Evaluation of a predictive method for the H&amp;E-based molecular profiling of breast cancer with deep learning

Arslan, Salim; Li, Xiusi; Schmidt, Julian; Hense, Julius; Geraldes, Andre; Bass, Cher; Brown, K. D.; Marcia, Angelica; Dewhirst, Tim; Pandya, Pahini; Singhal, Shikha; Mehrotra, Debapriya G.; Raharja-Liu, Pandu

doi:10.1101/2022.01.04.474882

Cited by 4 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model hyperparameters and the CNN architecture were determined based on a relevant benchmark analysis from the clinical validation study of a DL model developed for molecular profiling of breast cancer 60 . We adopted the best-performing model’s feature extractor network (based on a “resnet34” architecture 61 ) and hyper-parameters to configure a CNN for each biomarker in the current pan-cancer study.…”

Section: Methodsmentioning

confidence: 99%

Deep learning can predict multi-omic biomarkers from routine pathology images: A systematic large-scale study

Arslan¹,

Mehrotra

Schmidt³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

We assessed the pan-cancer predictability of multi-omic biomarkers from haematoxylin and eosin (H&E)-stained whole slide image (WSI) using deep learning and standard evaluation measures throughout a systematic study. A total of 13,443 deep learning (DL) models predicting 4,481 multi-omic biomarkers across 32 cancer types were trained and validated. The investigated biomarkers included genetic mutations, transcriptomic (mRNA) and proteomic under- and over-expression status, metabolomic pathways, established markers relevant for prognosis, including gene expression signatures, molecular subtypes, clinical outcomes and response to treatment. Overall, we established the general feasibility of predicting multi-omic markers across solid cancer types, where 50% of the models could predict biomarkers with the area under the curve (AUC) of more than 0.633 (with 25% of the models having AUC larger than 0.711). Aggregating across the omic types, our deep learning models achieved the following performance: mean AUC of 0.634 ±0.117 in predicting driver SNV mutations; 0.637 ±0.108 for over-/under-expression of transcriptomic genes; 0.666 ±0.108 for over-/under-expression of proteomes; 0.564 ±0.081 for metabolomic pathways; 0.653 ±0.097 for gene signatures and molecular subtypes; 0.742 ±0.120 for standard of care biomarkers; and 0.671 ±0.120 for clinical outcomes and treatment responses. The biomarkers were shown to be detectable from routine histology images across all investigated cancer types, with aggregate mean AUC exceeding 0.62 in almost all cancers. In addition, we observed that predictability is reproducible within-marker and less dependent on sample size and positivity ratio, indicating a degree of true predictability inherent to the biomarker itself.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep learning can predict multi-omic biomarkers from routine pathology images: A systematic large-scale study

Arslan¹,

Mehrotra

Schmidt³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In 2020, 12% of malignant tumors in the human population were caused by breast cancer [ 1 ]. By 2040, the number of cases is predicted to increase by more than 46% [ 2 ]. Breast cancer remains the second most lethal cancer diagnosis, even though mortality rates from the disease fell by 1% in 2013, possibly due to therapeutic advancements.…”

Section: Introductionmentioning

confidence: 99%

Strategies for Enhancing the Multi-Stage Classification Performances of HER2 Breast Cancer from Hematoxylin and Eosin Images

et al. 2022

View full text Add to dashboard Cite

Breast cancer is a significant health concern among women. Prompt diagnosis can diminish the mortality rate and direct patients to take steps for cancer treatment. Recently, deep learning has been employed to diagnose breast cancer in the context of digital pathology. To help in this area, a transfer learning-based model called ‘HE-HER2Net’ has been proposed to diagnose multiple stages of HER2 breast cancer (HER2-0, HER2-1+, HER2-2+, HER2-3+) on H&E (hematoxylin & eosin) images from the BCI dataset. HE-HER2Net is the modified version of the Xception model, which is additionally comprised of global average pooling, several batch normalization layers, dropout layers, and dense layers with a swish activation function. This proposed model exceeds all existing models in terms of accuracy (0.87), precision (0.88), recall (0.86), and AUC score (0.98) immensely. In addition, our proposed model has been explained through a class-discriminative localization technique using Grad-CAM to build trust and to make the model more transparent. Finally, nuclei segmentation has been performed through the StarDist method.

show abstract

Deep learning for dual detection of microsatellite instability and POLE mutations in colorectal cancer histopathology

Gustav,

Reitsam,

Carrero

et al. 2024

npj Precis. Onc.

View full text Add to dashboard Cite

In the spectrum of colorectal tumors, microsatellite-stable (MSS) tumors with DNA polymerase ε (POLE) mutations exhibit a hypermutated profile, holding the potential to respond to immunotherapy similarly to their microsatellite-instable (MSI) counterparts. Yet, due to their rarity and the associated testing costs, systematic screening for these mutations is not commonly pursued. Notably, the histopathological phenotype resulting from POLE mutations is theorized to resemble that of MSI. This resemblance not only could facilitate their detection by a transformer-based Deep Learning (DL) system trained on MSI pathology slides, but also indicates the possibility for MSS patients with POLE mutations to access enhanced treatment options, which might otherwise be overlooked. To harness this potential, we trained a Deep Learning classifier on a large dataset with the ground truth for microsatellite status and subsequently validated its capabilities for MSI and POLE detection across three external cohorts. Our model accurately identified MSI status in both the internal and external resection cohorts using pathology images alone. Notably, with a classification threshold of 0.5, over 75% of POLE driver mutant patients in the external resection cohorts were flagged as “positive” by a DL system trained on MSI status. In a clinical setting, deploying this DL model as a preliminary screening tool could facilitate the efficient identification of clinically relevant MSI and POLE mutations in colorectal tumors, in one go.

show abstract

Evaluation of a predictive method for the H&E-based molecular profiling of breast cancer with deep learning

Cited by 4 publications

References 25 publications

Deep learning can predict multi-omic biomarkers from routine pathology images: A systematic large-scale study

Deep learning can predict multi-omic biomarkers from routine pathology images: A systematic large-scale study

Strategies for Enhancing the Multi-Stage Classification Performances of HER2 Breast Cancer from Hematoxylin and Eosin Images

Deep learning for dual detection of microsatellite instability and POLE mutations in colorectal cancer histopathology

Contact Info

Product

Resources

About