segmentation techniques to a set of images obtained from the Mini-MIAS mammography image database. GrowCut segmentation was compared to Region Growing, Active Contours, Random Walks and Graph Cut techniques. Experiments showed that GrowCut, when compared to the other techniques, was able to acquire better results for the metrics analyzed. Moreover, the proposed semi-supervised versions of GrowCut was proved to have a clinically satisfactory quality of segmentation.

* Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, v. 5, p. 1-19, 2017 
Access Paper or Ask Questions