scholarly journals Deep Learning identifies new morphological patterns of Homologous Recombination Deficiency in luminal breast cancers from whole slide images

2021 ◽  
Author(s):  
Tristan Lazard ◽  
Guillaume Bataillon ◽  
Peter Naylor ◽  
Tatiana Popova ◽  
François-Clément Bidard ◽  
...  
Keyword(s):  
Deep Learning ◽  
Homologous Recombination ◽  
Parp Inhibitor ◽  
Breast Cancers ◽  
Genomic Signatures ◽  
Repair Deficiency ◽  
Dna Repair Deficiency ◽  
Deep Learning Model ◽  
Whole Slide Images ◽  
Morphological Patterns

AbstractHomologous Recombination DNA-repair deficiency (HRD) is a well-recognized marker of platinum-salt and PARP inhibitor chemotherapies in ovarian and breast cancers (BC). Causing high genomic instability, HRD is currently determined by BRCA1/2 sequencing or by genomic signatures, but its morphological manifestation is not well understood. Deep Learning (DL) is a powerful machine learning technique that has been recently shown to be capable of predicting genomic signatures from stained tissue slides. However, DL is known to be sensitive to dataset biases and lacks interpretability. Here, we present and evaluate a strategy to control for biases in retrospective cohorts. We train a deep-learning model to predict the HRD in a controlled cohort with unprecedented accuracy (AUC: 0.86) and we develop a new visualization technique that allows for automatic extraction of new morphological features related to HRD. We analyze in detail the extracted morphological patterns that open new hypotheses on the phenotypic impact of HRD.

Deep learning to predict subtypes of poorly differentiated lung cancer from biopsy whole slide images.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 8536-8536
Author(s):  
Gouji Toyokawa ◽  
Fahdi Kanavati ◽  
Seiya Momosaki ◽  
Kengo Tateishi ◽  
Hiroaki Takeoka ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Learning Model ◽  
Test Set ◽  
Cancer Subtypes ◽  
Independent Test ◽  
Poorly Differentiated ◽  
Test Sets ◽  
Deep Learning Model ◽  
Whole Slide Images

8536 Background: Lung cancer is the leading cause of cancer-related death in many countries, and its prognosis remains unsatisfactory. Since treatment approaches differ substantially based on the subtype, such as adenocarcinoma (ADC), squamous cell carcinoma (SCC) and small cell lung cancer (SCLC), an accurate histopathological diagnosis is of great importance. However, if the specimen is solely composed of poorly differentiated cancer cells, distinguishing between histological subtypes can be difficult. The present study developed a deep learning model to classify lung cancer subtypes from whole slide images (WSIs) of transbronchial lung biopsy (TBLB) specimens, in particular with the aim of using this model to evaluate a challenging test set of indeterminate cases. Methods: Our deep learning model consisted of two separately trained components: a convolutional neural network tile classifier and a recurrent neural network tile aggregator for the WSI diagnosis. We used a training set consisting of 638 WSIs of TBLB specimens to train a deep learning model to classify lung cancer subtypes (ADC, SCC and SCLC) and non-neoplastic lesions. The training set consisted of 593 WSIs for which the diagnosis had been determined by pathologists based on the visual inspection of Hematoxylin-Eosin (HE) slides and of 45 WSIs of indeterminate cases (64 ADCs and 19 SCCs). We then evaluated the models using five independent test sets. For each test set, we computed the receiver operator curve (ROC) area under the curve (AUC). Results: We applied the model to an indeterminate test set of WSIs obtained from TBLB specimens that pathologists had not been able to conclusively diagnose by examining the HE-stained specimens alone. Overall, the model achieved ROC AUCs of 0.993 (confidence interval [CI] 0.971-1.0) and 0.996 (0.981-1.0) for ADC and SCC, respectively. We further evaluated the model using five independent test sets consisting of both TBLB and surgically resected lung specimens (combined total of 2490 WSIs) and obtained highly promising results with ROC AUCs ranging from 0.94 to 0.99. Conclusions: In this study, we demonstrated that a deep learning model could be trained to predict lung cancer subtypes in indeterminate TBLB specimens. The extremely promising results obtained show that if deployed in clinical practice, a deep learning model that is capable of aiding pathologists in diagnosing indeterminate cases would be extremely beneficial as it would allow a diagnosis to be obtained sooner and reduce costs that would result from further investigations.

scholarly journals HRness in Breast and Ovarian Cancers

2020 ◽  
Vol 21 (11) ◽  
pp. 3850 ◽  
Author(s):  
Elizabeth Santana dos Santos ◽  
François Lallemand ◽  
Ambre Petitalot ◽  
Sandrine M. Caputo ◽  
Etienne Rouleau
Keyword(s):  
Dna Repair ◽  
Breast Cancers ◽  
Ovarian Carcinomas ◽  
Ovarian Cancers ◽  
Hormonal Cycle ◽  
Repair Deficiency ◽  
Cancer Initiation ◽  
Dna Repair Deficiency ◽  
Tumor Level ◽  
New Biomarkers

Ovarian and breast cancers are currently defined by the main pathways involved in the tumorigenesis. The majority are carcinomas, originating from epithelial cells that are in constant division and subjected to cyclical variations of the estrogen stimulus during the female hormonal cycle, therefore being vulnerable to DNA damage. A portion of breast and ovarian carcinomas arises in the context of DNA repair defects, in which genetic instability is the backdrop for cancer initiation and progression. For these tumors, DNA repair deficiency is now increasingly recognized as a target for therapeutics. In hereditary breast/ovarian cancers (HBOC), tumors with BRCA1/2 mutations present an impairment of DNA repair by homologous recombination (HR). For many years, BRCA1/2 mutations were only screened on germline DNA, but now they are also searched at the tumor level to personalize treatment. The reason of the inactivation of this pathway remains uncertain for most cases, even in the presence of a HR-deficient signature. Evidence indicates that identifying the mechanism of HR inactivation should improve both genetic counseling and therapeutic response, since they can be useful as new biomarkers of response.

DNA repair deficiency association with prognosis in pancreatic cancer: A single-institution experience.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e15798-e15798
Author(s):  
Suhaib Bajwa ◽  
Thomas A Odeny ◽  
Anwaar Saeed ◽  
Anup Kasi
Keyword(s):  
Pancreatic Cancer ◽  
Dna Repair ◽  
Cancer Patients ◽  
Parp Inhibitor ◽  
Survival Outcomes ◽  
Dna Repair Genes ◽  
Repair Deficiency ◽  
Dna Repair Deficiency ◽  
Baseline Characteristics ◽  
Repair Genes

e15798 Background: Understanding survival outcomes of various pathogenic mutations helps guide treatment decision making for patients. Classic pancreatic cancer mutations such as KRAS and TP53 have well documented survival outcomes while other mutations leading to DNA repair deficiency do not have well understood survival outcomes. Methods: We retrospectively evaluated survival outcomes of 70 pancreatic cancer patients who had their cancers genetically profiled by NGS methods. Patients with DNA repair deficiency harbored mutations in genes such as BRCA1 (1 Pts), BRCA2 (8 Pts), ATM (5 Pts), NBN (1 Pt), and BRIP1 (1 Pt). We compared baseline characteristics, tumor stage and clinical outcomes between patients with DNA repair deficiency versus DNA repair proficient cancer patients. Comparative survival analysis between the two groups was performed using Kaplan-Meir methods. Results: Baseline characteristics for all patients are recorded in (Table). Median OS is 24 months for DNA repair proficient group and 20 months for DNA repair deficient group. A comparison of Kaplan-Meir survival curves between the two groups yielded a p-value of 0.72. This is most likely due to sample size and different chemotherapy regimens which make it hard to retrospectively compare patient groups. Conclusions: Patients with mutated DNA repair genes did not have significantly worse survival. We are designing a clinical trial utilizing a PARP inhibitor, for these patients in order to better control for all factors in order to better ascertain any survival differences between the two groups. PARP inhibitor will create multiple single strand breaks which cancer cells deficient in DNA repair genes cannot repair and thus trigger cancer cell death[Table: see text]

A New Deep Learning Model Selection Method for Colorectal Cancer Classification

2020 ◽  
Vol 11 (3) ◽  
pp. 72-88
Author(s):  
Nassima Dif ◽  
Zakaria Elberrichi
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
Learning Strategy ◽  
Cancer Classification ◽  
Complex Morphology ◽  
Histopathological Image ◽  
Voting Strategy ◽  
Deep Learning Model ◽  
Aided Diagnosis ◽  
Whole Slide Images

Deep learning is one of the most commonly used techniques in computer-aided diagnosis systems. Their exploitation for histopathological image analysis is important because of the complex morphology of whole slide images. However, the main limitation of these methods is the restricted number of available medical images, which can lead to an overfitting problem. Many studies have suggested the use of static ensemble learning methods to address this issue. This article aims to propose a new dynamic ensemble deep learning method. First, it generates a set of models based on the transfer learning strategy from deep neural networks. Then, the relevant subset of models is selected by the particle swarm optimization algorithm and combined by voting or averaging methods. The proposed approach was tested on a histopathological dataset for colorectal cancer classification, based on seven types of CNNs. The method has achieved accurate results (94.52%) by the Resnet121 model and the voting strategy, which provides important insights into the efficiency of dynamic ensembling in deep learning.

Clinical assays for assessment of homologous recombination DNA repair deficiency

2020 ◽  
Vol 159 (3) ◽  
pp. 887-898
Author(s):  
Elizabeth H. Stover ◽  
Katherine Fuh ◽  
Panagiotis A. Konstantinopoulos ◽  
Ursula A. Matulonis ◽  
Joyce F. Liu
Keyword(s):  
Dna Repair ◽  
Homologous Recombination ◽  
Repair Deficiency ◽  
Dna Repair Deficiency

scholarly journals Identification of nodal micrometastasis in colorectal cancer using deep learning on annotation-free whole-slide images

2021 ◽  
Author(s):  
Wen-Yu Chuang ◽  
Chi-Chung Chen ◽  
Wei-Hsiang Yu ◽  
Chi-Ju Yeh ◽  
Shang-Hung Chang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Colorectal Cancer ◽  
Deep Learning ◽  
Lymph Node ◽  
Lymph Nodes ◽  
Tumor Size ◽  
Manual Annotation ◽  
Nodal Micrometastasis ◽  
Deep Learning Model ◽  
Whole Slide Images

AbstractDetection of nodal micrometastasis (tumor size: 0.2–2.0 mm) is challenging for pathologists due to the small size of metastatic foci. Since lymph nodes with micrometastasis are counted as positive nodes, detecting micrometastasis is crucial for accurate pathologic staging of colorectal cancer. Previously, deep learning algorithms developed with manually annotated images performed well in identifying micrometastasis of breast cancer in sentinel lymph nodes. However, the process of manual annotation is labor intensive and time consuming. Multiple instance learning was later used to identify metastatic breast cancer without manual annotation, but its performance appears worse in detecting micrometastasis. Here, we developed a deep learning model using whole-slide images of regional lymph nodes of colorectal cancer with only a slide-level label (either a positive or negative slide). The training, validation, and testing sets included 1963, 219, and 1000 slides, respectively. A supercomputer TAIWANIA 2 was used to train a deep learning model to identify metastasis. At slide level, our algorithm performed well in identifying both macrometastasis (tumor size > 2.0 mm) and micrometastasis with an area under the receiver operating characteristics curve (AUC) of 0.9993 and 0.9956, respectively. Since most of our slides had more than one lymph node, we then tested the performance of our algorithm on 538 single-lymph node images randomly cropped from the testing set. At single-lymph node level, our algorithm maintained good performance in identifying macrometastasis and micrometastasis with an AUC of 0.9944 and 0.9476, respectively. Visualization using class activation mapping confirmed that our model identified nodal metastasis based on areas of tumor cells. Our results demonstrate for the first time that micrometastasis could be detected by deep learning on whole-slide images without manual annotation.

scholarly journals Optimized detection of somatic allelic imbalances specific for homologous recombination deficiency improves the prediction of clinical outcomes in ovarian cancer

2021 ◽  
Author(s):  
Fernando Ramon Perez-Villatoro ◽  
Julia Casado ◽  
Anniina Farkkila
Keyword(s):  
Ovarian Cancer ◽  
Homologous Recombination ◽  
Clinical Outcomes ◽  
Repair Deficiency ◽  
Improve Patient Selection ◽  
Dna Repair Deficiency ◽  
Tumor Types ◽  
Improve Patient ◽  
Pan Cancer

Specific patterns of genomic allelic imbalances (AIs) have been associated with Homologous recombination DNA-repair deficiency (HRD). We performed a systematic pan-cancer characterization of AIs across tumor types, revealing unique patterns in ovarian cancer. Using machine learning on a multi-omics dataset, we generated an optimized algorithm to detect HRD in ovarian cancer (ovaHRDscar). ovaHRDscar improved the prediction of clinical outcomes in three independent validation cohorts (PCAWG, HERCULES, TERVA). Characterization of 98 spatiotemporally distinct tumor samples indicated ovary/adnex as the preferred site to assess HRD. In conclusion, ovaHRDscar improves the detection of HRD in ovarian cancer with the premise to improve patient selection for HR-targeted therapies.

scholarly journals A deep learning model for breast ductal carcinoma in situ classification in whole slide images

2022 ◽  
Author(s):  
Fahdi Kanavati ◽  
Shin Ichihara ◽  
Masayuki Tsuneki
Keyword(s):  
Deep Learning ◽  
Ductal Carcinoma In Situ ◽  
Carcinoma In Situ ◽  
Ductal Carcinoma ◽  
New Techniques ◽  
Large Numbers ◽  
Computational Pathology ◽  
Deep Learning Model ◽  
Whole Slide Images

The pathological differential diagnosis between breast ductal carcinoma in situ (DCIS) and invasive ductal carcinoma (IDC) is of pivotal importance for determining optimum cancer treatment(s) and clinical outcomes. Since conventional diagnosis by pathologists using microscopes is limited in terms of human resources, it is necessary to develop new techniques that can rapidly and accurately diagnose large numbers of histopathological specimens. Computational pathology tools which can assist pathologists in detecting and classifying DCIS and IDC from whole slide images (WSIs) would be of great benefit for routine pathological diagnosis. In this paper, we trained deep learning models capable of classifying biopsy and surgical histopathological WSIs into DCIS, IDC, and benign. We evaluated the models on two independent test sets (n=1,382, n=548), achieving ROC areas under the curves (AUCs) up to 0.960 and 0.977 for DCIS and IDC, respectively.

Implementation and Practice of Deep Learning-Based Instance Segmentation Algorithm for Quantification of Hepatic Fibrosis at Whole Slide Level in Sprague-Dawley Rats

2021 ◽  
pp. 019262332110571
Author(s):  
Ji-Hee Hwang ◽  
Hyun-Ji Kim ◽  
Heejin Park ◽  
Byoung-Seok Lee ◽  
Hwa-Young Son ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Hepatic Fibrosis ◽  
Ground Truth ◽  
Learning Technology ◽  
Sprague Dawley ◽  
Sprague Dawley Rats ◽  
Deep Learning Model ◽  
Instance Segmentation ◽  
Whole Slide Images

Exponential development in artificial intelligence or deep learning technology has resulted in more trials to systematically determine the pathological diagnoses using whole slide images (WSIs) in clinical and nonclinical studies. In this study, we applied Mask Regions with Convolution Neural Network (Mask R-CNN), a deep learning model that uses instance segmentation, to detect hepatic fibrosis induced by N-nitrosodimethylamine (NDMA) in Sprague-Dawley rats. From 51 WSIs, we collected 2011 cropped images with hepatic fibrosis annotations. Training and detection of hepatic fibrosis via artificial intelligence methods was performed using Tensorflow 2.1.0, powered by an NVIDIA 2080 Ti GPU. From the test process using tile images, 95% of model accuracy was verified. In addition, we validated the model to determine whether the predictions by the trained model can reflect the scoring system by the pathologists at the WSI level. The validation was conducted by comparing the model predictions in 18 WSIs at 20× and 10× magnifications with ground truth annotations and board-certified pathologists. Predictions at 20× showed a high correlation with ground truth ( R 2 = 0.9660) and a good correlation with the average fibrosis rank by pathologists ( R 2 = 0.8887). Therefore, the Mask R-CNN algorithm is a useful tool for detecting and quantifying pathological findings in nonclinical studies.

Sign in / Sign up

Export Citation Format

Share Document