scholarly journals Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer

Tomography ◽  
2022 ◽  
Vol 8 (1) ◽  
pp. 131-141
Author(s):  
Kanae Takahashi ◽  
Tomoyuki Fujioka ◽  
Jun Oyama ◽  
Mio Mori ◽  
Emi Yamaga ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Image Classification ◽  
Test Data ◽  
Characteristic Curve ◽  
Maximum Intensity Projection ◽  
Maximum Intensity ◽  
Training Data ◽  
Ct Image ◽  
Pet Ct

Deep learning (DL) has become a remarkably powerful tool for image processing recently. However, the usefulness of DL in positron emission tomography (PET)/computed tomography (CT) for breast cancer (BC) has been insufficiently studied. This study investigated whether a DL model using images with multiple degrees of PET maximum-intensity projection (MIP) images contributes to increase diagnostic accuracy for PET/CT image classification in BC. We retrospectively gathered 400 images of 200 BC and 200 non-BC patients for training data. For each image, we obtained PET MIP images with four different degrees (0°, 30°, 60°, 90°) and made two DL models using Xception. One DL model diagnosed BC with only 0-degree MIP and the other used four different degrees. After training phases, our DL models analyzed test data including 50 BC and 50 non-BC patients. Five radiologists interpreted these test data. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Our 4-degree model, 0-degree model, and radiologists had a sensitivity of 96%, 82%, and 80–98% and a specificity of 80%, 88%, and 76–92%, respectively. Our 4-degree model had equal or better diagnostic performance compared with that of the radiologists (AUC = 0.936 and 0.872–0.967, p = 0.036–0.405). A DL model similar to our 4-degree model may lead to help radiologists in their diagnostic work in the future.

Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

Heart ◽  
2018 ◽  
Vol 104 (23) ◽  
pp. 1921-1928 ◽  
Author(s):  
Ming-Zher Poh ◽  
Yukkee Cheung Poh ◽  
Pak-Hei Chan ◽  
Chun-Ka Wong ◽  
Louise Pun ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Test Data ◽  
Predictive Value ◽  
Characteristic Curve ◽  
Performance Comparison ◽  
Learning System ◽  
Training Data ◽  
Validation Data ◽  
Data Set

ObjectiveTo evaluate the diagnostic performance of a deep learning system for automated detection of atrial fibrillation (AF) in photoplethysmographic (PPG) pulse waveforms.MethodsWe trained a deep convolutional neural network (DCNN) to detect AF in 17 s PPG waveforms using a training data set of 149 048 PPG waveforms constructed from several publicly available PPG databases. The DCNN was validated using an independent test data set of 3039 smartphone-acquired PPG waveforms from adults at high risk of AF at a general outpatient clinic against ECG tracings reviewed by two cardiologists. Six established AF detectors based on handcrafted features were evaluated on the same test data set for performance comparison.ResultsIn the validation data set (3039 PPG waveforms) consisting of three sequential PPG waveforms from 1013 participants (mean (SD) age, 68.4 (12.2) years; 46.8% men), the prevalence of AF was 2.8%. The area under the receiver operating characteristic curve (AUC) of the DCNN for AF detection was 0.997 (95% CI 0.996 to 0.999) and was significantly higher than all the other AF detectors (AUC range: 0.924–0.985). The sensitivity of the DCNN was 95.2% (95% CI 88.3% to 98.7%), specificity was 99.0% (95% CI 98.6% to 99.3%), positive predictive value (PPV) was 72.7% (95% CI 65.1% to 79.3%) and negative predictive value (NPV) was 99.9% (95% CI 99.7% to 100%) using a single 17 s PPG waveform. Using the three sequential PPG waveforms in combination (<1 min in total), the sensitivity was 100.0% (95% CI 87.7% to 100%), specificity was 99.6% (95% CI 99.0% to 99.9%), PPV was 87.5% (95% CI 72.5% to 94.9%) and NPV was 100% (95% CI 99.4% to 100%).ConclusionsIn this evaluation of PPG waveforms from adults screened for AF in a real-world primary care setting, the DCNN had high sensitivity, specificity, PPV and NPV for detecting AF, outperforming other state-of-the-art methods based on handcrafted features.

scholarly journals Deep learning identifies morphological features in breast cancer predictive of cancer ERBB2 status and trastuzumab treatment efficacy

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Dmitrii Bychkov ◽  
Nina Linder ◽  
Aleksei Tiulpin ◽  
Hakan Kücükel ◽  
Mikael Lundin ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Deep Learning ◽  
Gene Amplification ◽  
Characteristic Curve ◽  
Disease Free Survival ◽  
Morphological Features ◽  
Training Data ◽  
Primary Breast Tumor ◽  
Trastuzumab Treatment

AbstractThe treatment of patients with ERBB2 (HER2)-positive breast cancer with anti-ERBB2 therapy is based on the detection of ERBB2 gene amplification or protein overexpression. Machine learning (ML) algorithms can predict the amplification of ERBB2 based on tumor morphological features, but it is not known whether ML-derived features can predict survival and efficacy of anti-ERBB2 treatment. In this study, we trained a deep learning model with digital images of hematoxylin–eosin (H&E)-stained formalin-fixed primary breast tumor tissue sections, weakly supervised by ERBB2 gene amplification status. The gene amplification was determined by chromogenic in situ hybridization (CISH). The training data comprised digitized tissue microarray (TMA) samples from 1,047 patients. The correlation between the deep learning–predicted ERBB2 status, which we call H&E-ERBB2 score, and distant disease-free survival (DDFS) was investigated on a fully independent test set, which included whole-slide tumor images from 712 patients with trastuzumab treatment status available. The area under the receiver operating characteristic curve (AUC) in predicting gene amplification in the test sets was 0.70 (95% CI, 0.63–0.77) on 354 TMA samples and 0.67 (95% CI, 0.62–0.71) on 712 whole-slide images. Among patients with ERBB2-positive cancer treated with trastuzumab, those with a higher than the median morphology–based H&E-ERBB2 score derived from machine learning had more favorable DDFS than those with a lower score (hazard ratio [HR] 0.37; 95% CI, 0.15–0.93; P = 0.034). A high H&E-ERBB2 score was associated with unfavorable survival in patients with ERBB2-negative cancer as determined by CISH. ERBB2-associated morphology correlated with the efficacy of adjuvant anti-ERBB2 treatment and can contribute to treatment-predictive information in breast cancer.

scholarly journals Challenge for Diagnostic Assessment of Deep Learning Algorithm for Metastases Classification in Sentinel Lymph Nodes on Frozen Tissue Section Digital Slides in Women with Breast Cancer

2020 ◽  
Author(s):  
Young-Gon Kim ◽  
In Hye Song ◽  
Hyunna Lee ◽  
Dong Hyun Yang ◽  
Namkug Kim ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Lymph Nodes ◽  
Learning Algorithm ◽  
Medical Center ◽  
Characteristic Curve ◽  
Lobular Carcinoma ◽  
Sentinel Lymph Nodes ◽  
Neoadjuvant Systemic Therapy ◽  
Frozen Tissue

Abstract Assessing the status of metastasis in sentinel lymph nodes (SLNs) by pathologists is an essential task for the accurate staging of breast cancer. However, histopathological evaluation of sentinel lymph nodes by a pathologist is not easy and is a tedious and time-consuming task. The purpose of this study is to review a challenge competition (HeLP 2018) to develop automated solutions for the classification of metastases in hematoxylin and eosin–stained frozen tissue sections of SLNs in breast cancer patients. A total of 297 digital slides were obtained from frozen SLN sections, which include post–neoadjuvant cases (n = 144, 48.5%) in Asan Medical Center, South Korea. The slides were divided into training, development, and validation sets. All of the imaging datasets have been manually segmented by expert pathologists. A total of 10 participants were allowed to use the Kakao challenge platform for six weeks with two P40 GPUs. The algorithms were assessed in terms of the AUC (area under receiver operating characteristic curve). The top three teams showed 0.986, 0.985, and 0.945 AUCs for the development set and 0.805, 0.776, and 0.765 AUCs for the validation set. Micrometastatic tumors, neoadjuvant systemic therapy, invasive lobular carcinoma, and histologic grade 3 were associated with lower diagnostic accuracy. In a challenge competition, accurate deep learning algorithms have been developed, which can be helpful in making frozen diagnosis of intraoperative sentinel lymph node biopsy. Whether this approach has clinical utility will require evaluation in a clinical setting.

scholarly journals Deep learning-based research on the influence of training data size for breast cancer pathology detection

2019 ◽  
Vol 2019 (23) ◽  
pp. 8729-8732
Author(s):  
Chongyang Cui ◽  
Shangchun Fan ◽  
Han Lei ◽  
Xiaolei Qu ◽  
Dezhi Zheng
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Training Data ◽  
Cancer Pathology ◽  
Breast Cancer Pathology

scholarly journals Morphological Estimation of Cellularity on Neo-Adjuvant Treated Breast Cancer Histological Images

2020 ◽  
Vol 6 (10) ◽  
pp. 101
Author(s):  
Mauricio Alberto Ortega-Ruiz ◽  
Cefa Karabağ ◽  
Victor García Garduño ◽  
Constantino Carlos Reyes-Aldasoro
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Morphological Features ◽  
Training Data ◽  
Morphological Operations ◽  
Morphological Parameters ◽  
Learning Approaches ◽  
Residual Cancer Burden ◽  
Histological Images ◽  
Treated Breast

This paper describes a methodology that extracts key morphological features from histological breast cancer images in order to automatically assess Tumour Cellularity (TC) in Neo-Adjuvant treatment (NAT) patients. The response to NAT gives information on therapy efficacy and it is measured by the residual cancer burden index, which is composed of two metrics: TC and the assessment of lymph nodes. The data consist of whole slide images (WSIs) of breast tissue stained with Hematoxylin and Eosin (H&E) released in the 2019 SPIE Breast Challenge. The methodology proposed is based on traditional computer vision methods (K-means, watershed segmentation, Otsu’s binarisation, and morphological operations), implementing colour separation, segmentation, and feature extraction. Correlation between morphological features and the residual TC after a NAT treatment was examined. Linear regression and statistical methods were used and twenty-two key morphological parameters from the nuclei, epithelial region, and the full image were extracted. Subsequently, an automated TC assessment that was based on Machine Learning (ML) algorithms was implemented and trained with only selected key parameters. The methodology was validated with the score assigned by two pathologists through the intra-class correlation coefficient (ICC). The selection of key morphological parameters improved the results reported over other ML methodologies and it was very close to deep learning methodologies. These results are encouraging, as a traditionally-trained ML algorithm can be useful when limited training data are available preventing the use of deep learning approaches.

scholarly journals Automated Breast Cancer Detection in Digital Mammograms of Various Densities via Deep Learning

2020 ◽  
Vol 10 (4) ◽  
pp. 211 ◽  
Author(s):  
Yong Joon Suh ◽  
Jaewon Jung ◽  
Bum-Joo Cho
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Operating Characteristic ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
Malignant Lesion ◽  
Model Performance ◽  
Mean Values ◽  
The Mean ◽  
Deep Learning Model

Mammography plays an important role in screening breast cancer among females, and artificial intelligence has enabled the automated detection of diseases on medical images. This study aimed to develop a deep learning model detecting breast cancer in digital mammograms of various densities and to evaluate the model performance compared to previous studies. From 1501 subjects who underwent digital mammography between February 2007 and May 2015, craniocaudal and mediolateral view mammograms were included and concatenated for each breast, ultimately producing 3002 merged images. Two convolutional neural networks were trained to detect any malignant lesion on the merged images. The performances were tested using 301 merged images from 284 subjects and compared to a meta-analysis including 12 previous deep learning studies. The mean area under the receiver-operating characteristic curve (AUC) for detecting breast cancer in each merged mammogram was 0.952 ± 0.005 by DenseNet-169 and 0.954 ± 0.020 by EfficientNet-B5, respectively. The performance for malignancy detection decreased as breast density increased (density A, mean AUC = 0.984 vs. density D, mean AUC = 0.902 by DenseNet-169). When patients’ age was used as a covariate for malignancy detection, the performance showed little change (mean AUC, 0.953 ± 0.005). The mean sensitivity and specificity of the DenseNet-169 (87 and 88%, respectively) surpassed the mean values (81 and 82%, respectively) obtained in a meta-analysis. Deep learning would work efficiently in screening breast cancer in digital mammograms of various densities, which could be maximized in breasts with lower parenchyma density.

Abbreviated Breast Magnetic Resonance Imaging (MRI): First Postcontrast Subtracted Images and Maximum-Intensity Projection—A Novel Approach to Breast Cancer Screening With MRI

2014 ◽  
Vol 32 (22) ◽  
pp. 2304-2310 ◽  
Author(s):  
Christiane K. Kuhl ◽  
Simone Schrading ◽  
Kevin Strobel ◽  
Hans H. Schild ◽  
Ralf-Dieter Hilgers ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Magnetic Resonance Imaging ◽  
Reading Time ◽  
Breast Magnetic Resonance Imaging ◽  
Maximum Intensity Projection ◽  
Maximum Intensity ◽  
Acquisition Time ◽  
Resonance Imaging ◽  
Breast Magnetic Resonance ◽  
Magnetic Resonance Imaging Mri

Purpose We investigated whether an abbreviated protocol (AP), consisting of only one pre- and one postcontrast acquisition and their derived images (first postcontrast subtracted [FAST] and maximum-intensity projection [MIP] images), was suitable for breast magnetic resonance imaging (MRI) screening. Methods We conducted a prospective observational reader study in 443 women at mildly to moderately increased risk who underwent 606 screening MRIs. Eligible women had normal or benign digital mammograms and, for those with heterogeneously dense or extremely dense breasts (n = 427), normal or benign ultrasounds. Expert radiologists reviewed the MIP image first to search for significant enhancement and then reviewed the complete AP (consisting of MIP and FAST images and optionally their nonsubtracted source images) to characterize enhancement and establish a diagnosis. Only thereafter was the regular full diagnostic protocol (FDP) analyzed. Results MRI acquisition time for FDP was 17 minutes, versus 3 minutes for the AP. Average time to read the single MIP and complete AP was 2.8 and 28 seconds, respectively. Eleven breast cancers (four ductal carcinomas in situ and seven invasive cancers; all T1N0 intermediate or high grade) were diagnosed, for an additional cancer yield of 18.2 per 1,000. MIP readings were positive in 10 (90.9%) of 11 cancers and allowed establishment of the absence of breast cancer, with a negative predictive value (NPV) of 99.8% (418 of 419). Interpretation of the complete AP, as with the FDP, allowed diagnosis of all cancers (11 [100%] of 11). Specificity and positive predictive value (PPV) of AP versus FDP were equivalent (94.3% v 93.9% and 24.4% v 23.4%, respectively). Conclusion An MRI acquisition time of 3 minutes and an expert radiologist MIP image reading time of 3 seconds are sufficient to establish the absence of breast cancer, with an NPV of 99.8%. With a reading time < 30 seconds for the complete AP, diagnostic accuracy was equivalent to that of the FDP and resulted in an additional cancer yield of 18.2 per 1,000.

scholarly journals Deep Learning Neural Networks to Predict Serious Complications After Bariatric Surgery: Analysis of Scandinavian Obesity Surgery Registry Data (Preprint)

2019 ◽  
Author(s):  
Yang Cao ◽  
Scott Montgomery ◽  
Johan Ottosson ◽  
Erik Näslund ◽  
Erik Stenberg
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bariatric Surgery ◽  
Deep Learning ◽  
Postoperative Complications ◽  
Obesity Surgery ◽  
Test Data ◽  
Registry Data ◽  
Training Data ◽  
Complications After Bariatric Surgery

BACKGROUND Obesity is one of today’s most visible public health problems worldwide. Although modern bariatric surgery is ostensibly considered safe, serious complications and mortality still occur in some patients. OBJECTIVE This study aimed to explore whether serious postoperative complications of bariatric surgery recorded in a national quality registry can be predicted preoperatively using deep learning methods. METHODS Patients who were registered in the Scandinavian Obesity Surgery Registry (SOReg) between 2010 and 2015 were included in this study. The patients who underwent a bariatric procedure between 2010 and 2014 were used as training data, and those who underwent a bariatric procedure in 2015 were used as test data. Postoperative complications were graded according to the Clavien-Dindo classification, and complications requiring intervention under general anesthesia or resulting in organ failure or death were considered serious. Three supervised deep learning neural networks were applied and compared in our study: multilayer perceptron (MLP), convolutional neural network (CNN), and recurrent neural network (RNN). The synthetic minority oversampling technique (SMOTE) was used to artificially augment the patients with serious complications. The performances of the neural networks were evaluated using accuracy, sensitivity, specificity, Matthews correlation coefficient, and area under the receiver operating characteristic curve. RESULTS In total, 37,811 and 6250 patients were used as the training data and test data, with incidence rates of serious complication of 3.2% (1220/37,811) and 3.0% (188/6250), respectively. When trained using the SMOTE data, the MLP appeared to have a desirable performance, with an area under curve (AUC) of 0.84 (95% CI 0.83-0.85). However, its performance was low for the test data, with an AUC of 0.54 (95% CI 0.53-0.55). The performance of CNN was similar to that of MLP. It generated AUCs of 0.79 (95% CI 0.78-0.80) and 0.57 (95% CI 0.59-0.61) for the SMOTE data and test data, respectively. Compared with the MLP and CNN, the RNN showed worse performance, with AUCs of 0.65 (95% CI 0.64-0.66) and 0.55 (95% CI 0.53-0.57) for the SMOTE data and test data, respectively. CONCLUSIONS MLP and CNN showed improved, but limited, ability for predicting the postoperative serious complications after bariatric surgery in the Scandinavian Obesity Surgery Registry data. However, the overfitting issue is still apparent and needs to be overcome by incorporating intra- and perioperative information. CLINICALTRIAL

scholarly journals Deep Learning-Based Breast Cancer Diagnosis at Ultrasound: Initial Application of Weakly-Supervised Algorithm Without Image Annotation Original Research

2021 ◽  
Author(s):  
Jaeil Kim ◽  
Hye Jung Kim ◽  
Chanho Kim ◽  
Jin Hwa Lee ◽  
Keum Won Kim ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Image Annotation ◽  
Characteristic Curve ◽  
External Validation ◽  
Region Of Interest ◽  
Breast Cancer Diagnosis ◽  
Original Research ◽  
Internal Validation ◽  
Weakly Supervised

Abstract Conventional deep learning (DL) algorithm requires full supervision of annotating the region of interest (ROI) that is laborious and often biased. We aimed to develop a weakly-supervised DL algorithm that diagnosis breast cancer at ultrasound without image annotation. Weakly-supervised DL algorithms were implemented with three networks (VGG16, ResNet34, and GoogLeNet) and trained using 1000 unannotated US images (500 benign and 500 malignant masses). Two sets of 200 images (100 benign and 100 malignant masses) were used for internal and external validation sets. For comparison with fully-supervised algorithms, ROI annotation was performed manually and automatically. Diagnostic performances were calculated as the area under the receiver operating characteristic curve (AUC). Using the class activation map, we determined how accurately the weakly-supervised DL algorithms localized the breast masses. For internal validation sets, the weakly-supervised DL algorithms achieved excellent diagnostic performances, with AUC values of 0.92–0.96, which were not statistically different (all Ps > 0.05) from those of fully-supervised DL algorithms with either manual or automated ROI annotation (AUC, 0.92–0.96). For external validation sets, the weakly-supervised DL algorithms achieved AUC values of 0.86–0.90, which were not statistically different (Ps > 0.05) or higher (P = 0.04, VGG16 with automated ROI annotation) from those of fully-supervised DL algorithms (AUC, 0.84–0.92). In internal and external validation sets, weakly-supervised algorithms could localize 100% of malignant masses, except for ResNet34 (98%). The weakly-supervised DL algorithms developed in the present study were feasible for US diagnosis of breast cancer with well-performing localization and differential diagnosis.

Sign in / Sign up

Export Citation Format

Share Document