Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Ophthalmology Ophthalmology

A column-based deep learning method for the detection and quantification of atrophy associated with AMD in OCT scans.

In Medical image analysis

The objective quantification of retinal atrophy associated with age-related macular degeneration (AMD) is required for clinical diagnosis, follow-up, treatment efficacy evaluation, and clinical research. Spectral Domain Optical Coherence Tomography (OCT) has become an essential imaging technology to evaluate the macula. This paper describes a novel automatic method for the identification and quantification of atrophy associated with AMD in OCT scans and its visualization in the corresponding infrared imaging (IR) image. The method is based on the classification of light scattering patterns in vertical pixel-wide columns (A-scans) in OCT slices (B-scans) in which atrophy appears with a custom column-based convolutional neural network (CNN). The network classifies individual columns with 3D column patches formed by adjacent neighboring columns from the volumetric OCT scan. Subsequent atrophy columns form atrophy segments which are then projected onto the IR image and are used to identify and segment atrophy lesions in the IR image and to measure their areas and distances from the fovea. Experimental results on 106 clinical OCT scans (5,207 slices) in which cRORA atrophy (the end point of advanced dry AMD) was identified in 2,952 atrophy segments and 1,046 atrophy lesions yield a mean F1 score of 0.78 (std 0.06) and an AUC of 0.937, both close to the observer variability. Automated computer-based detection and quantification of atrophy associated with AMD using a column-based CNN classification in OCT scans can be performed at expert level and may be a useful clinical decision support and research tool for the diagnosis, follow-up and treatment of retinal degenerations and dystrophies.

Szeskin Adi, Yehuda Roei, Shmueli Or, Levy Jaime, Joskowicz Leo


CNN deep learning, Column-based OCT scattering, OCT scan analysis, Retinal atrophy in dry age-related macular degeneration

Radiology Radiology

Normalization of breast MRIs using cycle-consistent generative adversarial networks.

In Computer methods and programs in biomedicine

OBJECTIVES : Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is widely used to complement ultrasound examinations and x-ray mammography for early detection and diagnosis of breast cancer. However, images generated by various MRI scanners (e.g., GE Healthcare, and Siemens) differ both in intensity and noise distribution, preventing algorithms trained on MRIs from one scanner to generalize to data from other scanners. In this work, we propose a method to solve this problem by normalizing images between various scanners.

METHODS : MRI normalization is challenging because it requires normalizing intensity values and mapping noise distributions between scanners. We utilize a cycle-consistent generative adversarial network to learn a bidirectional mapping and perform normalization between MRIs produced by GE Healthcare and Siemens scanners in an unpaired setting. Initial experiments demonstrate that the traditional CycleGAN architecture struggles to preserve the anatomical structures of the breast during normalization. Thus, we propose two technical innovations in order to preserve both the shape of the breast as well as the tissue structures within the breast. First, we incorporate mutual information loss during training in order to ensure anatomical consistency. Second, we propose a modified discriminator architecture that utilizes a smaller field-of-view to ensure the preservation of finer details in the breast tissue.

RESULTS : Quantitative and qualitative evaluations show that the second innovation consistently preserves the breast shape and tissue structures while also performing the proper intensity normalization and noise distribution mapping.

CONCLUSION : Our results demonstrate that the proposed model can successfully learn a bidirectional mapping and perform normalization between MRIs produced by different vendors, potentially enabling improved diagnosis and detection of breast cancer. All the data used in this study are publicly available at

Modanwal Gourav, Vellal Adithya, Mazurowski Maciej A


CycleGAN, Deep learning, MRI intensity normalization, Medical image translation, Vendor normalization

General General

Upregulation of miR-210-5p impairs dead cell clearance by macrophages through the inhibition of Sp1-and HSCARG-dependent NADPH oxidase pathway.

In Free radical biology & medicine

The deficiency of dead cell clearance is a prominent pathogenic factor in systemic lupus erythematosus (SLE). In this study, the overexpression of miR-210-5p resulted in the accumulation of secondary necrotic cells (SNECs) in macrophages through the reduction of protein degradation. The upreguation of miR-210-5p inhibited NADPH oxidase (NOX) activation, reactive oxygen species (ROS) generation, and SNEC clearance. miR-210-5p overexpression suppressed Sp1 and HSCARG expression, and the knockdown of SP1 and HSCARG inhibited NOX expression and superoxide production in macrophages. Furthermore, patients with active SLE expressed a higher level of miR-210-5p and lower expression of SP1 and HSCARG in peripheral blood mononuclear cells. In summary, our findings indicate that the upregulation of miR-210-5p increases the accumulation of SNECs through a decrease in the Sp1-and HSCARG-mediated NOX activity and ROS generation in macrophages. Our results also suggest that targeting miR-210-5p may have therapeutic potential for SLE.

Wu Yi-Hsuan, Kuo Chang-Fu, Hsieh Ao-Ho, Hsieh Hsi-Lung, Chan Yen-Fan, Hwang Tsong-Long


Dead cell clearance, NOX signaling, Systemic lupus erythematosus, miR-210–5p

Pathology Pathology

Development and Performance of a CD8 Gene Signature for Characterizing Inflammation in the Tumor Microenvironment Across Multiple Tumor Types.

In The Journal of molecular diagnostics : JMD

Across multiple tumor types, immune checkpoint inhibitors (ICIs) have demonstrated clinical benefit to patients with cancer, yet there is a need to identify predictive biomarkers of response to these therapies. A multiparameter gene expression profiling (GEP)-based tumor inflammation assay may offer robust characterization of the tumor microenvironment (TME), thereby extending the utility of single-gene analysis or immunohistochemistry (IHC) in predicting response to ICIs. We interrogated 1778 commercially procured, formalin-fixed, paraffin-embedded samples using GEP and pathology-assisted digital CD8 IHC. A machine-learning approach was used to develop gene expression signatures that predicted CD8+ immune cell abundance as surrogates for tumor inflammation in melanoma and squamous cell carcinoma of the head and neck samples. An assay for a 16-gene CD8 signature was developed and analytically validated across 12 tumor types. CD8 signature scores correlated with CD8 IHC in a platform-independent manner, and inflammation prevalence was similar between assay methods for all tumor types except prostate cancer and small cell lung cancer. In retrospective analyses, CD8 signature scores associated with progression-free survival and overall survival with nivolumab in patients with urothelial carcinoma from CheckMate 275. This study demonstrated that the CD8 signature assay can be used to accurately quantify CD8+ immune cell abundance in the TME and has potential clinical utility for determining patients with cancer who are likely to respond to ICIs.

Szabo Peter M, Pant Saumya, Ely Scott, Desai Keyur, Anguiano Esperanza, Wang Lisu, Edwards Robin, Green George, Zhang Nancy


Radiology Radiology

GANDA: A deep generative adversarial network conditionally generates intratumoral nanoparticles distribution pixels-to-pixels.

In Journal of controlled release : official journal of the Controlled Release Society

Intratumoral nanoparticles (NPs) distribution is critical for the success of nanomedicine in imaging and treatment, but computational models to describe the NPs distribution remain unavailable due to the complex tumor-nano interactions. Here, we develop a Generative Adversarial Network for Distribution Analysis (GANDA) to describe and conditionally generates the intratumoral quantum dots (QDs) distribution after i.v. injection. This deep generative model is trained automatically by 27,775 patches of tumor vessels and cell nuclei decomposed from whole-slide images of 4 T1 breast cancer sections. The GANDA model can conditionally generate images of intratumoral QDs distribution under the constraint of given tumor vessels and cell nuclei channels with the same spatial resolution (pixels-to-pixels), minimal loss (mean squared error, MSE = 1.871) and excellent reliability (intraclass correlation, ICC = 0.94). Quantitative analysis of QDs extravasation distance (ICC = 0.95) and subarea distribution (ICC = 0.99) is allowed on the generated images without knowing the real QDs distribution. We believe this deep generative model may provide opportunities to investigate how influencing factors affect NPs distribution in individual tumors and guide nanomedicine optimization for molecular imaging and personalized treatment.

Tang Yuxia, Zhang Jiulou, He Doudou, Miao Wenfang, Liu Wei, Li Yang, Lu Guangming, Wu Feiyun, Wang Shouju


Artificial intelligence, Deep generative model, Deep learning, Generative adversarial network, Nanoparticles

Dermatology Dermatology

Funding sources: NoneUse of convolutional neural networks for the detection of u-serrated patterns in direct immunofluorescence images to facilitate the diagnosis of epidermolysis bullosa acquisita.

In The American journal of pathology ; h5-index 54.0

The u-serrated immunodeposition pattern in direct immunofluorescence (DIF) microscopy is a recognizable feature and confirmative for diagnosis of epidermolysis bullosa acquisita (EBA). Due to unfamiliarity with serrated patterns, serration pattern recognition is still of limited use in routine DIF microscopy. The objective of this study is to investigate the feasibility of using convolutional neural networks (CNNs) for the recognition of u-serrated patterns that can assist in diagnosis of EBA. Nine most commonly used CNNs are trained and validated by using 220,800 manually delineated DIF image patches from 106 images of 46 different patients. The dataset was split into 10 subsets; 9 training subsets from 42 patients to train CNNs and the remaining subset from the remaining 4 patients for validation dataset of diagnostic accuracy. This process was repeated 10 times with a different subset used for validation. The best performing CNN achieved specificity of 89.3% and corresponding sensitivity of 89.3% in the classification of u-serrated DIF image patches, a diagnostic accuracy of expert level. Experiments and results demonstrate the effectiveness of convolutional neural networks approaches for u-serrated patterns recognition with a high accuracy. The proposed approach can assist clinicians and pathologists in recognition of u-serrated patterns in DIF images, and facilitate diagnosis of EBA.

Shi Chenyu, Meijer Joost M, Azzopardi George, Diercks Gilles F H, Guo Jiapan, Petkov Nicolai


Convolutional neural network, direct immunofluorescence, epidermolysis bullosa acquisita, machine learning, pemphigoid, serration pattern analysis